generated: '2026-10-24T14:51:54' study: yc_pseudo_dermatophyte script: path: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/enrich_novelties_v2.py sha256: d1e8fe16f6842e86fb6c226f822c8c173450a8fec660ca6879a6f8a821ad5aa7 command: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/.pixi/envs/default/bin/python3 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/enrich_novelties_v2.py --results /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/config.csv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations --study yc_pseudo_dermatophyte --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/analysis/enrichment/outputs/cache --threads 4 --pfam-dat /srv/projects/db/pfam/2026-01-27-Pfam38.2/Pfam-A.hmm.dat --interpro-entries /srv/projects/db/interproscan/6.0.0/110.0/interpro/110.0/entries.json --controls /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/actin_controls.tsv --ingroup-min-frac 0.75 --universe proteome --cluster-background --direction novelty --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/analysis/enrichment/outputs/novelty/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: novelty target_group: label: IN species: - Tricrubr - Micrcani - Tricinte - Nanngyps other_group: label: OUT species: - Anid - Talastip universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations annotation_files: Tricrubr: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000008864.tsv.gz Micrcani: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/Microsporum_canis_BMU_08102.proteins.tsv.gz Tricinte: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000024533.tsv.gz Nanngyps: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/Nannizzia_gypsea_CBS_118893.proteins.tsv.gz Anid: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000000560.tsv.gz Talastip: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000001745.tsv.gz annotation_sources: Tricrubr: not recorded (no sidecar) Micrcani: Pfam-A HMM search (hmmsearch); Pfam only Tricinte: not recorded (no sidecar) Nanngyps: Pfam-A HMM search (hmmsearch); Pfam only Anid: not recorded (no sidecar) Talastip: not recorded (no sidecar) vocabulary_coverage: pfam: species_with_terms: - Tricrubr - Micrcani - Tricinte - Nanngyps species_without_terms: [] n_with: 4 n_species: 4 pfam_clan: species_with_terms: - Tricrubr - Micrcani - Tricinte - Nanngyps species_without_terms: [] n_with: 4 n_species: 4 interpro: species_with_terms: - Tricrubr - Tricinte species_without_terms: - Micrcani - Nanngyps n_with: 2 n_species: 4 go: species_with_terms: - Tricrubr - Tricinte species_without_terms: - Micrcani - Nanngyps n_with: 2 n_species: 4 parameters: min_bg: 5 exclude_iea: false report_ids_fdr: 0.05 ingroup_min_frac: 0.75 other_max_frac: 0.0 cluster_background: true statistics: one-sided hypergeometric scipy.stats.hypergeom.sf(k-1,M,n,N); BH (lib/stats_util.bh_fdr) within scope x level x vocabulary; scope-B fdr_bh_all_species = BH across species tests of one level x vocabulary. goatools only parses the OBO and gives is_a ancestors. candidate_check: matrix_in_rule_and_0_out: 3023 candidates_txt: 3023 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/presence_matrix.uniprot.tsv rule: IN count / 4 >= 0.75 and OUT count / 2 <= 0.0 (own proteome counts toward the target group) only_in_matrix_rule: [] only_in_candidates_file: [] background_clustering: key: fce8b20974fc8151 n_sequences: 30400 n_clusters: 11492 mmseqs: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/.pixi/envs/default/bin/mmseqs mmseqs_version: 18.8cc5c command: mmseqs easy-cluster --threads N --min-seq-id 0.3 -c 0.8 --cov-mode 0 runtime_s: 44.1 threads: 4 created: '2026-10-24T14:51:49' cache_hit: false pipeline_candidate_families: 'novelties..tsv family_id (nf_NovInvenio MMSEQS_CLUSTER: mmseqs easy-cluster --min-seq-id 0.3 -c 0.8 --cov-mode 0 on candidates.fa)' candidates_without_family_row: 0 go_obo: