ehsanestaji · Oct 24, 2026 · Oct 24, 2026 · Oct 24, 2026 · Oct 24, 2026 · Oct 24, 2026
diff --git a/.gitignore b/.gitignore
@@ -7,3 +7,18 @@ __pycache__/
 /.nextflow.log*
 /.snakemake/
 /work/
+
+# LaTeX build artifacts (keep paper/*.tex, *.bib, Makefile, README)
+paper/*.aux
+paper/*.bbl
+paper/*.blg
+paper/*.fdb_latexmk
+paper/*.fls
+paper/*.log
+paper/*.out
+paper/*.synctex.gz
+paper/*.toc
+paper/*.lof
+paper/*.lot
+paper/*.pdf
+paper/build/
diff --git a/.zenodo.json b/.zenodo.json
@@ -0,0 +1,36 @@
+{
+  "title": "FastaGuard: FASTA preflight QC for modern bioinformatics pipelines",
+  "description": "FastaGuard is a streaming-first Rust CLI for FASTA preflight quality control in assembly pipelines. It validates structure, flags FASTA-level red flags, and emits a stable HTML/JSON/TSV/MultiQC report contract with explicit pipeline gates before expensive downstream QC (QUAST, BUSCO, BlobToolKit, CheckM, annotation, or official validators). This Zenodo deposit archives a citable software release accompanying the Bioinformatics Application Note.",
+  "upload_type": "software",
+  "access_right": "open",
+  "license": "MIT",
+  "creators": [
+    {
+      "name": "Estaji, Ehsan",
+      "orcid": "0009-0005-0838-228X",
+      "affiliation": "Umeå Plant Science Centre, Department of Plant Physiology, Umeå University"
+    },
+    {
+      "name": "Mao, Jian-Feng",
+      "orcid": "0000-0001-9735-8516",
+      "affiliation": "Umeå Plant Science Centre, Department of Plant Physiology, Umeå University"
+    }
+  ],
+  "keywords": [
+    "FASTA",
+    "quality control",
+    "genome assembly",
+    "preflight",
+    "bioinformatics",
+    "Rust",
+    "pipelines"
+  ],
+  "related_identifiers": [
+    {
+      "identifier": "https://github.com/ehsanestaji/FastaGuard/releases/tag/v1.0.0",
+      "relation": "isSupplementTo",
+      "resource_type": "software"
+    }
+  ],
+  "notes": "Deposit the existing GitHub release tag v1.0.0 (Reference Contract Gate / Bioconda-published line). Do not invent DOIs. After Zenodo mints a version DOI, paste it into paper/submission.yml and the Availability sentence in paper/main.tex, then rebuild the PDF."
+}
diff --git a/docs/evidence/results/v1.0.0-rerun/evidence_summary.json b/docs/evidence/results/v1.0.0-rerun/evidence_summary.json
@@ -0,0 +1,153 @@
+{
+  "binary_sha256": "8a76785d89f2f7c7f569dba0bbc741124f8b506851f5bff25d5eb134d87b897f",
+  "binary_to_source_reproducibility_attested": false,
+  "cases": [
+    {
+      "accession": null,
+      "category": "synthetic",
+      "downstream_route": "If this fails, fix the FastaGuard run before comparing with QUAST, BUSCO, or other downstream tools.",
+      "elapsed_seconds": 0.0256,
+      "evidence_role": "offline valid FASTA smoke case",
+      "exit_code": 0,
+      "expected_scale": "tiny synthetic fixture",
+      "finding_count": 0,
+      "finding_ids": [],
+      "gate_blocking_findings": "",
+      "gate_mode": "pipeline",
+      "gate_status": "PASS",
+      "id": "synthetic_valid",
+      "input_bytes": 676,
+      "input_sha256": "71152ba646d1f2d077e0a3a185524c2138a0657ab62f5f0694709c15420c3e5d",
+      "label": "Deterministic synthetic FASTA",
+      "n50": 160,
+      "n90": 140,
+      "sequence_count": 4,
+      "source": "local",
+      "source_url": null,
+      "total_length": 604,
+      "verdict": "PASS"
+    },
+    {
+      "accession": null,
+      "category": "fixture",
