feat(reads): raw FASTQ quality control

AGENTS.md

@@ -62,10 +62,51 @@ src/
   config.rs         — YAML configuration loading (serde), nested tool configs
   io.rs             — Shared I/O utilities (gzip-transparent file reading)
   gtf.rs            — GTF annotation file parser (with configurable attribute extraction)
+  common/
+    mod.rs            — Re-exports the shared modules
+    bam_flags.rs      — BAM flag constants and aux-tag helpers
+    bam_stat.rs       — bam_stat.py reimplementation, result types
+    bam_stat_accum.rs — Read-level counter accumulator feeding bam_stat and samtools
+    cpp_rng.rs        — C++ RNG FFI shim for preseq bootstrap reproducibility
+    preseq.rs         — preseq lc_extrap library complexity extrapolation
+    samtools/
+      mod.rs          — Re-exports the samtools writers
+      stats.rs        — samtools stats full output (SN + all histogram sections)
+      flagstat.rs     — samtools flagstat-compatible output
+      idxstats.rs     — samtools idxstats-compatible output
+  dna/
+    mod.rs            — Re-exports the DNA submodules
+    depth.rs          — Per-contig depth accumulator (delta array, CIGAR walk,
+                        mate-overlap correction, prefix sum)
+    gc_bias.rs        — Picard CollectGcBiasMetrics reimplementation
+    hs_metrics.rs     — Picard CollectHsMetrics reimplementation (targeted mode)
+    insert_size.rs    — Picard CollectInsertSizeMetrics reimplementation
+    intervals.rs      — BED interval parsing and merging for targeted mode
+    qualimap.rs       — Qualimap bamqc accumulation (windows, coverage, composition)
+    qualimap_output.rs — genome_results.txt, the raw data tables and the HTML report
+    wgs_metrics.rs    — Picard CollectWgsMetrics reimplementation
+    mosdepth/
+      mod.rs          — Per-contig summarisation feeding the mosdepth outputs
+      output.rs       — The six mosdepth-compatible writers (bgzf for the BED outputs)
+  reads/
+    mod.rs
+    fastq.rs        — Streaming FASTQ reader
+    metrics.rs      — Read-level metrics (seqkit and FastQC conventions)
+    output.rs       — seqkit stats table and fastqc_data.txt
+  protein/
+    mod.rs
+    sequence/
+      mod.rs        — FASTA parsing into per-sequence records
+      stats.rs      — Length statistics reproducing seqkit stats -a
+      defects.rs    — Internal stops, non-standard residues, duplicates
+      output.rs     — The seqkit-compatible table and the RustQC report
+    spectra/        — behind the `proteomics` cargo feature
+      mod.rs        — mzML reading via mzdata
+      metrics.rs    — Per-run and per-level spectrum metrics
+      output.rs     — The run report
   rna/
-    mod.rs          — Re-exports all submodules (dupradar, featurecounts, rseqc, bam_flags, cpp_rng, preseq, qualimap)
-    bam_flags.rs    — BAM flag constants
-    cpp_rng.rs      — C++ RNG FFI shim for preseq bootstrap reproducibility
+    mod.rs          — Re-exports the RNA submodules (dupradar, featurecounts, rseqc, qualimap)
+                      and re-exports the shared ones from `common` for compatibility
     dupradar/
       mod.rs        — Re-exports counting, dupmatrix, fitting, plots
       counting.rs   — BAM read counting engine (largest module)
@@ -75,7 +116,6 @@ src/
     featurecounts/
       mod.rs        — Re-exports output
       output.rs     — featureCounts-format output & biotype counting
-    preseq.rs       — preseq lc_extrap library complexity extrapolation
     qualimap/
       mod.rs        — Re-exports all Qualimap modules
       accumulator.rs — Gene body coverage accumulation logic
@@ -88,17 +128,13 @@ src/
       mod.rs                — Re-exports all RSeQC modules + common helpers
       accumulators.rs       — Shared RSeQC accumulator infrastructure (read dispatch)
       common.rs             — Shared junction/intron extraction, from_genes builders
-      bam_stat.rs           — bam_stat.py reimplementation
-      flagstat.rs           — samtools flagstat-compatible output
-      idxstats.rs           — samtools idxstats-compatible output
       infer_experiment.rs   — infer_experiment.py reimplementation
       inner_distance.rs     — inner_distance.py reimplementation
       junction_annotation.rs — junction_annotation.py reimplementation
       junction_saturation.rs — junction_saturation.py reimplementation
       plots.rs              — RSeQC plot generation (duplication, junctions, etc.)
