openomicsbench 2.2.0__tar.gz → 4.0.0__tar.gz

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/CITATION.cff

@@ -2,7 +2,7 @@ cff-version: 1.2.0
 message: "Please cite the archived release corresponding to the version you used."
 title: "OpenOmicsBench"
 type: software
-version: "2.2.0"
+version: "4.0.0"
 license: Apache-2.0
 doi: "10.5281/zenodo.22551734"
 authors:

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: openomicsbench
-Version: 2.2.0
-Summary: Traceable omics benchmarks and deterministic FASTA and FASTQ tools
+Version: 4.0.0
+Summary: Traceable RNA, DNA and protein benchmarks with policy-driven evaluation
 Author: Vivaan Patni
 Maintainer: Vivaan Patni
 License-Expression: Apache-2.0
@@ -11,7 +11,7 @@ Project-URL: Issues, https://github.com/vxxqv/openomicsbench/issues
 Project-URL: Changelog, https://github.com/vxxqv/openomicsbench/blob/main/CHANGELOG.md
 Project-URL: Zenodo, https://doi.org/10.5281/zenodo.22551734
 Project-URL: ORCID, https://orcid.org/0009-0005-1859-5107
-Keywords: bioinformatics,computational-biology,genomics,transcriptomics,proteomics,bulk-rna-seq,dna-seq,fasta,fastq,dna,rna,protein-sequence,amino-acid-analysis,sequence-analysis,quality-control,kmer,variant-truth,benchmarking,benchmark-data,test-data,data-validation,data-provenance,data-integrity,reproducibility,scientific-workflows,research-software,expression-atlas,ensembl,deseq2
+Keywords: bioinformatics,computational-biology,genomics,transcriptomics,proteomics,bulk-rna-seq,dna-seq,fasta,fastq,vcf,dna,rna,protein-sequence,peptide-identification,tryptic-digest,amino-acid-analysis,sequence-analysis,quality-control,kmer,variant-truth,variant-benchmarking,multi-assay,quality-gate,run-fingerprint,trend-report,ro-crate,benchmarking,benchmark-data,test-data,data-validation,data-provenance,data-integrity,reproducibility,scientific-workflows,research-software,expression-atlas,ensembl,deseq2
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Science/Research
@@ -33,9 +33,9 @@ Dynamic: license-file
 
 # OpenOmicsBench
 
-OpenOmicsBench is a compact benchmark collection and local sequence toolkit for bioinformatics software testing, method checks and teaching. Version 2 keeps the 12 certified bulk RNA-seq objects from version 1 and adds strict FASTA and FASTQ handling, DNA, RNA and protein support, paired-read checks, preprocessing, sequence QC and five deterministic sequence benchmarks.
+OpenOmicsBench is a compact benchmark collection and local sequence toolkit for bioinformatics software testing, method checks and teaching. It contains 12 certified bulk RNA-seq objects, six deterministic DNA, RNA, protein and proteomics fixtures, strict FASTA and FASTQ tools, and a CI-ready evaluation system.
 
-Version 2.2 adds multi-method benchmark matrices, report-to-report regression gates and portable benchmark bundles. Suite reports can be written as JSON, Markdown, JUnit XML, CSV or a self-contained HTML page.
+Version 4 evaluates RNA differential-expression results, DNA variant calls and protein-peptide identifications in the same run. It adds a deterministic tryptic-peptide benchmark, portable run fingerprints, versioned quality and resource policies, and multi-run trend reports. The version 3 VCF scoring, multi-method matrices, offline dashboards and RO-Crate evidence remain available.
 
 The package runs offline after installation. Sequence files stay on the local computer. The built-in tools cover inspection and lightweight preprocessing; they do not claim to replace aligners, variant callers, taxonomic classifiers or assay-specific statistical workflows.
 
