Nicholas K. Wang

A low-rank covariance probe on Evo 2 embeddings predicts ClinVar pathogenicity across SNVs and indels, while annotation probes plus an LLM produce mechanistic hypotheses; scores released for 4.2 million variants.

Metapipeline-DNA automates comprehensive analysis of DNA sequencing data from raw reads to visualization, supporting germline and somatic genomic features.

Pleiades, a whole-genome epigenetic model, detects Alzheimer's and Parkinson's disease from plasma cell-free DNA with high accuracy.

A 40B-parameter DNA model trained on 9.3 trillion tokens scores coding and noncoding variants zero-shot, exposes interpretable sequence features, and writes chromosome-scale sequences.

The paper quantifies the impact of genome build differences on variant calling and introduces StableLift, an algorithm to predict cross-build variant stability.