PGx: full call detail (PGX-016..020, 027/028, 031), pgx coverage (PGX-009/035), full HGVS

- supporting_variants.tsv, unresolved_variants.tsv, variants_not_covered.tsv with PGX-026 metadata; per-allele
  supporting/unresolved sites for both alleles of every candidate; variant_change vs top, distant_alternative,
  unexplained_variants, alleles_impacted_by_no_call, alleles_tested.
- simurg pgx coverage: callable / not_covered / masked / equivalent_to per allele and manifest.
- HGVS on GRCh38 RefSeq accessions (NC_...:g.).

docs/messages.md

@@ -106,6 +106,7 @@ Generated from `src/simurg/core/errors.py` — do not edit by hand.
 | `W_PGX_BATCH_BELOW_RECOMMENDED` | warning | Fewer passing samples than recommended | PCN-004 |
 | `W_PGX_BATCH_COMPOSITION` | warning | Batch spans several lots/batches or > 14 days of scans | PCN-006 |
 | `W_PGX_NO_ALT_CONTIG` | warning | FASTA lacks a contig carrying a PGx region; REF written as N | IN-062 |
+| `W_PGX_NO_PROBE_MAP` | warning | The PGx DB has no probe map for this manifest | PGX-035 |
 | `W_PGX_REGION_FEW_PROBES` | warning | PGx CN region has fewer than 10 unmasked probes | PCN-008 |
 | `W_QC_LABEL_SANITIZED` | warning | Dataset label was sanitized | QC-042 |
 | `W_QC_NO_BAF` | warning | GTC has no B-allele frequencies; contamination not estimated | QC-064 |

docs/validation/V2_pgx_star.md

@@ -61,6 +61,14 @@ so the per-call error is 1e-3 (GS ≥ 0.15) and errors are handled by the probe
 * CPIC now defines the GRCh38 reference as its own allele where it differs from *1 (CYP2C19 *38): a sample
   heterozygous at the *1-defining rs3758581 fits *1/*38 best (raw score 0.98), but *38 has no CPIC frequency, so the
   prior keeps *1/*1 on top — which is what legacy GeT-RM reports.
+* `simurg pgx coverage` (PGX-009/035) on GSA v4 PGx with the mask: 438 alleles callable, 68 array-equivalent to
+  another allele, 88 not covered, 4 masked. Against the reference's known limitations: CYP4F2 *2 not covered (reported
+  as *1) and *4 ≡ *3 — as the reference; UGT1A1 *28 callable (its C>CAT probe matches 1000G) and *37 masked (the
+  C>CATAT probe fails); CYP2D6 *40/*58 and NUDT15 *6/*9 are separable here (CPIC core definitions differ from the
+  reference's).
+* Detail outputs (PGX-016 … PGX-020, PGX-027/028, PGX-031): `supporting_variants.tsv`, `unresolved_variants.tsv`,
+  `variants_not_covered.tsv`, per-allele supporting/unresolved sites for **both** alleles of every candidate,
+  `variant_change` vs the top solution (`distant_alternative` above 3 changes), `unexplained_variants`, full HGVS on
+  GRCh38 RefSeq accessions.
 * Not yet: named-haplotype (G6PD), variant-based and tagging genes; CYP2D6 hybrids (*13, *36, *68); PharmVar-only
-  genes (CYP2A6, CYP3A4, CYP1A2, …); DPWG tables; the full per-allele supporting/unresolved-variant detail of
+  genes (CYP2A6, CYP3A4, CYP1A2, …); DPWG tables.
-  PGX-027/028 (`supporting_variants.tsv`, `unresolved_variants.tsv`, `variants_not_covered.tsv`).

src/simurg/cli/main.py

@@ -910,6 +910,22 @@ def pgx_annotate_cmd(
     _pgx_phenotype(calls, db, out, guideline, force, log_json, debug, quiet, "pgx annotate")
 
 
+@pgx_app.command("coverage")
+def pgx_coverage_cmd(
+    bpm: Annotated[Path, typer.Option("--bpm", help="BPM manifest (required).")],
+    db: Annotated[Path, typer.Option("--db", help="PGx DB built with this manifest (required).")],
+    out: Annotated[Path, typer.Option("--out", help="Output folder.")] = Path("."),
+    log_json: LogJson = False,
+    debug: Debug = False,
+    quiet: Quiet = False,
+) -> None:
+    """Which alleles this array can call: pgx_coverage.tsv (PGX-009, PGX-035)."""
+    from simurg.pipeline.pgx_db import run_coverage
+
+    rep = _reporter("pgx coverage", out, log_json, debug, quiet)
+    run_guarded(rep, lambda: run_coverage(bpm, db, out, rep))
+
+
 @pgx_cn_app.command("train")
 def pgx_cn_train_cmd(
     gtcs: Annotated[Path, typer.Option("--gtcs", help="Folder searched recursively for training GTCs (required).")],