@@ -54,6 +54,8 @@ List and validate the bundled benchmarks:
 omicsbench list
 omicsbench validate rnaseq-002
 omicsbench validate sequence-004
+omicsbench variant compare sequence-005 calls.vcf.gz
+omicsbench peptide compare sequence-006 identifications.peptides.tsv
 ```
 
 The wheel contains the complete collection. A repository checkout and network connection are not required.
@@ -135,6 +137,28 @@ Then run:
 omicsbench suite compare results --id rnaseq-002 --id rnaseq-003 --junit reports/comparison.xml
 ```
 
+For a mixed RNA, DNA and protein run, add benchmark-named VCF and peptide output alongside the expression tables:
+
+```text
+results/
+  method.json
+  rnaseq-002.tsv.gz
+  sequence-005.vcf.gz
+  sequence-006.peptides.tsv
+```
+
+```sh
+omicsbench suite evaluate results \
+  --id rnaseq-002 \
+  --id sequence-005 \
+  --id sequence-006 \
+  --json reports/evaluation.json \
+  --html reports/evaluation.html \
+  --evidence reports/evaluation-evidence.zip
+```
+
+`method.json` is optional. When supplied, it records the exact method version, command, container or source revision, parameters, runtime, peak memory and thread count. Missing selected outputs fail as benchmark cases.
+
 Compare several tools or parameter sets in one matrix:
 
 ```sh
@@ -146,13 +170,57 @@ omicsbench suite matrix \
   --html reports/matrix.html
 ```
 
+Use `evaluate-matrix` when each method directory contains a mixture of RNA tables, VCF calls and peptide tables:
+
+```sh
+omicsbench suite evaluate-matrix \
+  --method current=results/current \
+  --method candidate=results/candidate \
+  --id rnaseq-002 \
+  --id sequence-005 \
+  --id sequence-006 \
+  --html reports/multi-assay.html
+```
+
+The leaderboard uses pass counts and keeps assay metrics separate. It does not average unlike measurements into a single score.
+
+Each evaluation records SHA-256 hashes for the submitted results and benchmark manifests, then builds a `run_fingerprint` from those hashes and the validated method receipt. Local directory names do not affect this identity.
+
+Apply a checked-in policy to an evaluation before accepting a run:
+
+```sh
+omicsbench suite gate reports/evaluation.json policy.json \
+  --json reports/gate.json \
+  --junit reports/gate.xml
+```
+
+A policy can require named benchmarks, overall and per-assay pass rates, a method receipt, runtime and memory ceilings, and metric floors scoped to an assay or comparator. Missing required evidence fails the gate.
+
+Track several accepted or candidate runs in chronological order:
+
+```sh
+omicsbench suite trend \
+  --run v4.0=reports/v4.0.json \
+  --run candidate=reports/candidate.json \
+  --json reports/trend.json \
+  --html reports/trend.html
+```
+
+Trend reports preserve each source fingerprint, method receipt, resource measurements, pass rate and per-benchmark metric history.
+
 Use a previously accepted report as a regression baseline:
 
 ```sh
 omicsbench suite regress accepted.json candidate.json --absolute-tolerance 0.01 --junit reports/regression.xml
 ```
 
-Omit `--id` to require results for all 12 comparable RNA-seq objects. A completed suite exits with status 0 when every check passes, status 2 when a benchmark or regression gate fails, and status 1 for invalid input. Existing report files are protected unless `--force` is supplied. The [suite reference](docs/benchmark-suites.md) describes the file convention and report fields.
+Omit `--id` from `suite compare` to require results for all 12 comparable RNA-seq objects. Omit it from `suite evaluate` to require every benchmark with a supported comparator. A completed suite exits with status 0 when every check passes, status 2 when a benchmark, policy or regression gate fails, and status 1 for invalid input. Existing report files are protected unless `--force` is supplied. The [suite reference](docs/benchmark-suites.md) describes the file convention and report fields.
+
+Verify an evaluation evidence crate without extracting it:
+
+```sh
+omicsbench evidence verify reports/evaluation-evidence.zip
+```
 
