diff --git "a/catalog.json" "b/catalog.json" --- "a/catalog.json" +++ "b/catalog.json" @@ -1,1430 +1,1489 @@ [ { - "id": "alphagenome_tss1mb_regulatory_tracksummary_pca256", - "name": "AlphaGenome-TSS1Mb-regulatoryTrackSummary-PCA256-v1.1", + "algorithm": "signed log1p per summary feature, z-score across genes, PCA to 256 dimensions", "category": "Regulatory", "category_source": "manual", - "modality": "regulatory genomics / AlphaGenome regulatory-track summary", - "algorithm": "signed log1p per summary feature, z-score across genes, PCA to 256 dimensions", - "description": "Gene-level regulatory representation derived from AlphaGenome track-summary predictions around the transcription start site and reduced to 256 dimensions.", - "n_genes": 20084, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 99.94, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/alphagenome_tss1mb_regulatory_tracksummary_pca256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/alphagenome_tss1mb_regulatory_tracksummary_pca256", + "description": "Gene-level regulatory representation derived from AlphaGenome track-summary predictions around the transcription start site and reduced to 256 dimensions.", + "id": "alphagenome_tss1mb_regulatory_tracksummary_pca256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/alphagenome_tss1mb_regulatory_tracksummary_pca256/metadata.json", + "modality": "regulatory genomics / AlphaGenome regulatory-track summary", + "n_dims": 256, + "n_genes": 20084, + "name": "AlphaGenome-TSS1Mb-regulatoryTrackSummary-PCA256-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/alphagenome_tss1mb_regulatory_tracksummary_pca256", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "basenji2_tss_131kb_human_central3", - "name": "Basenji2-TSS-131kb-human-central3-log1p-zscore-v1.1", + "algorithm": "Basenji2 PyTorch port", "category": "Regulatory", "category_source": "heuristic", - "modality": "regulatory DNA / Basenji2 TSS sequence model", - "algorithm": "Basenji2 PyTorch port", - "description": "Basenji2-TSS-131kb-human-central3-log1p-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 20097, - "n_dims": 5313, + "community_contribution": false, "coverage_pct": 100.0, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/basenji2_tss_131kb_human_central3", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/basenji2_tss_131kb_human_central3", + "description": "Basenji2-TSS-131kb-human-central3-log1p-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "basenji2_tss_131kb_human_central3", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/basenji2_tss_131kb_human_central3/metadata.json", + "modality": "regulatory DNA / Basenji2 TSS sequence model", + "n_dims": 5313, + "n_genes": 20097, + "name": "Basenji2-TSS-131kb-human-central3-log1p-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/basenji2_tss_131kb_human_central3", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "biobert_gene_protein_summary", - "name": "BioBERT-GeneProteinSummary-v1.1", + "algorithm": "dmis-lab/biobert-base-cased-v1.2", "category": "Protein", "category_source": "heuristic", - "modality": "literature_text_gene_summary", - "algorithm": "dmis-lab/biobert-base-cased-v1.2", - "description": "NCBI gene card summaries plus UniProt protein summaries when available", - "n_genes": 19168, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 95.38, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/biobert_gene_protein_summary", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/biobert_gene_protein_summary", + "description": "NCBI gene card summaries plus UniProt protein summaries when available", + "id": "biobert_gene_protein_summary", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/biobert_gene_protein_summary/metadata.json", + "modality": "literature_text_gene_summary", + "n_dims": 768, + "n_genes": 19168, + "name": "BioBERT-GeneProteinSummary-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/biobert_gene_protein_summary", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "bioconceptvec_cbow", - "name": "BioConceptVec-CBOW-v1.1", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "biomedical_literature_text", - "algorithm": "see package metadata", - "description": "BioConceptVec-CBOW-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17040, - "n_dims": 100, + "community_contribution": false, "coverage_pct": 84.79, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/bioconceptvec_cbow", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_cbow", + "description": "BioConceptVec-CBOW-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "bioconceptvec_cbow", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_cbow/metadata.json", + "modality": "biomedical_literature_text", + "n_dims": 100, + "n_genes": 17040, + "name": "BioConceptVec-CBOW-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_cbow", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "bioconceptvec_fasttext", - "name": "BioConceptVec-fastText-v1.1", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "biomedical_literature_text", - "algorithm": "see package metadata", - "description": "BioConceptVec-fastText-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17040, - "n_dims": 100, + "community_contribution": false, "coverage_pct": 84.79, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/bioconceptvec_fasttext", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_fasttext", + "description": "BioConceptVec-fastText-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "bioconceptvec_fasttext", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_fasttext/metadata.json", + "modality": "biomedical_literature_text", + "n_dims": 100, + "n_genes": 17040, + "name": "BioConceptVec-fastText-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_fasttext", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "bioconceptvec_glove", - "name": "BioConceptVec-GloVe-v1.1", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "biomedical_literature_text", - "algorithm": "see package metadata", - "description": "BioConceptVec-GloVe-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17040, - "n_dims": 100, + "community_contribution": false, "coverage_pct": 84.79, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/bioconceptvec_glove", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_glove", + "description": "BioConceptVec-GloVe-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "bioconceptvec_glove", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_glove/metadata.json", + "modality": "biomedical_literature_text", + "n_dims": 100, + "n_genes": 17040, + "name": "BioConceptVec-GloVe-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_glove", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "bioconceptvec_skipgram", - "name": "BioConceptVec-SkipGram-v1.1", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "biomedical_literature_text", - "algorithm": "see package metadata", - "description": "BioConceptVec-SkipGram-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17040, - "n_dims": 100, + "community_contribution": false, "coverage_pct": 84.79, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/bioconceptvec_skipgram", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_skipgram", + "description": "BioConceptVec-SkipGram-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "bioconceptvec_skipgram", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_skipgram/metadata.json", + "modality": "biomedical_literature_text", + "n_dims": 100, + "n_genes": 17040, + "name": "BioConceptVec-SkipGram-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/bioconceptvec_skipgram", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "cmap_gse106127_cgs_mean_landmark978_zscore", - "name": "CMap-GSE106127-CGS-mean-landmark978-zscore-v1.1", + "algorithm": "see package metadata", "category": "Expression", "category_source": "heuristic", - "modality": "perturbational transcriptomics / L1000 consensus genetic perturbation signatures", - "algorithm": "see package metadata", - "description": "CMap-GSE106127-CGS-mean-landmark978-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 4070, - "n_dims": 978, + "community_contribution": false, "coverage_pct": 20.25, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/cmap_gse106127_cgs_mean_landmark978_zscore", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/cmap_gse106127_cgs_mean_landmark978_zscore", + "description": "CMap-GSE106127-CGS-mean-landmark978-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "cmap_gse106127_cgs_mean_landmark978_zscore", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/cmap_gse106127_cgs_mean_landmark978_zscore/metadata.json", + "modality": "perturbational transcriptomics / L1000 consensus genetic perturbation signatures", + "n_dims": 978, + "n_genes": 