src/simurg/core/errors.py

@@ -175,6 +175,7 @@ CATALOGUE: dict[str, MessageDef] = dict(
         _m("E_PGX_VCF_UNINDEXED", "error", "SNV VCFs for PGx must be bgzipped and indexed", "PGX-011"),
         _m("E_PGX_VCF_UNSUITABLE", "error", "SNV VCF unsuitable for PGx (squashing/locus filters/foreign)", "PGX-011"),
         _m("E_PGX_GUIDELINE", "error", "Guideline tables not present in the PGx DB", "PGX-025"),
+        _m("W_PGX_NO_PROBE_MAP", "warning", "The PGx DB has no probe map for this manifest", "PGX-035"),
         _m("E_PGX_SOURCE", "error", "PGx source tables missing; run scripts/pgx/fetch_sources.sh", "PGX-001"),
         # --- methylation control QC (MET-001 .. MET-018) -------------------------------------------------
         _m("E_METH_NO_ASSAY", "error", "Probe section not found", "MET-002"),

src/simurg/pgx/db.py

@@ -19,7 +19,23 @@ from typing import Any
 Fetch = Callable[[str, int, int], str]
 HGVS_RE = re.compile(r"^([gm])\.(\d+)(?:_(\d+))?(.*)$")
 REPEAT_RE = re.compile(r"^([ACGT]+)\((\d+)\)$")
-IUPAC_WILDCARD = set("RYSWKMBDHVN")  # CPIC core-allele definitions: the position does not constrain the allele
+IUPAC_WILDCARD = set("RYSWKMBDHVN")
+# GRCh38 RefSeq chromosome accessions, for full HGVS (PGX-028 "NC_000022.11:g.42126611C>G")
+REFSEQ_GRCH38 = {"1": "NC_000001.11", "2": "NC_000002.12", "3": "NC_000003.12", "4": "NC_000004.12",
+                 "5": "NC_000005.10", "6": "NC_000006.12", "7": "NC_000007.14", "8": "NC_000008.11",
+                 "9": "NC_000009.12", "10": "NC_000010.11", "11": "NC_000011.10", "12": "NC_000012.12",
+                 "13": "NC_000013.11", "14": "NC_000014.9", "15": "NC_000015.10", "16": "NC_000016.10",
+                 "17": "NC_000017.11", "18": "NC_000018.10", "19": "NC_000019.10", "20": "NC_000020.11",
+                 "21": "NC_000021.9", "22": "NC_000022.11", "X": "NC_000023.11", "Y": "NC_000024.10",
+                 "M": "NC_012920.1", "MT": "NC_012920.1"}  # fmt: skip
+
+
+def full_hgvs(chrom: str, hgvs: str) -> str:
+    """``g.…``/``m.…`` → ``NC_…:g.…`` on the GRCh38 chromosome accession (unchanged when unknown)."""
+    acc = REFSEQ_GRCH38.get(chrom.removeprefix("chr"))
+    return (
+        f"{acc}:{hgvs.split(';')[0].strip()}" if acc and not hgvs.startswith("NC_") else hgvs
+    )  # CPIC core-allele definitions: the position does not constrain the allele
 
 
 @dataclass(frozen=True)

src/simurg/pgx/star.py

@@ -59,6 +59,7 @@ class Solution:
     raw_score: float = 0.0
     score: float = 0.0
     copy_number: int = 2
+    copies: tuple[int, ...] = ()  # haplotype index of every gene copy of the representative (SNV model)
 
     @property
     def genotype(self) -> str:
@@ -157,8 +158,8 @@ def call_gene(
                 p *= 2
             pri.append(p)
         best = members[int(np.argmax(pri))]
-        sols.append(Solution(cands[best][1], float(ll[best]), float(sum(pri)),
+        sols.append(Solution(cands[best][1], float(ll[best]), float(sum(pri)), [cands[k][1] for k in members],
-                             [cands[k][1] for k in members], copy_number=cn if cn is not None else 2))  # fmt: skip
+                             copy_number=cn if cn is not None else 2, copies=cands[best][0]))  # fmt: skip
     lls = np.array([s.ll for s in sols])
     lp = lls + np.log([s.prior for s in sols])
     raw = np.exp(lls - lls.max())

src/simurg/pipeline/pgx_db.py

@@ -113,7 +113,7 @@ def run_db_build(o: PgxDbOptions, rep: Reporter) -> int:
     """``simurg pgx db build`` (CLI-035)."""
     from simurg.formats.bpm import read_bpm
     from simurg.formats.fasta import ContigMap, Genome
-    from simurg.pgx.db import cpic_definitions, result_basis
+    from simurg.pgx.db import cpic_definitions, full_hgvs, result_basis
 
