SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.10240 · ICLR · 2021

Learning Neural Generative Dynamics for Molecular Conformation Generation

Yoshua Bengio, Jian Peng, Minkai Xu, Jian Tang, Shitong Luo

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
deepgraphlearning/cgcf-confgen reimplementation 2 of 2
luost26/CGCF-ConfGen — 0 of 2
FunctionStatusWhere it lives
reduce_tensor Ran deepgraphlearning/cgcf-confgen/models/cnf_edge/cnf.py
pointer only (licence: NONE) · get_code("11965d5ebfe77481")
stable_var Ran deepgraphlearning/cgcf-confgen/models/cnf_edge/cnf.py
pointer only (licence: NONE) · get_code("27ca363b776a43f8")
ODEfunc Not yet run luost26/CGCF-ConfGen/models/cnf_edge/odefunc.py
pointer only (licence: NONE) · get_code("cd19b552f2be09f2")
divergence_approx Not yet run luost26/CGCF-ConfGen/models/cnf_edge/odefunc.py
pointer only (licence: NONE) · get_code("58625622277c98f5")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamics, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph. We propose a method combining the advantages of both flow-based and energy-based models, enjoying: (1) a high model capacity to estimate the multimodal conformation distribution; (2) explicitly capturing the complex long-range dependencies between atoms in the observation space. Extensive experiments demonstrate the superior performance of the proposed method on several benchmarks, including conformation generation and distance modeling tasks, with a significant improvement over existing generative models for molecular conformation sampling 1 . * Equal contribution. Work was done during Shitong's internship at Mila.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2102.10240")
get_code_for_paper("2102.10240")
have("2102.10240")

Connect an agent — have() is free.