Neural network potentials have recently emerged as an efficient and accurate tool for accelerating molecular dynamics (AIMD) in order to simulate complex condensed phases such as electrolyte solutions. Their principal limitation, however, is their requirement for sufficiently large and accurate training sets, which are often composed of Kohn-Sham density functional theory (DFT) calculations. Here we examine the feasibility of using existing density functional tight-binding (DFTB) molecular dynamics trajectory data available in the IonSolvR database in order to accelerate the training of E(3)-equivariant graph neural network potentials. We show that the solvation structure of Na and Cl in aqueous NaCl solutions can be accurately reproduced with remarkably small amounts of data (i.e., 100 MD frames). We further show that these predictions can be systematically improved further via an embarrassingly parallel resampling approach.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1021/acs.jpclett.3c01783 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Integrating scRNA-seq and scATAC-seq with inter-type attention heterogeneous graph neural networks.
Brief Bioinform
November 2024
Department of Electronic Engineering, Tsinghua University, 100084 Beijing, China.
Single-cell multi-omics techniques, which enable the simultaneous measurement of multiple modalities such as RNA gene expression and Assay for Transposase-Accessible Chromatin (ATAC) within individual cells, have become a powerful tool for deciphering the intricate complexity of cellular systems. Most current methods rely on motif databases to establish cross-modality relationships between genes from RNA-seq data and peaks from ATAC-seq data. However, these approaches are constrained by incomplete database coverage, particularly for novel or poorly characterized relationships.
View Article and Find Full Text PDFAn examination of daily CO emissions prediction through a comparative analysis of machine learning, deep learning, and statistical models.
Environ Sci Pollut Res Int
January 2025
Department of Geology and Mineral Science, Kwara State University, Malete, P.M.B. 1530, Ilorin, Kwara State, Nigeria.
Human-induced global warming, primarily attributed to the rise in atmospheric CO, poses a substantial risk to the survival of humanity. While most research focuses on predicting annual CO emissions, which are crucial for setting long-term emission mitigation targets, the precise prediction of daily CO emissions is equally vital for setting short-term targets. This study examines the performance of 14 models in predicting daily CO emissions data from 1/1/2022 to 30/9/2023 across the top four polluting regions (China, India, the USA, and the EU27&UK).
View Article and Find Full Text PDFFunctional resting state connectivity is differentially associated with IL-6 and TNF-α in depression and in healthy controls.
Sci Rep
January 2025
Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, University of Heidelberg, J5, 68159, Mannheim, Germany.
Inflammatory processes have been implicated in the pathophysiology of depression. In human studies, inflammation has been shown to act as a critical disease modifier, promoting susceptibility to depression and modulating specific endophenotypes of depression. However, there is scant documentation of how inflammatory processes are associated with neural activity in patients with depression.
View Article and Find Full Text PDFAnnotation-free deep learning algorithm trained on hematoxylin & eosin images predicts epithelial-to-mesenchymal transition phenotype and endocrine response in estrogen receptor-positive breast cancer.
Breast Cancer Res
January 2025
School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK.
Recent evidence indicates that endocrine resistance in estrogen receptor-positive (ER+) breast cancer is closely correlated with phenotypic characteristics of epithelial-to-mesenchymal transition (EMT). Nonetheless, identifying tumor tissues with a mesenchymal phenotype remains challenging in clinical practice. In this study, we validated the correlation between EMT status and resistance to endocrine therapy in ER+ breast cancer from a transcriptomic perspective.
View Article and Find Full Text PDFDTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks.
BMC Bioinformatics
January 2025
School of Information and Artificial Intelligence, Anhui Agricultural University, Changjiang West Road, Hefei, 230036, Anhui, China.
Drug-target interactions (DTIs) are pivotal in drug discovery and development, and their accurate identification can significantly expedite the process. Numerous DTI prediction methods have emerged, yet many fail to fully harness the feature information of drugs and targets or address the issue of feature redundancy. We aim to refine DTI prediction accuracy by eliminating redundant features and capitalizing on the node topological structure to enhance feature extraction.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!