Files
SimurgArray/src/simurg/qc/control_names.yaml
T
kemal 8758178df6 v2 methylation control QC (WIP): simurg methyl qc|convert-manifest (MET-001..018)
Methylation CSV manifest reader (MET-002/003), raw M/U assembly with bead masking
(MET-005), pOOBAH detection p-values, noob background correction, linear/nonlinear dye
bias, beta and M-values (MET-010..012), the 21 methylation control metrics (MET-006,
bs-conv red-bg set option), per-sample ctrl/cgs tables, summary tsv/xlsx/html with the
detection histogram and a beta PCA, pcs.tsv.gz, controls_raw/controls_qc.tsv; methylation
datasets load in qc report (MET-014); qc controls --array-type methylation; minfi-style
Sentrix_ID/Sentrix_Position sheet keys. Vendor EPIC manifests carry a 5th field on some
control lines: >= 4 fields accepted. Runs on the public minfiDataEPIC set (3 x NA12878).
2026-09-29 00:13:22 +01:00

99 lines
2.9 KiB
YAML

# Canonical control-probe IDs (spec QC-002). Keys are *normalised* names: case-folded, whitespace collapsed,
# no spaces next to or inside parentheses, "bgnd" written as "bkg". Several manifest spellings map to one ID.
canonical:
# staining
biotin(high): biotin_high
biotin(bkg): biotin_bkg
biotin(5k): biotin_5k
dnp(high): dnp_high
dnp(bkg): dnp_bkg
dnp(20k): dnp_20k
# extension
extension(a): ext_A
extension(t): ext_T
extension(c): ext_C
extension(g): ext_G
# hybridization
hyb(high): hyb_high
hyb(medium): hyb_medium
hyb(low): hyb_low
# target removal
target removal: target_removal_1
target removal(1): target_removal_1
target removal 1: target_removal_1
target removal(2): target_removal_2
target removal 2: target_removal_2
# stringency
string(pm): string_pm
string(mm): string_mm
# non-specific binding (one bead type per colour label on genotyping chips)
nsb(bkg): nsb_bkg
nsb(bkg) red: nsb_bkg
nsb(bkg) green: nsb_bkg
nsb(bkg) blue: nsb_bkg
nsb(bkg) purple: nsb_bkg
# non-polymorphic
np(a): np_A
np(t): np_T
np(c): np_C
np(g): np_G
# restoration (FFPE)
restoration: restoration
restore: restoration
# methylation (metrics in v2; names mapped already so controls_raw.tsv is labelled consistently)
bs conversion i c1: bs1_C1
bs conversion i c2: bs1_C2
bs conversion i c3: bs1_C3
bs conversion i c4: bs1_C4
bs conversion i c5: bs1_C5
bs conversion i u1: bs1_U1
bs conversion i u2: bs1_U2
bs conversion i u3: bs1_U3
bs conversion i u4: bs1_U4
bs conversion i u5: bs1_U5
bs conversion i-c1: bs1_C1
bs conversion i-c2: bs1_C2
bs conversion i-c3: bs1_C3
bs conversion i-c4: bs1_C4
bs conversion i-c5: bs1_C5
bs conversion i-c6: bs1_C6
bs conversion i-u1: bs1_U1
bs conversion i-u2: bs1_U2
bs conversion i-u3: bs1_U3
bs conversion i-u4: bs1_U4
bs conversion i-u5: bs1_U5
bs conversion i-u6: bs1_U6
bs conversion i c6: bs1_C6
bs conversion i u6: bs1_U6
bs conversion ii-1: bs2_1
bs conversion ii-2: bs2_2
bs conversion ii-3: bs2_3
bs conversion ii-4: bs2_4
gt mismatch 1(pm): gtmm_1_pm
gt mismatch 2(pm): gtmm_2_pm
gt mismatch 3(pm): gtmm_3_pm
gt mismatch 4(pm): gtmm_4_pm
gt mismatch 5(pm): gtmm_5_pm
gt mismatch 6(pm): gtmm_6_pm
gt mismatch 1(mm): gtmm_1_mm
gt mismatch 2(mm): gtmm_2_mm
gt mismatch 3(mm): gtmm_3_mm
gt mismatch 4(mm): gtmm_4_mm
gt mismatch 5(mm): gtmm_5_mm
gt mismatch 6(mm): gtmm_6_mm
specificity 1: spec2_1
specificity 2: spec2_2
specificity 3: spec2_3
# Categories treated as methylation-only (dataset type detection, QC-043).
methylation_categories:
- bisulfite conversion i
- bisulfite conversion ii
- specificity i
- specificity ii
# Report exclusion list (QC-010): raw-probe views leave these out; derived metrics still use them.
report_exclude:
categories: [negative, norm]
names: ["np(g) 1", "np(g) 2", "np(g) 3", "np(g) 4", "np(g) 5", "biotin(5k)", "dnp(20k)"]