#!/bin/bash -Ceuo pipefail
SEX=$(python3 -c "
import pandas as pd
sex = pd.read_csv('sex_calls.csv')
lookup = dict(zip(sex['specimen_id'], sex['inferred_sex']))
s = lookup.get('1029_0W2', 'unknown')
print('male' if s != 'female' else 'female')
")

python /usr/local/bin/normalize_sample.py \
    --counts 1029_0W2-N1-BDNA-1_B23KGCJLT4_1_probes.tsv.gz \
    --batch-reference batch_reference.parquet \
    --gc-reference /usr/local/share/probe_gc_content.tsv \
    --sex $SEX \
    --sample-id 1029_0W2-N1-BDNA-1_B23KGCJLT4_1 \
    --specimen-id 1029_0W2 \
    --flowcell unknown \
    --sample-type normal \
    --output 1029_0W2-N1-BDNA-1_B23KGCJLT4_1_normalized.parquet \
    --feature-stats-output 1029_0W2-N1-BDNA-1_B23KGCJLT4_1_gam_stats.json

cat <<-END_VERSIONS > versions.yml
"NFCORE_SAREK:SAREK:BAM_VARIANT_CALLING_SOMATIC_ALL:SOMATIC_CNV_CALLING:SOMA_CNV_NORMALIZE":
    soma-cnv: 20260603-050173b
END_VERSIONS