 ## Portable bundles
 
@@ -186,12 +254,17 @@ Profiles are available for whole-genome, exome, targeted-panel, bulk RNA-seq, si
 | `sequence-003` | standard, ambiguous and terminating protein records | FASTA | 3 |
 | `sequence-004` | paired DNA reads with mixed qualities and duplication | FASTQ | 4 pairs |
 | `sequence-005` | paired DNA-seq reads, reference and three known SNVs | FASTQ | 20 pairs |
+| `sequence-006` | protein FASTA and exact in-silico tryptic peptide truth | FASTA/TSV | 3 proteins |
+
+These six objects are project-authored synthetic fixtures. Each has an exact file inventory, checksums, format and molecule declarations, expected summary metrics and a deterministic rebuild workflow. `sequence-005` also verifies that every truth-set reference allele matches the bundled reference and that every alternate allele is supported by the paired reads. `sequence-006` verifies exact protein-peptide pairs from a declared tryptic digest. The objects test software behavior and do not represent a biological cohort or sequencing instrument.
+
+The version 3 VCF comparator for `sequence-005` matches contig, one-based position, REF and ALT exactly. It reports precision, recall and F1 for A/C/G/T substitutions and verifies REF against the packaged synthetic reference. Genotypes, indels, complex representations and confident-region stratification are outside this fixture. Use a haplotype-aware benchmarking engine such as [hap.py](https://github.com/Illumina/hap.py) or vcfeval with an appropriate truth set and confident regions for real germline benchmarking; the [GA4GH benchmarking project](https://github.com/ga4gh/benchmarking-tools) documents that broader problem.
 
-These five objects are project-authored synthetic fixtures. Each has an exact file inventory, checksums, format and molecule declarations, expected summary metrics and a deterministic rebuild workflow. `sequence-005` also verifies that every truth-set reference allele matches the bundled reference and that every alternate allele is supported by the paired reads. The objects test software behavior and do not represent a biological cohort or sequencing instrument.
+The version 4 peptide comparator accepts `protein_id` and `peptide` columns, with an optional `q_value` column. It scores unmodified pairs after the declared q-value filter and reports peptide precision, recall and F1, protein recall and covered truth residues. It does not parse spectra or claim to replace a full identification standard. The [HUPO-PSI mzIdentML specification](https://github.com/HUPO-PSI/mzIdentML) is the appropriate interchange model for complete mass-spectrometry identification results.
 
 ## Bulk RNA-seq benchmarks
 
-Version 2 retains the complete version 1 biological collection unchanged.
+Version 4 retains the complete version 1 biological collection unchanged.
 
 | ID | Design | Samples | Pocket genes |
 |---|---|---:|---:|

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/README.md

@@ -1,8 +1,8 @@
 # OpenOmicsBench
 
-OpenOmicsBench is a compact benchmark collection and local sequence toolkit for bioinformatics software testing, method checks and teaching. Version 2 keeps the 12 certified bulk RNA-seq objects from version 1 and adds strict FASTA and FASTQ handling, DNA, RNA and protein support, paired-read checks, preprocessing, sequence QC and five deterministic sequence benchmarks.
+OpenOmicsBench is a compact benchmark collection and local sequence toolkit for bioinformatics software testing, method checks and teaching. It contains 12 certified bulk RNA-seq objects, six deterministic DNA, RNA, protein and proteomics fixtures, strict FASTA and FASTQ tools, and a CI-ready evaluation system.
 
-Version 2.2 adds multi-method benchmark matrices, report-to-report regression gates and portable benchmark bundles. Suite reports can be written as JSON, Markdown, JUnit XML, CSV or a self-contained HTML page.
+Version 4 evaluates RNA differential-expression results, DNA variant calls and protein-peptide identifications in the same run. It adds a deterministic tryptic-peptide benchmark, portable run fingerprints, versioned quality and resource policies, and multi-run trend reports. The version 3 VCF scoring, multi-method matrices, offline dashboards and RO-Crate evidence remain available.
 
 The package runs offline after installation. Sequence files stay on the local computer. The built-in tools cover inspection and lightweight preprocessing; they do not claim to replace aligners, variant callers, taxonomic classifiers or assay-specific statistical workflows.
 
