Libmolgrid：用于深度学习应用的图形处理单元加速分子网格化
libmolgrid: Graphics Processing Unit Accelerated Molecular Gridding for Deep Learning Applications.
作者信息
Sunseri Jocelyn, Koes David R
机构信息
Department of Computational and Systems Biology, University of Pittsburgh, 3501 Fifth Avenue, Pittsburgh, Pennsylvania 15260, United States.
出版信息
J Chem Inf Model. 2020 Mar 23;60(3):1079-1084. doi: 10.1021/acs.jcim.9b01145. Epub 2020 Feb 26.
Abstract
We describe libmolgrid, a general-purpose library for representing three-dimensional molecules using multidimensional arrays of voxelized molecular data. libmolgrid provides functionality for sampling batches of data suited to machine learning workflows, and it also supports temporal and spatial recurrences over that data to facilitate work with convolutional and recurrent neural networks. It was designed for seamless integration with popular deep learning frameworks and features optimized performance by leveraging graphics processing units (GPUs). libmolgrid is a free and open source project (GPLv2) that aims to democratize grid-based modeling in computational chemistry.
摘要
我们介绍了libmolgrid，这是一个通用库，用于使用体素化分子数据的多维数组来表示三维分子。libmolgrid提供了对适合机器学习工作流程的批量数据进行采样的功能，并且还支持对该数据进行时间和空间递归，以方便使用卷积神经网络和递归神经网络。它旨在与流行的深度学习框架无缝集成，并通过利用图形处理单元（GPU）实现性能优化。libmolgrid是一个免费的开源项目（GPLv2），旨在使计算化学中基于网格的建模民主化。
相似文献
1
libmolgrid: Graphics Processing Unit Accelerated Molecular Gridding for Deep Learning Applications.Libmolgrid：用于深度学习应用的图形处理单元加速分子网格化
J Chem Inf Model. 2020 Mar 23;60(3):1079-1084. doi: 10.1021/acs.jcim.9b01145. Epub 2020 Feb 26.
2
Data Integration Using Advances in Machine Learning in Drug Discovery and Molecular Biology.利用机器学习进展进行药物发现和分子生物学中的数据整合
Methods Mol Biol. 2021;2190:167-184. doi: 10.1007/978-1-0716-0826-5_7.
3
Learning image-based spatial transformations via convolutional neural networks: A review.通过卷积神经网络学习基于图像的空间变换：综述。
Magn Reson Imaging. 2019 Dec;64:142-153. doi: 10.1016/j.mri.2019.05.037. Epub 2019 Jun 11.
4
Advancing Biosensors with Machine Learning.借助机器学习推动生物传感器发展。
ACS Sens. 2020 Nov 25;5(11):3346-3364. doi: 10.1021/acssensors.0c01424. Epub 2020 Nov 13.
5
Semi-supervised learning for automatic segmentation of the knee from MRI with convolutional neural networks.基于卷积神经网络的膝关节 MRI 半自动分割的半监督学习。
Comput Methods Programs Biomed. 2020 Jun;189:105328. doi: 10.1016/j.cmpb.2020.105328. Epub 2020 Jan 11.
6
Deep Learning for Time Series Forecasting: A Survey.深度学习在时间序列预测中的应用：综述。
Big Data. 2021 Feb;9(1):3-21. doi: 10.1089/big.2020.0159. Epub 2020 Dec 3.
7
Deep Learning in Chemistry.深度学习在化学中的应用。
J Chem Inf Model. 2019 Jun 24;59(6):2545-2559. doi: 10.1021/acs.jcim.9b00266. Epub 2019 Jun 13.
8
Comparison of Deep-Learning and Conventional Machine-Learning Methods for the Automatic Recognition of the Hepatocellular Carcinoma Areas from Ultrasound Images.深度学习与传统机器学习方法在自动识别超声图像肝癌区域的比较。
Sensors (Basel). 2020 May 29;20(11):3085. doi: 10.3390/s20113085.
9
DeepEP: a deep learning framework for identifying essential proteins.DeepEP：一种用于识别必需蛋白质的深度学习框架。
BMC Bioinformatics. 2019 Dec 2;20(Suppl 16):506. doi: 10.1186/s12859-019-3076-y.
10
Machine Learning and Deep Learning in Medical Imaging: Intelligent Imaging.医学成像中的机器学习与深度学习：智能成像
J Med Imaging Radiat Sci. 2019 Dec;50(4):477-487. doi: 10.1016/j.jmir.2019.09.005. Epub 2019 Oct 7.
引用本文的文献
1
Investigating the volume and diversity of data needed for generalizable antibody-antigen ΔΔG prediction.研究可推广的抗体 - 抗原ΔΔG预测所需数据的量和多样性。
Nat Comput Sci. 2025 Jul 8. doi: 10.1038/s43588-025-00823-8.