     cdir = _latest(o.sources, "cpic")
     if cdir is None:
@@ -145,14 +145,14 @@ def run_db_build(o: PgxDbOptions, rep: Reporter) -> int:
                     continue
                 pos, ref, alt = s.alleles[val]
                 rows["allele_variants"].append(
-                    (gene, d.name, "GRCh38", s.chrom, pos, ref, alt, s.hgvs, s.rsid, lid, val)
+                    (gene, d.name, "GRCh38", s.chrom, pos, ref, alt, full_hgvs(s.chrom, s.hgvs), s.rsid, lid, val)
                 )
             for lid in d.wildcards:
                 rows["allele_wildcards"].append((gene, d.name, lid))
             for pop, f in sorted(d.frequencies.items()):
                 rows["frequencies"].append((gene, d.name, pop, f))
     for lid, s in sorted(sites.items()):
-        rows["sites"].append((s.gene, lid, s.chrom, s.hgvs, s.rsid, s.ref_value))
+        rows["sites"].append((s.gene, lid, s.chrom, full_hgvs(s.chrom, s.hgvs), s.rsid, s.ref_value))
         for val, (pos, ref, alt) in sorted(s.alleles.items()):
             rows["site_values"].append((s.gene, lid, val, pos, ref, alt))
     results = {r["id"]: r for r in t["gene_result"]}
@@ -221,3 +221,71 @@ def run_db_build(o: PgxDbOptions, rep: Reporter) -> int:
     rep.info(f"PGx DB: {len(defs)} genes, {len(rows['alleles'])} alleles, {len(rows['allele_variants'])} variant "
              f"rows, {len(rows['probe_map'])} probe links → {final} (content sha256 {sha})")  # fmt: skip
     return ExitCode.OK
+
+
+# ------------------------------------------------------------------------------------------------ coverage
+def coverage_rows(db: Path, manifest: str) -> list[dict[str, Any]]:
+    """PGX-009 / PGX-035: per allele, callable | not_covered | masked | equivalent_to:<allele> on a manifest."""
+    import numpy as np
+
+    from simurg.pipeline.pgx_star import load_models
+
+    con = sqlite3.connect(db)
+    links: dict[tuple[str, int, str, str], list[str]] = {}
+    for probe, c, p, r, a in con.execute("SELECT probe_name, chrom, pos, ref, alt FROM probe_map WHERE manifest = ?",
+                                         (manifest,)):  # fmt: skip
+        links.setdefault((c, p, r, a), []).append(probe)
+    masked = {p for (p,) in con.execute("SELECT probe_name FROM masks WHERE manifest = ?", (manifest,))}
+    basis = dict(con.execute("SELECT gene, result_basis FROM genes").fetchall())
+    kinds = {(g, a): (k, d) for g, a, k, d in con.execute("SELECT gene, allele, kind, defined FROM alleles")}
+    con.close()
+    out = []
+    for gene, m in sorted(load_models(db, "global").items()):
+        usable = np.array([bool(links.get(v)) and not all(pr in masked for pr in links[v]) for v in m.variants])
+        masked_v = np.array([bool(links.get(v)) and all(pr in masked for pr in links[v]) for v in m.variants])
+        sig: dict[bytes, list[int]] = {}
+        for h in range(len(m.haplotypes)):
+            sig.setdefault(np.where(usable, m.carries[h], -9).tobytes(), []).append(h)
+        rep = {}
+        for members in sig.values():
+            best = max(members, key=lambda h: (m.freq[h], -h))
+            for h in members:
+                rep[h] = best
+        for h, name in enumerate(m.haplotypes):
+            defining = m.carries[h] == 1
+            probes = sorted({pr for k in np.flatnonzero(defining).tolist() for pr in links.get(m.variants[k], [])})
+            if defining.any() and not (defining & usable).any():
+                status = "masked" if (defining & masked_v).any() else "not_covered"
+            elif rep[h] != h:
+                status = f"equivalent_to:{m.haplotypes[rep[h]]}"
+            else:
+                status = "callable"
+            out.append({"gene": gene, "allele": name, "allele_kind": kinds.get((gene, name), ("", 1))[0],
+                        "result_basis": basis.get(gene, ""), "status": status,
+                        "covering_probes": ";".join(probes)})  # fmt: skip
+    con = sqlite3.connect(db)
+    for gene, allele, kind in con.execute("SELECT gene, allele, kind FROM alleles WHERE defined = 0 ORDER BY 1, 2"):
+        out.append({"gene": gene, "allele": allele, "allele_kind": kind, "result_basis": basis.get(gene, ""),
+                    "status": "not_covered", "covering_probes": ""})  # fmt: skip
+    con.close()
+    return out
+
+
+def run_coverage(bpm: Path, db: Path, out: Path, rep: Reporter) -> int:
+    """``simurg pgx coverage --bpm --db`` (PGX-035)."""
+    from simurg.formats.bpm import read_bpm
+    from simurg.pipeline.pgx_pheno import db_meta, tsv_header, write_meta_tsv
+
+    name = read_bpm(bpm).manifest_name
+    rows = coverage_rows(db, name)
+    if not any(r["covering_probes"] for r in rows):
+        rep.warn("W_PGX_NO_PROBE_MAP", f"the PGx DB has no probe map for {name}; rebuild it with --manifests")
+    out.mkdir(parents=True, exist_ok=True)
+    cols = ["gene", "allele", "allele_kind", "result_basis", "status", "covering_probes"]
+    write_meta_tsv(out / "pgx_coverage.tsv", tsv_header(db, db_meta(db), "none")[:-1], cols, rows)
+    counts: dict[str, int] = {}
+    for r in rows:
+        k = r["status"].split(":")[0]
+        counts[k] = counts.get(k, 0) + 1
+    rep.info(f"{name}: " + ", ".join(f"{k} {v}" for k, v in sorted(counts.items())))
+    return ExitCode.OK