@@ -21,6 +21,8 @@ List and validate the bundled benchmarks:
 omicsbench list
 omicsbench validate rnaseq-002
 omicsbench validate sequence-004
+omicsbench variant compare sequence-005 calls.vcf.gz
+omicsbench peptide compare sequence-006 identifications.peptides.tsv
 ```
 
 The wheel contains the complete collection. A repository checkout and network connection are not required.
@@ -102,6 +104,28 @@ Then run:
 omicsbench suite compare results --id rnaseq-002 --id rnaseq-003 --junit reports/comparison.xml
 ```
 
+For a mixed RNA, DNA and protein run, add benchmark-named VCF and peptide output alongside the expression tables:
+
+```text
+results/
+  method.json
+  rnaseq-002.tsv.gz
+  sequence-005.vcf.gz
+  sequence-006.peptides.tsv
+```
+
+```sh
+omicsbench suite evaluate results \
+  --id rnaseq-002 \
+  --id sequence-005 \
+  --id sequence-006 \
+  --json reports/evaluation.json \
+  --html reports/evaluation.html \
+  --evidence reports/evaluation-evidence.zip
+```
+
+`method.json` is optional. When supplied, it records the exact method version, command, container or source revision, parameters, runtime, peak memory and thread count. Missing selected outputs fail as benchmark cases.
+
 Compare several tools or parameter sets in one matrix:
 
 ```sh
@@ -113,13 +137,57 @@ omicsbench suite matrix \
   --html reports/matrix.html
 ```
 
+Use `evaluate-matrix` when each method directory contains a mixture of RNA tables, VCF calls and peptide tables:
+
+```sh
+omicsbench suite evaluate-matrix \
+  --method current=results/current \
+  --method candidate=results/candidate \
+  --id rnaseq-002 \
+  --id sequence-005 \
+  --id sequence-006 \
+  --html reports/multi-assay.html
+```
+
+The leaderboard uses pass counts and keeps assay metrics separate. It does not average unlike measurements into a single score.
+
+Each evaluation records SHA-256 hashes for the submitted results and benchmark manifests, then builds a `run_fingerprint` from those hashes and the validated method receipt. Local directory names do not affect this identity.
+
+Apply a checked-in policy to an evaluation before accepting a run:
+
+```sh
+omicsbench suite gate reports/evaluation.json policy.json \
+  --json reports/gate.json \
+  --junit reports/gate.xml
+```
+
+A policy can require named benchmarks, overall and per-assay pass rates, a method receipt, runtime and memory ceilings, and metric floors scoped to an assay or comparator. Missing required evidence fails the gate.
+
+Track several accepted or candidate runs in chronological order:
+
+```sh
+omicsbench suite trend \
+  --run v4.0=reports/v4.0.json \
+  --run candidate=reports/candidate.json \
+  --json reports/trend.json \
+  --html reports/trend.html
+```
+
+Trend reports preserve each source fingerprint, method receipt, resource measurements, pass rate and per-benchmark metric history.
+
 Use a previously accepted report as a regression baseline:
 
 ```sh
 omicsbench suite regress accepted.json candidate.json --absolute-tolerance 0.01 --junit reports/regression.xml
 ```
 
-Omit `--id` to require results for all 12 comparable RNA-seq objects. A completed suite exits with status 0 when every check passes, status 2 when a benchmark or regression gate fails, and status 1 for invalid input. Existing report files are protected unless `--force` is supplied. The [suite reference](docs/benchmark-suites.md) describes the file convention and report fields.
+Omit `--id` from `suite compare` to require results for all 12 comparable RNA-seq objects. Omit it from `suite evaluate` to require every benchmark with a supported comparator. A completed suite exits with status 0 when every check passes, status 2 when a benchmark, policy or regression gate fails, and status 1 for invalid input. Existing report files are protected unless `--force` is supplied. The [suite reference](docs/benchmark-suites.md) describes the file convention and report fields.
+
+Verify an evaluation evidence crate without extracting it:
+
+```sh
+omicsbench evidence verify reports/evaluation-evidence.zip
+```
 