path: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/data/go/go-basic.obo data_version: releases/2026-07-26 sha256: b08d45b268b8c24ccb2513dbbbc7d4df9f6521c099b413f79eb31e06e0fa3bcc pfam_dat: path: /srv/projects/db/pfam/2026-01-27-Pfam38.2/Pfam-A.hmm.dat sha256: ead9a40cdb871e1e6ceb151ea15c7aeaff083add2558031b4811afb9d7496b2d release_note: release taken from directory name; the .dat file has no version line interpro_entries: /srv/projects/db/interproscan/6.0.0/110.0/interpro/110.0/entries.json inputs_sha256: ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/config.csv : 5b58378692ee5449b1c71d3bb5754ae6cd18b3d75449c49bc2c98b58396ccd3e /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/candidates.txt: c04e8a19b71fa53b01390590cd5df64fdd67b8479e6e50742a9927ea26bec470 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/novelties.Tricrubr.tsv: 753da8c79de4dd0864ded41f1fc161b8d74ebd0ba4568f2e5a5be84b7ba856cc /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/novelties.Micrcani.tsv: 3680490d5820277f52cce29d4b9289b951969d076583ee6e07171f802e638153 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/novelties.Tricinte.tsv: 365ad84d55f387d3b46520ea35747d82b7f6462fb34ab689c5a8a3e4ecdba084 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/novelties.Nanngyps.tsv: 911fa4e519fd10636519cd571e6909641d4eb660d98b22d436e7b5e77d2842e4 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pseudo_dermatophyte/presence_matrix.uniprot.tsv: 82e72fd2884d96ba7b22909af163d7c6d52d84d6431afc9dedbc978cbccf31ee ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/data_dir/pep/UP000008864_559305.pep.fa : 3b62984fdcdc9ac549047cc3025e2abdabaaefde7a17bff066be4c4f40a84552 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/data_dir/pep/Micrcani.pep.fa : bbdc66acc9b1d4754aa3dbdffed34abdede6df2ebb8cf6a6bcf2f498e82adf53 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/data_dir/pep/UP000024533_1215338.pep.fa : 49db8ee7168ef3a426cd727175a53abf32c9ba3e57af15ac791c85893aa06104 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/data_dir/pep/Nanngyps.pep.fa : 13df2a2e69fc5d7e3deb09a0b38044dcd35e1b8a75ca48f04b3afb5845ff3163 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/species.csv : ed23d1e53ebe264ac291beb81fffc874d4988461587eb14c5c8f0ee45a851b4b ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000008864.tsv.gz : 60d1ad081da989724c1872832a69e6432385210eab61f4f64c38fa353e246885 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/Microsporum_canis_BMU_08102.proteins.tsv.gz : 44cb98c7f909340843ae4a17e266b1c8ba1ed7b3052e01c8b023a6c7628c0f6a ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000024533.tsv.gz : ddad87128940f1113360060c513b9cc875fda30514e36cf87fefe320bc1fe544 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/Nannizzia_gypsea_CBS_118893.proteins.tsv.gz : b2afc566d13c29cd870b4f1346c53ac43007164c23dd7c97f43575c6bf924fbe ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000000560.tsv.gz : 39c8a51f76bbfcff402e73adc4af1bba62df58f8e76af87a63c2aa7e5204de3d ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/UP000001745.tsv.gz : d858b84e6e03b950834d4b036778b406329a9d34422b86c46b4f160e07ec4961 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/Microsporum_canis_BMU_08102.proteins.tsv.gz.provenance.yaml : 9572ec90a81441c87a703f29ae41460da94edd780eb608448c8cf7ce932c1ebf ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pseudo_dermatophyte/annotations/Nannizzia_gypsea_CBS_118893.proteins.tsv.gz.provenance.yaml : 3b66639f8b38cf9d8776070047d11597050d5073e616d0d06878d9f6087ea186 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/zoosporic_dikarya/analysis/enrichment/actin_controls.tsv : dd7c85c91f413f3eee48b75b51c1ad75f7e2de6afcb611c5e0b3659f777a23d1 tools: python: 3.12.14 scipy: 1.18.1 goatools: 1.6.4 mmseqs: 18.8cc5c runtimes_s: load_s: 3.7 background_cluster_s: 44.4 tests_s: 3.2 total_s: 52.6 host: r11 slurm_job: '30452604'