Boxue Tian

ICFinder: ion channel identification and ion permeation residue prediction using protein language models

ICFinder uses protein language models to identify ion channels and predict permeation residues, outperforming existing methods and providing a public resource.

Automatically Defining Protein Words for Diverse Functional Predictions Based on Attention Analysis of a Protein Language Model

The paper introduces a toolkit using protein language models to define 'protein words' for functional prediction, outperforming motif-based methods across multiple tasks.

CodonTranslator: a conditional codon language model for codon optimization across all domains of life

CodonTranslator is a Transformer-based model for codon optimization across species, achieving better codon usage and stability than existing methods.

A disease mutation reveals a non-swapped pore and rewired gating cycle of the mechanically activated PIEZO1 channel

This paper investigates the structural and functional changes in the PIEZO1-R2482H mutant, revealing a non-swapped pore and altered gating cycle that explain its heightened mechanosensitivity and slowed inactivation.

De novo Design of A Fusion Protein Tool for GPCR Research

This paper introduces a de novo design strategy called 'click fusion' to create stable GPCR fusion proteins, enabling structural studies via cryo-EM.

H3-OPT: Accurate prediction of CDR-H3 loop structures of antibodies with deep learning

H3-OPT predicts CDR-H3 loop structures of antibodies with high accuracy using deep learning, outperforming existing methods on a high-quality dataset.

Central pore-opening structure and gating of the mechanosensitive PIEZO1 channel

This study defines the structural states and curvature-based activation/inactivation mechanisms of PIEZO1 using a mutant and molecular dynamics simulations.