Jiahao Gao

A PERTURBATION CELL ATLAS OF HUMAN INDUCED PLURIPOTENT STEM CELLS

The paper generates a CRISPRi perturbation cell atlas in human induced pluripotent stem cells, identifies novel regulators of pluripotency and metabolism, and proposes a machine learning framework for predicting perturbation recipes.

HyperMap: An Efficient Framework for Transferring Perturbation Responses Across Diverse Biological Contexts

HyperMap transfers perturbation responses across biological contexts using a meta-learning framework, achieving accurate predictions with fewer parameters than typical models.

scLong: A Billion-Parameter Foundation Model for Capturing Long-Range Gene Context in Single-Cell Transcriptomics

scLong is a billion-parameter foundation model that captures long-range gene context in scRNA-seq by modeling all genes and integrating gene knowledge, outperforming existing models in various tasks.

Binding profiles for 954 Drosophila and C. elegans transcription factors revealtissue specific regulatory relationships

The paper presents a catalog of transcription factor binding sites in Drosophila and C. elegans, revealing tissue-specific regulatory relationships using machine learning.

The EN-TEx resource of multi-tissue personal epigenomes & variant-impact models

The paper introduces the EN-TEx resource, which provides personal epigenomes and variant-impact models across multiple tissues, revealing allele-specific loci and their associations with GWAS loci.

To mock or not: a comprehensive comparison of mock IP and DNA input for ChIP-seq

This study compares mock IP and DNA input controls in ChIP-seq, showing that mock IP better removes spurious sites, while DNA input has unique advantages, and proposes combining both for improved binding site detection.

Discovering a less-is-more effect to select transcription factor binding sites informative for motif inference

The paper identifies that less crowded and shorter transcription factor binding sites improve motif inference, showing a 30%-70% improvement in motif quality.