generated: '2026-10-14T21:58:21'
study: UHM_lachnoNovelclade
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/UHM_lachnoNovelclade --config /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/analysis/enrichment/config.fasta_stems.csv
  --species-csv /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/species.csv
  --proteins-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/data_dir/pep
  --annotations /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations
  --study UHM_lachnoNovelclade --cache-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/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
  --universe proteome --cluster-background --direction loss --ingroup-min-frac 0.75 --other-max-frac 0.0 --out-dir /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/analysis/enrichment/outputs/loss/proteome_clustered
class: ephemeral analysis output (not tracked; regenerate with the command above)
direction: loss
target_group:
  label: OUT
  species:
  - Ub56
  - Ub85
  - Ub22
  - Ub119
other_group:
  label: IN
  species:
  - Ub71
  - Lsp1
  - Lsph
  - Easp
  - Cami
universe: proteome
annotations: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations
annotation_files:
  Ub56: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM1088.41098__UHM1088.41098_R.bin.56.tsv.gz
  Ub85: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM1210.23070__UHM1210.23070_R.bin.85.tsv.gz
  Ub22: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM896.23052__UHM896.23052_R.bin.22.tsv.gz
  Ub119: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM904.23055__UHM904.23055_R.bin.119.tsv.gz
  Ub71: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM207.23041__UHM207.23041_R.bin.71.tsv.gz
  Lsp1: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_000687555.1.tsv.gz
  Lsph: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_002797975.1.tsv.gz
  Easp: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_025149125.1.tsv.gz
  Cami: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_900112885.1.tsv.gz
annotation_sources:
  Ub56: Pfam-A HMM search (hmmsearch); Pfam only
  Ub85: Pfam-A HMM search (hmmsearch); Pfam only
  Ub22: Pfam-A HMM search (hmmsearch); Pfam only
  Ub119: Pfam-A HMM search (hmmsearch); Pfam only
  Ub71: Pfam-A HMM search (hmmsearch); Pfam only
  Lsp1: Pfam-A HMM search (hmmsearch); Pfam only
  Lsph: Pfam-A HMM search (hmmsearch); Pfam only
  Easp: Pfam-A HMM search (hmmsearch); Pfam only
  Cami: Pfam-A HMM search (hmmsearch); Pfam only
vocabulary_coverage:
  pfam:
    species_with_terms:
    - Ub56
    - Ub85
    - Ub22
    - Ub119
    species_without_terms: []
    n_with: 4
    n_species: 4
  pfam_clan:
    species_with_terms:
    - Ub56
    - Ub85
    - Ub22
    - Ub119
    species_without_terms: []
    n_with: 4
    n_species: 4
  interpro:
    species_with_terms: []
    species_without_terms:
    - Ub56
    - Ub85
    - Ub22
    - Ub119
    n_with: 0
    n_species: 4
  go:
    species_with_terms: []
    species_without_terms:
    - Ub56
    - Ub85
    - Ub22
    - Ub119
    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: 1523
  candidates_txt: 1523
  symmetric_difference: 0
  candidates_file: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/UHM_lachnoNovelclade/loss_candidates.txt
  presence_matrix: /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/UHM_lachnoNovelclade/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: 9f9d35f4c2e30160
  n_sequences: 7068
  n_clusters: 3256
  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: 6.5
  threads: 8
  created: '2026-10-14T21:58:19'
  cache_hit: false
pipeline_candidate_families: '/bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/UHM_lachnoNovelclade/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/bacteria/UHM_lachnoNovelclade/analysis/enrichment/config.fasta_stems.csv
  : 7334b746c73714a70cf3f97ce1bc3671def408a31256eb275270c989cf699f64
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/UHM_lachnoNovelclade/loss_candidates.txt: b218a0bd45323497ba9e245427f991c3d5b1fd8bbcc85820f9735f1efc1f2eb3
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/UHM_lachnoNovelclade/clusters/loss_clusters_cluster.tsv
  : db59eadb0d28a7a85231b679891dc07e6a5c4a41a60f90c5286c715623f82a53
