--- license: other tags: - single-cell - transcriptomics - foundation-model - circulating-tumor-cells library_name: pytorch --- # BioMod BioMod is a single-cell transcriptomics foundation model built around gene modules and a Performer-based encoder. This repository provides pretrained model assets, pretraining and fine-tuning code, downstream task tutorials, and interpretability tools. BioMod is released by **CTC-Atlas**, the joint laboratory of **Raymind Biotechnology Co., Ltd** and the **Shenzhen Research Institute of Big Data (SRIBD)**. [Installation](#installation) · [BioMod model weights](#biomod-model-weights) · [Tasks and examples](#tasks-and-examples) · [Usage notes](#usage-notes) · [Repository layout](#repository-layout) ## Installation Download the project from [Hugging Face](https://huggingface.co/ctcatlas/BioMod). Run the following commands from the parent of your intended project directory: ```bash python -m pip install --upgrade huggingface_hub hf auth login hf download ctcatlas/BioMod --local-dir ./BioMod cd BioMod ``` The download includes source code, model dependencies, the pretrained checkpoint, and datasets. To omit datasets, add `--exclude "data/**"` to the download command. If you already have the project, start from its root directory. Create and activate the supplied Conda environment: ```bash conda env create -f BioMod/environment.yml conda activate performer_module ``` The environment specification uses Python 3.9, PyTorch 2.6, CUDA 12.4, and PyTorch Geometric 2.6. See [environment.yml](BioMod/environment.yml) and [requirements.txt](BioMod/requirements.txt) for the complete dependency lists. Match the GPU packages to your system when adapting the environment. Pretraining uses CUDA/NCCL. The zero-shot runner selects CUDA when available and otherwise uses CPU. Native Windows execution has not been validated for the supplied environment. ## BioMod model weights This release includes the **BioMod model weights** and their matching configuration. Use these files together; the configuration records the model architecture and gene-module definitions. | Asset | File | | --- | --- | | BioMod model weights | [mae_tost_70M_75mask_ec2_epoch0.pth](weight/0810model/mae_tost_70M_75mask_ec2_epoch0.pth) | | Matching model configuration | [mae_tost_70M_75mask_ec2.pkl](weight/0810model/mae_tost_70M_75mask_ec2.pkl) | | Model gene order | [selected_genes_27k.txt](model_dependencies/selected_genes_27k.txt) | | Gene identifier mapping | [gene2ens.csv](model_dependencies/gene2ens.csv) | | Gene2Vec embeddings | [selected_gene2vec_27k.npy](model_dependencies/selected_gene2vec_27k.npy) | | Shared module definitions | [merged_modules.json](model_dependencies/module_data_all/merged_modules.json) | The model components are bundled under [`model_dependencies/performer_pytorch_cont/`](model_dependencies/performer_pytorch_cont/). Task-specific checkpoint arguments are listed under [Usage notes](#checkpoint-arguments). ## Tasks and examples The following tasks have implementations in this repository. The links identify available source code and examples; these workflows have not been validated end to end with the bundled checkpoint. | Task | Implementation | Notebook | | --- | --- | --- | | Cell-type annotation | [Fine-tuning script](BioMod/cell_annotation/performer_module_finetune.py) | [Notebook](BioMod/toturials/cell_annotation.ipynb) | | Zero-shot cell embeddings and batch-effect evaluation | [Embedding and evaluation script](BioMod/zero_shot_batch/performer_module_zero_shot.py) | [Notebook](BioMod/toturials/zero_shot_batch_integration.ipynb) | | Single-drug response regression (IC50) | [Training script](BioMod/drug_response/train_drug_performer_module.py) | [Notebook](BioMod/toturials/drug_response_prediction.ipynb) | | Drug-pair synergy classification | [Training script](BioMod/drug_combination/train_drug_combination_performer_module.py) | [Notebook](BioMod/toturials/drug_combination.ipynb) | | Gene perturbation response prediction | [Training script](BioMod/gene_perturbation/train_module.py) | [Notebook](BioMod/toturials/gene_perturbation.ipynb) | ### Pretraining and analysis scripts The repository also includes the following supporting workflows. | Workflow | Implementation | Documentation | | --- | --- | --- | | Pretraining and continued pretraining | [Pretraining script](BioMod/performer_module.py) | [Source guide](BioMod/README.md), [launcher reference](BioMod/command.txt) | | Module interpretability analysis | [Module geometry](BioMod/interpretability/module_geometry.py), [module importance](BioMod/interpretability/module_importance/module_importance.py), [text alignment](BioMod/interpretability/module_text_alignment/module_text_alignment.py) | [Overview](BioMod/interpretability/README.md), [attention](BioMod/interpretability/attention/README.md), [module importance guide](BioMod/interpretability/module_importance/README.md) | Tutorials and launcher references retain some historical checkpoint paths, server paths, and arguments. Adapt them to the current assets above and check the selected script's `--help` before running. Some notebook plotting steps also refer to external scripts or reference results that are not bundled here. ## Usage notes ### Project paths and notebooks The project root contains `BioMod/`, `model_dependencies/`, `weight/`, and `data/`. The inner `BioMod/` directory contains the source code. Task commands may assume different working directories; adjust relative paths when following a guide. Before running a notebook, update its configuration cells: | Setting | Location | | --- | --- | | `BASE` or `ASSET_ROOT` | Project root | | `PROJECT_ROOT` | Inner `BioMod/` source directory | | `MODULE_MODEL` or `LEGACY_MODULE_MODEL` | `model_dependencies/` under the project root | | Weight and configuration paths | The BioMod model weights and matching configuration listed above | | `MODULE_DATA_DIR` | `BioMod/module_data_all/` under the project root | | Data and output paths | Your task inputs and a writable output directory | Checkpoint variable names differ by notebook: `CKPT_PATH` / `CONFIG_PKL` for cell annotation, drug response, and zero-shot integration; `SCFM_CKPT` / `SCFM_HYPER` for gene perturbation; and `CHECKPOINT_PATH` / `HYPER_PARAMS_PATH` for drug combination. Updating environment variables alone does not replace hard-coded notebook paths. ### Checkpoint arguments | Task | Weights argument | Configuration argument | | --- | --- | --- | | Drug response / drug combination | `--checkpoint_path` | `--hyper_params_path` | | Zero-shot / gene perturbation | `--scfm_ckpt_path` | `--scfm_hyper_params_path` | | Cell annotation / backbone interpretation | `--performer_checkpoint` | `--config_pkl` | | Continued pretraining | `--model_path` | `--model_config_path` or paired-file discovery | ### Data and evaluation Datasets are stored under `data/`. Input formats, metadata fields, preprocessing, and train/validation splits depend on the task; follow the linked implementation and tutorial. For zero-shot embeddings, provide an h5ad expression matrix and specify the gene, batch, and cell-type metadata fields. The runner aligns genes to the model gene list and fills missing genes with zeros. It does not normalize or log-transform the input matrix, so prepare expression values according to the intended protocol. Resolve duplicate gene identifiers and inspect gene overlap before evaluating embeddings. The drug-response and drug-combination workflows use validation metrics for checkpoint selection. Their validation results should not be presented as performance on an independent final test set. For checks of the shared training utilities, see [Training utility checks](BioMod/README.md#training-utility-checks). ## Repository layout The tree below includes source files, model dependencies, and the pretrained checkpoint. The top-level `data/` and `.cache/` directories are omitted for readability. Folder descriptions explain where to find each component.
