generated: '2026-10-24T14:31:21' study: yc_chaetothyriales 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_chaetothyriales --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/config.csv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations --study yc_chaetothyriales --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/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_chaetothyriales/analysis/enrichment/outputs/novelty/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: novelty target_group: label: IN species: - Exopderm - Exopspin - Exopphae - Exopolig - Exopmeso other_group: label: OUT species: - Caprcoro - Cladcarr - Fonspedr universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations annotation_files: Exopderm: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000007304.tsv.gz Exopspin: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000053328.tsv.gz Exopphae: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/Exophiala_phaeomuriformis_CBS_132758.proteins.tsv.gz Exopolig: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000053342.tsv.gz Exopmeso: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000054302.tsv.gz Caprcoro: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000019484.tsv.gz Cladcarr: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000094526.tsv.gz Fonspedr: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000053029.tsv.gz annotation_sources: Exopderm: not recorded (no sidecar) Exopspin: not recorded (no sidecar) Exopphae: Pfam-A HMM search (hmmsearch); Pfam only Exopolig: not recorded (no sidecar) Exopmeso: not recorded (no sidecar) Caprcoro: not recorded (no sidecar) Cladcarr: not recorded (no sidecar) Fonspedr: not recorded (no sidecar) vocabulary_coverage: pfam: species_with_terms: - Exopderm - Exopspin - Exopphae - Exopolig - Exopmeso species_without_terms: [] n_with: 5 n_species: 5 pfam_clan: species_with_terms: - Exopderm - Exopspin - Exopphae - Exopolig - Exopmeso species_without_terms: [] n_with: 5 n_species: 5 interpro: species_with_terms: - Exopderm - Exopspin - Exopolig - Exopmeso species_without_terms: - Exopphae n_with: 4 n_species: 5 go: species_with_terms: - Exopderm - Exopspin - Exopolig - Exopmeso species_without_terms: - Exopphae 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: 163 candidates_txt: 163 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/presence_matrix.uniprot.tsv rule: IN count / 5 >= 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: f916a56a6e1ae953 n_sequences: 51018 n_clusters: 15749 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: 56.8 threads: 4 created: '2026-10-24T14:31:14' 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_chaetothyriales/config.csv : d4d3053408fe01d3617203348009c7e8a93ea921a50d9aec3ae3079dd2684e92 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/candidates.txt: 6f692b1577900b304e3c151dc5f83019f60ea2c6b2a99d4569dc1e2be31dfbdd /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/novelties.Exopderm.tsv: c2146d0ebd1f2883583015d097a5e4aec5c178e8c81d6407fce5e48371fa5ec4 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/novelties.Exopspin.tsv: 931a55be151e75381831e979ebabc7437b87245f716943ae3b99ee11e78b0beb /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/novelties.Exopphae.tsv: ad8f933dd394d935e912d863e71dd8bc5dec2becad0cad4dec6eb985cfcd8ba1 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/novelties.Exopolig.tsv: 7ec9347492b71261dc0ea422179aa9b7594158cbd6b46675527104bacec5e3d7 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/novelties.Exopmeso.tsv: 91b89c0f54ffa38dbab57eebe6c0491457223dac03030ee8113b8cea60fcb2b8 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_chaetothyriales/presence_matrix.uniprot.tsv: c35931559eb95223dbf5c280328180627a15b9aeb384aeefccd97cd01e1516d7 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/data_dir/pep/UP000007304_858893.pep.fa : 9cf1448a5ed2b84d2ca3f2df54c67ed594c8c95f7c5edf9b91c0a63c7769f478 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/data_dir/pep/UP000053328_91928.pep.fa : 742939bb067e810837b6d674a5c0ae961ce0c04821e8642eb79e1a4866ef5dfd ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/data_dir/pep/Exopphae.pep.fa : 4454d8ab6a9d8e387940b7031ebc52488c3cc5679e1269b60d49788df3935b46 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/data_dir/pep/UP000053342_215243.pep.fa : 2b26433f235248dcc41a56cbcd6cbfa9f27f6bec413410ecf130b2555884a52a ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/data_dir/pep/UP000054302_212818.pep.fa : df133c1f67c0cea4ff00150479de541ec730da591faf522cb2737875471ff197 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/species.csv : acd604021beea7a363e5632f03182ad9785a9ca1994e5cfdbbacd67477622896 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000007304.tsv.gz : 85f01303d01dccba682fbbf162afa9420f998dab4f9129dbc676c6bad66380bb ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000053328.tsv.gz : 28a4cfb17710d37608266b78a9bdc6098e7e806ce3d679a663c71c818e392588 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/Exophiala_phaeomuriformis_CBS_132758.proteins.tsv.gz : 0ba612ac5cdff2d6ed5282b2f74add434a1e1a422b7e06028df5cdc9d9ceb1f6 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000053342.tsv.gz : 95aa1868e624a97ab7e0ddda5732d1a1af63bcc5609aa9dc5457bc17429f0dc1 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000054302.tsv.gz : 2f714e4d396238632308ac55aff9176eef37904410b9c7d1bbe3c361f6b292a1 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000019484.tsv.gz : d2c31fab5674f8cfac582e24411ec94d13d602769f14f1d86d5bcfc8b1848649 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000094526.tsv.gz : 1113bcc855fa09d02b55ed2da09aa000537fbce5a77a53e6991a034a8cc197ab ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/UP000053029.tsv.gz : 5ad639903fab13c7f390a2f7799900623e5ee252392d64c1457f10e5416a084e ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_chaetothyriales/annotations/Exophiala_phaeomuriformis_CBS_132758.proteins.tsv.gz.provenance.yaml : ed10b3ac84bb674da2684bf3737fe181746948a9691584eabc97d2b255c286e8 ? /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: 5.5 background_cluster_s: 57.4 tests_s: 5.2 total_s: 70.0 host: r11 slurm_job: '30452604'