Opportunities and challenges for machine learning-assisted enzyme engineering

J Yang, FZ Li, FH Arnold - ACS Central Science, 2024‏ - ACS Publications
Enzymes can be engineered at the level of their amino acid sequences to optimize key
properties such as expression, stability, substrate range, and catalytic efficiency─ or even to …

Unveiling the evolution of policies for enhancing protein structure predictions: A comprehensive analysis

F Rahimzadeh, LM Khanli, P Salehpoor… - Computers in Biology …, 2024‏ - Elsevier
Predicting protein structure is both fascinating and formidable, playing a crucial role in
structure-based drug discovery and unraveling diseases with elusive origins. The Critical …

Multimodal pretraining for unsupervised protein representation learning

VTD Nguyen, TS Hy - Biology Methods and Protocols, 2024‏ - academic.oup.com
Proteins are complex biomolecules essential for numerous biological processes, making
them crucial targets for advancements in molecular biology, medical research, and drug …

Re-dock: towards flexible and realistic molecular docking with diffusion bridge

Y Huang, O Zhang, L Wu, C Tan, H Lin, Z Gao… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Accurate prediction of protein-ligand binding structures, a task known as molecular docking
is crucial for drug design but remains challenging. While deep learning has shown promise …

Advances of deep learning in protein science: A comprehensive survey

B Hu, C Tan, L Wu, J Zheng, J **a, Z Gao, Z Liu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Protein representation learning plays a crucial role in understanding the structure and
function of proteins, which are essential biomolecules involved in various biological …

S‐PLM: Structure‐Aware Protein Language Model via Contrastive Learning Between Sequence and Structure

D Wang, M Pourmirzaei, UL Abbas, S Zeng… - Advanced …, 2025‏ - Wiley Online Library
Proteins play an essential role in various biological and engineering processes. Large
protein language models (PLMs) present excellent potential to reshape protein research by …

Prot2Token: A multi-task framework for protein language processing using autoregressive language modeling

M Pourmirzaei, F Esmaili, M Pourmirzaei, D Wang… - bioRxiv, 2024‏ - biorxiv.org
This paper proposes a versatile tokenization method and introduces Prot2Token, a model
that combines autoregressive language modeling with protein language models (PLMs) to …