Thank you!

Prior knowledge informs graph neural networks to improve phenotype prediction from proteomics High-throughput proteomics data provides dense individual-level molecular readouts, enabling the development of machine learning models for predicting diverse phenotypes relevant to patient health. Pr...

Excited to share our work from the Battle Lab! It’s on an innovative deep learning model architecture incorporating biological domain knowledge to predict traits from large scale proteomic data: www.medrxiv.org/content/10.1...

Polygenic prediction of phenotypes with a neural empirical Bayes approach Polygenic risk scores (PRS) estimate the expected value of a phenotype based on individual genotypes. Although statistical approaches for calculating PRS have advanced considerably in recent years, fe...

Really excited to share our new PRS method, developed with @aprilkim.bsky.social and @alexisbattle.bsky.social ! Our approach is to use a lot of recently developed functional annotations to better estimate the weights of the SNPs.
www.medrxiv.org/content/10.1...

Check out the amazing work from my colleague and friend!

Excited to share our latest work on comparing and visualizing multiple genome assemblies to identify conservation and structural variation in pangenomes with Mumemto! Check out poster 250 at #bog25 if you are here. New preprint coming very soon 👀

If you are here at #bog25 please check out my poster (number 87) tonight! 😁 Showing our work on common variation associated with aneuploidy in human embryos

1/n 🚨Very excited to share our recent work!🚨
To understand gene regulation across diverse environmental conditions and cellular contexts, we treated a broad array of human cell types with three environmental exposures in vitro.
www.biorxiv.org/content/10.1...

Uncalled4: a toolkit for nanopore signal alignment, analysis and visualization of DNA and RNA modifications.

www.nature.com/articles/s41...

SV prioritization tools in both prioritizing coding and noncoding variant benchmarks. Finally, we were able to prioritize confident rare disease candidate SVs and genes in the Undiagnosed Disease Network data. To learn more, read our paper here: genome.cshlp.org/content/earl....

After extensive analyses of rare SVs near gene expression outliers using long and short-read sequencing, we developed Watershed-SV, extending Watershed, to prioritize functional rare SVs and genes they impact. Our model significantly improves from a baseline model and state-of-the-art

Happy to share our work characterizing functional rare SVs in rare diseases with long-read genome sequencing and transcriptomic outlier data: genome.cshlp.org/content/earl...

Mumemto: efficient maximal matching across pangenomes Aligning genomes into common coordinates is central to pangenome analysis and construction, but it is also computationally expensive. Multi-sequence maximal unique matches (multi-MUMs) are guideposts ...

Excited to share a preprint for (w/ @benlangmead.bsky.social) our new tool, Mumemto, on biorxiv! Mumemto finds multi-MUMs across pangenomes (i.e. mummer but for pangenomes). It can rapidly visualize synteny, identify misassemblies, and accelerate core genome and multiple alignment, highlighting SVs.

Mumemto: efficient maximal matching across pangenomes www.biorxiv.org/content/10.1101/2025.01....