generated: '2026-10-14T21:57:46' study: pezizo_set1 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/pezizo_set1 --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/config.csv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations --study pezizo_set1 --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/analysis/enrichment/outputs/cache --threads 8 --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 --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/analysis/enrichment/outputs/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: novelty target_group: label: IN species: - Amega - Ncra - Afum - Ztri - Cimm other_group: label: OUT species: - Nirr - CneoH99 - Ccin - Mcir - Spom - Scer universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations annotation_files: Amega: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP001658139.tsv.gz Ncra: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000001805.tsv.gz Afum: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000002530.tsv.gz Ztri: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000008062.tsv.gz Cimm: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000001261.tsv.gz Nirr: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000186594.tsv.gz CneoH99: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000010091.tsv.gz Ccin: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000001861.tsv.gz Mcir: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000014254.tsv.gz Spom: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000002485.tsv.gz Scer: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000002311.tsv.gz annotation_sources: Amega: UniProt reference proteome (no GO/Pfam/InterPro in the UniProt entries) + Pfam-A HMM search (hmmsearch) for pfam_ids/pfam_names Ncra: not recorded (no sidecar) Afum: not recorded (no sidecar) Ztri: not recorded (no sidecar) Cimm: not recorded (no sidecar) Nirr: not recorded (no sidecar) CneoH99: not recorded (no sidecar) Ccin: not recorded (no sidecar) Mcir: not recorded (no sidecar) Spom: not recorded (no sidecar) Scer: not recorded (no sidecar) vocabulary_coverage: pfam: species_with_terms: - Amega - Ncra - Afum - Ztri - Cimm species_without_terms: [] n_with: 5 n_species: 5 pfam_clan: species_with_terms: - Amega - Ncra - Afum - Ztri - Cimm species_without_terms: [] n_with: 5 n_species: 5 interpro: species_with_terms: - Ncra - Afum - Ztri - Cimm species_without_terms: - Amega n_with: 4 n_species: 5 go: species_with_terms: - Ncra - Afum - Ztri - Cimm species_without_terms: - Amega n_with: 4 n_species: 5 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: 3193 candidates_txt: 3193 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/presence_matrix.uniprot.tsv rule: IN count / 5 >= 0.75 and OUT count / 6 <= 0.0 (own proteome counts toward the target group) only_in_matrix_rule: [] only_in_candidates_file: [] background_clustering: key: 0e343548b7fe11b9 n_sequences: 48610 n_clusters: 26964 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: 96.3 threads: 4 created: '2026-10-12T14:42:09' cache_hit: true 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/pezizo_set1/config.csv: e07595644d3146648b9fc40d96fa14205b78c7421fa782402b7385981ba197ef /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/candidates.txt: acac1134f1730d945b48970afa363215ae080e30b2ba3b06425e89eba03fc421 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/novelties.Amega.tsv: bb7ac4d4224bde251a6a064183019b85fbaa83b509b673bda34f5871e6e46de0 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/novelties.Ncra.tsv: 5e347073cc4797ed182ed5aed46b443405bc8a8001a712a86f274bd428b274e7 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/novelties.Afum.tsv: a44ee67b9dfec43a82007b5df8a366996995e3efbe7a5750a3da24b386314664 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/novelties.Ztri.tsv: 639c8327d21f6c2114dccc33e20d2c9ed2676939eb3825b01b9eb99a8717f820 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/novelties.Cimm.tsv: 9625880dad63f109a54e6683b86b171959170309686349cd469020e58b91b8c1 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/pezizo_set1/presence_matrix.uniprot.tsv: add2e340fc746fefe556f7f9f41fd401ee78f0bb711369280572ec15220c825a /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/data_dir/pep/Amega.pep.fa: 32510ef5d5c17a8ea72f1a88f9695d152ad908e5ead9c4bce4e4534b4ef9d0d7 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/data_dir/pep/Ncra.pep.fa: 64510ca60f0efbd7831689a409eafcd1ad5251eb1a541663a223f396148d54eb /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/data_dir/pep/Afum.pep.fa: 1e888bb1a1aa58b9ff6adf3eb221affa7a67c57618aa4663eebaeea81eea7a28 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/data_dir/pep/Ztri.pep.fa: 3224be4a0ac028418b7571d322c8e837d85c1a3923bb0a606d4e2898b6b3673a /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/data_dir/pep/Cimm.pep.fa: 71b0445457051f4e4faaf2fbf45f35c4c88e5722e5f890c28ed5deac1d7e9e3a /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/species.csv: a73170da299b4f890cac59854cbf974933d7b1ec3de59006ee538726076d1a19 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP001658139.tsv.gz: 96b19c6ccbed33f91955ae1236e6a1ba585cfde0840cf3721f37b83a8f63d048 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000001805.tsv.gz: a15af9195cbb0a281c431f7cd75c9296f45c9ff48f093c0bc40934d2e145e12c /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000002530.tsv.gz: a5b7b48dfb0bae7656399d5b4ae263d7422f6edbfef38560e757056afa7a7577 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000008062.tsv.gz: b3c0a46bb2299ccccbcfc8c780ce9ce08772a126e6dba2528cf0382549d54a13 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000001261.tsv.gz: eef9a7afbd45341c4a0a41e370a8e05249fda7a31e16b45fa201d785ba4bc89c /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000186594.tsv.gz: c49f80107f2f929a67869fc0815508b2290813f2e4bb9b52ba27f993dc44c51d /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000010091.tsv.gz: b7621c7a9a589042564980a46807b81d3c9b53b191b9cff0adf9d3b09e30f73c /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000001861.tsv.gz: 254921dd73f18d34346aa35b2a709bd42e94cba1359debe0d800232093dc4c1e /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000014254.tsv.gz: 263d27b0a2977efd3faa7a39ae3056796c970fcb9b114b447a3660a2a0990eef /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000002485.tsv.gz: d520a30aea4f063a12ea0b0be8730c879073646534c58095d18268b98b9905d2 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP000002311.tsv.gz: 2bbf3241cabc412c7f560e95c4d55ac83dc868e7203a6bc75fa523155d72ce67 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/pezizo_set1/annotations/UP001658139.tsv.gz.provenance.yaml : 4da209bd0b03720dac8cfb46d159a7b48c07dbcb61cac2167058ec662d1dbbf4 ? /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: 13.5 background_cluster_s: 0.1 tests_s: 8.2 total_s: 25.1 host: r22 slurm_job: '29966667'