src/simurg/pipeline/pgx_pheno.py

@@ -98,15 +98,24 @@ def run_phenotype(o: PhenoOptions, rep: Reporter) -> int:
             else:
                 res, per = gene_phenotype(t, feas)
             flags = list(g.get("flags", [])) + (res.flags if res else [])
-            entry = {"gene": g["gene"], "call_type": "star_allele", "genotype": g["genotype"],
+            top = g["candidates"][0] if g["candidates"] else {}
+            top_alleles = top.get("alleles", [])
+            entry = {"gene": g["gene"], "call_type": g.get("call_type", "star_allele"), "genotype": g["genotype"],
                      "feasible_solutions": g["feasible_solutions"],
                      "activity_score": res.activity_score if res else None,
                      "phenotype": res.phenotype if res else None, "per_solution_phenotypes": per,
-                     "score": g["candidates"][0]["score"] if g["candidates"] else None,
+                     "score": top.get("score"), "raw_score": top.get("raw_score"),
-                     "raw_score": g["candidates"][0]["raw_score"] if g["candidates"] else None,
                      "flags": sorted(set(flags)), "copy_number": g.get("copy_number"),
-                     "candidate_solutions": [{"rank": i + 1, **c} for i, c in enumerate(g["candidates"])],
+                     "array_equivalent_alleles": [{"allele": a["allele"], "equivalents": a["array_equivalent_alleles"]}
-                     "alleles_tested": sorted(tested.get(g["gene"], []), key=_natural)}  # fmt: skip
+                                                  for a in top_alleles],
+                     "supporting_variants": [v for a in top_alleles for v in a["supporting_variants"]],
+                     "variant_no_calls": g.get("variant_no_calls", []),
+                     "variants_not_covered": g.get("variants_not_covered", []),
+                     "unexplained_variants": g.get("unexplained_variants", []),
+                     "candidate_solutions": [{"rank": i + 1, **c, "phenotype": _pheno_of(tables.get(g["gene"]), c)}
+                                             for i, c in enumerate(g["candidates"])],
+                     "alleles_tested": g.get("alleles_tested")
+                     or sorted(tested.get(g["gene"], []), key=_natural)}  # fmt: skip
             genes.append(entry)
             ann_rows.append({"sample_id": s["sample_id"], "sample_name": s.get("sample_name", s["sample_id"]),
                              "gene": g["gene"], "guideline": o.guideline, "genotype": g["genotype"],
@@ -126,6 +135,12 @@ def run_phenotype(o: PhenoOptions, rep: Reporter) -> int:
     return ExitCode.OK
 
 
+def _pheno_of(t: Any, cand: dict[str, Any]) -> str | None:
+    from simurg.pgx.phenotype import phenotype
+
+    return phenotype(t, tuple(cand["genotype"].split("/"))).phenotype if t is not None else None
+
+
 def _natural(a: str) -> tuple[Any, ...]:
     import re
 

src/simurg/pipeline/pgx_star.py

@@ -17,12 +17,15 @@ from pathlib import Path
 from typing import Any
 
 import numpy as np
+import numpy.typing as npt
 
 from simurg import __version__
 from simurg.core.errors import ExitCode, SimurgError
 from simurg.core.log import Reporter
 from simurg.pgx.star import CALLED, MASKED, NO_CALL, NOT_COVERED, GeneModel, Observations, Solution, call_gene
 
+MAX_EDIT_DISTANCE = 3  # PGX-019
+
 CN_REGION = {"CYP2D6": "CYP2D6.p5"}  # PGX-013: total gene copies from the 5′ region
 DELETION_ALLELE = {"CYP2D6": "*5"}
 