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/results/UHM_lachnoNovelclade/loss_presence_matrix.tsv: 8feec53cd045ab53f5edc5b53203a66d813ac164c90fabd57888abb89b81f1d8
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/data_dir/pep/Ub56.pep.fa
  : 78240ff74980e027af865013e406dff2e9b1c71cf5565b47f74b39127d1ba3f6
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/data_dir/pep/Ub85.pep.fa
  : f24cea77837d4be510c6dc38d79288385faff370c75a2bcd3bd4b87bb5accd55
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/data_dir/pep/Ub22.pep.fa
  : e931b63947ef8f5992460c363cb7f92fd8e41cf0c070f04a40562d4d0f2e8128
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/data_dir/pep/Ub119.pep.fa
  : af2175ed018a6c843e3d35032d0ff6758c70d1276b1bae807ac669a5c9fbf25c
  /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/species.csv: 6b955f9ad5b6b366cf85bdb4605fa0475b99899830440e3428db93f9e511c0c9
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM1088.41098__UHM1088.41098_R.bin.56.tsv.gz
  : 6a9f5e549fe3df575100b84bf02dbba8bd632e2b1c975ea0d067679ce96fc1d0
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM1210.23070__UHM1210.23070_R.bin.85.tsv.gz
  : c1632d8afd49d6f6f28f4e23a54c89861993ec25eabb732f18590412d4c61065
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM896.23052__UHM896.23052_R.bin.22.tsv.gz
  : d665b1bc43a527ed634e6d55b6b67a795c49de7f0915607e82055d8d3d681481
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM904.23055__UHM904.23055_R.bin.119.tsv.gz
  : 3551ee267b12957c92a268f7143dde8de70c85618e9eee231682f49c8f90fcef
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM207.23041__UHM207.23041_R.bin.71.tsv.gz
  : 5963986ea95c527427345273a730af77f6eb76cc057696053540c27346eba0c6
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_000687555.1.tsv.gz
  : c08925c1a9e645a0192da80438059e84a4746689b3f681054f2905171546b2fc
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_002797975.1.tsv.gz
  : 323069503f50f994d331fbfb2b0ea7497542458156111126d6f8e9e201b6946d
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_025149125.1.tsv.gz
  : 859f2a53826b27876d2879fbc41e04df1d1bc0da3be331c8f958b2584ff23a64
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_900112885.1.tsv.gz
  : 0eb7e4b3b0e36dfcf42380e16b7e5c1a76cf5265562c6d3da58091aa77661cab
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM1088.41098__UHM1088.41098_R.bin.56.tsv.gz.provenance.yaml
  : 797ef9f7b2a013ea0ad30ce637e11e864a723760f81c448dd28f72407ff759a0
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM1210.23070__UHM1210.23070_R.bin.85.tsv.gz.provenance.yaml
  : e8e8afa637a2bee4005ee6ad7bf840d34755a0d380491008d0a77e393abcaa8b
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM896.23052__UHM896.23052_R.bin.22.tsv.gz.provenance.yaml
  : 0239b860957e650032d9b3ef3884bc28d212093a37bf62057e2188ef715446b7
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM904.23055__UHM904.23055_R.bin.119.tsv.gz.provenance.yaml
  : d514243004f70b98d80cca83b063f5e4af0ac11a6754a29d750389dfe6bb3052
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/UHM207.23041__UHM207.23041_R.bin.71.tsv.gz.provenance.yaml
  : e70d06809e44d00bea1a25e4f541f0607d2edf1b2f0def5500932545fc45b8c2
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_000687555.1.tsv.gz.provenance.yaml
  : 13ee1fc5941bac7bd2a8e2bc5e0f239b5a0fe89faef249cfab0a5d86e903e159
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_002797975.1.tsv.gz.provenance.yaml
  : c85e6cd0f118cf4deb5705be6a3256ec875727fdbeda07fec31170156c453a3c
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_025149125.1.tsv.gz.provenance.yaml
  : ca1f2058dc60a4f17c2396e1216f82ebd9d43b4a22ff5b734c041905a125cc7c
  ? /bigdata/stajichlab/jstajich/projects/NovInvenio_Investigations/studies/bacteria/UHM_lachnoNovelclade/annotations/GCF_900112885.1.tsv.gz.provenance.yaml
  : c6f04356f2bf56d95088e787983e72015dcc0ddec838cc1c82ead0a4ff20b9aa
  ? /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: 3.6
  background_cluster_s: 6.5
  tests_s: 0.5
  total_s: 11.4
host: r22
slurm_job: '29966687'
candidate_annotation:
  frac_loss_candidates_any_annotation: 0.742
  low_coverage: false
  rule: "low_coverage = fraction < 0.5 (flag only; no run was excluded on this value)"
  wall_s_enrichment: 13