+      "downstream_route": "Fix FASTA-level blockers before QUAST, BUSCO, BlobToolKit, CheckM, annotation, or submission validators.",
+      "elapsed_seconds": 0.0304,
+      "evidence_role": "local blocker case for duplicate IDs, invalid characters, high-N records, and tiny contigs",
+      "exit_code": 0,
+      "expected_scale": "tiny intentionally problematic fixture",
+      "finding_count": 8,
+      "finding_ids": [
+        "duplicate_ids",
+        "duplicate_first_token_ids",
+        "invalid_chars",
+        "high_n_rate",
+        "gap_runs",
+        "terminal_ns",
+        "length_outliers",
+        "composite_anomalies"
+      ],
+      "gate_blocking_findings": "duplicate_ids,duplicate_first_token_ids,invalid_chars,high_n_rate",
+      "gate_mode": "pipeline",
+      "gate_status": "FAIL",
+      "id": "problem_fixture",
+      "input_bytes": 187,
+      "input_sha256": "4b8551daeda739b62c8e7aaa1ebf300e4118167ca582c51eeccfa1549c96f0a5",
+      "label": "Problem assembly fixture",
+      "n50": 110,
+      "n90": 8,
+      "sequence_count": 5,
+      "source": "local",
+      "source_url": null,
+      "total_length": 145,
+      "verdict": "FAIL"
+    },
+    {
+      "accession": null,
+      "category": "fixture",
+      "downstream_route": "If this passes, the pipeline can accept compressed FASTA before heavier QC tools.",
+      "elapsed_seconds": 0.025,
+      "evidence_role": "offline gzipped FASTA input smoke case",
+      "exit_code": 0,
+      "expected_scale": "tiny gzipped fixture",
+      "finding_count": 1,
+      "finding_ids": [
+        "terminal_ns"
+      ],
+      "gate_blocking_findings": "",
+      "gate_mode": "pipeline",
+      "gate_status": "WARN",
+      "id": "gzipped_valid",
+      "input_bytes": 81,
+      "input_sha256": "544240d141ede11647a5cbdce60b23793dde1cc0559f2e918ecc80e9cc3fb48e",
+      "label": "Gzipped valid assembly fixture",
+      "n50": 16,
+      "n90": 15,
+      "sequence_count": 3,
+      "source": "local",
+      "source_url": null,
+      "total_length": 47,
+      "verdict": "WARN"
+    },
+    {
+      "accession": "GCF_000005845.2",
+      "category": "bacterial",
+      "downstream_route": "If FastaGuard passes, route to QUAST for assembly metrics and BUSCO when biological completeness is in scope.",
+      "elapsed_seconds": 0.0885,
+      "evidence_role": "small bacterial reference assembly",
+      "exit_code": 0,
+      "expected_scale": "about 4.6 Mbp",
+      "finding_count": 0,
+      "finding_ids": [],
+      "gate_blocking_findings": "",
+      "gate_mode": "pipeline",
+      "gate_status": "PASS",
+      "id": "ecoli_k12_mg1655",
+      "input_bytes": 4699745,
+      "input_sha256": "53bb6a51b6e92139ced1e38f74b7938781027c52200922ff03718c2237d23bb4",
+      "label": "Escherichia coli K-12 MG1655",
+      "n50": 4641652,
+      "n90": 4641652,
+      "sequence_count": 1,
+      "source": "public_ncbi",
+      "source_url": "https://www.ncbi.nlm.nih.gov/datasets/genome/GCF_000005845.2/",
+      "total_length": 4641652,
+      "verdict": "PASS"
+    },
+    {
+      "accession": "GCF_000182925.2",
+      "category": "fungal",
+      "downstream_route": "If FastaGuard passes, route to QUAST, BUSCO, and BlobToolKit-style follow-up when assembly quality or composition signals need deeper review.",
+      "elapsed_seconds": 0.8113,
+      "evidence_role": "small eukaryotic fungal reference assembly",
