Author

Hengshi Yu

University of MichiganORCID 0000-0001-9850-9347Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 2

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 2 Assay:scRNA-seq· 2 Approach:contrastive learning· 1 Research Focus:dimensionality reduction· 1 Research Focus:drug response / drug discovery· 1 Approach:experimental assay· 1 Research Focus:gene regulatory network inference· 1 Organism:human· 1

Frequent Co-Authors

Joshua D. WelchiD· 2 shared Weizhou QianiD· 1 shared Yuxuan SongiD· 1 shared

Activity by Year

2021-2025 · peak 1/yr

Co-Author Collaboration Network

3 top collaborators · 3 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

2 shared papersBioinformatics

Joshua D. WelchORCID

Mutual co-authors in cluster

Author profile →

2 papers

Recent·Most cited

BioinformaticsMolecular Systems BiologyPeer-reviewedJul 10, 2025

PerturbNet predicts single-cell responses to unseen chemical and genetic perturbations

Hengshi Yu, Weizhou Qian, Yuxuan Song, Joshua D. Welch

PerturbNet predicts cell state changes from unseen chemical and genetic perturbations using deep learning and perturbation response data.

57 citationstop 1%

BioinformaticsGenome biologyPeer-reviewedMay 20, 2021

Sampling from Disentangled Representations of Single-Cell Data Using Generative Adversarial Networks

Hengshi Yu, Joshua D. Welch

The paper develops MichiGAN, a generative model combining VAE and GAN strengths, to sample from disentangled single-cell RNA-seq representations and predict drug responses.

38 citations

scRNA-seqdeep learning