@@ -145,6 +148,72 @@ def observations(
     return Observations(state, dosage, gs, baf), ploidy
 
 
+def variant_records(m: GeneModel, recs: dict[tuple[str, int], list[dict[str, Any]]]) -> list[dict[str, Any] | None]:
+    """The VCF record that carries each defining variant (same REF, ALT among the ALTs), or None."""
+    out: list[dict[str, Any] | None] = []
+    for c, p, r_, a_ in m.variants:
+        out.append(next((rec for rec in recs.get((c, p), []) if rec["ref"] == r_ and a_ in rec["alts"]), None))
+    return out
+
+
+def _vcn(obs: Observations, k: int, n: int) -> int | None:
+    """PGX-012 variant copy number: GT dosage at CN 2, else the ML k of BAF ~ N(k/n, σ²)."""
+    if obs.state[k] != CALLED:
+        return None
+    if n == 2 or math.isnan(obs.baf[k]):
+        return int(obs.dosage[k])
+    return int(min(n, max(0, round(obs.baf[k] * n))))
+
+
+def solution_detail(m: GeneModel, obs: Observations, recs: list[dict[str, Any] | None], s: Solution, top: Solution,
+                    low_gs: float, max_edit: int) -> dict[str, Any]:  # fmt: skip
+    """PGX-018 … PGX-020, PGX-028: per-allele supporting / unresolved variants, no-call impact, change vs top."""
+    n = max(1, len(s.copies))
+    alleles = []
+    names = list(s.haplotypes)
+    hap_of = {m.haplotypes[i]: i for i in s.copies}
+    reason = {NO_CALL: "no_call", MASKED: "masked", NOT_COVERED: "not_on_array"}
+    for name in names:
+        core = name.split("x")[0] if "x" in name and name.split("x")[-1].isdigit() else name
+        h = hap_of.get(core)
+        sup, unres = [], []
+        if h is not None:
+            for k in np.flatnonzero(m.carries[h] == 1).tolist():
+                c, p, r_, a_ = m.variants[k]
+                hg, rs = m.variant_ids[k]
+                rec = recs[k]
+                if obs.state[k] == CALLED:
+                    sup.append({"chrom": c, "pos": p, "ref": r_, "alts": rec["alts"] if rec else [a_],
+                                "gt": rec["gt"] if rec else None, "gs": None if math.isnan(obs.gs[k]) else
+                                round(float(obs.gs[k]), 4), "baf": None if math.isnan(obs.baf[k]) else
+                                round(float(obs.baf[k]), 4), "variant_copy_number": _vcn(obs, k, n), "hgvs": hg,
+                                "rsid": rs, "probe_ids": rec["id"].split(",") if rec else [],
+                                "low_gs": bool(obs.gs[k] < low_gs)})  # fmt: skip
+                else:
+                    unres.append({"hgvs": hg, "rsid": rs, "reason": reason[int(obs.state[k])],
+                                  "probe_ids": rec["id"].split(",") if rec else []})  # fmt: skip
+        background = None
+        if "+" in name:
+            background = name.split("+")[-1]
+        alleles.append({"allele": name, "supporting_variants": sup, "unresolved_variant_sites": unres,
+                        "array_equivalent_alleles": sorted({mm[names.index(name)] for mm in s.members
+                                                            if len(mm) == len(names)}, key=_natural),
+                        "background_allele": background})  # fmt: skip
+    exp = _expected(m, s.copies)
+    exp_top = _expected(m, top.copies)
+    called = obs.state == CALLED
+    changed = [m.variant_ids[k][0] for k in np.flatnonzero(called & (exp != exp_top)).tolist()]
+    flags = ["distant_alternative"] if len(changed) > max_edit else []
+    return {"alleles": alleles, "variant_change": changed if s is not top else None, "flags": flags}
+
+
+def _expected(m: GeneModel, copies: tuple[int, ...]) -> npt.NDArray[np.int16]:
+    e = np.zeros(m.carries.shape[1], dtype=np.int16)
+    for i in copies:
+        e += np.maximum(m.carries[i], 0)
+    return e
+
+
 def read_cn_vcf(path: Path) -> dict[str, int | None]:
     out: dict[str, int | None] = {}
     with gzip.open(path, "rt") as fh:
@@ -172,7 +241,7 @@ def _discover(dirs: list[Path]) -> tuple[dict[str, Path], dict[str, Path]]:
 def run_star_call(o: StarOptions, rep: Reporter) -> int:
     """``simurg pgx star-allele call`` (CLI-033)."""
     from simurg.core.atomic import check_outputs_absent
-    from simurg.pipeline.qc import write_tsv
+    from simurg.pipeline.pgx_pheno import db_meta, tsv_header, write_meta_tsv
 
