Daven Lim

A sequence-only convolutional neural network and an annotation-based random forest predict human structural variant breakpoints from 400 bp windows (AUROC 0.903, 0.904); their ensemble reaches 0.916.

This study identifies 35.3 million structural variants across vertebrates, showing significant variation in their abundance, mechanisms, and functional impact across species.

The Vertebrate Genomes Project Phase I provides high-quality reference genomes for 816 species, enabling evolutionary and conservation insights across vertebrates.

This paper presents a framework using LLMs and cheminformatics to extract and validate enzymatic reactions from scientific text, showing accurate inference of incomplete reactions.

The paper develops a structure-aware method to annotate Leucine-rich Repeat (LRR) domains by integrating geometric properties of protein structures, improving accuracy over sequence-based approaches.