Virtual screening can accelerate drug discovery by identifying promising candidates for experimental evaluation. Machine learning is a powerful method for screening, as it can learn complex structure-property relationships from experimental data and make rapid predictions over virtual libraries. Molecules inherently exist as a three-dimensional ensemble and their biological action typically occurs through supramolecular recognition. However, most deep learning approaches to molecular property prediction use a 2D graph representation as input, and in some cases a single 3D conformation. Here we investigate how the 3D information of multiple conformers, traditionally known as 4D information in the cheminformatics community, can improve molecular property prediction in deep learning models. We introduce multiple deep learning models that expand upon key architectures such as ChemProp and Schnet, adding elements such as multiple-conformer inputs and conformer attention. We then benchmark the performance trade-offs of these models on 2D, 3D and 4D representations in the prediction of drug activity using a large training set of geometrically resolved molecules. The new architectures perform significantly better than 2D models, but their performance is often just as strong with a single conformer as with many. We also find that 4D deep learning models learn interpretable attention weights for each conformer.
We investigate Siamese networks for learning related embeddings for augmented samples of molecular conformers. We find that a non-contrastive (positive-pair only) auxiliary task aids in supervised training of Euclidean neural networks (E3NNs) and increases manifold smoothness (MS) around point-cloud geometries. We demonstrate this property for multiple drug-activity prediction tasks while maintaining relevant performance metrics, and propose an extension of MS to probabilistic and regression settings. We provide an analysis of representation collapse, finding substantial effects of task-weight…
Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements (e.g. torsion angles), separate optimization stages prone to error accumulation, and the need for structure fine-tuning based on approximate classical force-fields or computationally expensive methods such as metadynamics with approximate quantum mechanics calculations at each geometry. We propose GeoMol--an end-to-end, non-autoregressive and S…
Massachusetts Institute of Technology（麻省理工学院）；Harvard University（哈佛大学）
Molecular conformer generation is a fundamental task in computational chemistry. Several machine learning approaches have been developed, but none have outperformed state-of-the-art cheminformatics methods. We propose torsional diffusion, a novel diffusion framework that operates on the space of torsion angles via a diffusion process on the hypertorus and an extrinsic-to-intrinsic score model. On a standard benchmark of drug-like molecules, torsional diffusion generates superior conformer ensembles compared to machine learning and cheminformatics methods in terms of both RMSD and chemical prop…
University of Stuttgart（斯图加特大学）；Max Planck Research School for Intelligent Systems (IMPRS-IS)（马克斯·普朗克智能系统研究学校（IMPRS-IS））；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Technische Universitat Darmstadt（达姆施塔特工业大学）；University of Queensland（昆士兰大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Oldenburg University（奥尔登堡大学）；NEC Laboratories Europe（日本电气欧洲实验室）
MolFM-Lite: Multi-Modal Molecular Property Prediction with Conformer Ensemble Attention and Cross-Modal Fusion
Department of Computer Science and Engineering, University at Buffalo（布法罗大学计算机科学与工程系）；Khoury College of Computer Sciences, Northeastern University（东北大学科赫里学院）；Department of Computer Science, Muffakham Jah College of Engineering and Technology（穆法卡姆·贾赫工程与技术学院计算机科学系）；Department of Computer Science and Artificial Intelligence, Muffakham Jah College of Engineering and Technology（穆法卡姆·贾赫工程与技术学院计算机科学与人工智能系）
Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
Machine learning (ML) outperforms traditional approaches in many molecular design tasks. ML models usually predict molecular properties from a 2D chemical graph or a single 3D structure, but neither of these representations accounts for the ensemble of 3D conformers that are accessible to a molecule. Property prediction could be improved by using conformer ensembles as input, but there is no large-scale dataset that contains graphs annotated with accurate conformers and experimental data. Here we use advanced sampling and semi-empirical density functional theory (DFT) to generate 37 million mo…
Sampling 3D Molecular Conformers with Diffusion Transformers
Technical University Berlin（技术大学柏林）；BIFOLD Berlin（柏林BIFOLD）；Google DeepMind（谷歌DeepMind）；MPI for Informatics, Saarbrücken（萨尔布吕肯信息研究所）；Department of Artificial Intelligence, Korea University（韩国大学人工智能系）
Molecular geometry prediction of flexible molecules, or conformer search, is a long-standing challenge in computational chemistry. This task is of great importance for predicting structure-activity relationships for a wide variety of substances ranging from biomolecules to ubiquitous materials. Substantial computational resources are invested in Monte Carlo and Molecular Dynamics methods to generate diverse and representative conformer sets for medium to large molecules, which are yet intractable to chemoinformatic conformer search methods. We present TorsionNet, an efficient sequential confor…