+      "exit_code": 0,
+      "expected_scale": "tens of Mbp",
+      "finding_count": 2,
+      "finding_ids": [
+        "gap_runs",
+        "gap_pattern_warnings"
+      ],
+      "gate_blocking_findings": "",
+      "gate_mode": "pipeline",
+      "gate_status": "WARN",
+      "id": "neurospora_crassa_or74a",
+      "input_bytes": 41618285,
+      "input_sha256": "8176a4ac98fe05dffa4fa92df030ce0f15af23fbc382c8d8176ffedd3012d847",
+      "label": "Neurospora crassa OR74A",
+      "n50": 6000761,
+      "n90": 4218384,
+      "sequence_count": 21,
+      "source": "public_ncbi",
+      "source_url": "https://www.ncbi.nlm.nih.gov/datasets/genome/GCF_000182925.2/",
+      "total_length": 41102378,
+      "verdict": "WARN"
+    }
+  ],
+  "fastaguard_version": "1.0.0",
+  "generated_at": "2026-10-24T18:11:39+00:00",
+  "platform": "macOS-26.7.1-arm64-arm-64bit-Mach-O",
+  "provenance_scope": "source_commit records verified release-tag and source-tree equality. fastaguard_version and binary_sha256 record the observed executable. Binary-to-source reproducibility was not independently attested.",
+  "python": "3.14.5",
+  "runtime_context": "Elapsed seconds are contextual measurements from one local run, not cross-platform performance guarantees.",
+  "schema_version": 1,
+  "source_commit": "103ee343737e7f4d5719a6f8bda7c05c4676e9a9"
+}
diff --git a/docs/evidence/results/v1.0.0-rerun/evidence_summary.tsv b/docs/evidence/results/v1.0.0-rerun/evidence_summary.tsv
@@ -0,0 +1,6 @@
+schema_version	generated_at	fastaguard_version	source_commit	binary_sha256	provenance_scope	binary_to_source_reproducibility_attested	platform	python	runtime_context	id	label	category	source	accession	source_url	evidence_role	expected_scale	downstream_route	input_bytes	input_sha256	elapsed_seconds	exit_code	verdict	gate_mode	gate_status	gate_blocking_findings	sequence_count	total_length	n50	n90	finding_ids	finding_count
+1	2026-10-24T18:11:39+00:00	1.0.0	103ee343737e7f4d5719a6f8bda7c05c4676e9a9	8a76785d89f2f7c7f569dba0bbc741124f8b506851f5bff25d5eb134d87b897f	source_commit records verified release-tag and source-tree equality. fastaguard_version and binary_sha256 record the observed executable. Binary-to-source reproducibility was not independently attested.	false	macOS-26.7.1-arm64-arm-64bit-Mach-O	3.14.5	Elapsed seconds are contextual measurements from one local run, not cross-platform performance guarantees.	synthetic_valid	Deterministic synthetic FASTA	synthetic	local			offline valid FASTA smoke case	tiny synthetic fixture	If this fails, fix the FastaGuard run before comparing with QUAST, BUSCO, or other downstream tools.	676	71152ba646d1f2d077e0a3a185524c2138a0657ab62f5f0694709c15420c3e5d	0.0256	0	PASS	pipeline	PASS		4	604	160	140		0
+1	2026-10-24T18:11:39+00:00	1.0.0	103ee343737e7f4d5719a6f8bda7c05c4676e9a9	8a76785d89f2f7c7f569dba0bbc741124f8b506851f5bff25d5eb134d87b897f	source_commit records verified release-tag and source-tree equality. fastaguard_version and binary_sha256 record the observed executable. Binary-to-source reproducibility was not independently attested.	false	macOS-26.7.1-arm64-arm-64bit-Mach-O	3.14.5	Elapsed seconds are contextual measurements from one local run, not cross-platform performance guarantees.	problem_fixture	Problem assembly fixture	fixture	local			local blocker case for duplicate IDs, invalid characters, high-N records, and tiny contigs	tiny intentionally problematic fixture	Fix FASTA-level blockers before QUAST, BUSCO, BlobToolKit, CheckM, annotation, or submission validators.	187	4b8551daeda739b62c8e7aaa1ebf300e4118167ca582c51eeccfa1549c96f0a5	0.0304	0	FAIL	pipeline	FAIL	duplicate_ids,duplicate_first_token_ids,invalid_chars,high_n_rate	5	145	110	8	duplicate_ids,duplicate_first_token_ids,invalid_chars,high_n_rate,gap_runs,terminal_ns,length_outliers,composite_anomalies	8