Expand the full repository structure ```text BioMod/ # Project root: source code, model dependencies and weights ├── BioMod/ # Task code: training, evaluation, interpretability and tutorials │ ├── cell_annotation/ # Cell-type annotation and model fine-tuning │ │ ├── module_data/ # Hallmark and Reactome modules with loading utilities │ │ │ ├── load_module.py │ │ │ ├── module1_hallmarks.json │ │ │ └── module2_reactome_2022_filtered.json │ │ ├── cmd_finetune.md │ │ └── performer_module_finetune.py │ ├── drug_combination/ # Drug-combination synergy prediction │ │ ├── README.md │ │ └── train_drug_combination_performer_module.py │ ├── drug_response/ # Single-drug response prediction and training │ │ ├── cmd.txt │ │ └── train_drug_performer_module.py │ ├── gene_perturbation/ # Perturbation response prediction: processing, training and inference │ │ ├── data_utils_local.py │ │ ├── gears_reduce_local.py │ │ ├── inference_local.py │ │ ├── model_module.py │ │ ├── pertdata_local.py │ │ ├── README.md │ │ ├── scfm_utils_local.py │ │ ├── train_module.py │ │ └── utils.py │ ├── interpretability/ # Module representations and biological interpretability │ │ ├── attention/ # Module crosstalk and within-module gene attention │ │ │ ├── __init__.py │ │ │ ├── module_crosstalk.py │ │ │ ├── module_gene_attention.py │ │ │ ├── README.md │ │ │ └── README_gene_attention.md │ │ ├── module_importance/ # Module importance, ablation studies and marker-gene validation │ │ │ ├── __init__.py │ │ │ ├── cross_class_similarity.py │ │ │ ├── family_ablation.py │ │ │ ├── family_importance_analysis.py │ │ │ ├── marker_gene_verification.py │ │ │ ├── masking_ablation.py │ │ │ ├── module_importance.py │ │ │ ├── module_importance_publication.py │ │ │ ├── pub_utils.py │ │ │ ├── random_baseline.py │ │ │ ├── README.md │ │ │ ├── RESULTS.md │ │ │ ├── tcell_reactome_analysis.py │ │ │ └── TODO.md │ │ ├── module_text_alignment/ # Semantic alignment of module representations and pathway text │ │ │ ├── __init__.py │ │ │ ├── DESIGN.md │ │ │ ├── fetch_reactome_descriptions.py │ │ │ ├── MANUSCRIPT_SECTION.md │ │ │ ├── module_text_alignment.py │ │ │ ├── module_text_alignment_extended.py │ │ │ ├── module_text_alignment_publication.py │ │ │ └── reactome_descriptions.json │ │ ├── __init__.py │ │ ├── module_geometry.py │ │ ├── README.md │ │ └── utils.py │ ├── module_data_all/ # Module definitions, merging and uncovered-gene tools │ │ ├── create_uncovered_modules.py │ │ ├── merge_modules.py │ │ └── merged_modules.json │ ├── tests/ # CPU tests for shared training utilities │ │ └── test_training_utils.py │ ├── toturials/ # Jupyter tutorials for five downstream tasks │ │ ├── cell_annotation.ipynb │ │ ├── drug_combination.ipynb │ │ ├── drug_response_prediction.ipynb │ │ ├── gene_perturbation.ipynb │ │ └── zero_shot_batch_integration.ipynb │ ├── zero_shot_batch/ # Zero-shot batch integration, evaluation and visualization │ │ ├── sequencing_depth/ # Low-depth data generation and zero-shot evaluation │ │ │ ├── cmd.txt │ │ │ ├── make_low_depth_h5ad.py │ │ │ └── run_zero_shot_low_depth.py │ │ ├── performer_module_zero_shot.py │ │ ├── README.md │ │ └── visualize_results.py │ ├── .env.example │ ├── .gitattributes │ ├── .gitignore │ ├── command.txt │ ├── environment.yml │ ├── models_performer_module.py │ ├── module_dataset.py │ ├── performer_module.py │ ├── README.md │ ├── requirements.txt │ └── training_utils.py ├── model_dependencies/ # Shared gene mappings, gene lists, embeddings and model components │ ├── module_data_all/ # Shared module definitions and construction tools │ │ ├── create_uncovered_modules.py │ │ ├── merge_modules.py │ │ └── merged_modules.json │ ├── performer_pytorch_cont/ # Performer attention and model components │ │ ├── performer_pytorch_cont/ # Nested package containing copies of the model component source files │ │ │ ├── __init__.py │ │ │ ├── ding_models.py │ │ │ ├── performer_pytorch.py │ │ │ ├── performer_pytorch_old.py │ │ │ └── reversible.py │ │ ├── __init__.py │ │ ├── ding_models.py │ │ ├── performer_pytorch.py │ │ ├── performer_pytorch_old.py │ │ └── reversible.py │ ├── gene2ens.csv │ ├── selected_gene2vec_27k.npy │ └── selected_genes_27k.txt ├── weight/ # Pretrained weights and matching model configurations │ └── 0810model/ # BioMod model weights and matching configuration │ ├── mae_tost_70M_75mask_ec2.pkl │ └── mae_tost_70M_75mask_ec2_epoch0.pth ├── .gitattributes ├── .gitignore └── README.md ```
## Partners - [Raymind Biotechnology Co., Ltd](https://en.raymind.com/) - [Shenzhen Research Institute of Big Data (SRIBD)](https://www.sribd.cn/en)