4070, + "name": "CMap-GSE106127-CGS-mean-landmark978-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/cmap_gse106127_cgs_mean_landmark978_zscore", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "deepnf_string_v12_ppmi_svd_fusion", - "name": "deepNF-STRING-v12-PPMI-SVD-fusion-v1.1", + "algorithm": "see package metadata", "category": "Network", "category_source": "heuristic", - "modality": "STRING network multimodal sparse PPMI/SVD fusion", - "algorithm": "see package metadata", - "description": "deepNF-STRING-v12-PPMI-SVD-fusion-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19071, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 94.89, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/deepnf_string_v12_ppmi_svd_fusion", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/deepnf_string_v12_ppmi_svd_fusion", + "description": "deepNF-STRING-v12-PPMI-SVD-fusion-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "deepnf_string_v12_ppmi_svd_fusion", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/deepnf_string_v12_ppmi_svd_fusion/metadata.json", + "modality": "STRING network multimodal sparse PPMI/SVD fusion", + "n_dims": 256, + "n_genes": 19071, + "name": "deepNF-STRING-v12-PPMI-SVD-fusion-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/deepnf_string_v12_ppmi_svd_fusion", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "deepsea_tss_1kb_epigenomic_probs", - "name": "DeepSEA-TSS-1kb-epigenomic-probabilities-zscore-v1.1", + "algorithm": "DeepSEA/predict from Kipoi", "category": "Regulatory", "category_source": "heuristic", - "modality": "regulatory DNA / promoter-TSS sequence model", - "algorithm": "DeepSEA/predict from Kipoi", - "description": "DeepSEA-TSS-1kb-epigenomic-probabilities-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 20097, - "n_dims": 919, + "community_contribution": false, "coverage_pct": 100.0, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/deepsea_tss_1kb_epigenomic_probs", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/deepsea_tss_1kb_epigenomic_probs", + "description": "DeepSEA-TSS-1kb-epigenomic-probabilities-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "deepsea_tss_1kb_epigenomic_probs", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/deepsea_tss_1kb_epigenomic_probs/metadata.json", + "modality": "regulatory DNA / promoter-TSS sequence model", + "n_dims": 919, + "n_genes": 20097, + "name": "DeepSEA-TSS-1kb-epigenomic-probabilities-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/deepsea_tss_1kb_epigenomic_probs", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "depmap_crispr_gene_effect_pca256", - "name": "DepMap-CRISPRGeneEffect-PCA256-v1.1", + "algorithm": "see package metadata", "category": "Functional Genomics", "category_source": "manual", - "modality": "functional genomics / CRISPR dependency", - "algorithm": "see package metadata", - "description": "Gene representation derived from DepMap CRISPR gene-effect profiles across cancer cell-line models, standardized and reduced to 256 dimensions using PCA.", - "n_genes": 18562, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 92.36, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/depmap_crispr_gene_effect_pca256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/depmap_crispr_gene_effect_pca256", + "description": "Gene representation derived from DepMap CRISPR gene-effect profiles across cancer cell-line models, standardized and reduced to 256 dimensions using PCA.", + "id": "depmap_crispr_gene_effect_pca256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/depmap_crispr_gene_effect_pca256/metadata.json", + "modality": "functional genomics / CRISPR dependency", + "n_dims": 256, + "n_genes": 18562, + "name": "DepMap-CRISPRGeneEffect-PCA256-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/depmap_crispr_gene_effect_pca256", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "dnabert2_117m_cds", - "name": "dnabert2_117m_cds_v1_1", + "algorithm": "DNABERT-2 117M", "category": "Protein", "category_source": "heuristic", - "modality": "canonical protein-coding CDS DNA sequence", - "algorithm": "DNABERT-2 117M", - "description": "dnabert2_117m_cds_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 20085, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 99.94, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/dnabert2_117m_cds", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/dnabert2_117m_cds", + "description": "dnabert2_117m_cds_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "dnabert2_117m_cds", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/dnabert2_117m_cds/metadata.json", + "modality": "canonical protein-coding CDS DNA sequence", + "n_dims": 768, + "n_genes": 20085, + "name": "dnabert2_117m_cds_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/dnabert2_117m_cds", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "enformer_tss_393kb_human_central3", - "name": "Enformer-TSS-393kb-human-central3-log1p-zscore-v1.1", + "algorithm": "Enformer", "category": "Regulatory", "category_source": "heuristic", - "modality": "regulatory DNA / long-range TSS sequence model", - "algorithm": "Enformer", - "description": "Enformer-TSS-393kb-human-central3-log1p-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 20097, - "n_dims": 5313, + "community_contribution": false, "coverage_pct": 100.0, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/enformer_tss_393kb_human_central3", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/enformer_tss_393kb_human_central3", + "description": "Enformer-TSS-393kb-human-central3-log1p-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "enformer_tss_393kb_human_central3", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/enformer_tss_393kb_human_central3/metadata.json", - "source_dataset": "embeddingsSSRF/gene_embeddings", - "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "modality": "regulatory DNA / long-range TSS sequence model", + "n_dims": 5313, + "n_genes": 20097, + "name": "Enformer-TSS-393kb-human-central3-log1p-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/enformer_tss_393kb_human_central3", + "qc_status": "processed_qc_passed", + "source_dataset": "embeddingsSSRF/gene_embeddings", + "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", + "zero_vectors": 0 }, { - "id": "esm2", - "name": "ESM2-v1.1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein_sequence", - "algorithm": "see package metadata", - "description": "ESM2-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18690, - "n_dims": 1280, + "community_contribution": false, "coverage_pct": 93.0, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/esm2", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/esm2", + "description": "ESM2-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "esm2", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/esm2/metadata.json", + "modality": "protein_sequence", + "n_dims": 1280, + "n_genes": 18690, + "name": "ESM2-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/esm2", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 + }, + { + "algorithm": "deterministic Gaussian fixture", + "availability_status": "available_at_acceptance", + "category": "other", + "category_source": "community_submission", + "community_contribution": true, + "coverage_pct": 7.5, + "dataset_path": "candidate_embedding", + "description": "Deterministic synthetic float32 vectors for 1,500 human Ensembl gene IDs, created solely to verify the automatic contribution, validation, registration, and external-reference publication workflow.", + "id": "external_reference_smoke_20260727_v1", + "license": "cc0-1.0", + "metadata_url": "https://huggingface.co/datasets/danieltslz/gene-embeddings-external-reference-smoke/blob/098258908de86982d2ced04e70f1353e46055d08/candidate_embedding/metadata.json", + "modality": "synthetic external-reference pipeline smoke test", + "n_dims": 16, + "n_genes": 1500, + "name": "External Reference Smoke Test 2026-07-27", + "package_url": "https://huggingface.co/datasets/danieltslz/gene-embeddings-external-reference-smoke/tree/098258908de86982d2ced04e70f1353e46055d08/candidate_embedding", + "qc_status": "AUTO_PASS", + "source_dataset": "danieltslz/gene-embeddings-external-reference-smoke", + "source_repo_type": "dataset", + "source_revision": "098258908de86982d2ced04e70f1353e46055d08", + "storage_mode": "external_reference", + "trace": [ + 0.424897, + 0.0, + 1.0, + 0.044766, + 0.719459, + 0.813992, + 0.319309, + 0.473156, + 0.761471, + 0.535774, + 0.274129, + 0.555382, + 0.573005, + 0.786742, + 0.576876, + 0.088022, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755, + 0.569755 + ], + "trace_gene": "ENSG00000000003", + "validation_path": "data/community_validation/external_reference_smoke_20260727_v1" }, { - "id": "frogs_archs4_256", - "name": "frogs_archs4_256_v1_1", + "algorithm": "FRoGS