genome: --genomeType SuperTranscriptome

CHANGELOG.md

@@ -169,6 +169,35 @@ Sections commonly used: Features, Bug fixes, Other changes.
   union: they came from one molecule. Writes `matrix.mtx`,
   `features.tsv` and `transcriptEndDistanceDistribution.txt` under
   `Solo.out/Transcript3p/raw/`.
+- **`--genomeTransformOutput SAM`** reports alignments in the original
+  genome's coordinates. `--genomeTransformType Haploid` bakes a VCF's
+  variants into the genome, so reads carrying those alleles align
+  without mismatches, but every reported coordinate then refers to a
+  genome nobody else has. This maps each alignment back through the
+  conversion blocks written at build time: an indel baked into the
+  sequence reappears as an `I`/`D` CIGAR operation at the original
+  position, and junction motifs are reclassified against the original
+  genome rather than the transformed one. The SAM header comes from
+  the original genome too. `SJ` and `Quant` remain unimplemented and
+  are refused, as are the flag combinations whose other outputs would
+  stay in transformed coordinates.
+
+- **`--genomeType SuperTranscriptome`** condenses the genome to the union
+  of its annotated exons: overlapping exons are merged, the merged
+  intervals concatenated, and overlapping transcripts grouped into
+  superTranscripts, one per condensed chromosome (`st0`, `st1`, ...).
+  The index then covers only exonic sequence, and introns cannot be
+  crossed because they are not present. Requires `--sjdbGTFfile`.
+  Writes `superTranscriptSequences.fasta`, `transcriptSequences.fasta`,
+  `superTranscriptSJcollapsed.tsv` and
+  `fullGenome/conversionToFullGenome.tsv` alongside the index.
+
+  Diverges from STAR on minus-strand exons, deliberately. STAR condenses
+  the sequence before filling the reverse-complement half of its genome
+  buffer, so minus-strand superTranscripts read uninitialised memory;
+  here they hold the actual reverse complement. Recorded in
+  `docs-old/dev/divergences.md` and locked by a test asserting the
+  hand-derived sequence.
 
 ### Bug fixes
 

src/genome/mod.rs

@@ -1,12 +1,13 @@
 pub mod fasta;
+pub mod supertranscript;
 pub mod transform;
 
 use std::path::Path;
 
 use crate::error::Error;
 use crate::params::Parameters;
 
-use fasta::parse_fasta_files;
+use fasta::{Chromosome, parse_fasta_files};
 
 /// STAR's genome spacing character (used for inter-chromosome padding).
 const GENOME_SPACING_CHAR: u8 = 5;
@@ -213,10 +214,25 @@ impl Genome {
             None
         };
 
+        Self::from_chromosomes(&chromosomes, bin_nbits, transform_blocks)
+    }
+
+    /// Lay out a genome from chromosome sequences already in base codes:
+    /// pad each to a `2^chr_bin_nbits` boundary, then fill the
+    /// reverse-complement half.
+    ///
+    /// [`from_fasta`](Self::from_fasta) is this plus FASTA parsing and the
+    /// VCF transform. `--genomeType SuperTranscriptome` uses it directly,
+    /// since its chromosomes are built rather than read.
+    pub fn from_chromosomes(
+        chromosomes: &[Chromosome],
+        bin_nbits: u32,
+        transform_blocks: Option<Vec<[u64; 3]>>,
+    ) -> Result<Self, Error> {
         // First pass: chromosome names/lengths, validating non-zero length.
         let mut chr_name = Vec::new();
         let mut chr_length = Vec::new();
-        for chrom in &chromosomes {
+        for chrom in chromosomes {
             let len = chrom.sequence.len() as u64;
             if len == 0 {
                 return Err(Error::Fasta(format!(