generated: '2026-10-14T14:13:39' study: agaricomycetes_pairwise 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/agaricomycetes_pairwise --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/config.csv --presence-matrix /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/presence_matrix.tsv --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations --study agaricomycetes_pairwise --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/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/agaricomycetes_pairwise/analysis/enrichment/outputs/proteome_clustered class: ephemeral analysis output (not tracked; regenerate with the command above) direction: novelty target_group: label: IN species: - Scom - Ccin - Agbi - Lbic other_group: label: OUT species: - Cneo - Umay - Rtor universe: proteome annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations annotation_files: Scom: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCF_000143185.2.tsv.gz Ccin: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000182895.1.tsv.gz Agbi: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000300555.1.tsv.gz Lbic: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000143565.1.tsv.gz Cneo: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000149245.1.tsv.gz Umay: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000328475.2.tsv.gz Rtor: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000320785.1.tsv.gz annotation_sources: Scom: Pfam-A HMM search (hmmsearch); Pfam only Ccin: Pfam-A HMM search (hmmsearch); Pfam only Agbi: Pfam-A HMM search (hmmsearch); Pfam only Lbic: Pfam-A HMM search (hmmsearch); Pfam only Cneo: Pfam-A HMM search (hmmsearch); Pfam only Umay: Pfam-A HMM search (hmmsearch); Pfam only Rtor: Pfam-A HMM search (hmmsearch); Pfam only vocabulary_coverage: pfam: species_with_terms: - Scom - Ccin - Agbi - Lbic species_without_terms: [] n_with: 4 n_species: 4 pfam_clan: species_with_terms: - Scom - Ccin - Agbi - Lbic species_without_terms: [] n_with: 4 n_species: 4 interpro: species_with_terms: [] species_without_terms: - Scom - Ccin - Agbi - Lbic n_with: 0 n_species: 4 go: species_with_terms: [] species_without_terms: - Scom - Ccin - Agbi - Lbic n_with: 0 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: 9961 candidates_txt: 9961 symmetric_difference: 0 candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/candidates.txt presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/presence_matrix.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: 5722002aed3f89dd n_sequences: 49063 n_clusters: 27704 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: 35.8 threads: 8 created: '2026-10-14T14:13:35' 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/agaricomycetes_pairwise/config.csv: fab6168dbcd9c3373b07cd11e84a78c2c140a32df781af3a7fa1b6074dc28be2 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/candidates.txt: 523a5556963c5b577d4414a59e8ec1cbb2ca716a4d31760696a0180f4a08fd83 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/novelties.Scom.tsv: 1c1157bc4e85d6f71896f9c7db8f53f771c0c13bccfa876861312f6be57bf997 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/novelties.Ccin.tsv: abe99ce1012e1170f56382f2786e5592c212a918b298a7bacc9e56c0b6c0997b /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/novelties.Agbi.tsv: 4a6cf030621562334dde4724a4bf69f2854aceec0c11d40197e63eb5f8c9af93 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/novelties.Lbic.tsv: 7b67dc6410b823b60e5f29ba6ae1473adf38af56d8e7dc3e773a3132033cbf20 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/presence_matrix.tsv: bcf4577295a6dff0223414e3cad56cb197a82434d7865b715f99466a0c05dbd9 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Scom.pep.fa : afcf088e2862b330b0ceaa4b2c4da36c6c5eb94c5fed83afe601111da921bff8 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Ccin.pep.fa : f6765e9547156fae74e3c4c019ee28f55aa669dd4b2e03183962bc0f5271d28d ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Agbi.pep.fa : bbc042a0af36a8b91c87bcfe1143a9f0cb6856309c7b46ae0beb55862ea8c29f ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Lbic.pep.fa : f320969008d2ef02a7fc5de64ed3154a927d983a6f7d53ca38f7844fcb3cbc03 /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/species.csv: b688d7ed5ad5f65413cc6a3fca95a359f32c830d2ebe1666e822df91f3676aba ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCF_000143185.2.tsv.gz : 4241ce13591af37d26d75c20690309fd2e84d21f11873849a57586dfbd5b820b ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000182895.1.tsv.gz : 0897dbf3c94983a9ac46e3ceac205a279001425c472b43e0a6e9bf3aa43b0939 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000300555.1.tsv.gz : 4f27bbbc49745cf9a81eaae7564d00c5113a90c139d372b63c88a73582820b77 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000143565.1.tsv.gz : 9d85e8e8b80e105b24c765d494a3b2f803a83a8bf832356406340b0034ede18e ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000149245.1.tsv.gz : 353004c2f51cdb1617bfec710b380579849c964097a3e2ca80981be796aceedd ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000328475.2.tsv.gz : ef29e0d969da57d6202ec7359360f561331d5ed5f4b5e0936ba060412d9cd923 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000320785.1.tsv.gz : badd1401905ee39172207cef577d095b961a3b54ced51b7d9009f468f6ab418a ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCF_000143185.2.tsv.gz.provenance.yaml : 08c1ab84bf63c1c5049ab75756392886f05a8ef267f10627a06696c5dd1a97e4 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000182895.1.tsv.gz.provenance.yaml : edff1d6eb8c3c733cb9f493adb892d5398421f425e18d07c856099f116113e3c ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000300555.1.tsv.gz.provenance.yaml : 9377275fbbce488c476486d2bc3d6e57986e2536d0681f884a1b410c187697e5 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000143565.1.tsv.gz.provenance.yaml : 7134c236817b1e4457dc6a01e36cbb11d6277f26ec4007c2de557d6194342dbd ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000149245.1.tsv.gz.provenance.yaml : e9c11e2fac89e74a45af53a848a259947a08d0168eae5803240326524f0a7875 ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000328475.2.tsv.gz.provenance.yaml : 7c1f54445fd4e77b51055c91ac174afcb20e77934d11788be81345ff596cba6a ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations/GCA_000320785.1.tsv.gz.provenance.yaml : a17fcb07693ff3ee090aacb44430b1eb174c14eee3e7b3c5d29490f278d9902a ? /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: 6.1 background_cluster_s: 36.2 tests_s: 2.5 total_s: 46.8 host: r11 slurm_job: '29957444'