ARCHS4 gene embedding", "category": "Functional Genomics", "category_source": "manual", - "modality": "functional gene representation / ARCHS4 expression", - "algorithm": "FRoGS ARCHS4 gene embedding", - "description": "FRoGS gene representation incorporating functional relationships learned using large-scale ARCHS4 gene-expression information.", - "n_genes": 16265, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 80.93, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/frogs_archs4_256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/frogs_archs4_256", + "description": "FRoGS gene representation incorporating functional relationships learned using large-scale ARCHS4 gene-expression information.", + "id": "frogs_archs4_256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/frogs_archs4_256/metadata.json", + "modality": "functional gene representation / ARCHS4 expression", + "n_dims": 256, + "n_genes": 16265, + "name": "frogs_archs4_256_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/frogs_archs4_256", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "gene2vec", - "name": "Gene2Vec-v1.1", + "algorithm": "see package metadata", "category": "Expression", "category_source": "heuristic", - "modality": "coexpression_expression", - "algorithm": "see package metadata", - "description": "Gene2Vec-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17916, - "n_dims": 200, + "community_contribution": false, "coverage_pct": 89.15, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/gene2vec", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/gene2vec", + "description": "Gene2Vec-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "gene2vec", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/gene2vec/metadata.json", + "modality": "coexpression_expression", + "n_dims": 200, + "n_genes": 17916, + "name": "Gene2Vec-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/gene2vec", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "genecompass_base_gene_token", - "name": "genecompass_base_gene_token_v1_1", + "algorithm": "none; static learned token embedding weight extracted directly from checkpoint", "category": "Single-cell", "category_source": "heuristic", - "modality": "gene expression single-cell foundation model / knowledge-informed gene-token embedding", - "algorithm": "none; static learned token embedding weight extracted directly from checkpoint", - "description": "genecompass_base_gene_token_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 16578, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 82.49, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/genecompass_base_gene_token", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genecompass_base_gene_token", + "description": "genecompass_base_gene_token_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "genecompass_base_gene_token", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genecompass_base_gene_token/metadata.json", + "modality": "gene expression single-cell foundation model / knowledge-informed gene-token embedding", + "n_dims": 768, + "n_genes": 16578, + "name": "genecompass_base_gene_token_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genecompass_base_gene_token", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "geneformer_v2_316m", - "name": "Geneformer-V2-316M-v1.1", + "algorithm": "see package metadata", "category": "Single-cell", "category_source": "heuristic", - "modality": "single_cell_expression_foundation_model", - "algorithm": "see package metadata", - "description": "Geneformer-V2-316M-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 20007, - "n_dims": 1152, + "community_contribution": false, "coverage_pct": 99.55, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/geneformer_v2_316m", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/geneformer_v2_316m", + "description": "Geneformer-V2-316M-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "geneformer_v2_316m", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/geneformer_v2_316m/metadata.json", + "modality": "single_cell_expression_foundation_model", + "n_dims": 1152, + "n_genes": 20007, + "name": "Geneformer-V2-316M-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/geneformer_v2_316m", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "genept_ada_conservative", - "name": "GenePT-ADA-v1.1-conservative", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "biomedical_literature_text", - "algorithm": "see package metadata", - "description": "GenePT-ADA-v1.1-conservative. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19099, - "n_dims": 1536, + "community_contribution": false, "coverage_pct": 95.03, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/genept_ada", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genept_ada", + "description": "GenePT-ADA-v1.1-conservative. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "genept_ada_conservative", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genept_ada/metadata.json", + "modality": "biomedical_literature_text", + "n_dims": 1536, + "n_genes": 19099, + "name": "GenePT-ADA-v1.1-conservative", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genept_ada", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "genept_model3_gene_protein_conservative", - "name": "GenePT-Model3-GeneProtein-v1.1-conservative", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "biomedical_literature_text_plus_protein_sequence_text", - "algorithm": "see package metadata", - "description": "GenePT-Model3-GeneProtein-v1.1-conservative. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19103, - "n_dims": 3072, + "community_contribution": false, "coverage_pct": 95.05, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/genept_model3_gene_protein", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genept_model3_gene_protein", + "description": "GenePT-Model3-GeneProtein-v1.1-conservative. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "genept_model3_gene_protein_conservative", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genept_model3_gene_protein/metadata.json", + "modality": "biomedical_literature_text_plus_protein_sequence_text", + "n_dims": 3072, + "n_genes": 19103, + "name": "GenePT-Model3-GeneProtein-v1.1-conservative", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/genept_model3_gene_protein", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "gtex_tissue_median_log1p_zscore", - "name": "GTEx-tissue-median-log1p-zscore-v1.1", + "algorithm": "see package metadata", "category": "Expression", "category_source": "heuristic", - "modality": "bulk RNA expression / normal tissue expression", - "algorithm": "see package metadata", - "description": "GTEx-tissue-median-log1p-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19353, - "n_dims": 68, + "community_contribution": false, "coverage_pct": 96.3, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/gtex_tissue_median_log1p_zscore", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/gtex_tissue_median_log1p_zscore", + "description": "GTEx-tissue-median-log1p-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "gtex_tissue_median_log1p_zscore", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/gtex_tissue_median_log1p_zscore/metadata.json", + "modality": "bulk RNA expression / normal tissue expression", + "n_dims": 68, + "n_genes": 19353, + "name": "GTEx-tissue-median-log1p-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/gtex_tissue_median_log1p_zscore", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "helix_mrna_full_transcript", - "name": "helix_mrna_full_transcript_v1_1", + "algorithm": "helical-ai/helix-mRNA", "category": "RNA", "category_source": "manual", - "modality": "RNA language model / mature mRNA transcript", - "algorithm": "helical-ai/helix-mRNA", - "description": "Gene-level mature-transcript representation generated with Helix-mRNA and mean-pooled across non-special sequence tokens.", - "n_genes": 19976, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 99.4, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/helix_mrna_full_transcript", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/helix_mrna_full_transcript", + "description": "Gene-level mature-transcript representation generated with Helix-mRNA and mean-pooled across non-special sequence tokens.", + "id": "helix_mrna_full_transcript", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/helix_mrna_full_transcript/metadata.json", + "modality": "RNA language model / mature mRNA transcript", + "n_dims": 256, + "n_genes": 19976, + "name": "helix_mrna_full_transcript_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/helix_mrna_full_transcript", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "hetionet_nonppi_biomedical_context_tfidf_svd256", - "name": "Hetionet-nonPPI-biomedical-context-TFIDF-SVD256-v1.1", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "heterogeneous