陈天涞 Tianlai Chen

MS of Biomedical Engineering

Duke University

Tianlai (Leo) Chen

I’m a Master student of Biomedical Engineering at Duke University. Currently, I am working at the Programmable Biology Group with Dr. Pranam Chatterjee. Before my graduate studies, I obtained my B.S. degree of Data Science from Duke University and Duke Kunshan University in 2023. My research interests revolve around molecular engineering and AI for Biology. Most recently, my work has focused on:

Using protein language models for binder design
Improving Protein Language Model representation
Combining Generative AI with protein language Models
Applying causal inference for gut microbiome analysis

I am also deeply interested in RNA engineering.

Interests

Protein/RNA Language Model
Protein Engineering
RNA Engineering
Generative AI
Causal Inference

Education

MS in Biomedical Engineering, 2025
Duke University
BS in Data Science, 2023
Duke University
BS in Data Science, 2023
Duke Kunshan University

Featured Publications

Tianlai Chen, Pranay Vure, Rishab Pulugurta, Pranam Chatterjee

January, 2023 NeurIPS 2023 Generative AI and Biology (GenBio) Workshop

AMP-Diffusion: Integrating Latent Diffusion with Protein Language Models for Antimicrobial Peptide Generation

We introduce AMP-Diffusion, a latent space diffusion model tailored for antimicrobial peptide (AMP) design, harnessing the capabilities of ESM-2, to de novo generate functional AMPs for downstream experimental application. (Accepted as Poster at NeurIPS 23’ GenBio Workshop)

Tianlai Chen, Sarah Pertsemlidis, Rio Watson, Venkata Srikar Kavirayuni, Ashley Hsu, Pranay Vure, Rishab Pulugurta, Sophia Vincoff, Lauren Hong, Tian Wang, Others

January, 2023 ArXiv

PepMLM: Target Sequence-Conditioned Generation of Peptide Binders via Masked Language Modeling

We introduce PepMLM, a purely target sequence-conditioned de novo generator of linear peptide binders. By employing a novel masking strategy that uniquely positions cognate peptide sequences at the terminus of target protein sequences, PepMLM tasks ESM-2 to fully reconstruct the binder region, achieving low perplexities matching or improving upon previously-validated peptide-protein sequence pairs. (Accepted as Poster at ICLR GEM Workshop)

Recent Publications

Tianlai Chen, Xiwen Shu, Huiyuan Zhou, Floyd a Beckford, Mustafa Misir (2023). Algorithm selection for protein--ligand docking: strategies and analysis on ACE. Scientific Reports.

PDF Cite

Tianlai Chen, Pranay Vure, Rishab Pulugurta, Pranam Chatterjee (2023). AMP-Diffusion: Integrating Latent Diffusion with Protein Language Models for Antimicrobial Peptide Generation. NeurIPS 2023 Generative AI and Biology (GenBio) Workshop.

PDF Cite

Suhaas Bhat, Kalyan Palepu, Vivian Yudistyra, Lauren Hong, Venkata Srikar Kavirayuni, Tianlai Chen, Lin Zhao, Tian Wang, Sophia Vincoff, Pranam Chatterjee (2023). De Novo Generation and Prioritization of Target-Binding Peptide Motifs from Sequence Alone. bioRxiv.

PDF Cite

Tianlai Chen, Lauren Hong, Vivian Yudistyra, Sophia Vincoff, Pranam Chatterjee (2023). Generative Design of Therapeutics that Bind and Modulate Protein States. Current Opinion in Biomedical Engineering.

PDF Cite

Tianlai Chen, Sarah Pertsemlidis, Rio Watson, Venkata Srikar Kavirayuni, Ashley Hsu, Pranay Vure, Rishab Pulugurta, Sophia Vincoff, Lauren Hong, Tian Wang, Others (2023). PepMLM: Target Sequence-Conditioned Generation of Peptide Binders via Masked Language Modeling. ArXiv.

PDF Cite Code

See all

Gallery

Contact

[email protected]