Tong Si

Toward De Novo Protein Design from Natural Language

This paper introduces Pinal, a foundation model that designs proteins from natural language descriptions, achieving functional alignment and experimental success in four design tasks.

Decoding Prokaryotic Whole Genomes with a Product-Contextualized Large Language Model

The paper introduces GenSyntax, a large language model for prokaryotic genomes that captures functional context, achieving competitive performance in genome-scale tasks.

CombinGym: a benchmark platform for machine learning-assisted design of combinatorial protein variants

CombinGym benchmarks machine learning for combinatorial protein variant design using curated datasets and evaluates model performance across multiple tasks and data splits.

Democratizing Protein Language Model Training, Sharing and Collaboration

The paper introduces SaprotHub, a platform that simplifies training and sharing of protein language models, enabling non-experts to build and collaborate on customized models.

Execution-aware agent harness for accessible and responsible synthetic biology automation

LabscriptAI translates natural language into robot scripts for synthetic biology, achieving high simulation accuracy and enabling secure, standardized, and traceable lab automation.

Degradation of indole-3-acetic acid by plant-associated microbes

This study identifies bacterial isolates capable of degrading indole-3-acetic acid (IAA) from Arabidopsis and rice roots, revealing their functional roles and association with IAA producers.

A novel f-divergence based generative adversarial imputation method for scRNA-seq data analysis

This paper introduces sc-f GAIN, an f-divergence-based generative adversarial imputation method for scRNA-seq data that improves accuracy and robustness compared to traditional methods.

Protein engineering via Bayesian optimization-guided evolutionary algorithm and robotic experiments

This paper introduces BO-EVO, a Bayesian optimization-guided evolutionary algorithm that improves protein engineering efficiency by enabling batched robotic experiments and achieving significant improvements in enzyme specificity.