 ## Portable bundles
 
@@ -153,12 +221,17 @@ Profiles are available for whole-genome, exome, targeted-panel, bulk RNA-seq, si
 | `sequence-003` | standard, ambiguous and terminating protein records | FASTA | 3 |
 | `sequence-004` | paired DNA reads with mixed qualities and duplication | FASTQ | 4 pairs |
 | `sequence-005` | paired DNA-seq reads, reference and three known SNVs | FASTQ | 20 pairs |
+| `sequence-006` | protein FASTA and exact in-silico tryptic peptide truth | FASTA/TSV | 3 proteins |
+
+These six objects are project-authored synthetic fixtures. Each has an exact file inventory, checksums, format and molecule declarations, expected summary metrics and a deterministic rebuild workflow. `sequence-005` also verifies that every truth-set reference allele matches the bundled reference and that every alternate allele is supported by the paired reads. `sequence-006` verifies exact protein-peptide pairs from a declared tryptic digest. The objects test software behavior and do not represent a biological cohort or sequencing instrument.
+
+The version 3 VCF comparator for `sequence-005` matches contig, one-based position, REF and ALT exactly. It reports precision, recall and F1 for A/C/G/T substitutions and verifies REF against the packaged synthetic reference. Genotypes, indels, complex representations and confident-region stratification are outside this fixture. Use a haplotype-aware benchmarking engine such as [hap.py](https://github.com/Illumina/hap.py) or vcfeval with an appropriate truth set and confident regions for real germline benchmarking; the [GA4GH benchmarking project](https://github.com/ga4gh/benchmarking-tools) documents that broader problem.
 
-These five objects are project-authored synthetic fixtures. Each has an exact file inventory, checksums, format and molecule declarations, expected summary metrics and a deterministic rebuild workflow. `sequence-005` also verifies that every truth-set reference allele matches the bundled reference and that every alternate allele is supported by the paired reads. The objects test software behavior and do not represent a biological cohort or sequencing instrument.
+The version 4 peptide comparator accepts `protein_id` and `peptide` columns, with an optional `q_value` column. It scores unmodified pairs after the declared q-value filter and reports peptide precision, recall and F1, protein recall and covered truth residues. It does not parse spectra or claim to replace a full identification standard. The [HUPO-PSI mzIdentML specification](https://github.com/HUPO-PSI/mzIdentML) is the appropriate interchange model for complete mass-spectrometry identification results.
 
 ## Bulk RNA-seq benchmarks
 
-Version 2 retains the complete version 1 biological collection unchanged.
+Version 4 retains the complete version 1 biological collection unchanged.
 
 | ID | Design | Samples | Pocket genes |
 |---|---|---:|---:|

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/datasets/sequences/sequence-005/expected/validation.json

@@ -74,5 +74,11 @@
   "reference": "nano/reference.fasta",
   "variant_truth": "expected/variants.tsv",
   "variant_count": 3,
-  "context_bases": 10
+  "context_bases": 10,
+  "variant_comparison": {
+    "mode": "exact_allele",
+    "scope": "single_nucleotide_substitutions",
+    "minimum_precision": 1.0,
+    "minimum_recall": 1.0
+  }
 }

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/datasets/sequences/sequence-005/manifest.json

@@ -2,7 +2,7 @@
   "schema_version": "2.0",
   "id": "sequence-005",
   "title": "Synthetic paired DNA-seq variant benchmark",
-  "release": "2.0.0",
+  "release": "3.0.0",
   "assay": "whole_genome_dna_seq",
   "kind": "synthetic_fixture",
   "status": "validated",
@@ -93,13 +93,13 @@
       "tier": "expected",
       "role": "metrics",
       "media_type": "application/json",
-      "bytes": 1739,
-      "sha256": "9b21fb89fe782b9e7ced92f0bebba8e84f4d3e50188e7af18ad2a429ba87b9bb"
+      "bytes": 1902,
+      "sha256": "da0813bf715df2a455a7c0eb86dc804dbb8cf582c9aa09119e8d976e3548cd88"
     }
   ],
   "validation": {
     "profile": "expected/validation.json",
-    "baseline_version": "dnaseq-truth-v1",
+    "baseline_version": "dnaseq-truth-v2",
     "metrics": []
   },
   "sequence": {

openomicsbench-4.0.0/datasets/sequences/sequence-006/expected/peptides.tsv

@@ -0,0 +1,16 @@
+protein_id	peptide	start	end	missed_cleavages
+proteome_alpha	MPEPTIDER	0	9	0
+proteome_alpha	MPEPTIDERK	0	10	1
+proteome_alpha	KAAAGMSTNPK	9	20	1
+proteome_alpha	AAAGMSTNPK	10	20	0
+proteome_alpha	AAAGMSTNPKVVVVK	10	25	1
+proteome_alpha	VVVVKQWER	20	29	1
+proteome_alpha	QWERTYIPK	25	34	1
+proteome_beta	GILGFVFTLTVPSER	0	15	0
+proteome_beta	GILGFVFTLTVPSERDVLK	0	19	1
+proteome_beta	DVLKQHPMWQK	15	26	1
+proteome_beta	QHPMWQK	19	26	0
+proteome_gamma	ACDEFGHIK	0	9	0
+proteome_gamma	ACDEFGHIKLMNPQR	0	15	1
+proteome_gamma	LMNPQRSTVWYK	9	21	1
+proteome_gamma	STVWYKR	15	22	1