       read_distribution.rs  — read_distribution.py reimplementation
       read_duplication.rs   — read_duplication.py reimplementation
-      stats.rs              — samtools stats full output (SN + all histogram sections)
       tin.rs                — TIN (Transcript Integrity Number) analysis
 tests/
   integration_test.rs  — 12 integration tests vs R dupRadar reference output
@@ -107,13 +143,23 @@ tests/
   create_test_data.R   — R script to regenerate test data + references
 ```
 
-Nested module structure — top-level modules (`cli`, `config`, `io`, `gtf`, `rna`) declared
-in `main.rs`, no `lib.rs`. The `rna` module contains sub-modules for each tool group.
-Inter-module access uses `crate::` paths (e.g., `use crate::rna::dupradar::counting::GeneCounts;`).
+Nested module structure. The library crate root is `src/lib.rs`, which declares
+`common`, `config`, `cpu`, `gtf`, `io`, `rna` and `summary`; the binary
+(`src/main.rs`) additionally declares `cli`, `citations` and `ui`.
+Inter-module access uses `crate::` paths (e.g., `use crate::common::bam_stat_accum::BamStatAccum;`).
+Assay-agnostic analyses belong in `common`; put new code under `rna` only if it
+needs a gene annotation or a library strand protocol.
 
-The CLI uses a single subcommand:
+The CLI has two subcommands:
 
 - `rustqc rna <BAM>... --gtf <GTF> [OPTIONS]`
+- `rustqc dna <BAM>... [OPTIONS]`
+
+The `dna` subcommand needs no annotation. It runs depth of coverage
+(mosdepth-compatible), the samtools-compatible outputs and preseq in one pass,
+with one worker per contig. Shared flags keep their `rna` names, short forms
+and `RUSTQC_*` environment variables, with one deliberate exception:
+`-Q/--mapq` defaults to 0 for `dna`, matching mosdepth, rather than 30.
 
 A GTF gene annotation file (`--gtf`) is required. This runs all analyses:
 dupRadar duplicate rate analysis, featureCounts-compatible gene counting,

CHANGELOG.md

@@ -1,5 +1,39 @@
 # RustQC Changelog
 
+## Unreleased
+
+### Features
+
+- New `rustqc dna` subcommand for DNA (WGS) quality control: depth of coverage
+  with mosdepth-compatible outputs, samtools-compatible stats, flagstat and
+  idxstats, and preseq library complexity, all in a single pass over the
+  alignment with one worker per contig, plus Picard-compatible
+  CollectWgsMetrics, CollectInsertSizeMetrics and CollectGcBiasMetrics.
+  Passing `--targets` switches on targeted mode and Picard-compatible
+  CollectHsMetrics. Qualimap-compatible `bamqc` output rounds it out, with
+  `genome_results.txt`, the raw data tables and an HTML summary. Validated
+  against mosdepth 0.3.14, samtools 1.24, Picard 3.4.0 and Qualimap 2.3.
+
+- New `rustqc reads` subcommand: raw FASTQ quality control before alignment,
+  reproducing `seqkit stats -a` exactly and four of FastQC's modules (per base
+  sequence quality, per sequence quality scores, per base sequence content and
+  per base N content).
+- New `rustqc protein sequence` mode: protein FASTA quality control, with
+  length statistics reproducing `seqkit stats -a` exactly, plus amino acid
+  composition and defect detection (internal stop codons, non-standard
+  residues, duplicate sequences and identifiers) that seqkit does not report.
+- New `rustqc protein spectra` mode: mass spectrometry run QC from mzML, with
+  per-level spectrum and peak counts, total ion current, retention time range
+  and precursor charge distribution. Behind the `proteomics` cargo feature,
+  which is on by default; `--no-default-features` drops it along with mzdata.
+
+### Changed
+
+- Internal: assay-agnostic analyses (BAM flag helpers, read-level statistics,
+  the samtools stats/flagstat/idxstats writers, preseq) moved from `rna` to a
+  new `common` module. The old `rustqc::rna::...` paths still resolve through
+  re-exports, so this is not a breaking change for library users.
+
 ## [Version 0.2.1](https://github.com/seqeralabs/RustQC/releases/tag/v0.2.1) - 2026-04-09
 
 ### Bug fixes