Spaces:
Running
Running
| """The NTv3 annotation benchmark: test species, released files and published scores.""" | |
| from dataclasses import dataclass | |
| DATASET_REPO = "InstaDeepAI/NTv3_annot_dataset" | |
| class TestSpecies: | |
| """One held-out species of the benchmark.""" | |
| name: str | |
| clade: str | |
| assembly: str | |
| released_gff: str | |
| gene_f1: float | |
| cds_f1: float | |
| def model_repo(self) -> str: | |
| """Hugging Face repo of the clade model, which also holds its predictions.""" | |
| return f"InstaDeepAI/NTv3_annot_{self.clade}" | |
| def dataset_dir(self) -> str: | |
| """Folder of the species in ``DATASET_REPO``.""" | |
| return f"{self.clade}/test_species/{self.assembly}" | |
| def reference_gff(self) -> str: | |
| """Benchmark reference in ``DATASET_REPO``.""" | |
| return f"{self.dataset_dir}/reference_longest_isoform.gff3.gz" | |
| def genome_fasta(self) -> str: | |
| """Soft-masked genome in ``DATASET_REPO`` (bgzipped, indexed).""" | |
| return f"{self.dataset_dir}/genome.fa.gz" | |
| def _species( | |
| name: str, clade: str, assembly: str, tag: str, gene_f1: float, cds_f1: float | |
| ) -> TestSpecies: | |
| return TestSpecies( | |
| name, | |
| clade, | |
| assembly, | |
| f"annot_results/ntv3_{name}_{tag}.gff3.gz", | |
| gene_f1, | |
| cds_f1, | |
| ) | |
| # Gene / CDS F1 (%) of the released NTv3 GFF3s, whole genome, as in the paper. | |
| TEST_SPECIES = { | |
| s.name: s | |
| for s in ( | |
| _species( | |
| "bos_taurus", | |
| "mammals", | |
| "GCF_002263795.3_ARS-UCD2.0", | |
| "GCF_002263795.3", | |
| 58.06, | |
| 90.60, | |
| ), | |
| _species( | |
| "delphinapterus_leucas", | |
| "mammals", | |
| "GCF_002288925.2_ASM228892v3", | |
| "GCF_002288925.2", | |
| 54.66, | |
| 89.68, | |
| ), | |
| _species( | |
| "brachypodium_distachyon", | |
| "plants", | |
| "GCF_000005505.3_Brachypodium_distachyon_v3.0", | |
| "GCF_000005505.3", | |
| 71.89, | |
| 89.68, | |
| ), | |
| _species( | |
| "eschscholzia_californica", | |
| "plants", | |
| "EcalifornicavarOrangeKingHAP1v1.1", | |
| "OrangeKingHAP1v1.1", | |
| 73.17, | |
| 91.07, | |
| ), | |
| _species( | |
| "freycinetia_multiflora", | |
| "plants", | |
| "FmultifloravarABG20040013HAP1v1.1", | |
| "ABG20040013HAP1v1.1", | |
| 68.36, | |
| 88.73, | |
| ), | |
| _species( | |
| "medicago_truncatula", | |
| "plants", | |
| "GCF_003473485.1_MtrunA17r5.0-ANR", | |
| "GCF_003473485.1", | |
| 72.63, | |
| 89.33, | |
| ), | |
| _species( | |
| "mimulus_guttatus", | |
| "plants", | |
| "MguttatusvarIM62v3.1", | |
| "IM62v3.1", | |
| 80.73, | |
| 93.54, | |
| ), | |
| _species( | |
| "bombyx_mori", | |
| "insects", | |
| "GCF_030269925.1_ASM3026992v2", | |
| "GCF_030269925.1", | |
| 56.53, | |
| 85.19, | |
| ), | |
| _species( | |
| "cataglyphis_hispanica", | |
| "insects", | |
| "GCF_021464435.1_ULB_Chis1_1.0", | |
| "GCF_021464435.1", | |
| 63.94, | |
| 87.85, | |
| ), | |
| _species( | |
| "colias_croceus", | |
| "insects", | |
| "GCF_905220415.1_ilColCroc2.1", | |
| "GCF_905220415.1", | |
| 62.65, | |
| 88.13, | |
| ), | |
| _species( | |
| "danaus_plexippus", | |
| "insects", | |
| "GCF_018135715.1_MEX_DaPlex", | |
| "GCF_018135715.1", | |
| 65.68, | |
| 89.38, | |
| ), | |
| _species( | |
| "leptidea_sinapis", | |
| "insects", | |
| "GCF_905404315.1_ilLepSina1.1", | |
| "GCF_905404315.1", | |
| 55.00, | |
| 81.99, | |
| ), | |
| _species( | |
| "nymphalis_io", | |
| "insects", | |
| "GCF_905147045.1_ilAglIoxx1.1", | |
| "GCF_905147045.1", | |
| 66.02, | |
| 89.19, | |
| ), | |
| _species( | |
| "osmia_bicornis", | |
| "insects", | |
| "GCF_907164935.1_iOsmBic2.1", | |
| "GCF_907164935.1", | |
| 58.75, | |
| 86.26, | |
| ), | |
| _species( | |
| "tribolium_castaneum", | |
| "insects", | |
| "GCF_031307605.1_icTriCast1.1", | |
| "GCF_031307605.1", | |
| 53.05, | |
| 80.60, | |
| ), | |
| _species( | |
| "vanessa_cardui", | |
| "insects", | |
| "GCF_905220365.1_ilVanCard2.1", | |
| "GCF_905220365.1", | |
| 64.37, | |
| 88.77, | |
| ), | |
| _species( | |
| "zerene_cesonia", | |
| "insects", | |
| "GCF_012273895.1_Zerene_cesonia_1.1", | |
| "GCF_012273895.1", | |
| 61.31, | |
| 85.14, | |
| ), | |
| ) | |
| } | |