Enzymeflow: Generating reaction-specific enzyme catalytic pockets through flow matching and co-evolutionary dynamics

C Hua, Y Liu, D Zhang, O Zhang, S Luan… - arXiv preprint arXiv …, 2024 - arxiv.org
Enzyme design is a critical area in biotechnology, with applications ranging from drug
development to synthetic biology. Traditional methods for enzyme function prediction or …

Descriptor: Benchmarking secure neural network evaluation methods for protein sequence classification (iDASH24)

A Harmanci, L Chen, M Kim, X Jiang - IEEE data descriptions, 2024 - ieeexplore.ieee.org
To uniformly test and benchmark the secure evaluation of transformer-based models, we
designed the iDASH24 homomorphic encryption track dataset. The dataset comprises a …

MAIR: A Massive Benchmark for Evaluating Instructed Retrieval

W Sun, Z Shi, J Wu, L Yan, X Ma, Y Liu, M Cao… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive
datasets and tasks, enabling them to perform well on a wide range of tasks and potentially …

Reaction-conditioned De Novo Enzyme Design with GENzyme

C Hua, J Lu, Y Liu, O Zhang, J Tang, R Ying… - arXiv preprint arXiv …, 2024 - arxiv.org
The introduction of models like RFDiffusionAA, AlphaFold3, AlphaProteo, and Chai1 has
revolutionized protein structure modeling and interaction prediction, primarily from a binding …

EnzymeCAGE: A Geometric Foundation Model for Enzyme Retrieval with Evolutionary Insights

Y Liu, C Hua, T Zeng, J Rao, Z Zhang, R Wu, CW Coley… - bioRxiv, 2024 - biorxiv.org
Enzyme catalysis is fundamental to life, driving the chemical transformations that sustain
biological processes and support industrial applications. However, unraveling the …