openvax / topiary

87%

master: 90%

LAST BUILD ON BRANCH v5.1.0

branch: v5.1.0

CHANGE BRANCH

x

Reset

• v5.1.0
• add-agents-md
• add-cache-sharding
• add-cached-predictor
• add-model-colon-kind-syntax
• add-netmhc-cache-loaders
• add-protected-tissues-scope
• add-self-proteome-nearest
• antigen-fragment
• bare-ident-brackets
• best-allele-aggregation
• cached-predictor-cli
• cached-predictor-vaxrank-polish
• chore/varcode-floor-122
• ci-caching
• cleanup-dsl-version-syntax
• codex/mhctools-3-7-compat
• codex/predict-wt-peptides
• combine-predictor-results
• csv-fasta-inputs
• dsl-extensions
• dsl-polish
• dsl-polish-v5.0.1
• dsl-refactor-v5
• eval-context-default-methods
• evaluate-scores-helper
• expression-data
• expression-dsl-v2
• feature/peptide-property-dsl
• filter-auto-aggregate
• fix-127-autowrap-test
• fix-165-backfill-value-from-score
• fix-biopython-dependency
• fix-deploy-python-selection
• improve-cli-errors
• inline-blosum62
• io-wide-v4.11
• lazy-varcode-imports
• lens-loader
• master
• multi-model-disambiguation
• openvax_switch
• peptide-provenance
• pirlygenes-5.1-expression-accessors
• plumb-kind-support
• pr-b-fragment-refactor
• promote-kind-aliases-public
• pvacseq-loader
• refactor-for-protein-sequences
• release-4.8.0
• restore-varcode-cli-parser-delegation
• shrink-cached-predictor-index
• test-audit-v4.10
• topiary-result
• v4.10.0
• v4.11.0
• v4.11.1
• v4.11.2
• v4.12.0
• v4.3.0
• v4.3.1
• v4.3.2
• v4.4.0
• v4.5.0
• v4.5.1
• v4.6.0
• v4.8.0
• v4.9.0
• v5.0.0
• v5.0.1
• v5.10.0
• v5.10.1
• v5.10.2
• v5.10.3
• v5.10.4
• v5.10.5
• v5.10.6
• v5.10.7
• v5.10.8
• v5.11.0
• v5.12.0
• v5.13.0
• v5.14.0
• v5.14.1
• v5.15.0
• v5.16.1
• v5.16.2
• v5.2.0
• v5.4.0
• v5.5.0
• v5.6.0
• v5.8.0
• v5.9.0
• v5.9.1

Build # 24331826267

Build Type

push

github

Committed by web-flow

Commit Message

Add LENS report loader + logistic_normalized (#110, #116) — v5.1.0 (#117)

topiary.read_lens(path) — load LENS (Landscape of Effective Neoantigens
Software) reports in three schema variants (v1.4, v1.5.1, v1.9-dev)
into Topiary's wide-form schema (#110).

- Column-based version detection (netmhcstabpan_1.0.* → v1.4,
  snaf_exp → v1.5.1, lohhla_allele_loss_pval → v1.9).
- Binding column remap (netmhcpan_4.1b.aff_nm → netmhcpan_affinity_value,
  etc.) with per-model versions captured in Metadata.models.
- Allele normalization via mhcgnomes (handles Class I, II, mouse —
  removes the manual "insert a star" hack).
- effect_type synthesized from HGVS variant_effect when present
  (p.Ala290Val → Substitution, p.Thr259fs → FrameShift, etc.); falls
  back to antigen_source mapping for v1.4 which lacks variant_effect.
- Flanks derived from pep_context only for SNV/SPLICE/FUSION where the
  peptide occurs exactly once; ERV/INDEL/CTA skipped because pep_context
  is the full ORF (up to ~550 residues) or ambiguous.
- tpm handled carefully: fusion rows have composite "ENST1:tpm1-ENST2:tpm2"
  strings — numeric gene_tpm is NaN with the raw string preserved in
  gene_tpm_raw; when every row is cleanly numeric the raw column is
  dropped.
- LENS-specific annotations (erv_*, priority_score_*, b2m_*, hla_*,
  lohhla_*, normal-tissue TPMs, agretopicity, etc.) pass through
  verbatim and are accessible via Column("…") in the DSL.
- Honest about losses: peptide_offset set to 0 (not in LENS);
  contains_mutant_residues / mutation_start_in_peptide left NaN
  (mut_aa_pos semantics ambiguous across antigen_source types).

DSLNode.logistic_normalized(midpoint, width) — logistic sigmoid
rescaled to approach 1 as x → -∞ rather than capping at
1/(1+exp(-m/w)) (~0.912 at (350, 150)) (#116). Separate
LogisticNormalizedExpr AST node so to_expr_string() round-trips
cleanly through parse(); registered in the parser's transform
whitelist. The raw .logistic(...) is unchanged.

Fixtures:... (continued)

Coverage Stats

157 of 174 new or added lines in 3 files covered. (90.23%)

2745 of 3145 relevant lines covered (87.28%)

2.62 hits per line