Author

Zhilei Bei

Massachusetts Institute of TechnologyORCID 0009-0008-7663-5551Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 2 Synthetic Biology· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 3 Approach:transformer / foundation model· 3 Assay:protein structure· 2 Research Focus:protein structure prediction· 2 Research Focus:benchmarking· 1 Approach:large language model· 1 Organism:mouse· 1 Organism:multiple species· 1

Frequent Co-Authors

Bo CheniD· 2 shared Le SongiD· 2 shared Xingyi ChengiD· 2 shared Ajinkya Deshpande· 1 shared Aohan ZengiD· 1 shared Boyan WangiD· 1 shared Chi-Ming LiuiD· 1 shared Jian MaiD· 1 shared

Activity by Year

2023-2025 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 25 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

Bo ChenORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

BioinformaticsbioRxivPreprintNov 24, 2025

MIMYR: Generative modeling of missing tissue in spatial transcriptomics

Ajinkya Deshpande, Zhilei Bei, Jian Ma, Spencer Krieger

MIMYR reconstructs missing tissue regions in spatial transcriptomics data using a generative framework that predicts cell locations, assigns cell types, and generates gene expression profiles.

1 citation

mousespatial transcriptomics

𝕏 PostBluesky

BioinformaticsbioRxivPreprintJun 10, 2024

MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training

Bo Chen, Zhilei Bei, Xingyi Cheng…·Le Song

MSAGPT improves protein structure prediction by generating virtual MSAs through pre-training, enhancing accuracy in low-MSA scenarios.

5 citations

protein structuredeep learning

𝕏 PostBluesky

Synthetic BiologybioRxivPreprintJul 5, 2023

✦ In-depth digest

xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein

Bo Chen, Xingyi Cheng, Pan Li…·Le Song

A 100-billion-parameter protein language model trained with masked and autoregressive objectives together, topping prior results on 15 of 18 benchmarks and powering a fast structure predictor.

108 citations

multiple speciesprotein sequence

𝕏 PostBluesky