openomicsbench-4.0.0/datasets/sequences/sequence-006/expected/validation.json

@@ -0,0 +1,61 @@
+{
+  "profile": "sequence-summary-v1",
+  "files": [
+    {
+      "path": "nano/proteins.fasta",
+      "expected": {
+        "format": "fasta",
+        "molecule": "protein",
+        "records": 3,
+        "letters": 82,
+        "length": {
+          "minimum": 22,
+          "maximum": 34,
+          "mean": 27.333333333333332,
+          "median": 26,
+          "n50": 26,
+          "l50": 2
+        },
+        "composition": {
+          "A": 4,
+          "C": 1,
+          "D": 3,
+          "E": 5,
+          "F": 3,
+          "G": 4,
+          "H": 2,
+          "I": 4,
+          "K": 8,
+          "L": 4,
+          "M": 4,
+          "N": 2,
+          "P": 7,
+          "Q": 4,
+          "R": 5,
+          "S": 3,
+          "T": 6,
+          "V": 8,
+          "W": 3,
+          "Y": 2
+        },
+        "gc_fraction": null,
+        "ambiguity_fraction": 0.0,
+        "duplicate_sequences": 0
+      }
+    }
+  ],
+  "protein_reference": "nano/proteins.fasta",
+  "peptide_truth": "expected/peptides.tsv",
+  "peptide_count": 15,
+  "peptide_comparison": {
+    "enzyme": "trypsin",
+    "missed_cleavages": 1,
+    "minimum_length": 7,
+    "maximum_length": 30,
+    "maximum_q_value": 0.01,
+    "minimum_precision": 1.0,
+    "minimum_recall": 1.0,
+    "minimum_protein_recall": 1.0,
+    "minimum_residue_coverage": 1.0
+  }
+}

openomicsbench-4.0.0/datasets/sequences/sequence-006/manifest.json

@@ -0,0 +1,100 @@
+{
+  "schema_version": "2.0",
+  "id": "sequence-006",
+  "title": "Synthetic proteomics peptide-identification benchmark",
+  "release": "4.0.0",
+  "assay": "sequence_protein",
+  "kind": "synthetic_fixture",
+  "status": "validated",
+  "archetype": "protein FASTA and exact in-silico tryptic peptide truth",
+  "organism": "Synthetic proteome model",
+  "taxon_id": null,
+  "source": {
+    "repository": "Project generator",
+    "accession": "sequence-006",
+    "url": "https://github.com/vxxqv/openomicsbench",
+    "citation": "OpenOmicsBench sequence-006, project-authored deterministic proteomics fixture.",
+    "retrieved": "2026-10-10",
+    "sha256": null
+  },
+  "rights": {
+    "status": "GREEN",
+    "license": "Apache-2.0",
+    "evidence": "Generated by the project workflow without third-party protein sequences or spectra.",
+    "checked": "2026-10-10"
+  },
+  "reference": {
+    "genome": "not_applicable",
+    "annotation": "not_applicable",
+    "namespace": "project synthetic protein identifiers",
+    "compatibility": "verified"
+  },
+  "samples": [
+    {
+      "sample_id": "synthetic-proteome-1",
+      "condition": "defined tryptic digest",
+      "replicate": 1,
+      "batch": "not_applicable",
+      "strandedness": "not_applicable"
+    }
+  ],
+  "derivation": {
+    "workflow": "workflows/build_sequence_fixtures.py",
+    "commit": null,
+    "seed": 0,
+    "algorithm": "deterministic in-silico tryptic digestion of project-authored protein sequences",
+    "parameters": {
+      "proteins": 3,
+      "enzyme": "trypsin",
+      "missed_cleavages": 1,
+      "minimum_length": 7,
+      "maximum_length": 30,
+      "peptides": 15
+    },
+    "versions": {
+      "python": "3.12",
+      "openomicsbench_contract": "2.0"
+    }
+  },
+  "files": [
+    {
+      "path": "nano/proteins.fasta",
+      "tier": "nano",
+      "role": "sequence",
+      "media_type": "text/x-fasta",
+      "bytes": 186,
+      "sha256": "b9a02f2e1a62751b96b3287214f3b7120a7ac4337cbb0b7797742316d56e4fdc"
+    },
+    {
+      "path": "expected/peptides.tsv",
+      "tier": "expected",
+      "role": "effects",
+      "media_type": "text/tab-separated-values",
+      "bytes": 560,
+      "sha256": "1c4a7f3a6976424ec7748355994b8a9999de6b580f7987a17b6e390c788e0a52"
+    },
+    {
+      "path": "expected/validation.json",
+      "tier": "expected",
+      "role": "metrics",
+      "media_type": "application/json",
+      "bytes": 1316,
+      "sha256": "5e0a211d4278b5962dbaaaa6297c4a06f54ea697fdc22447d94352c944f0bb3d"
+    }
+  ],
+  "validation": {
+    "profile": "expected/validation.json",
+    "baseline_version": "peptide-identification-v1",
+    "metrics": []
+  },
+  "sequence": {
+    "format": "fasta",
+    "molecule": "protein",
+    "paired": false,
+    "quality_encoding": "not_applicable"
+  },
+  "limitations": [
+    "The benchmark scores protein-peptide pairs from a deterministic digest; it contains no mass spectra.",
+    "Post-translational modifications, charge states, spectrum matching, protein inference and FDR calibration are outside this object."
+  ]
+}