     snv, cnv = _discover(o.vcfs)
     if not snv:
@@ -195,7 +264,10 @@ def run_star_call(o: StarOptions, rep: Reporter) -> int:
     for m in models.values():
         for c, p, _, _ in m.variants:
             wanted[c].add(p)
-    rows = []
+    rows: list[dict[str, Any]] = []
+    sup_rows: list[dict[str, Any]] = []
+    unres_rows: list[dict[str, Any]] = []
+    not_cov_rows: dict[tuple[str, str], dict[str, Any]] = {}
     calls_json = []
     for sid, path in sorted(snv.items()):
         recs, meta = read_vcf_sites(path, wanted)
@@ -215,42 +287,130 @@ def run_star_call(o: StarOptions, rep: Reporter) -> int:
         sample_name = sid
         genes_out = []
         for gene, m in sorted(models.items()):
-            obs, ploidy = observations(m, recs, masked)
+            gene_json, g_rows, g_sup, g_unres, g_ncov = call_one_gene(sid, sample_name, m, recs, masked, cn, o)
-            region = CN_REGION.get(gene)
+            if gene_json is None:
-            gcn = cn.get(region) if region else None
+                continue
-            sols, feasible = call_gene(m, obs, cn=gcn if region else None, ploidy=ploidy,
+            genes_out.append(gene_json)
-                                       max_candidates=o.max_candidates, feasible_ratio=o.feasible_ratio)  # fmt: skip
+            rows += g_rows
-            flags = []
+            sup_rows += g_sup
-            low = [k for k in range(len(m.variants)) if obs.state[k] == CALLED and obs.gs[k] < o.low_gs]
+            unres_rows += g_unres
-            if low:
+            for x in g_ncov:
-                flags.append("review_alternatives")
+                not_cov_rows[(gene, str(x["hgvs"]))] = x
-            no_calls = [k for k in range(len(m.variants)) if obs.state[k] == NO_CALL]
-            genotype = ";".join(s.genotype for s in feasible)
-            for rank, s in enumerate(sols, start=1):
-                rows.append({"sample_id": sid, "sample_name": sample_name, "solution_id": rank, "gene": gene,
-                             "call_type": "star_allele", "solution": s.genotype,
-                             "array_equivalent_alleles_1": ";".join(sorted({mm[0] for mm in s.members})),
-                             "array_equivalent_alleles_2": ";".join(sorted({mm[-1] for mm in s.members})),
-                             "no_call_variants": ";".join(m.variant_ids[k][0] for k in no_calls),
-                             "alleles_impacted_by_no_call": "", "background_alleles": "", "variant_change": "",
-                             "score": f"{s.score:.4f}", "raw_score": f"{s.raw_score:.4f}",
-                             "copy_number_solution": f"{region}={gcn}" if region and gcn is not None else "",
-                             "flags": ";".join(flags + (["feasible"] if s in feasible else []))})  # fmt: skip
-            genes_out.append({"gene": gene, "genotype": genotype, "feasible_solutions": [s.genotype for s in feasible],
-                              "candidates": [_sol_json(s) for s in sols], "copy_number": gcn,
-                              "flags": flags})  # fmt: skip
         calls_json.append({"sample_id": sid, "genes": genes_out})
     cols = ["sample_id", "sample_name", "solution_id", "gene", "call_type", "solution", "array_equivalent_alleles_1",
             "array_equivalent_alleles_2", "no_call_variants", "alleles_impacted_by_no_call", "background_alleles",
             "variant_change", "score", "raw_score", "copy_number_solution", "flags"]  # fmt: skip
     o.out.mkdir(parents=True, exist_ok=True)
-    write_tsv(o.out / "diplotype_summary.tsv", cols, rows)
+    head = tsv_header(o.db, db_meta(o.db), "none")[:-1]  # PGX-026 metadata (no guideline before phenotyping)
+    write_meta_tsv(o.out / "diplotype_summary.tsv", head, cols, rows)
+    write_meta_tsv(o.out / "supporting_variants.tsv", head,
+                   ["sample_id", "solution_id", "gene", "allele", "hgvs", "rsid", "chrom", "pos", "ref", "alts",
+                    "genotype", "variant_copy_number", "gs", "baf", "probe_ids", "low_gs"], sup_rows)  # fmt: skip
+    write_meta_tsv(o.out / "unresolved_variants.tsv", head,
+                   ["sample_id", "gene", "solution_id", "allele", "hgvs", "rsid", "reason", "probe_ids"],
+                   unres_rows)  # fmt: skip
+    write_meta_tsv(o.out / "variants_not_covered.tsv", head, ["gene", "hgvs", "rsid", "alleles_impacted"],
+                   [not_cov_rows[k] for k in sorted(not_cov_rows)])  # fmt: skip
     (o.out / "pgx_calls.json").write_text(json.dumps({"software": f"SimurgArray {__version__}", "db": o.db.name,
                                                       "samples": calls_json}, indent=1))  # fmt: skip
     rep.info(f"star alleles: {len(calls_json)} sample(s), {len(models)} gene(s)")
     return ExitCode.OK
 