biomedical knowledge graph / non-PPI gene context", - "algorithm": "see package metadata", - "description": "Hetionet-nonPPI-biomedical-context-TFIDF-SVD256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18787, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 93.48, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/hetionet_nonppi_biomedical_context_tfidf_svd256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hetionet_nonppi_biomedical_context_tfidf_svd256", + "description": "Hetionet-nonPPI-biomedical-context-TFIDF-SVD256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "hetionet_nonppi_biomedical_context_tfidf_svd256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hetionet_nonppi_biomedical_context_tfidf_svd256/metadata.json", + "modality": "heterogeneous biomedical knowledge graph / non-PPI gene context", + "n_dims": 256, + "n_genes": 18787, + "name": "Hetionet-nonPPI-biomedical-context-TFIDF-SVD256-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hetionet_nonppi_biomedical_context_tfidf_svd256", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "hpa_normal_ihc_tissue_level_zscore", - "name": "HPA-normal-IHC-tissue-level-zscore-v1.1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein expression / normal tissue immunohistochemistry", - "algorithm": "see package metadata", - "description": "HPA-normal-IHC-tissue-level-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 13420, - "n_dims": 59, + "community_contribution": false, "coverage_pct": 66.78, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/hpa_normal_ihc_tissue_level_zscore", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hpa_normal_ihc_tissue_level_zscore", + "description": "HPA-normal-IHC-tissue-level-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "hpa_normal_ihc_tissue_level_zscore", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hpa_normal_ihc_tissue_level_zscore/metadata.json", + "modality": "protein expression / normal tissue immunohistochemistry", + "n_dims": 59, + "n_genes": 13420, + "name": "HPA-normal-IHC-tissue-level-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hpa_normal_ihc_tissue_level_zscore", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "hpa_subcellular_location_multihot_zscore", - "name": "HPA-subcellular-location-multihot-zscore-v1.1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein subcellular localization", - "algorithm": "see package metadata", - "description": "HPA-subcellular-location-multihot-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 13581, - "n_dims": 50, + "community_contribution": false, "coverage_pct": 67.58, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/hpa_subcellular_location_multihot_zscore", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hpa_subcellular_location_multihot_zscore", + "description": "HPA-subcellular-location-multihot-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "hpa_subcellular_location_multihot_zscore", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hpa_subcellular_location_multihot_zscore/metadata.json", + "modality": "protein subcellular localization", + "n_dims": 50, + "n_genes": 13581, + "name": "HPA-subcellular-location-multihot-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hpa_subcellular_location_multihot_zscore", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "hyenadna_medium_160k_cds", - "name": "hyenadna_medium_160k_cds_v1_1", + "algorithm": "final hidden-state mean pooling over non-special nucleotide tokens; long CDS split into chunks and token-count weighted", "category": "DNA", "category_source": "manual", - "modality": "DNA language model / canonical coding sequence", - "algorithm": "final hidden-state mean pooling over non-special nucleotide tokens; long CDS split into chunks and token-count weighted", - "description": "Gene-level canonical-CDS representation generated with the HyenaDNA medium 160k sequence-length model.", - "n_genes": 20085, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 99.94, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/hyenadna_medium_160k_cds", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hyenadna_medium_160k_cds", + "description": "Gene-level canonical-CDS representation generated with the HyenaDNA medium 160k sequence-length model.", + "id": "hyenadna_medium_160k_cds", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hyenadna_medium_160k_cds/metadata.json", + "modality": "DNA language model / canonical coding sequence", + "n_dims": 256, + "n_genes": 20085, + "name": "hyenadna_medium_160k_cds_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/hyenadna_medium_160k_cds", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "mahi_all_contexts_mean", - "name": "mahi_all_contexts_mean_v1_1", + "algorithm": "mean across all non-global tissue/cell contexts per Entrez gene", "category": "Multimodal", "category_source": "manual", - "modality": "multimodal tissue-aware graph representation / mean across non-global contexts", - "algorithm": "mean across all non-global tissue/cell contexts per Entrez gene", - "description": "Mahi gene representation formed by averaging embeddings across all available non-global tissue and cell contexts.", - "n_genes": 18918, - "n_dims": 3666, + "community_contribution": false, "coverage_pct": 94.13, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/mahi_all_contexts_mean", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mahi_all_contexts_mean", + "description": "Mahi gene representation formed by averaging embeddings across all available non-global tissue and cell contexts.", + "id": "mahi_all_contexts_mean", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mahi_all_contexts_mean/metadata.json", + "modality": "multimodal tissue-aware graph representation / mean across non-global contexts", + "n_dims": 3666, + "n_genes": 18918, + "name": "mahi_all_contexts_mean_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mahi_all_contexts_mean", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "mahi_global", - "name": "mahi_global_v1_1", + "algorithm": "global context only", "category": "Multimodal", "category_source": "manual", - "modality": "multimodal tissue-aware graph representation / global context", - "algorithm": "global context only", - "description": "Global-context Mahi gene representation integrating regulatory, protein and network-derived molecular information.", - "n_genes": 18918, - "n_dims": 3666, + "community_contribution": false, "coverage_pct": 94.13, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/mahi_global", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mahi_global", + "description": "Global-context Mahi gene representation integrating regulatory, protein and network-derived molecular information.", + "id": "mahi_global", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mahi_global/metadata.json", + "modality": "multimodal tissue-aware graph representation / global context", + "n_dims": 3666, + "n_genes": 18918, + "name": "mahi_global_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mahi_global", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "mashup_string", - "name": "Mashup-STRING-v1.1", + "algorithm": "see package metadata", "category": "Network", "category_source": "heuristic", - "modality": "network_ppi", - "algorithm": "see package metadata", - "description": "Mashup-STRING-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 16331, - "n_dims": 800, + "community_contribution": false, "coverage_pct": 81.26, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/mashup_string", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mashup_string", + "description": "Mashup-STRING-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "mashup_string", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mashup_string/metadata.json", + "modality": "network_ppi", + "n_dims": 800, + "n_genes": 16331, + "name": "Mashup-STRING-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/mashup_string", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "msa_transformer_depth1_uniprot_human", - "name": "MSATransformer-depth1-UniProt-human-v1.1", + "algorithm": "esm_msa1b_t12_100M_UR50S", "category": "Protein", "category_source": "heuristic", - "modality": "protein_sequence_msa_transformer_depth1", - "algorithm": "esm_msa1b_t12_100M_UR50S", - "description": "MSATransformer-depth1-UniProt-human-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19472, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 