Nicholas J. Haradhvala

This paper introduces scSet, a diffusion-based autoencoder that learns patient-level representations from single-cell data, outperforming existing methods in clinical prediction with limited labeled data.

This paper designs viral diagnostics using a model-based optimization approach, achieving higher sensitivity and specificity across viral genomic variation.

The paper introduces the Cancer LncRNA Census (CLC), a curated resource of lncRNAs with causative roles in cancer, and shows their genomic and evolutionary features.

ActivePathways integrates multivariate omics data to identify enriched pathways, revealing cancer driver genes and prognostic pathways in breast cancer.

This paper demonstrates that GPU-accelerated machine learning libraries significantly speed up and reduce the cost of computational genomics tasks like QTL mapping and Bayesian non-negative matrix factorization.

This paper shows that many cancer hotspots are passengers, not drivers, and introduces a new model to better identify true driver mutations.

This study analyzes RNA-seq data from 6,700 normal tissues to identify somatic mutations and their association with age and tissue proliferation, finding tissue-specific cancer mutation hotspots.

The paper predicts cancer cell-of-origin from DNA sequences by matching mutational landscapes to chromatin modification patterns in normal tissues.

The paper identifies and characterizes coding and non-coding driver mutations across 2,500 cancer genomes, revealing new candidates and questioning previous findings.