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Massachusetts Institute of Technology（麻省理工学院）；Department of Chemical Engineering（化学工程系）；Cambridge, MA 02139, USA（美国马萨诸塞州剑桥市（注意：此为地址，按规则不应提取，但原文中该部分紧邻机构名，此处需特别说明，按要求应仅提取明确的机构名，此处实际机构为麻省理工学院，化学工程系是其下属部门，按规则“机构粒度：提取到大学/学院/公司/研究院级别即可”，故正确提取为麻省理工学院），修正后仅保留：{）
Molecular chirality, a form of stereochemistry most often describing relative spatial arrangements of bonded neighbors around tetrahedral carbon centers, influences the set of 3D conformers accessible to the molecule without changing its 2D graph connectivity. Chirality can strongly alter (bio)chemical interactions, particularly protein-drug binding. Most 2D graph neural networks (GNNs) designed for molecular property prediction at best use atomic labels to naïvely treat chirality, while E(3)-invariant 3D GNNs are invariant to chirality altogether. To enable representation learning on molecule…
ConfRetro: a 3D-aware template-free method for enhancing retrosynthesis via molecular conformer information
School of Computer Science and Technology, East China Normal University（东华师范大学计算机科学与技术学院）；Shanghai Institute of Artificial Intelligence for Education, East China Normal University（东华师范大学上海人工智能教育研究所）；Shanghai Frontiers Science Center of Molecule Intelligent Syntheses（上海分子智能合成前沿科学中心）
Institute for Neurodegenerative Diseases（神经退行性疾病研究所）；University of California, San Francisco（加州大学旧金山分校）
The three-dimensional shape and conformation of small-molecule ligands are critical for biomolecular recognition, yet encoding 3D geometry has not improved ligand-based virtual screening approaches. We describe an end-to-end deep learning approach that operates directly on small-molecule conformational ensembles and identifies key conformational poses of small-molecules. Our networks leverage two levels of representation learning: 1) individual conformers are first encoded as spatial graphs using a graph neural network, and 2) sampled conformational ensembles are represented as sets using an a…
FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms
Fundamental AI Research at Meta（Meta 基础人工智能研究）；Department of Materials Science and Engineering, Carnegie Mellon University（卡内基梅隆大学材料科学与工程系）；Department of Chemistry, University of California Riverside（加州大学河滨分校化学系）；Reality Labs Research at Meta（Meta 现实实验室研究）；Department of Physics, Carnegie Mellon University（卡内基梅隆大学物理系）；Department of Chemistry, Carnegie Mellon University（卡内基梅隆大学化学系）
The prediction of quantum mechanical properties is historically plagued by a trade-off between accuracy and speed. Machine learning potentials have previously shown great success in this domain, reaching increasingly better accuracy while maintaining computational efficiency comparable with classical force fields. In this work we propose TorchMD-NET, a novel equivariant transformer (ET) architecture, outperforming state-of-the-art on MD17, ANI-1, and many QM9 targets in both accuracy and computational efficiency. Through an extensive attention weight analysis, we gain valuable insights into th…
Boltzmann-Expected Molecular Design with Decoupled Annealing Flows
Department of Computer Science and Engineering（计算机科学与工程系）；Chalmers University of Technology（楚姆勒技术大学）；University of Gothenburg（哥德堡大学）；Molecular AI Discovery Sciences, R&D（分子AI发现科学，研发）
University of Cambridge（剑桥大学）；ML Collective（ML集体）；Universitat Rovira i Virgili（罗维拉-威尔吉利大学）；McGill University（麦吉尔大学）；Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）；Obafemi Awolowo University（奥巴费米·阿沃洛沃大学）
In order to advance large-scale graph machine learning, the Open Graph Benchmark Large Scale Challenge (OGB-LSC) was proposed at the KDD Cup 2021. The PCQM4M-LSC dataset defines a molecular HOMO-LUMO property prediction task on about 3.8M graphs. In this short paper, we show our current work-in-progress solution which builds an ensemble of three graph neural networks models based on GIN, Bayesian Neural Networks and DiffPool. Our approach outperforms the provided baseline by 7.6%. Moreover, using uncertainty in our ensemble's prediction, we can identify molecules whose HOMO-LUMO gaps are harde…
Previous works have demonstrated the importance of considering different modalities on molecules, each of which provide a varied granularity of information for downstream property prediction tasks. Our method combines variants of the recent TransformerM architecture with Transformer, GNN, and ResNet backbone architectures. Models are trained on the 2D data, 3D data, and image modalities of molecular graphs. We ensemble these models with a HuberRegressor. The models are trained on 4 different train/validation splits of the original train + valid datasets. This yields a winning solution to the 2…
Synthetic polymers are versatile and widely used materials. Similar to small organic molecules, a large chemical space of such materials is hypothetically accessible. Computational property prediction and virtual screening can accelerate polymer design by prioritizing candidates expected to have favorable properties. However, in contrast to organic molecules, polymers are often not well-defined single structures but an ensemble of similar molecules, which poses unique challenges to traditional chemical representations and machine learning approaches. Here, we introduce a graph representation o…
