Výsledky vyhledávání

Report

RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation

Autor: Wang, Yiming, Song, Yuxuan, Xu, Minkai, Wang, Rui, Zhou, Hao, Ma, Weiying

Retrosynthesis poses a fundamental challenge in biopharmaceuticals, aiming to aid chemists in finding appropriate reactant molecules and synthetic pathways given determined product molecules. With the reactant and product represented as 2D graphs, re

Externí odkaz: http://arxiv.org/abs/2311.14077

Zobrazit plný text záznamu

Report

UniMAP: Universal SMILES-Graph Representation Learning

Autor: Feng, Shikun, Yang, Lixin, Huang, Yanwen, Ni, Yuyan, Ma, Weiying, Lan, Yanyan

Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To effectively leverage both modal

Externí odkaz: http://arxiv.org/abs/2310.14216

Zobrazit plný text záznamu

Report

ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

Autor: Gao, Bowen, Jia, Yinjun, Mo, Yuanle, Ni, Yuyan, Ma, Weiying, Ma, Zhiming, Lan, Yanyan

Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features and pretrained representations have demonstrated prom

Externí odkaz: http://arxiv.org/abs/2310.07229

Zobrazit plný text záznamu

Report

DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening

Autor: Gao, Bowen, Qiang, Bo, Tan, Haichuan, Ren, Minsi, Jia, Yinjun, Lu, Minsi, Liu, Jingjing, Ma, Weiying, Lan, Yanyan

Virtual screening, which identifies potential drugs from vast compound databases to bind with a particular protein pocket, is a critical step in AI-assisted drug discovery. Traditional docking methods are highly time-consuming, and can only work with

Externí odkaz: http://arxiv.org/abs/2310.06367

Zobrazit plný text záznamu

Report

Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D

Autor: Qiang, Bo, Song, Yuxuan, Xu, Minkai, Gong, Jingjing, Gao, Bowen, Zhou, Hao, Ma, Weiying, Lan, Yanyan

Generating desirable molecular structures in 3D is a fundamental problem for drug discovery. Despite the considerable progress we have achieved, existing methods usually generate molecules in atom resolution and ignore intrinsic local structures such

Externí odkaz: http://arxiv.org/abs/2305.13266

Zobrazit plný text záznamu