菜单
How to load krewlyzer parquet feature files with correct suffixes and schemas per feature type.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Testing conventions, patterns, and best practices for kreview. MANDATORY reading before adding or modifying tests.
nbdev cell directives, module export conventions, editing workflow, and testing patterns for notebook-first development. MANDATORY reading before editing any kreview Python module.
5-tier ctDNA labeling hierarchy with IMPACT tissue rescue, CH hotspot filtering, configurable VAF/variant thresholds, and continuous VAF regression stats.
How to parse cBioPortal MAF, SV, CNA, and clinical files for the labeling pipeline.
Structured debugging framework for kreview data pipeline issues
DuckDB glob scan patterns, connection management, and performance for kreview
| name | parquet-feature-loading |
| description | How to load krewlyzer parquet feature files with correct suffixes and schemas per feature type. |
from kreview.core import load_sample_feature
# Load a feature parquet for one sample
df = load_sample_feature(
sample_id="P-0000280-T02-XS1",
feature_suffix=".FSC.gene.parquet", # exact suffix from §4 table
results_dir="/path/to/results/",
)
| Evaluator | source_file |
|---|---|
| FSC.gene | .FSC.gene.parquet |
| FSC bin-level | .FSC.ontarget.parquet |
| FSC.regions | .FSC.regions.parquet |
| FSD | .FSD.ontarget.parquet |
| FSR | .FSR.ontarget.parquet |
| OCF ontarget | .OCF.ontarget.parquet |
| OCF offtarget | .OCF.offtarget.parquet |
| ATAC | .ATAC.ontarget.parquet |
| TFBS | .TFBS.ontarget.parquet |
| MDS | .MDS.ontarget.parquet |
| MDS.gene | .MDS.gene.parquet |
| MDS.exon | .MDS.exon.parquet |
| EndMotif | .EndMotif.ontarget.parquet |
| BreakPointMotif | .BreakPointMotif.ontarget.parquet |
| EndMotif1mer | .EndMotif1mer.parquet |
| WPS.panel | .WPS.panel.parquet |
| WPS genome | .WPS.parquet |
| WPS background | .WPS_background.parquet |
| metadata | .metadata.parquet |
.tsv.gz or .features.jsonload_sample_feature().correction_factors.parquet or .fsc_counts.parquet (excluded)