generated: '2026-10-24T14:27:43' study: yc_saccharomycotina 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_saccharomycotina --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/config.csv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations --study yc_saccharomycotina --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/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 loss --other-max-frac 0.0 --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/analysis/enrichment/outputs/loss/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: loss target_group: label: OUT species: - Amega - Tubemela - Ncra - Anid other_group: label: IN species: - Scer - Lipostar - Ylip - Komaphaf - Candalbi universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations annotation_files: Amega: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP001658139.tsv.gz Tubemela: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000006911.tsv.gz Ncra: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000001805.tsv.gz Anid: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000000560.tsv.gz Scer: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000002311.tsv.gz Lipostar: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000094385.tsv.gz Ylip: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000001300.tsv.gz Komaphaf: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000000314.tsv.gz Candalbi: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000000559.tsv.gz annotation_sources: Amega: not recorded (no sidecar) Tubemela: not recorded (no sidecar) Ncra: not recorded (no sidecar) Anid: not recorded (no sidecar) Scer: not recorded (no sidecar) Lipostar: not recorded (no sidecar) Ylip: not recorded (no sidecar) Komaphaf: not recorded (no sidecar) Candalbi: not recorded (no sidecar) vocabulary_coverage: pfam: species_with_terms: - Amega - Tubemela - Ncra - Anid species_without_terms: [] n_with: 4 n_species: 4 pfam_clan: species_with_terms: - Amega - Tubemela - Ncra - Anid species_without_terms: [] n_with: 4 n_species: 4 interpro: species_with_terms: - Amega - Tubemela - Ncra - Anid species_without_terms: [] n_with: 4 n_species: 4 go: species_with_terms: - Tubemela - Ncra - Anid species_without_terms: - Amega 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: 3672 candidates_txt: 3672 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_saccharomycotina/loss_candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_saccharomycotina/loss_presence_matrix.tsv rule: OUT count / 4 >= 0.75 and IN count / 5 <= 0.0 (own proteome counts toward the target group) only_in_matrix_rule: [] only_in_candidates_file: [] background_clustering: key: bb91c54c96e3372f n_sequences: 36001 n_clusters: 21933 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: 70.4 threads: 4 created: '2026-10-24T14:27:35' cache_hit: false pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_saccharomycotina/clusters/loss_clusters_cluster.tsv (nf_NovInvenio MMSEQS_CLUSTER: mmseqs easy-cluster --min-seq-id 0.3 -c 0.8 --cov-mode 0 on loss_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_saccharomycotina/config.csv : deecbde38aafcc041378ffc582e483d977c5eeb2f34c3df8f5c2d0b851353095 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_saccharomycotina/loss_candidates.txt: 6c3bf2d4deda257fbf85577d9b988baf88332fde56ef09591c04142f1ebad268 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_saccharomycotina/clusters/loss_clusters_cluster.tsv : df2007651f081a092799a5aa8db6948747c26e86805ccf50cf210177edd2a5f3 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_saccharomycotina/loss_presence_matrix.tsv: 926438d3b0037746512e999fabf0ad16e72a63bc688f047357411f48427b982e ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/data_dir/pep/UP001658139_2528406.pep.fa : 2f3e3fabaa24307b063911f3ad1f01c2d9b49d0602fc56e31679894476facde4 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/data_dir/pep/UP000006911_656061.pep.fa : f098cab4186822eb2fd59279de5a586ccbad5efab1d2965bfab22170388289bd ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/data_dir/pep/UP000001805_367110.pep.fa : 6c3a6d498fb30b129e2ab084f95789b3c510164f34661a5c85acb6a14e5f3dde ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/data_dir/pep/UP000000560_227321.pep.fa : 929546c62a96b539b87eff1da79f95462d02f3853e6a1301cc43572bf8f3f7cc ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/species.csv : d9a786ec640646651e0de6cbb223b433f2201f251210f865d34e5fc270328ed7 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP001658139.tsv.gz : ad733d34f19586ffe37ffea92f5da242fbba8c9965f5f5cda4f58157da482d22 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000006911.tsv.gz : a60be7c90d8def222f211d14b270a6ef1cb9b5e832de9b02fa62ca6b1d2ad2b6 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000001805.tsv.gz : bef3e2b7d985d46ed6edd299d15420b8e8d1987d1886bebb2ca5eab116888bf9 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000000560.tsv.gz : 59e3bf3c002f0341bc772b583eba5ebb0b45185874ecc0f9b04c1acdc6653ce9 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000002311.tsv.gz : 6bb8cd4fdaf082109b729c39dacce1a67e585cb22402a23d86c4256067a4561e ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000094385.tsv.gz : 986f829438d52ea497806e723b3271e8331281277b359694a21198a1545e3da0 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000001300.tsv.gz : 8b0053748250a11ee3e1441bb7dcd3564361bc0a0d70f54bc1cf9f01e3c53f21 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000000314.tsv.gz : 33e433ea105d15d2aacec4f12b792a0d530b0e8a7d9442740ce1c0871711f8fd ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_saccharomycotina/annotations/UP000000559.tsv.gz : 3ae6bf15a6d2ec16726c89439fc0462975bf3f5820c38a994a4e12b9f366025c ? /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: 3.8 background_cluster_s: 70.8 tests_s: 6.1 total_s: 82.4 host: r11 slurm_job: '30452604'