+1	2026-10-24T18:11:39+00:00	1.0.0	103ee343737e7f4d5719a6f8bda7c05c4676e9a9	8a76785d89f2f7c7f569dba0bbc741124f8b506851f5bff25d5eb134d87b897f	source_commit records verified release-tag and source-tree equality. fastaguard_version and binary_sha256 record the observed executable. Binary-to-source reproducibility was not independently attested.	false	macOS-26.7.1-arm64-arm-64bit-Mach-O	3.14.5	Elapsed seconds are contextual measurements from one local run, not cross-platform performance guarantees.	gzipped_valid	Gzipped valid assembly fixture	fixture	local			offline gzipped FASTA input smoke case	tiny gzipped fixture	If this passes, the pipeline can accept compressed FASTA before heavier QC tools.	81	544240d141ede11647a5cbdce60b23793dde1cc0559f2e918ecc80e9cc3fb48e	0.025	0	WARN	pipeline	WARN		3	47	16	15	terminal_ns	1
+1	2026-10-24T18:11:39+00:00	1.0.0	103ee343737e7f4d5719a6f8bda7c05c4676e9a9	8a76785d89f2f7c7f569dba0bbc741124f8b506851f5bff25d5eb134d87b897f	source_commit records verified release-tag and source-tree equality. fastaguard_version and binary_sha256 record the observed executable. Binary-to-source reproducibility was not independently attested.	false	macOS-26.7.1-arm64-arm-64bit-Mach-O	3.14.5	Elapsed seconds are contextual measurements from one local run, not cross-platform performance guarantees.	ecoli_k12_mg1655	Escherichia coli K-12 MG1655	bacterial	public_ncbi	GCF_000005845.2	https://www.ncbi.nlm.nih.gov/datasets/genome/GCF_000005845.2/	small bacterial reference assembly	about 4.6 Mbp	If FastaGuard passes, route to QUAST for assembly metrics and BUSCO when biological completeness is in scope.	4699745	53bb6a51b6e92139ced1e38f74b7938781027c52200922ff03718c2237d23bb4	0.0885	0	PASS	pipeline	PASS		1	4641652	4641652	4641652		0
+1	2026-10-24T18:11:39+00:00	1.0.0	103ee343737e7f4d5719a6f8bda7c05c4676e9a9	8a76785d89f2f7c7f569dba0bbc741124f8b506851f5bff25d5eb134d87b897f	source_commit records verified release-tag and source-tree equality. fastaguard_version and binary_sha256 record the observed executable. Binary-to-source reproducibility was not independently attested.	false	macOS-26.7.1-arm64-arm-64bit-Mach-O	3.14.5	Elapsed seconds are contextual measurements from one local run, not cross-platform performance guarantees.	neurospora_crassa_or74a	Neurospora crassa OR74A	fungal	public_ncbi	GCF_000182925.2	https://www.ncbi.nlm.nih.gov/datasets/genome/GCF_000182925.2/	small eukaryotic fungal reference assembly	tens of Mbp	If FastaGuard passes, route to QUAST, BUSCO, and BlobToolKit-style follow-up when assembly quality or composition signals need deeper review.	41618285	8176a4ac98fe05dffa4fa92df030ce0f15af23fbc382c8d8176ffedd3012d847	0.8113	0	WARN	pipeline	WARN		21	41102378	6000761	4218384	gap_runs,gap_pattern_warnings	2
diff --git a/docs/paper-readiness.md b/docs/paper-readiness.md
@@ -0,0 +1,64 @@
+# FastaGuard paper readiness (*Bioinformatics* Application Note)
+
+Venue: **Bioinformatics (OUP) — Application Note** (user-confirmed).
