generated: '2026-10-24T14:42:16'
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 novelty --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/analysis/enrichment/outputs/novelty/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: novelty
target_group:
  label: IN
  species:
  - Rhodtoru
  - Rhodmuci
  - Rhodgram
  - Sporrose
  - Leuccrea
other_group:
  label: OUT
  species:
  - Micrlych
  - Puccgram
  - Melalari
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/annotations
annotation_files:
  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
  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
annotation_sources:
  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)
  Micrlych: not recorded (no sidecar)
  Puccgram: Pfam-A HMM search (hmmsearch); Pfam only
  Melalari: Pfam-A HMM search (hmmsearch); Pfam only
vocabulary_coverage:
  pfam:
    species_with_terms:
    - Rhodtoru
    - Rhodmuci
    - Rhodgram
    - Sporrose
    - Leuccrea
    species_without_terms: []
    n_with: 5
    n_species: 5
  pfam_clan:
    species_with_terms:
    - Rhodtoru
    - Rhodmuci
    - Rhodgram
    - Sporrose
    - Leuccrea
    species_without_terms: []
    n_with: 5
    n_species: 5
  interpro:
    species_with_terms:
    - Rhodmuci
    - Rhodgram
    - Leuccrea
    species_without_terms:
    - Rhodtoru
    - Sporrose
    n_with: 3
    n_species: 5
  go:
    species_with_terms:
    - Rhodmuci
    - Rhodgram
    - Leuccrea
    species_without_terms:
    - Rhodtoru
    - Sporrose
    n_with: 3
    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: 2406
  candidates_txt: 2406
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/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: d2bf56335517e3d7
  n_sequences: 38432
  n_clusters: 16166
  mmseqs: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/.pixi/envs/default/bin/mmseqs
  mmseqs_version: 18.8cc5c
  command: mmseqs easy-cluster <bg.fa> <out> <tmp> --threads N --min-seq-id 0.3 -c 0.8 --cov-mode 0
  runtime_s: 60.1
  threads: 4
  created: '2026-10-24T14:42:10'
  cache_hit: false
pipeline_candidate_families: 'novelties.<Short>.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_pucciniomycotina/config.csv
  : 2012d08ed3f414d84a44ea0c42742a6d01cd5e754ac3dd3bfd2a8b9e767dd21a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/candidates.txt: 9f9e190ccd52845650500334cb6f73dbcd4d042626f51dbcd4106ca4794f12df
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/novelties.Rhodtoru.tsv: ee9798043bbb490a5a10d45c5925dfa047a0276f6fbf2781256b674be1c93bfa
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/novelties.Rhodmuci.tsv: 7204e61f67765ebdd29835a23dd99a40673ca7867d6d717f1244ab5e770ee96a
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/novelties.Rhodgram.tsv: 458e1364190d24565e8e8e78bd07832bef11b01e9b61f421b93483a368b3ff59
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/novelties.Sporrose.tsv: ab7d05b194200a996f739d2a25c9f4b8540e2e9fbb281d5ab54a823afebcc769
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/novelties.Leuccrea.tsv: ec4d1b7e234441a0b37633dd0efecfa0331a9ea4647f733ca7ddcbdd07a63286
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/yc_pucciniomycotina/presence_matrix.uniprot.tsv: 51cd29416df937e0844afe537ac0914235e9fb59b965cee64536095a32ae87b9
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/Rhodtoru.pep.fa
  : 6037dd04c51ebd58fbf3042d55d58ad4aa69161914a7e48578cf8bbf97d08b49
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/UP000777482_5537.pep.fa
  : 1886ee86145128a1ab297265e005860b9eda577157c32b649d2305587ab47802
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/UP000053890_578459.pep.fa
  : 30a9d55be4ffa3d63eff10dfdb5e4c3714695fdafe07659640e24cb759822729
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/Sporrose.pep.fa
  : 634aea9eaaf70668f890804c7b28895ce39f0c2b53a4350ed2d4740491277cec
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/yeast_convergence/yc_pucciniomycotina/data_dir/pep/UP000193467_106004.pep.fa
  : 2083de97dc0c2bac75a6045abbe07d79bfde05381eee94400e6827b4db67fe93
  ? /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/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/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.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/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/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: 4.1
  background_cluster_s: 60.6
  tests_s: 4.4
  total_s: 70.7
host: r11
slurm_job: '30452604'
