Peiran Jin

RegDesign-Bench: Benchmarking computational methods for cell-type-specific regulatory DNA design

RegDesign-Bench evaluates computational methods for designing cell-type-specific regulatory DNA, showing that performance on individual metrics does not guarantee overall effectiveness.

Reconstructing sequence-grammar trajectories enables interpretable and tunable cis-regulatory element design

This paper introduces GO-CRE, a method for designing cell-type-specific cis-regulatory elements by reconstructing sequence-grammar trajectories and using reinforcement learning with predictor guidance.

HoloCell: A Generative Foundation Model for Holistic Cellular Modeling

HoloCell is a generative foundation model that integrates epigenomics, transcriptomics, and proteomics data across single-cell multi-omics modalities, demonstrating superior performance in representation learning and cross-modal generation.

Phenotype-Guided In Silico Molecular Generation Using Large Language Models

GEMGen generates small molecules from transcriptomic data to phenocopy gene knockdown effects and identify novel inhibitors.

FlexRibbon: Joint Sequence and Structure Pretraining for Protein Modeling

FlexRibbon is a pretrained protein model that jointly learns from sequences and structures, achieving state-of-the-art performance in mutation-rich settings.

Manipulating patterns of dynamic deformation elicits the impression of cloth with varying stiffness

The paper shows that manipulating dynamic deformation patterns can alter perceived cloth stiffness, identifying specific optical flow features that correlate with stiffness perception.

Estimating mechanical properties of cloth from videos using dense motion trajectories: human psychophysics and machine learning

This paper shows that humans and machine learning models use multi-frame motion information to estimate cloth stiffness from videos.