Journal of chemical information and modeling - AI Medical Compendium Journals

Predicting Collision Cross-Section Values for Small Molecules through Chemical Class-Based Multimodal Graph Attention Network.

Journal of chemical information and modeling Jul 3, 2024

Libraries of collision cross-section (CCS) values have the potential to facilitate compound identification in metabolomics. Although computational methods provide an opportunity to increase library size rapidly, accurate prediction of CCS values rema...

Humans Small Molecule Libraries Metabolomics Machine Learning

View on PubMed DOI

Neural Network-Based Filter Design for Compressive Raman Classification of Cells.

Journal of chemical information and modeling Jul 3, 2024

Cell-based therapies are bound to revolutionize medicine, but significant technical hurdles must be overcome before wider adoption. In particular, nondestructive, label-free methods to characterize cells in real time are needed to optimize the produc...

Neural Networks, Computer Spectrum Analysis, Raman Humans

View on PubMed DOI

Docking Score ML: Target-Specific Machine Learning Models Improving Docking-Based Virtual Screening in 155 Targets.

Journal of chemical information and modeling Jul 3, 2024

In drug discovery, molecular docking methods face challenges in accurately predicting energy. Scoring functions used in molecular docking often fail to simulate complex protein-ligand interactions fully and accurately leading to biases and inaccuraci...

Ligands Humans Machine Learning Drug Discovery Proteins Drug Evaluation, Preclinical User-Computer Interface Antineoplastic Agents Molecular Docking Simulation

View on PubMed DOI

Proximity Graph Networks: Predicting Ligand Affinity with Message Passing Neural Networks.

Journal of chemical information and modeling Jul 2, 2024

Message passing neural networks (MPNNs) on molecular graphs generate continuous and differentiable encodings of small molecules with state-of-the-art performance on protein-ligand complex scoring tasks. Here, we describe the proximity graph network (...

Molecular Docking Simulation Neural Networks, Computer Proteins Protein Binding Ligands

View on PubMed DOI

Accelerating Polymer Discovery with Uncertainty-Guided PGCNN: Explainable AI for Predicting Properties and Mechanistic Insights.

Journal of chemical information and modeling Jul 2, 2024

Deep learning holds great potential for expediting the discovery of new polymers from the vast chemical space. However, accurately predicting polymer properties for practical applications based on their monomer composition has long been a challenge. ...

Deep Learning Neural Networks, Computer Uncertainty Polymers

View on PubMed DOI