 
+def call_one_gene(
+    sid: str, sample_name: str, m: GeneModel, recs: dict[tuple[str, int], list[dict[str, Any]]], masked: set[str],
+    cn: dict[str, int | None], o: StarOptions,
+) -> tuple[dict[str, Any] | None, list[dict[str, Any]], list[dict[str, Any]], list[dict[str, Any]],
+           list[dict[str, Any]]]:  # fmt: skip
+    """One gene of one sample: call, details, and the rows of the four TSVs (PGX-012 … PGX-031)."""
+    gene = m.gene
+    obs, ploidy = observations(m, recs, masked)
+    vrec = variant_records(m, recs)
+    region = CN_REGION.get(gene)
+    gcn = cn.get(region) if region else None
+    sols, feasible = call_gene(m, obs, cn=gcn if region else None, ploidy=ploidy,
+                               max_candidates=o.max_candidates, feasible_ratio=o.feasible_ratio)  # fmt: skip
+    if not sols:
+        return None, [], [], [], []
+    top = sols[0]
+    details = [solution_detail(m, obs, vrec, s_, top, o.low_gs, MAX_EDIT_DISTANCE) for s_ in sols]
+    flags = []
+    if any(sv["low_gs"] for al in details[0]["alleles"] for sv in al["supporting_variants"]):
+        flags.append("review_alternatives")  # PGX-016
+    v_nc = [k for k in range(len(m.variants)) if obs.state[k] in (NO_CALL, MASKED)]
+    v_ncov = [k for k in range(len(m.variants)) if obs.state[k] == NOT_COVERED]
+
+    def impacted(k: int) -> list[str]:
+        return sorted((m.haplotypes[h] for h in np.flatnonzero(m.carries[:, k] == 1).tolist()), key=_natural)
+
+    def probes(k: int) -> list[str]:
+        rec = vrec[k]
+        return str(rec["id"]).split(",") if rec else []
+
+    exp_any = np.zeros(len(m.variants), dtype=np.int16)
+    for i in top.copies:
+        exp_any += m.carries[i] != 0
+    unexplained = [m.variant_ids[k][0] for k in range(len(m.variants))
+                   if obs.state[k] == CALLED and obs.dosage[k] > 0 and exp_any[k] == 0]  # fmt: skip
+    if unexplained:
+        flags.append("unexplained_variants")  # PGX-031
+    no_call_list = [{"hgvs": m.variant_ids[k][0], "rsid": m.variant_ids[k][1], "probe_ids": probes(k),
+                     "alleles_impacted": impacted(k)} for k in v_nc]  # fmt: skip
+    not_cov = [{"hgvs": m.variant_ids[k][0], "rsid": m.variant_ids[k][1], "alleles_impacted": impacted(k)}
+               for k in v_ncov]  # fmt: skip
+    covered = obs.state != NOT_COVERED
+    defining = m.carries == 1
+    tested = sorted((m.haplotypes[h] for h in range(len(m.haplotypes))
+                     if not defining[h].any() or (defining[h] & covered).any()), key=_natural)  # fmt: skip
+    imp_nc = sorted({a for k in v_nc for a in impacted(k)}, key=_natural)
+    rows, sup_rows, unres_rows = [], [], []
+    for rank, (s_, d) in enumerate(zip(sols, details, strict=True), start=1):
+        sflags = flags + d["flags"] + (["feasible"] if s_ in feasible else [])
+        rows.append({"sample_id": sid, "sample_name": sample_name, "solution_id": rank, "gene": gene,
+                     "call_type": "star_allele", "solution": s_.genotype,
+                     "array_equivalent_alleles_1": ";".join(d["alleles"][0]["array_equivalent_alleles"]),
+                     "array_equivalent_alleles_2": ";".join(d["alleles"][-1]["array_equivalent_alleles"]),
+                     "no_call_variants": ";".join(str(x["hgvs"]) for x in no_call_list),
+                     "alleles_impacted_by_no_call": ";".join(imp_nc),
+                     "background_alleles": ";".join(al["background_allele"] for al in d["alleles"]
+                                                    if al["background_allele"]),
+                     "variant_change": ";".join(d["variant_change"] or []),
+                     "score": f"{s_.score:.4f}", "raw_score": f"{s_.raw_score:.4f}",
+                     "copy_number_solution": f"{region}={gcn}" if region and gcn is not None else "",
+                     "flags": ";".join(sflags)})  # fmt: skip
+        for al in d["alleles"]:
+            for sv in al["supporting_variants"]:
+                sup_rows.append({"sample_id": sid, "solution_id": rank, "gene": gene, "allele": al["allele"],
+                                 "hgvs": sv["hgvs"], "rsid": sv["rsid"], "chrom": sv["chrom"], "pos": sv["pos"],
+                                 "ref": sv["ref"], "alts": ";".join(sv["alts"]), "genotype": sv["gt"],
+                                 "variant_copy_number": sv["variant_copy_number"], "gs": sv["gs"], "baf": sv["baf"],
+                                 "probe_ids": ";".join(sv["probe_ids"]),
+                                 "low_gs": str(sv["low_gs"]).lower()})  # fmt: skip
+            for uv in al["unresolved_variant_sites"]:
+                unres_rows.append({"sample_id": sid, "gene": gene, "solution_id": rank, "allele": al["allele"],
+                                   "hgvs": uv["hgvs"], "rsid": uv["rsid"], "reason": uv["reason"],
+                                   "probe_ids": ";".join(uv["probe_ids"])})  # fmt: skip
+    ncov_rows = [{"gene": gene, "hgvs": m.variant_ids[k][0], "rsid": m.variant_ids[k][1],
+                  "alleles_impacted": ";".join(impacted(k))} for k in v_ncov]  # fmt: skip
+    cands = []
+    for s_, d in zip(sols, details, strict=True):
+        cj = _sol_json(s_)
+        cj.update({"alleles": d["alleles"], "variant_change": d["variant_change"], "flags": d["flags"],
+                   "variant_no_calls": no_call_list, "alleles_impacted_by_no_calls": imp_nc})  # fmt: skip
+        cands.append(cj)
+    gene_json = {"gene": gene, "call_type": "star_allele", "genotype": ";".join(s_.genotype for s_ in feasible),
+                 "feasible_solutions": [s_.genotype for s_ in feasible], "candidates": cands, "copy_number": gcn,
+                 "flags": flags, "variant_no_calls": no_call_list, "variants_not_covered": not_cov,
+                 "unexplained_variants": unexplained, "alleles_tested": tested}  # fmt: skip
+    return gene_json, rows, sup_rows, unres_rows, ncov_rows
+
+
 def _sol_json(s: Solution) -> dict[str, Any]:
     return {"genotype": s.genotype, "score": round(s.score, 4), "raw_score": round(s.raw_score, 4),
             "equivalents": ["/".join(m) for m in s.members][:20], "copy_number": s.copy_number}  # fmt: skip
+
+
+def _natural(a: str) -> tuple[Any, ...]:
+    import re
+
+    return tuple(int(x) if x.isdigit() else x for x in re.split(r"(\d+)", a))