+
+Branch/PR: `cursor/paper-prep-venues-198e` / [#21](https://github.com/ehsanestaji/FastaGuard/pull/21).
+
+Control manifest: [`paper/submission.yml`](../paper/submission.yml).
+
+Machine check: `cd paper && make check`.
+
+## DONE (machine / repo complete)
+
+| Item | Status |
+| --- | --- |
+| Full Application Note draft (`paper/main.tex`) | DONE |
+| Structured abstract (Summary / Availability / Contact / SI) | DONE |
+| Authors, ORCID, Umeå affiliation, emails (from VariantFlow front-matter) | DONE |
+| Funding (WIFORCE/KAW), COI, AI disclosure, CRediT, acknowledgements | DONE |
+| Evidence freeze: Table 1 numbers match `docs/evidence/results/v0.6/evidence_summary.tsv` | DONE |
+| Cited software release for Availability: GitHub **`v1.0.0`** (Bioconda-published) | DONE |
+| Forbidden phrase guard (“FastQC for FASTA”) in `check_submission.py` | DONE |
+| `.zenodo.json` metadata prepared (no fake DOI) | DONE |
+| Zenodo DOI minted from `v1.0.0` (`10.5281/zenodo.23622311`) and cited in Availability + manifest | DONE |
+| Cover letter draft (`paper/cover-letter.md`) incl. preprint + AI disclosure + archive DOI (OUP policy) | DONE |
+| Upstream claims verified (Bioconda, BioContainers, nf-core module, Snakemake wrapper) | DONE |
+| Pre-submission review: claims re-tested against a v1.0.0 build; related work + references audited; fixes applied (see `paper/HANDOFF.md`) | DONE |
+| Zenodo record creators corrected (Estaji + Mao, ORCIDs, affiliation) | DONE |
+| Validator comparison vs py_fasta_validator, fa-lint, table2asn, SeqKit (Table 2, `paper/comparison/`) | DONE |
+| NCBI rows re-run with a v1.0.0 build (`docs/evidence/results/v1.0.0-rerun/`) | DONE |
+| AI-disclosure wording, funding line, SNIC acknowledgement settled with the author | DONE |
+| bioRxiv build target + checklist | DONE |
+| PDF builds (`make`) | DONE |
+| Word count ~2.0–2.6k band | DONE (~2.0k+) |
+
+## USER-ACTION (requires Ehsan / credentials / co-author)
+
+| Item | Notes |
+| --- | --- |
+| Co-author final OK (Jian-Feng Mao) | DONE 2026-10-24: reported in chat by Ehsan Estaji (Jian-Feng agreed and knew of the work); no written message seen by the agent |
+| Merge PR #21 | `paper/comparison/` is not in the v1.0.0 archive; merge before submission so paths in the paper resolve |
+| Record bioRxiv DOI | Submitted 2026-10-24 as `BIORXIV/2026/761563`; after screening (24-72 h) add the DOI to `paper/submission.yml` and the cover letter |
+| ScholarOne upload | Format-free first submission OK; upload PDF + cover letter; OUP General Template deferred to **revision** |
+| APC / Read & Publish / ISCB discount | Check before acceptance |
+| Suggested editors (optional) | Cover letter suggests assembly/sequence-analysis tools area |
+
+## Pre-submit command checklist
+
+```bash
+cd paper
+make check    # must exit 0
+make          # builds main.pdf
+make biorxiv  # optional preprint PDF copy
+```
+
+## Evidence vs software versions
+
+- **Availability / packaging cite:** FastaGuard **`v1.0.0`**
+  (<https://github.com/ehsanestaji/FastaGuard/releases/tag/v1.0.0>).
+- **Table 1 evidence freeze:** committed **v0.6.0** public-evidence pack
+  (`docs/evidence/…`); timings are contextual contract illustrations, not a
+  claim that v1.0.0 was re-benchmarked on that host.
+- Do **not** invent a new tag solely for the paper; `v1.0.0` already exists.
+  Latest GitHub “Latest” may be newer (e.g. v1.1.0) — paper cites v1.0.0 as the
+  Bioconda reference-contract release unless Availability is intentionally retargeted.