vcf-variant-filtering
VCF Variant Filtering Guide
Overview
Raw VCF files produced by variant callers (GATK HaplotypeCaller, bcftools mpileup, DeepVariant, etc.) contain a mixture of true variants and artifacts from sequencing errors, alignment issues, and low-coverage regions. Computing summary statistics -- Ts/Tv ratio, variant counts, allele frequency distributions -- on unfiltered data yields unreliable results because false-positive calls disproportionately inflate transversion counts and depress the Ts/Tv ratio. This guide covers how to detect whether a VCF is raw, how to apply appropriate quality filters, when filtering is not appropriate, and how to interpret the resulting statistics correctly.
Key Concepts
VCF Quality Scores (QUAL Field)
The QUAL column in a VCF file represents the Phred-scaled probability that the variant site is polymorphic. A QUAL score of 30 means a 1-in-1000 chance the call is wrong; a QUAL of 20 means 1-in-100. Variant callers assign QUAL scores based on read evidence, base qualities, and mapping qualities. Low-QUAL variants (below 20-30) are enriched for sequencing errors and alignment artifacts. Filtering on QUAL is the simplest and most widely used first-pass quality control step.
Common QUAL thresholds and their interpretation:
More from jaechang-hits/sciagent-skills
scientific-brainstorming
Structured ideation methods: SCAMPER, Six Thinking Hats, Morphological Analysis, TRIZ, Biomimicry, plus more. Decision framework for picking methods by challenge type (stuck, improving, systematic exploration, contradiction). Use when generating research ideas or exploring interdisciplinary connections.
12snakemake-workflow-engine
Python-based workflow management system for reproducible, scalable pipelines. Define rules with file-based dependencies; Snakemake automatically determines the execution order and parallelism. Supports local, SLURM, LSF, AWS, and Google Cloud execution via profiles; per-rule conda/Singularity environments. Use for bioinformatics NGS pipelines, ML training workflows, and any multi-step file-processing analysis. Use Nextflow instead for Groovy-based dataflow pipelines or when nf-core ecosystem integration is required.
11esm-protein-language-model
Protein language models (ESM3, ESM C) for sequence generation, structure prediction, inverse folding, and protein embeddings. Use when designing novel proteins, extracting sequence representations for downstream ML, or predicting structure from sequence. Local GPU or EvolutionaryScale Forge cloud API. For traditional structure prediction use AlphaFold; for small-molecule cheminformatics use RDKit.
11biopython-sequence-analysis
Biopython sequence analysis: parse FASTA/FASTQ/GenBank/GFF (SeqIO), NCBI Entrez (esearch/efetch/elink), remote/local BLAST, pairwise/MSA alignment (PairwiseAligner, MUSCLE/ClustalW), phylogenetic trees (Phylo). Use for gene family studies, phylogenomics, comparative genomics, NCBI pipelines. For PCR/restriction/cloning use biopython-molecular-biology; for SAM/BAM use pysam.
11shap-model-explainability
>-
11archs4-database
Query ARCHS4 REST API for uniformly processed RNA-seq expression, tissue patterns, co-expression across 1M+ human/mouse samples. Retrieve z-scores, co-expressed genes, samples by metadata, HDF5 matrices. For variant population genetics use gnomad-database; for pathway enrichment use gget-genomic-databases (Enrichr).
11