tests/unit/test_pgx_db.py

@@ -121,3 +121,29 @@ def test_db_build_deterministic(tmp_path: Path) -> None:  # IN-053, CLI-035
     meta = dict(con.execute("select key, value from meta").fetchall())
     assert meta["content_sha256"][:12] in outs[0].name and json.loads(meta["allele_sources"])[0]["name"] == "CPIC"
     assert con.execute("select phenotype from phenotypes").fetchone() == ("Poor Metabolizer",)
+
+
+def test_coverage_statuses(tmp_path: Path) -> None:  # PGX-009 / PGX-035
+    from simurg.pipeline.pgx_db import coverage_rows
+
+    src = tmp_path / "sources" / "cpic-20260101"
+    src.mkdir(parents=True)
+    for k, v in _tables().items():
+        (src / f"{k}.json").write_text(json.dumps(v))
+    (src / "source.json").write_text(json.dumps({"name": "CPIC", "version": "2026-01-01", "retrieved": "20260101"}))
+    fa = tmp_path / "g.fa"
+    fa.write_text(">chr1\n" + SEQ + "\n")
+    out = tmp_path / "db"
+    r = CliRunner().invoke(app, ["pgx", "db", "build", "--sources", str(tmp_path / "sources"), "--fasta", str(fa),
+                                 "--out", str(out), "--quiet"])  # fmt: skip
+    assert r.exit_code == 0, r.output
+    db = next(out.glob("pgx_db-1-*.sqlite"))
+    con = sqlite3.connect(db)
+    con.executemany("INSERT INTO probe_map VALUES (?, ?, ?, ?, ?, ?)",
+                    [("M", "p_star2", "chr1", 5, "A", "G"), ("M", "p_star3", "chr1", 7, "GT", "G")])  # fmt: skip
+    con.execute("INSERT INTO masks VALUES ('M', 'p_star3', 'test')")
+    con.commit()
+    con.close()
+    st = {r["allele"]: r["status"] for r in coverage_rows(db, "M")}
+    assert st["*1"] == "callable" and st["*2"] == "callable"
+    assert st["*3"] == "masked" and st["*5"] == "not_covered"