96.89, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/msa_transformer_depth1_uniprot_human", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/msa_transformer_depth1_uniprot_human", + "description": "MSATransformer-depth1-UniProt-human-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "msa_transformer_depth1_uniprot_human", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/msa_transformer_depth1_uniprot_human/metadata.json", + "modality": "protein_sequence_msa_transformer_depth1", + "n_dims": 768, + "n_genes": 19472, + "name": "MSATransformer-depth1-UniProt-human-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/msa_transformer_depth1_uniprot_human", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "newt_archs4_256", - "name": "NEWT-ARCHS4-256-v1.1", + "algorithm": "see package metadata", "category": "Regulatory", "category_source": "heuristic", - "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", - "algorithm": "see package metadata", - "description": "NEWT-ARCHS4-256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 16265, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 80.93, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/newt_archs4_256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_archs4_256", + "description": "NEWT-ARCHS4-256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "newt_archs4_256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_archs4_256/metadata.json", + "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", + "n_dims": 256, + "n_genes": 16265, + "name": "NEWT-ARCHS4-256-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_archs4_256", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "newt_cellnet", - "name": "NEWT-CellNet-v1.1", + "algorithm": "see package metadata", "category": "Regulatory", "category_source": "heuristic", - "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", - "algorithm": "see package metadata", - "description": "NEWT-CellNet-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17499, - "n_dims": 128, + "community_contribution": false, "coverage_pct": 87.07, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/newt_cellnet", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_cellnet", + "description": "NEWT-CellNet-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "newt_cellnet", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_cellnet/metadata.json", + "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", + "n_dims": 128, + "n_genes": 17499, + "name": "NEWT-CellNet-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_cellnet", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "newt_go_256", - "name": "NEWT-GO-256-v1.1", + "algorithm": "see package metadata", "category": "Regulatory", "category_source": "heuristic", - "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", - "algorithm": "see package metadata", - "description": "NEWT-GO-256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 13788, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 68.61, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/newt_go_256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_go_256", + "description": "NEWT-GO-256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "newt_go_256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_go_256/metadata.json", + "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", + "n_dims": 256, + "n_genes": 13788, + "name": "NEWT-GO-256-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_go_256", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "newt_go_graph", - "name": "NEWT-GO-graph-v1.1", + "algorithm": "see package metadata", "category": "Regulatory", "category_source": "heuristic", - "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", - "algorithm": "see package metadata", - "description": "NEWT-GO-graph-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 13788, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 68.61, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/newt_go_graph", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_go_graph", + "description": "NEWT-GO-graph-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "newt_go_graph", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_go_graph/metadata.json", + "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", + "n_dims": 256, + "n_genes": 13788, + "name": "NEWT-GO-graph-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_go_graph", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "newt_msigdb_bundle", - "name": "NEWT-MSigDB-bundle-v1.1", + "algorithm": "see package metadata", "category": "Regulatory", "category_source": "heuristic", - "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", - "algorithm": "see package metadata", - "description": "NEWT-MSigDB-bundle-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 15423, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 76.74, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/newt_msigdb_bundle", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_msigdb_bundle", + "description": "NEWT-MSigDB-bundle-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "newt_msigdb_bundle", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_msigdb_bundle/metadata.json", + "modality": "multimodal functional/regulatory/co-expression/pathway gene embedding component from NEWT", + "n_dims": 256, + "n_genes": 15423, + "name": "NEWT-MSigDB-bundle-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/newt_msigdb_bundle", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "node2vec_consensus_ppi", - "name": "Node2Vec-consensus-PPI-v1.1", + "algorithm": "see package metadata", "category": "Network", "category_source": "heuristic", - "modality": "PPI network embedding", - "algorithm": "see package metadata", - "description": "Node2Vec-consensus-PPI-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18356, - "n_dims": 128, + "community_contribution": false, "coverage_pct": 91.34, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/node2vec_consensus_ppi", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/node2vec_consensus_ppi", + "description": "Node2Vec-consensus-PPI-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "node2vec_consensus_ppi", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/node2vec_consensus_ppi/metadata.json", + "modality": "PPI network embedding", + "n_dims": 128, + "n_genes": 18356, + "name": "Node2Vec-consensus-PPI-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/node2vec_consensus_ppi", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "nt_v2_500m_multispecies_cds", - "name": "nt_v2_500m_multispecies_cds_v1_1", + "algorithm": "InstaDeepAI/nucleotide-transformer-v2-500m-multi-species", "category": "DNA", "category_source": "manual", - "modality": "DNA language model / canonical coding sequence", - "algorithm": "InstaDeepAI/nucleotide-transformer-v2-500m-multi-species", - "description": "Gene-level canonical-CDS representation generated with the 500M-parameter multispecies Nucleotide Transformer v2 checkpoint.", - "n_genes": 20085, - "n_dims": 1024, + "community_contribution": false, "coverage_pct": 99.94, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/nt_v2_500m_multispecies_cds", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/nt_v2_500m_multispecies_cds", + "description": "Gene-level canonical-CDS representation generated with the 500M-parameter multispecies Nucleotide Transformer v2 checkpoint.", + "id": "nt_v2_500m_multispecies_cds", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/nt_v2_500m_multispecies_cds/metadata.json", + "modality": "DNA language model / canonical coding sequence", + "n_dims": 1024, + "n_genes": 20085, + "name": "nt_v2_500m_multispecies_cds_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/nt_v2_500m_multispecies_cds", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "opa2vec_goa_human", - "name": "OPA2Vec-GOA-human-v1.1", + "algorithm": "see package metadata", "category": "Knowledge", "category_source": "heuristic", - "modality": "Gene Ontology / ontology-annotation semantic embedding", - "algorithm": "see package metadata", - "description": "OPA2Vec-GOA-human-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18660, - "n_dims": 200, + "community_contribution": false, "coverage_pct": 92.85, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/opa2vec_goa_human", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/opa2vec_goa_human", + "description": "OPA2Vec-GOA-human-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "opa2vec_goa_human", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/opa2vec_goa_human/metadata.json", + "modality": "Gene Ontology / ontology-annotation semantic embedding", + "n_dims": 200, + "n_genes": 18660, + "name": "OPA2Vec-GOA-human-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/opa2vec_goa_human", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "orthrus_base_4track_full_transcript", - "name": "orthrus_base_4track_full_transcript_v1_1", + "algorithm": "Orthrus base 4-track", "category": "RNA", "category_source": "manual", - "modality": "RNA