2
Nearl: extracting dynamic features from molecular dynamics trajectories for machine learning tasks.Nearl：从分子动力学轨迹中提取用于机器学习任务的动态特征。
Bioinformatics. 2025 Jul 1;41(7). doi: 10.1093/bioinformatics/btaf321.
3
GNINA 1.3: the next increment in molecular docking with deep learning.GNINA 1.3：深度学习在分子对接方面的下一次进展。
J Cheminform. 2025 Mar 2;17(1):28. doi: 10.1186/s13321-025-00973-x.
4
Machine learning approaches for predicting protein-ligand binding sites from sequence data.从序列数据预测蛋白质-配体结合位点的机器学习方法。
Front Bioinform. 2025 Feb 3;5:1520382. doi: 10.3389/fbinf.2025.1520382. eCollection 2025.
5
PharmRL: pharmacophore elucidation with deep geometric reinforcement learning.PharmRL：基于深度几何强化学习的药效团阐释
BMC Biol. 2024 Dec 31;22(1):301. doi: 10.1186/s12915-024-02096-5.
6
CACHE Challenge #1: Docking with GNINA Is All You Need.CACHE挑战#1：使用GNINA进行对接就足够了。
J Chem Inf Model. 2024 Dec 23;64(24):9388-9396. doi: 10.1021/acs.jcim.4c01429. Epub 2024 Dec 9.
7
PharmRL: Pharmacophore elucidation with Deep Geometric Reinforcement Learning.PharmRL：基于深度几何强化学习的药效团阐释
Res Sq. 2024 Sep 24:rs.3.rs-5033986. doi: 10.21203/rs.3.rs-5033986/v1.
8
CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks.CENsible：基于上下文解释网络的小分子结合的可解释见解。
J Chem Inf Model. 2024 Jun 24;64(12):4651-4660. doi: 10.1021/acs.jcim.4c00825. Epub 2024 Jun 7.
9
Physics-Guided Deep Generative Model for New Ligand Discovery.用于新配体发现的物理引导深度生成模型
ACM BCB. 2023 Sep;2023. doi: 10.1145/3584371.3613067. Epub 2023 Oct 4.
10
Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities.药物发现中的生成式人工智能：基本框架、最新进展、挑战与机遇
Front Pharmacol. 2024 Feb 7;15:1331062. doi: 10.3389/fphar.2024.1331062. eCollection 2024.
本文引用的文献
1
DeltaDelta neural networks for lead optimization of small molecule potency.用于小分子效力先导优化的DeltaDelta神经网络。
Chem Sci. 2019 Oct 16;10(47):10911-10918. doi: 10.1039/c9sc04606b. eCollection 2019 Dec 21.
2
A novel protein descriptor for the prediction of drug binding sites.一种用于预测药物结合位点的新型蛋白质描述符。
BMC Bioinformatics. 2019 Sep 18;20(1):478. doi: 10.1186/s12859-019-3058-0.
3
Optimization of Molecules via Deep Reinforcement Learning.通过深度强化学习优化分子。
Sci Rep. 2019 Jul 24;9(1):10752. doi: 10.1038/s41598-019-47148-x.
4
Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations.通过转换等效化学表示来学习连续且数据驱动的分子描述符。
Chem Sci. 2018 Nov 19;10(6):1692-1701. doi: 10.1039/c8sc04175j. eCollection 2019 Feb 14.
5
PotentialNet for Molecular Property Prediction.用于分子性质预测的PotentialNet
ACS Cent Sci. 2018 Nov 28;4(11):1520-1530. doi: 10.1021/acscentsci.8b00507. Epub 2018 Nov 2.
6
An equivariant Bayesian convolutional network predicts recombination hotspots and accurately resolves binding motifs.变分贝叶斯卷积网络预测重组热点，并准确解析结合基序。
Bioinformatics. 2019 Jul 1;35(13):2177-2184. doi: 10.1093/bioinformatics/bty964.
7
PlayMolecule BindScope: large scale CNN-based virtual screening on the web.PlayMolecule BindScope：基于大规模 CNN 的网络虚拟筛选。
Bioinformatics. 2019 Apr 1;35(7):1237-1238. doi: 10.1093/bioinformatics/bty758.
8
LigVoxel: inpainting binding pockets using 3D-convolutional neural networks.LigVoxel：使用 3D 卷积神经网络进行配体结合口袋的修复。
Bioinformatics. 2019 Jan 15;35(2):243-250. doi: 10.1093/bioinformatics/bty583.
9
EnzyNet: enzyme classification using 3D convolutional neural networks on spatial representation.EnzyNet：基于空间表示使用三维卷积神经网络进行酶分类
PeerJ. 2018 May 4;6:e4750. doi: 10.7717/peerj.4750. eCollection 2018.
10
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules.使用数据驱动的分子连续表示法进行自动化学设计。
ACS Cent Sci. 2018 Feb 28;4(2):268-276. doi: 10.1021/acscentsci.7b00572. Epub 2018 Jan 12.
Zotero 插件