generated: '2026-10-24T14:38:03' study: yc_tremellomycetes 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_tremellomycetes --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/config.csv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations --study yc_tremellomycetes --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/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_tremellomycetes/analysis/enrichment/outputs/novelty/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: novelty target_group: label: IN species: - CneoH99 - Kwonmang - Tricasah - Tremes other_group: label: OUT species: - Dacrprim - Calocorn - Ccin universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations annotation_files: CneoH99: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000010091.tsv.gz Kwonmang: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/Kwoniella_mangrovensis_CBS_8507.proteins.tsv.gz Tricasah: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000006757.tsv.gz Tremes: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000289152.tsv.gz Dacrprim: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000030653.tsv.gz Calocorn: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000076842.tsv.gz Ccin: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000001861.tsv.gz annotation_sources: CneoH99: not recorded (no sidecar) Kwonmang: Pfam-A HMM search (hmmsearch); Pfam only Tricasah: not recorded (no sidecar) Tremes: not recorded (no sidecar) Dacrprim: not recorded (no sidecar) Calocorn: not recorded (no sidecar) Ccin: not recorded (no sidecar) vocabulary_coverage: pfam: species_with_terms: - CneoH99 - Kwonmang - Tricasah - Tremes species_without_terms: [] n_with: 4 n_species: 4 pfam_clan: species_with_terms: - CneoH99 - Kwonmang - Tricasah - Tremes species_without_terms: [] n_with: 4 n_species: 4 interpro: species_with_terms: - CneoH99 - Tricasah - Tremes species_without_terms: - Kwonmang n_with: 3 n_species: 4 go: species_with_terms: - CneoH99 - Tricasah - Tremes species_without_terms: - Kwonmang n_with: 3 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: 2689 candidates_txt: 2689 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/presence_matrix.uniprot.tsv rule: IN count / 4 >= 0.75 and OUT count / 3 <= 0.0 (own proteome counts toward the target group) only_in_matrix_rule: [] only_in_candidates_file: [] background_clustering: key: 6f8e308086e5774c n_sequences: 29118 n_clusters: 15031 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: 50.0 threads: 4 created: '2026-10-24T14:37:58' 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_tremellomycetes/config.csv : 2764e26bddc94a8848e42aa8dae2345315cae01d8a4e3d6f669c415757ce536d /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/candidates.txt: 594c750d3f858fb43d6a8176b423313bf5cd987210612e2f5c06e86173421078 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/novelties.CneoH99.tsv: ecd23bd20063a748b1d00abaa40830174783e4f80a246773b1732f13331fd1d3 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/novelties.Kwonmang.tsv: 238b666841e95ed59bb179436ea056f2b94e9f843b2b79acee14ae3d506e9324 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/novelties.Tricasah.tsv: ae1dccfb1578bed147939e198c2a91f5bd78050025ea4d546d846381cf2ba1fa /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/novelties.Tremes.tsv: 580b6891eaf9e2aad58b3f4400df52abd5a0b8a4cab9097061ec9f1f30ed48c0 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_tremellomycetes/presence_matrix.uniprot.tsv: 562562ba365608491aa86648156e19b1f9aeec898eda66842ed53854f9f85931 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/data_dir/pep/UP000010091_235443.pep.fa : 0aac11ac6b8d8332a4d0b1ed530b14da22f11c33c32423844c4f015482dbcd36 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/data_dir/pep/Kwonmang.pep.fa : df2ecb9364404525d6edc00a74928694fbca0d55d4b1fd031d725a203c102d5c ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/data_dir/pep/UP000006757_1220162.pep.fa : 5a2b7e40ab14fd1622ef4e6d54ff008f005aef2495ddc25668a9286683895fec ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/data_dir/pep/UP000289152_5217.pep.fa : e7fb244b59656dbb6d4e204e622a6a9a9d27ce79a157f0abf7a298266ac216d3 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/species.csv : ae82141b90bf1cf681bc92385b7378d3d595faf654fc84a3c05b0ec9f0905dae ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000010091.tsv.gz : dd02a5d33482dba013da7e124c73b991cb09c72ebcce4ebce78d9fa57fb11100 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/Kwoniella_mangrovensis_CBS_8507.proteins.tsv.gz : db1e84e7e0d73ab9434fd74534a86d8a295cba1d950ddaea0d17e135020ce6ec ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000006757.tsv.gz : 6260cedaf1acaafed0712a45c5d15b27108bbf7985a8fa3065d1e1df164ddd43 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000289152.tsv.gz : c3d7c3860dc208784fcb655774cf510cf615ade87c8a891508a4dbda12cae87c ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000030653.tsv.gz : bf1bca91cd10d8ebf08cb049af219ae5e60af857251514f6071a146bb82422eb ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000076842.tsv.gz : 814fdac7f685fc44f43b779ee66d698571cad86cd040de7930defc4b95f081d0 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/UP000001861.tsv.gz : d9c9d7d2ba7462a6ec34aa250423058af301c3664e9c1249cd16a365c7fccd97 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_tremellomycetes/annotations/Kwoniella_mangrovensis_CBS_8507.proteins.tsv.gz.provenance.yaml : f0449ac3f73b36bf12b365d4caae90ba274a6bc55afe82d9593662af45ad917c ? /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: 50.4 tests_s: 3.5 total_s: 59.1 host: r11 slurm_job: '30452604'