foundation model / mature mRNA transcript", - "algorithm": "Orthrus base 4-track", - "description": "Mature-transcript representation generated with the Orthrus base four-track RNA foundation model.", - "n_genes": 19976, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 99.4, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/orthrus_base_4track_full_transcript", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/orthrus_base_4track_full_transcript", + "description": "Mature-transcript representation generated with the Orthrus base four-track RNA foundation model.", + "id": "orthrus_base_4track_full_transcript", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/orthrus_base_4track_full_transcript/metadata.json", + "modality": "RNA foundation model / mature mRNA transcript", + "n_dims": 256, + "n_genes": 19976, + "name": "orthrus_base_4track_full_transcript_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/orthrus_base_4track_full_transcript", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "primekg_nonppi_biomedical_context_tfidf_svd256", - "name": "PrimeKG-nonPPI-biomedical-context-TFIDF-SVD256-v1.1", + "algorithm": "see package metadata", "category": "Literature", "category_source": "heuristic", - "modality": "heterogeneous biomedical knowledge graph / non-PPI gene context", - "algorithm": "see package metadata", - "description": "PrimeKG-nonPPI-biomedical-context-TFIDF-SVD256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19216, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 95.62, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/primekg_nonppi_biomedical_context_tfidf_svd256", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/primekg_nonppi_biomedical_context_tfidf_svd256", + "description": "PrimeKG-nonPPI-biomedical-context-TFIDF-SVD256-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "primekg_nonppi_biomedical_context_tfidf_svd256", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/primekg_nonppi_biomedical_context_tfidf_svd256/metadata.json", + "modality": "heterogeneous biomedical knowledge graph / non-PPI gene context", + "n_dims": 256, + "n_genes": 19216, + "name": "PrimeKG-nonPPI-biomedical-context-TFIDF-SVD256-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/primekg_nonppi_biomedical_context_tfidf_svd256", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_aac", - "name": "probe_aac_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_aac_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 20, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_aac", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_aac", + "description": "probe_aac_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_aac", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_aac/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 20, + "n_genes": 18873, + "name": "probe_aac_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_aac", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_albert", - "name": "probe_albert_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_albert_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18453, - "n_dims": 4096, + "community_contribution": false, "coverage_pct": 91.82, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_albert", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_albert", + "description": "probe_albert_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_albert", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_albert/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 4096, + "n_genes": 18453, + "name": "probe_albert_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_albert", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_apaac", - "name": "probe_apaac_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_apaac_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18871, - "n_dims": 80, + "community_contribution": false, "coverage_pct": 93.9, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_apaac", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_apaac", + "description": "probe_apaac_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_apaac", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_apaac/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 80, + "n_genes": 18871, + "name": "probe_apaac_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_apaac", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_bert_bfd", - "name": "probe_bert_bfd_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_bert_bfd_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18453, - "n_dims": 1024, + "community_contribution": false, "coverage_pct": 91.82, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_bert_bfd", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_bert_bfd", + "description": "probe_bert_bfd_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_bert_bfd", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_bert_bfd/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 1024, + "n_genes": 18453, + "name": "probe_bert_bfd_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_bert_bfd", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_bert_pfam", - "name": "probe_bert_pfam_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_bert_pfam_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18461, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 91.86, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_bert_pfam", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_bert_pfam", + "description": "probe_bert_pfam_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_bert_pfam", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_bert_pfam/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 768, + "n_genes": 18461, + "name": "probe_bert_pfam_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_bert_pfam", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_blast", - "name": "probe_blast_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_blast_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 20421, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_blast", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_blast", + "description": "probe_blast_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_blast", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_blast/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 20421, + "n_genes": 18873, + "name": "probe_blast_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_blast", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_cpc_prot", - "name": "probe_cpc_prot_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_cpc_prot_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18453, - "n_dims": 512, + "community_contribution": false, "coverage_pct": 91.82, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_cpc_prot", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_cpc_prot", + "description": "probe_cpc_prot_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_cpc_prot", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_cpc_prot/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 512, + "n_genes": 18453, + "name": "probe_cpc_prot_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_cpc_prot", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_esmb1", - "name": "probe_esmb1_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_esmb1_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18453, - "n_dims": 1280, + "community_contribution": false, "coverage_pct": 91.82, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_esmb1", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_esmb1", + "description": "probe_esmb1_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_esmb1", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_esmb1/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 1280, + "n_genes": 18453, + "name": "probe_esmb1_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_esmb1", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_gene2vec_uniprot", - "name": "probe_gene2vec_uniprot_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_gene2vec_uniprot_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17564, - "n_dims": 200, + "community_contribution": false, "coverage_pct": 87.4, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_gene2vec_uniprot", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_gene2vec_uniprot", + "description": "probe_gene2vec_uniprot_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_gene2vec_uniprot", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_gene2vec_uniprot/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 200, + "n_genes": 17564, + "name": "probe_gene2vec_uniprot_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_gene2vec_uniprot", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_hmmer", - "name": "probe_hmmer_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_hmmer_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 