PGx CN: pgx copy-number train|call (CLI-031/032, PCN-001..017, IN-050), region BED v1, demo identities (K-028)

- simurg/pgx/cn.py: per-region CN mixture, mu_c = delta + gamma*log2((c+1)/3), free lower CN-0 component,
  Hardy-Weinberg-constrained weights over haplotype copy numbers, EM from a grid of label starts.
- pipeline/pgx_cn.py: model file (.simurg-pgxcn), batch rules (PCN-004), per-sample CN VCF + tbi, batch and
  sample summaries.
- The GSA v4 PGx demo arrays are 30 CEPH/1000G individuals (scripts/pgx/demo36_identity.tsv); against NYGC 30x
  SV RD_CN 224/240 region calls agree (GSTM1, UGT2B17 30/30), in-sample (docs/validation/V2_pgx_cn.md).

docs/messages.md

@@ -36,11 +36,15 @@ Generated from `src/simurg/core/errors.py` — do not edit by hand.
 | `E_METH_NO_CONTROLS` | error | Missing control probes in manifest | MET-002 |
 | `E_METH_NO_IDATS` | error | No IDATs found | MET-004 |
 | `E_METH_PREP_FAILED` | error | Prep failed (sample) | MET-010 |
+| `E_MODEL_CLUSTER_MISMATCH` | error | Input GTCs were called with another cluster file than the model | IN-050 |
 | `E_MODEL_MANIFEST_MISMATCH` | error | Model was built for a different manifest probe set | IN-051 |
 | `E_MODEL_VERSION` | error | Model schema is too old; rebuild it | IN-051 |
 | `E_NO_INPUT` | error | Neither an input folder nor a sample sheet was given | CLI-006 |
 | `E_NO_INPUT_FOLDER` | error | Sample sheet has no RootFolder and no folder was given | CLI-006 |
 | `E_OUTPUT_EXISTS` | error | Outputs already exist; use --force or --resume | CLI-010 |
+| `E_PGX_BATCH_TOO_SMALL` | error | Too few (passing) samples in the batch for PGx CN calling | PCN-004 |
+| `E_PGX_CN_FAILED` | error | PGx CN calling failed for the sample | PCN-002 |
+| `E_PGX_TRAIN_TOO_SMALL` | error | Too few (passing) samples to train a PGx CN model | PCN-005 |
 | `E_QC_CONFIG_EXT` | error | QC config file must be .yaml or .yml | QC-021 |
 | `E_QC_CONFIG_MISSING` | error | QC config file does not exist | QC-021 |
 | `E_QC_CONFIG_PARSE` | error | QC config file is not valid YAML | QC-021 |
@@ -92,7 +96,12 @@ Generated from `src/simurg/core/errors.py` — do not edit by hand.
 | `W_METH_MISSING_CONTROL_TYPES` | warning | Control types missing from the manifest; metric set to NA | MET-009 |
 | `W_METH_MISSING_SAMPLE` | warning | Missing sample: IDATs absent; the sample fails, the run continues | MET-015 |
 | `W_METH_NO_FEATURES` | warning | No features, skipping PCA plot | MET-013 |
+| `W_MODEL_CLUSTER_MISMATCH` | warning | Input GTCs were called with another cluster file than the model | IN-050 |
 | `W_NO_BGZIP` | warning | Uncompressed VCF written; downstream commands need bgzip + index | OUT-010 |
+| `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_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 |
 | `W_QC_PEDIGREE` | warning | Parent1/Parent2/Replicate value does not name a sample in the set | IN-018 |