Daniel Chang

This paper demonstrates that a genomic language model can generate functional regulatory DNA sequences using few examples, showing improved performance in cell-type-specific gene expression and neuronal labeling.

The paper constructs a genome-scale genetic interaction network from 4 million double mutants in HAP1 cells, revealing conserved genetic network principles across species and uncovering novel gene functions and cancer dependencies.

The paper uses long-read metagenomics to study prophage integration dynamics in gut microbiota, finding dynamic phage-host interactions and a new class of phages.

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 compares a ridge regression model to a deep learning method for predicting cancer genetic dependencies and finds ridge regression performs better.

The paper introduces GMWI2, a gut microbiome health index that improves disease prediction accuracy compared to previous models and traditional diversity indices.

TaxiBGC improves BGC prediction in metagenomes by using taxonomy-guided methods, showing better performance than read-based approaches and linking BGCs to human diseases.

The paper introduces GMHI-webtool, an online tool that computes and visualizes gut microbiome health indices from stool metagenomic data, enabling easier interpretation and comparison with reference datasets.