20421, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_hmmer", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_hmmer", + "description": "probe_hmmer_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_hmmer", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_hmmer/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 20421, + "n_genes": 18873, + "name": "probe_hmmer_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_hmmer", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_ksep", - "name": "probe_ksep_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_ksep_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18801, - "n_dims": 400, + "community_contribution": false, "coverage_pct": 93.55, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 23, "dataset_path": "data/embeddings/probe_ksep", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_ksep", + "description": "probe_ksep_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_ksep", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_ksep/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 400, + "n_genes": 18801, + "name": "probe_ksep_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_ksep", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 23 }, { - "id": "probe_learned_vec", - "name": "probe_learned_vec_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_learned_vec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 64, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_learned_vec", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_learned_vec", + "description": "probe_learned_vec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_learned_vec", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_learned_vec/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 64, + "n_genes": 18873, + "name": "probe_learned_vec_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_learned_vec", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_mut2vec", - "name": "probe_mut2vec_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_mut2vec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 17445, - "n_dims": 300, + "community_contribution": false, "coverage_pct": 86.8, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_mut2vec", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_mut2vec", + "description": "probe_mut2vec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_mut2vec", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_mut2vec/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 300, + "n_genes": 17445, + "name": "probe_mut2vec_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_mut2vec", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_pfam", - "name": "probe_pfam_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_pfam_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 6227, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 1532, "dataset_path": "data/embeddings/probe_pfam", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_pfam", + "description": "probe_pfam_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_pfam", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_pfam/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 6227, + "n_genes": 18873, + "name": "probe_pfam_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_pfam", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 1532 }, { - "id": "probe_protvec", - "name": "probe_protvec_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_protvec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 100, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_protvec", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_protvec", + "description": "probe_protvec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_protvec", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_protvec/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 100, + "n_genes": 18873, + "name": "probe_protvec_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_protvec", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_seqvec", - "name": "probe_seqvec_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_seqvec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 1024, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_seqvec", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_seqvec", + "description": "probe_seqvec_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_seqvec", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_seqvec/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 1024, + "n_genes": 18873, + "name": "probe_seqvec_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_seqvec", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_t5", - "name": "probe_t5_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_t5_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18453, - "n_dims": 1024, + "community_contribution": false, "coverage_pct": 91.82, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_t5", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_t5", + "description": "probe_t5_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_t5", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_t5/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 1024, + "n_genes": 18453, + "name": "probe_t5_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_t5", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_tcga_embedding", - "name": "probe_tcga_embedding_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_tcga_embedding_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18221, - "n_dims": 50, + "community_contribution": false, "coverage_pct": 90.67, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_tcga_embedding", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_tcga_embedding", + "description": "probe_tcga_embedding_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_tcga_embedding", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_tcga_embedding/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 50, + "n_genes": 18221, + "name": "probe_tcga_embedding_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_tcga_embedding", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_unirep", - "name": "probe_unirep_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_unirep_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18873, - "n_dims": 5700, + "community_contribution": false, "coverage_pct": 93.91, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_unirep", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_unirep", + "description": "probe_unirep_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_unirep", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_unirep/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 5700, + "n_genes": 18873, + "name": "probe_unirep_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_unirep", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "probe_xlnet", - "name": "probe_xlnet_v1_1", + "algorithm": "see package metadata", "category": "Protein", "category_source": "heuristic", - "modality": "protein sequence / protein representation from PROBE human UniProt archive", - "algorithm": "see package metadata", - "description": "probe_xlnet_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 18453, - "n_dims": 1024, + "community_contribution": false, "coverage_pct": 91.82, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/probe_xlnet", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_xlnet", + "description": "probe_xlnet_v1_1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "probe_xlnet", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_xlnet/metadata.json", + "modality": "protein sequence / protein representation from PROBE human UniProt archive", + "n_dims": 1024, + "n_genes": 18453, + "name": "probe_xlnet_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/probe_xlnet", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "pubmedbert_gene_protein_summary", - "name": "PubMedBERT-GeneProteinSummary-v1.1", + "algorithm": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext", "category": "Protein", "category_source": "heuristic", - "modality": "literature_text_gene_summary", - "algorithm": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext", - "description": "NCBI gene card summaries plus UniProt protein summaries when available", - "n_genes": 19168, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 95.38, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/pubmedbert_gene_protein_summary", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/pubmedbert_gene_protein_summary", + "description": "NCBI gene card summaries plus UniProt protein summaries when