Filter and rank protein designs using pLDDT, ipTM, PAE, and sequence liability thresholds.
npx skills add https://github.com/junior1p/ProteinClaw --skill protein-qc-junior1p
Please help me install this Agent Skill. Skill: protein-qc Source: https://github.com/junior1p/ProteinClaw/tree/main/skills/protein-qc Command: npx skills add https://github.com/junior1p/ProteinClaw --skill protein-qc-junior1p
Protein design outputs often contain many candidates with mixed structural confidence, binding potential, and expression risk; this Skill provides standardized metrics, thresholds, and guidance to screen, filter, and rank designs so teams can focus experimental validation on the most promising candidates.
Use the protein-qc skill to filter a design CSV by pLDDT > 0.85, ipTM > 0.5, even cysteine counts, and compute a composite score to select the top candidates.
High-intent search queries and answers about installing and using this skill.
Filter protein designs by applying threshold-based filters for structural confidence metrics like pLDDT > 0.85 and interface quality metrics like ipTM > 0.5 to reduce candidates to a high-quality set.
Composite scoring for protein design ranking combines pLDDT, ipTM, PAE, shape complementarity, and language-model plausibility into a single score to prioritize the most promising candidates for experimental testing.
Check protein sequences for liabilities by applying design-level heuristics that detect odd cysteines, deamidation motifs, and polybasic clusters to flag candidates with expression or stability risks.
You can run a sequential multi-stage filtering pipeline to reduce thousands of in silico binders to a top candidate set that meets structural, binding, and expression thresholds for experimental testing.
Protein design quality control uses metrics including pLDDT, pTM, ipTM, PAE, sequence liabilities, and PyRosetta interface metrics to assess structural confidence, binding potential, and expression risk.
Protein QC provides campaign health diagnostics and basic failure-recovery recommendations to help teams adjust their design strategies when filtering pipelines yield insufficient passing candidates.
adaptyvbioAutomate protein design quality-control checks with standardized thresholds and composite scoring.
lohasleConvert laboratory instrument output files to Allotrope Simple Model JSON or CSV.
adaptyvbioCompute protein embeddings and PLL scores using the ESM2 language model.
zongtingweiFilter protein-design candidates using structural, interface, and biophysical QC metrics.
