generated: '2026-10-14T14:14:19'
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
  --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
  --direction loss --ingroup-min-frac 0.75 --other-max-frac 0.0 --universe proteome --cluster-background --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/analysis/enrichment/outputs/loss/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: loss
target_group:
  label: OUT
  species:
  - Cneo
  - Umay
  - Rtor
other_group:
  label: IN
  species:
  - Scom
  - Ccin
  - Agbi
  - Lbic
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/annotations
annotation_files:
  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
  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
annotation_sources:
  Cneo: Pfam-A HMM search (hmmsearch); Pfam only
  Umay: Pfam-A HMM search (hmmsearch); Pfam only
  Rtor: Pfam-A HMM search (hmmsearch); Pfam only
  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
vocabulary_coverage:
  pfam:
    species_with_terms:
    - Cneo
    - Umay
    - Rtor
    species_without_terms: []
    n_with: 3
    n_species: 3
  pfam_clan:
    species_with_terms:
    - Cneo
    - Umay
    - Rtor
    species_without_terms: []
    n_with: 3
    n_species: 3
  interpro:
    species_with_terms: []
    species_without_terms:
    - Cneo
    - Umay
    - Rtor
    n_with: 0
    n_species: 3
  go:
    species_with_terms: []
    species_without_terms:
    - Cneo
    - Umay
    - Rtor
    n_with: 0
    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: 241
  candidates_txt: 241
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/loss_candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/loss_presence_matrix.tsv
  rule: OUT count / 3 >= 0.75 and IN count / 4 <= 0.0 (own proteome counts toward the target group)
  only_in_matrix_rule: []
  only_in_candidates_file: []
background_clustering:
  key: 7db97450805a2da4
  n_sequences: 22505
  n_clusters: 14544
  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: 29.7
  threads: 8
  created: '2026-10-14T14:14:17'
  cache_hit: false
pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/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/agaricomycetes_pairwise/config.csv: fab6168dbcd9c3373b07cd11e84a78c2c140a32df781af3a7fa1b6074dc28be2
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/loss_candidates.txt: 54b26569e6a8589d948a9659cd091699cfa76d39985bad5523f936b4e1b21874
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/clusters/loss_clusters_cluster.tsv
  : d382601e063e2aa0b6a5d9d960024cace3c5d1d1c61eaa4f9938b9cb67565373
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/agaricomycetes_pairwise/loss_presence_matrix.tsv: 4fb04dc9864346634079f1d60e071b934950e97bad323417cc8c7212eedffb21
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Cneo.pep.fa
  : b15078bc4a4f273afbae54d92bba43ee2f0de118c47368e83a19c11f6041ab2f
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Umay.pep.fa
  : 1c15b109a6a8c4fea2d8f3004c1f0cb68d1695c4acad00ae6041f4b9146336f3
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/data_dir/pep/Rtor.pep.fa
  : 6037dd04c51ebd58fbf3042d55d58ad4aa69161914a7e48578cf8bbf97d08b49
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/fungi/agaricomycetes_pairwise/species.csv: b688d7ed5ad5f65413cc6a3fca95a359f32c830d2ebe1666e822df91f3676aba
  ? /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
  : 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.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/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/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: 2.5
  background_cluster_s: 29.9
  tests_s: 0.9
  total_s: 34.4
host: r11
slurm_job: '29957444'
candidate_annotation:
  frac_loss_candidates_any_annotation: 0.7967
  low_coverage: false
  rule: "low_coverage = fraction < 0.5 (flag only; no run was excluded on this value)"
  wall_s_enrichment: 35