available", + "id": "pubmedbert_gene_protein_summary", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/pubmedbert_gene_protein_summary/metadata.json", + "modality": "literature_text_gene_summary", + "n_dims": 768, + "n_genes": 19168, + "name": "PubMedBERT-GeneProteinSummary-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/pubmedbert_gene_protein_summary", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "rnafm_full_transcript", - "name": "rnafm_full_transcript_v1_1", + "algorithm": "RNA-FM / rna_fm_t12", "category": "RNA", "category_source": "manual", - "modality": "RNA language model / mature mRNA transcript", - "algorithm": "RNA-FM / rna_fm_t12", - "description": "Mature-transcript representation generated from the final layer of RNA-FM using length-weighted token pooling.", - "n_genes": 19976, - "n_dims": 640, + "community_contribution": false, "coverage_pct": 99.4, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/rnafm_full_transcript", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/rnafm_full_transcript", + "description": "Mature-transcript representation generated from the final layer of RNA-FM using length-weighted token pooling.", + "id": "rnafm_full_transcript", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/rnafm_full_transcript/metadata.json", + "modality": "RNA language model / mature mRNA transcript", + "n_dims": 640, + "n_genes": 19976, + "name": "rnafm_full_transcript_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/rnafm_full_transcript", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "scfoundation_gene_pos", - "name": "scFoundation-gene-pos-v1.1", + "algorithm": "see package metadata", "category": "Single-cell", "category_source": "heuristic", - "modality": "single_cell_expression_foundation_model / learned gene identity-position embedding", - "algorithm": "see package metadata", - "description": "scFoundation-gene-pos-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19062, - "n_dims": 768, + "community_contribution": false, "coverage_pct": 94.85, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/scfoundation_gene_pos", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scfoundation_gene_pos", + "description": "scFoundation-gene-pos-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "scfoundation_gene_pos", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scfoundation_gene_pos/metadata.json", + "modality": "single_cell_expression_foundation_model / learned gene identity-position embedding", + "n_dims": 768, + "n_genes": 19062, + "name": "scFoundation-gene-pos-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scfoundation_gene_pos", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "scgpt_whole_human", - "name": "scGPT-whole-human-v1.1", + "algorithm": "see package metadata", "category": "Single-cell", "category_source": "heuristic", - "modality": "single_cell_expression_foundation_model", - "algorithm": "see package metadata", - "description": "scGPT-whole-human-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19280, - "n_dims": 512, + "community_contribution": false, "coverage_pct": 95.93, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/scgpt_whole_human", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scgpt_whole_human", + "description": "scGPT-whole-human-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "scgpt_whole_human", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scgpt_whole_human/metadata.json", + "modality": "single_cell_expression_foundation_model", + "n_dims": 512, + "n_genes": 19280, + "name": "scGPT-whole-human-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scgpt_whole_human", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "scgpt_pancancer", - "name": "scgpt_pancancer_v1_1", + "algorithm": "scGPT pan-cancer gene-token embedding", "category": "Single-cell", "category_source": "manual", - "modality": "single-cell transcriptomic foundation model / pan-cancer gene-token embedding", - "algorithm": "scGPT pan-cancer gene-token embedding", - "description": "Gene-token representation derived from a pan-cancer scGPT single-cell transcriptomic model.", - "n_genes": 19071, - "n_dims": 512, + "community_contribution": false, "coverage_pct": 94.89, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/scgpt_pancancer", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scgpt_pancancer", + "description": "Gene-token representation derived from a pan-cancer scGPT single-cell transcriptomic model.", + "id": "scgpt_pancancer", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scgpt_pancancer/metadata.json", + "modality": "single-cell transcriptomic foundation model / pan-cancer gene-token embedding", + "n_dims": 512, + "n_genes": 19071, + "name": "scgpt_pancancer_v1_1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scgpt_pancancer", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "scprint_medium_v1_5_gene", - "name": "scPRINT-medium-v1.5-gene-v1.1", + "algorithm": "see package metadata", "category": "Single-cell", "category_source": "heuristic", - "modality": "single_cell_expression_foundation_model / learned gene-token embedding", - "algorithm": "see package metadata", - "description": "scPRINT-medium-v1.5-gene-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19995, - "n_dims": 256, + "community_contribution": false, "coverage_pct": 99.49, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/scprint_medium_v1_5_gene", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scprint_medium_v1_5_gene", + "description": "scPRINT-medium-v1.5-gene-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "scprint_medium_v1_5_gene", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scprint_medium_v1_5_gene/metadata.json", + "modality": "single_cell_expression_foundation_model / learned gene-token embedding", + "n_dims": 256, + "n_genes": 19995, + "name": "scPRINT-medium-v1.5-gene-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/scprint_medium_v1_5_gene", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "spliceai_canonical_splice_site_profile", - "name": "SpliceAI-canonical-splice-site-profile-zscore-v1.1", + "algorithm": "SpliceAI", "category": "Regulatory", "category_source": "heuristic", - "modality": "splicing sequence model / canonical transcript splice-site profiles", - "algorithm": "SpliceAI", - "description": "SpliceAI-canonical-splice-site-profile-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 20097, - "n_dims": 606, + "community_contribution": false, "coverage_pct": 100.0, - "qc_status": "processed_qc_passed", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/spliceai_canonical_splice_site_profile", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/spliceai_canonical_splice_site_profile", + "description": "SpliceAI-canonical-splice-site-profile-zscore-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "spliceai_canonical_splice_site_profile", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/spliceai_canonical_splice_site_profile/metadata.json", + "modality": "splicing sequence model / canonical transcript splice-site profiles", + "n_dims": 606, + "n_genes": 20097, + "name": "SpliceAI-canonical-splice-site-profile-zscore-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/spliceai_canonical_splice_site_profile", + "qc_status": "processed_qc_passed", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 }, { - "id": "uce_33l", - "name": "UCE-33L-v1.1", + "algorithm": "see package metadata", "category": "Single-cell", "category_source": "heuristic", - "modality": "single_cell_expression_foundation_model / protein-informed gene-token embedding", - "algorithm": "see package metadata", - "description": "UCE-33L-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", - "n_genes": 19082, - "n_dims": 1280, + "community_contribution": false, "coverage_pct": 94.95, - "qc_status": "legacy_core_package", - "license": "not recorded in package metadata", - "zero_vectors": 0, "dataset_path": "data/embeddings/uce_33l", - "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/uce_33l", + "description": "UCE-33L-v1.1. Core embedding package from embeddingsSSRF/gene_embeddings.", + "id": "uce_33l", + "license": "not recorded in package metadata", "metadata_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/blob/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/uce_33l/metadata.json", + "modality": "single_cell_expression_foundation_model / protein-informed gene-token embedding", + "n_dims": 1280, + "n_genes": 19082, + "name": "UCE-33L-v1.1", + "package_url": "https://huggingface.co/datasets/embeddingsSSRF/gene_embeddings/tree/326b257a20e73df337ece40bb82401e277851f5b/data/embeddings/uce_33l", + "qc_status": "legacy_core_package", "source_dataset": "embeddingsSSRF/gene_embeddings", "source_revision": "326b257a20e73df337ece40bb82401e277851f5b", - "community_contribution": false + "zero_vectors": 0 } ]