Jianyu Yang

TPCAV: Interpreting deep learning genomics models via concept attribution

This paper introduces TPCAV, a method to interpret genomics deep learning models by adapting concept attribution, showing it can analyze both motif features and general genomic concepts.

Widespread Regulatory Turnover Across Human Segmental Duplications

This study investigates regulatory turnover in human segmental duplications using T2T genome assembly and ChIP-seq data, finding that regulatory elements are rarely conserved but gene expression and spatial proximity are preserved.

SEM: sized-based expectation maximization for characterizing nucleosome positions and subtypes

SEM identifies nucleosome subtypes from MNase-seq data by modeling fragment length distributions, revealing three nucleosome types including accessible short-fragment nucleosomes.

Systematic Dissection of Sequence Features Affecting the Binding Specificity of a Pioneer Factor Reveals Binding Synergy Between FOXA1 and AP-1

The paper uses ChIP-ISO to analyze sequence features affecting FOXA1 binding and finds that AP-1 influences FOXA1 binding specificity and context-dependent binding.

Joint sequence & chromatin neural networks characterize the differential abilities of Forkhead transcription factors to engage inaccessible chromatin

The paper investigates how sequence preferences and chromatin environments influence Fox TF binding using neural networks and mouse stem cells.