openomicsbench-4.0.0/datasets/sequences/sequence-006/nano/proteins.fasta

@@ -0,0 +1,6 @@
+>proteome_alpha synthetic protein
+MPEPTIDERKAAAGMSTNPKVVVVKQWERTYIPK
+>proteome_beta synthetic protein
+GILGFVFTLTVPSERDVLKQHPMWQK
+>proteome_gamma synthetic protein
+ACDEFGHIKLMNPQRSTVWYKR

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "openomicsbench"
-version = "2.2.0"
-description = "Traceable omics benchmarks and deterministic FASTA and FASTQ tools"
+version = "4.0.0"
+description = "Traceable RNA, DNA and protein benchmarks with policy-driven evaluation"
 readme = {file = "README.md", content-type = "text/markdown"}
 license = "Apache-2.0"
 authors = [{name = "Vivaan Patni"}]
 maintainers = [{name = "Vivaan Patni"}]
-keywords = ["bioinformatics", "computational-biology", "genomics", "transcriptomics", "proteomics", "bulk-rna-seq", "dna-seq", "fasta", "fastq", "dna", "rna", "protein-sequence", "amino-acid-analysis", "sequence-analysis", "quality-control", "kmer", "variant-truth", "benchmarking", "benchmark-data", "test-data", "data-validation", "data-provenance", "data-integrity", "reproducibility", "scientific-workflows", "research-software", "expression-atlas", "ensembl", "deseq2"]
+keywords = ["bioinformatics", "computational-biology", "genomics", "transcriptomics", "proteomics", "bulk-rna-seq", "dna-seq", "fasta", "fastq", "vcf", "dna", "rna", "protein-sequence", "peptide-identification", "tryptic-digest", "amino-acid-analysis", "sequence-analysis", "quality-control", "kmer", "variant-truth", "variant-benchmarking", "multi-assay", "quality-gate", "run-fingerprint", "trend-report", "ro-crate", "benchmarking", "benchmark-data", "test-data", "data-validation", "data-provenance", "data-integrity", "reproducibility", "scientific-workflows", "research-software", "expression-atlas", "ensembl", "deseq2"]
 requires-python = ">=3.11"
 dependencies = ["pydantic>=2.13,<3", "numpy>=2.3,<3"]
 classifiers = [

{openomicsbench-2.2.0 → openomicsbench-4.0.0}/src/omicsbench/__init__.py

@@ -1,2 +1,2 @@
 """Discovery, validation and local analysis of compact omics benchmarks."""
-__version__ = "2.2.0"
+__version__ = "4.0.0"