Downloading: s3://natera-platform-sandbox/pipeline-resources/ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/MantaFusion/foresight_panel_for_manta.bed
Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/8a/df1296d8be4e5ce70d41f64d112fd2/.command.sh
Downloading: s3://natera-platform-sandbox/pipeline-resources/ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/MantaFusion/protein_coding_genes.bed
Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/14/e192d7d6e3d50dcb27a1ce43752d33/COLO829_tumor_20pct_rep2.manta_fusion.somatic_sv.annotated.vcf.gz.tbi
Downloading: s3://natera-platform-sandbox/pipeline-resources/ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/MantaFusion/modelD/model.pkl
Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/8a/df1296d8be4e5ce70d41f64d112fd2/.command.run
Downloading: s3://natera-rnd-pltf-dev-nextflow-scratch-01/work/14/e192d7d6e3d50dcb27a1ce43752d33/COLO829_tumor_20pct_rep2.manta_fusion.somatic_sv.annotated.vcf.gz
Downloading: s3://natera-platform-sandbox/pipeline-resources/ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/MantaFusion/cosmic_fusion.tsv.gz
Downloading: s3://natera-platform-sandbox/pipeline-resources/ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh38/Annotation/MantaFusion/pon
==> STAGING COMPLETE (9 inputs)
/usr/local/lib/python3.11/site-packages/sklearn/utils/validation.py:2691: UserWarning: X does not have valid feature names, but LGBMClassifier was fitted with feature names
warnings.warn(
[predict] Loading model from model.pkl …
28 features loaded (LGBMClassifier, of 36 computed by annotator)
[predict] Loading PoN from pon …
1D bins: 43,871 2D pairs: 39,238
[predict] Loading COSMIC from cosmic_fusion.tsv.gz …
614 gene-pair orientations
[predict] Loading gene annotator from protein_coding_genes.bed …
[predict] Loading target panel from foresight_panel_for_manta.bed …
201,779 panel intervals across 26 contigs
[predict] Tumor sample ID: 'COLO829_c_0001_gDNA_0001_B23H2NLLT4_8' Normal sample ID: 'COLO829BL_c_01_gDNA_0001_A237FLHLT3_1'
[predict] Parsing VCF COLO829_tumor_20pct_rep2.manta_fusion.somatic_sv.annotated.vcf.gz …
14 calls parsed (after intergenic/same-gene/on_panel filter)
10 killed by hard filters → 4 surviving
is_paralog_of_higher_score_call=1 for 0/4 calls
[predict] Scored 4 calls: 3 PASS at threshold 0.05
After strict-match dedup: 4 calls (3 PASS)
Final call set: 4 calls (3 PASS)
[predict] Writing COLO829_tumor_20pct_rep2.manta_fusion.somatic_sv.scored.vcf.gz …
[predict] Writing COLO829_tumor_20pct_rep2.manta_fusion.fusion_calls.tsv …
[predict] Done.