Geometry-enhanced molecular representation learning for property prediction

Fang, Xiaomin; Liu, Lihang; Lei, Jieqiong; He, Donglong; Zhang, Shanzhuo; Zhou, Jingbo; Fan, Wei; Wu, Hua; Wang, Haifeng

doi:10.1038/s42256-021-00438-4

Cited by 288 publications

(279 citation statements)

References 38 publications

Supporting

Mentioning

230

Contrasting

Order By: Relevance

“…Datasets and setup MoleculeNet [48] is a widely used benchmark for molecular property prediction, including datasets focusing on different levels of properties of molecules, from quantum mechanics and physical chemistry to biophysics and physiology. Following previous work GEM [13], we use scaffold splitting for the dataset and report the mean and standard deviation of the results for three random seeds.…”

Section: Molecular Property Predictionmentioning

confidence: 99%

“…D-MPNN [49] and AttentiveFP [50] are supervised GNNs methods. N-gram [51], PretrainGNN [22], GROVER [11], GraphMVP [26], MolCLR [12], and GEM [13] are pretraining methods. N-gram embeds the nodes in the graph and assembles them in short walks as the graph representation.…”

Section: Molecular Property Predictionmentioning

confidence: 99%

“…For example, GraphMVP [26] proposes a contrastive learning GNN-based framework between 2D topology and 3D geometry. GEM [13] uses bond angles and bond length as additional edge attributes to enhance 3D information.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Zhou

Gao

Ding

et al. 2022

Preprint

View full text Add to dashboard Cite

Molecular representation learning (MRL) has gained tremendous attention due to its critical role in learning from limited supervised data for applications like drug design. In most MRL methods, molecules are treated as 1D sequential tokens or 2D topology graphs, limiting their ability to incorporate 3D information for downstream tasks and, in particular, making it almost impossible for 3D geometry prediction or generation. Herein, we propose Uni-Mol, a universal MRL framework that significantly enlarges the representation ability and application scope of MRL schemes. Uni-Mol is composed of two models with the same SE(3)-equivariant transformer architecture: a molecular pretraining model trained by 209M molecular conformations; a pocket pretraining model trained by 3M candidate protein pocket data. The two models are used independently for separate tasks, and are combined when used in protein-ligand binding tasks. By properly incorporating 3D information, Uni-Mol outperforms SOTA in 14/15 molecular property prediction tasks. Moreover, Uni-Mol achieves superior performance in 3D spatial tasks, including protein-ligand binding pose prediction, molecular conformation generation, etc. Finally, we show that Uni-Mol can be successfully applied to the tasks with few-shot data like pocket druggability prediction. The model and data will be made publicly available at \url{https://github.com/dptech-corp/Uni-Mol}

show abstract

Section: Molecular Property Predictionmentioning

confidence: 99%

Section: Molecular Property Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Zhou

Gao

Ding

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Existing domain-specific PTMs mainly lie in the domain of healthcare [1,14], biomedical [8,10,16], and academic & research [2]. Most of them learn the domain-specific knowledge by pre-training on domain-specific corpora with the MLM pre-training task.…”

Section: Domain-specific Ptmsmentioning

confidence: 99%

ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps

Huang,

Wang,

Sun

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Pre-trained models (PTMs) have become a fundamental backbone for downstream tasks in natural language processing and computer vision. Despite initial gains that were obtained by applying generic PTMs to geo-related tasks at Baidu Maps, a clear performance plateau over time was observed. One of the main reasons for this plateau is the lack of readily available geographic knowledge in generic PTMs. To address this problem, in this paper, we present POLARIS, which is a geographic pre-trained model designed and developed for improving the geo-related tasks at Baidu Maps. POLARIS is elaborately designed to learn a universal representation of geography-language by pre-training on large-scale data generated from a heterogeneous graph that contains abundant geographic knowledge. Extensive quantitative and qualitative experiments conducted on large-scale real-world datasets demonstrate the superiority and effectiveness of POLARIS. POLARIS has already been deployed in production at Baidu Maps since April 2021, which significantly benefits the performance of a wide range of downstream tasks. This demonstrates that POLARIS can serve as a fundamental backbone for geo-related tasks. CCS CONCEPTS• Information systems → Data mining.

show abstract

“…Geometric deep learning, which encompasses deep neural networks operating on non-Euclidean domains (Bronstein et al, 2017), has shown considerable benefits in representation learning on proteins (Zhang et al, 2022; Jing et al, 2021; Gligorijević et al, 2021; Hermosilla et al, 2021) and other molecular structures (Fang et al, 2022; Townshend et al, 2021), particularly in the context of drug discovery (Gaudelet et al, 2021; Méndez-Lucio et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Decoding Surface Fingerprints for Protein-Ligand Interactions

Igashov

Jamasb

Sadek

et al. 2022

Preprint

View full text Add to dashboard Cite

Small molecules have been the preferred modality for drug development and therapeutic interventions. This molecular format presents a number of advantages, e.g. long half-lives and cell permeability, making it possible to access a wide range of therapeutic targets. However, finding small molecules that engage “hard-to-drug” protein targets specifically and potently remains an arduous process, requiring experimental screening of extensive compound libraries to identify candidate leads. The search continues with further optimization of compound leads to meet the required potency and toxicity thresholds for clinical applications. Here, we propose a new computational workflow for high-throughput fragment-based screening and binding affinity prediction where we leverage the available protein-ligand complex structures using a state-of-the-art protein surface embedding framework (dMaSIF). We developed a tool capable of finding suitable ligands and fragments for a given protein pocket solely based on protein surface descriptors, that capture chemical and geometric features of the target pocket. The identified fragments can be further combined into novel ligands. Using the structural data, our ligand discovery pipeline learns the signatures of interactions between surface patches and small pharmacophores. On a query target pocket, the algorithm matches known target pockets and returns either potential ligands or identifies multiple ligand fragments in the binding site. Our binding affinity predictor is capable of predicting the affinity of a given protein-ligand pair, requiring only limited information about the ligand pose. This enables screening without the costly step of first docking candidate molecules. Our framework will facilitate the design of ligands based on the target’s surface information. It may significantly reduce the experimental screening load and ultimately reveal novel chemical compounds for targeting challenging proteins.

show abstract

Geometry-enhanced molecular representation learning for property prediction

Cited by 288 publications

References 38 publications

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps

Decoding Surface Fingerprints for Protein-Ligand Interactions

Contact Info

Product

Resources

About