Johnny Israeli

DTWax optimizes the sDTW algorithm for GPU to improve sequencing speed and compute efficiency in nanopore sequencing.

The paper accelerates Minimap2 for long read alignment on GPUs by optimizing the chaining step, achieving significant speedup and cost reduction.

The paper demonstrates the use of GPU computing with RAPIDS to accelerate single-cell genomic analysis workflows and provides open-source examples.

GEPSi simulates GWAS phenotype data with biological complexity to benchmark genetic analysis methods.

This paper trains deep learning models to reduce sequencing errors in PacBio HiFi reads, achieving 25-40% error reduction in human and E. coli genomes.

AtacWorks denoises and identifies accessible chromatin regions from low-quality ATAC-seq data, achieving high-resolution results with minimal input.

Kipoi provides a framework for standardized, reusable machine learning models in genomics, enabling tasks like variant effect prediction and model benchmarking.

Deep learning rivals or beats baselines across imaging, health records, genomics and drug discovery but is not yet transformative; scarce labels, privacy and opacity remain hurdles.