generated: '2026-10-24T14:43:31' study: yc_pucciniomycotina 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_pucciniomycotina --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/config.csv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations --study yc_pucciniomycotina --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/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_pucciniomycotina/analysis/enrichment/outputs/loss/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: loss target_group: label: OUT species: - Micrlych - Puccgram - Melalari other_group: label: IN species: - Rhodtoru - Rhodmuci - Rhodgram - Sporrose - Leuccrea universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations annotation_files: Micrlych: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000017200.tsv.gz Puccgram: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/GCF_000149925.1.tsv.gz Melalari: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/Melampsora_laricis-populina_98AG31.proteins.tsv.gz Rhodtoru: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/GCF_000320785.1.tsv.gz Rhodmuci: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000777482.tsv.gz Rhodgram: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000053890.tsv.gz Sporrose: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/Sporobolomyces_roseus_SR19.proteins.tsv.gz Leuccrea: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000193467.tsv.gz annotation_sources: Micrlych: not recorded (no sidecar) Puccgram: Pfam-A HMM search (hmmsearch); Pfam only Melalari: Pfam-A HMM search (hmmsearch); Pfam only Rhodtoru: Pfam-A HMM search (hmmsearch); Pfam only Rhodmuci: not recorded (no sidecar) Rhodgram: not recorded (no sidecar) Sporrose: Pfam-A HMM search (hmmsearch); Pfam only Leuccrea: not recorded (no sidecar) vocabulary_coverage: pfam: species_with_terms: - Micrlych - Puccgram - Melalari species_without_terms: [] n_with: 3 n_species: 3 pfam_clan: species_with_terms: - Micrlych - Puccgram - Melalari species_without_terms: [] n_with: 3 n_species: 3 interpro: species_with_terms: - Micrlych species_without_terms: - Puccgram - Melalari n_with: 1 n_species: 3 go: species_with_terms: - Micrlych species_without_terms: - Puccgram - Melalari n_with: 1 n_species: 3 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: 1049 candidates_txt: 1049 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/loss_candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/loss_presence_matrix.tsv rule: OUT count / 3 >= 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: bb50dad3396f41d4 n_sequences: 40639 n_clusters: 25701 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: 66.0 threads: 4 created: '2026-10-24T14:43:27' cache_hit: false pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/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_pucciniomycotina/config.csv : 2012d08ed3f414d84a44ea0c42742a6d01cd5e754ac3dd3bfd2a8b9e767dd21a /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/loss_candidates.txt: c1f894f0ba046de2a90986566dc6a5d262a8750f176d02c88e36e3465981e75d ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/clusters/loss_clusters_cluster.tsv : 646e8219a846c0c0afae82319cc01a6ede5879ccf424aa496766b69dd489125a /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/loss_presence_matrix.tsv: 8ea68545aa2a9a510a87c3d8446878c52f3b83437c5b2e8070bff9a155187d31 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/UP000017200_683840.pep.fa : 181699b46c423fb3550e303ba4c6d2a16e05d020b8cdb9ca42b4f78b9dc4aafa ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/Puccgram.pep.fa : 963c59686fb2ad94991ed12c63a2c88fd49da7b50014a0fa1b723e72d4d940d4 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/Melalari.pep.fa : 15c13a2eb82e2a8cc949de496849d8e1975f49115987eeaba87d70edef356f35 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/species.csv : 767b5b3b1589543003da6a5a4f613fcecfff2375ea1eff01ac3135ae942a506a ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000017200.tsv.gz : 7851737bebbe9a80f5b3a7a357d12c7f9d0e23d6a418a2d6f3440b63c87cdd0c ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/GCF_000149925.1.tsv.gz : f1b5366d077a645edb480cd1a11b845698ae040488f8717785db3f90f9c02318 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/Melampsora_laricis-populina_98AG31.proteins.tsv.gz : c1322949ee2ab67ec025fbf5da7fb84179143723249f001045ef6a351a44abdc ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/GCF_000320785.1.tsv.gz : a16855bdcd6bb3e197662ac41bab9edbc62dc1520c99c3edbf25853b08199ff9 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000777482.tsv.gz : 9e9c90f01c2e5af3a40c9ddf2268d8f4c7d85b43a3f97fe5f0d167030ea1ad09 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000053890.tsv.gz : 0ce036b67e82f2677b0063d0965b975aa5249556d86e9502badd353c6b954439 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/Sporobolomyces_roseus_SR19.proteins.tsv.gz : 14b1e7ca9faa2b0326541ac83a8170fb59ccc0f7f4d64a4e457131d1c80265a1 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/UP000193467.tsv.gz : 6313562242b0454d899748a8802823f1801cdbaa117b0ab62148a03d195dd902 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/GCF_000149925.1.tsv.gz.provenance.yaml : a936fa434effbe234fdec5d1939d54d7e34132f4f7250291e9dddfa361d10b48 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/Melampsora_laricis-populina_98AG31.proteins.tsv.gz.provenance.yaml : 304d672440e10066477f60482bff2155422b1a2714f971d098592b3eb47d5305 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/GCF_000320785.1.tsv.gz.provenance.yaml : cc9a6a2d26df1d21d35c4e01e3be38e6aee85324cc3e50ff92150d237f9c4a42 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations/Sporobolomyces_roseus_SR19.proteins.tsv.gz.provenance.yaml : 272597bd7f3194f24ea040fdd7b0b8766dde6d37f08e8152b22987f6dd526365 ? /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: 3.2 background_cluster_s: 66.3 tests_s: 2.4 total_s: 73.2 host: r11 slurm_job: '30452604'