Results 161 to 170 of about 3,135 (215)

Mapping ADHD Heterogeneity and Biotypes by Topological Deviations in Morphometric Similarity Networks.

open access: yesJAMA Psychiatry
Pan N   +13 more
europepmc   +1 more source

Mechanisms of Alkali Ionic Transport in Amorphous Oxyhalides Solid State Conductors

open access: yesAdvanced Energy Materials, EarlyView.
Large‐scale machine learning‐based molecular dynamics simulations are used to investigate isovalent amorphous oxyhalides, revealing a remarkable chemically independent ionic conductivity. A rigorous analysis of alkali residence times across different metal–anion environments identifies divalent anions as key diffusion bottlenecks.
Luca Binci   +3 more
wiley   +1 more source

SigmaFormer: Augmenting transformer encoders with COSMO sigma profiles for pure component property prediction

open access: yesAIChE Journal, EarlyView.
Abstract Transformer‐based molecular models pretrained on SMILES strings demonstrate strong performance in property prediction. However, these model often lack explicit integration of molecular surface charge distributions that govern intermolecular interactions such as hydrogen bonding and polarity.
Tae Hyun Kim   +2 more
wiley   +1 more source

Early classification of functional connectomes in Parkinson's disease: a comparison of machine learning classifiers using multi-scale topological features. [PDF]

open access: yesBMC Med Inform Decis Mak
Donisi L   +9 more
europepmc   +1 more source

Automated generative process synthesis via transformer‐based dual‐loop simulation and optimization

open access: yesAIChE Journal, EarlyView.
Abstract This study presents a novel framework for automated generative process synthesis, addressing the complexity of simultaneously optimizing discrete topologies and continuous operating variables. To overcome conventional superstructure limitations, we propose a dual‐loop architecture integrating generative transformers with rigorous process ...
Yeong Woo Son   +4 more
wiley   +1 more source

Topology‐Aware Machine Learning for High‐Throughput Screening of MOFs in C8 Aromatic Separation

open access: yesAdvanced Intelligent Discovery, EarlyView.
We screened 15,335 Computation‐Ready, Experimental Metal–Organic Frameworks (CoRE‐MOFs) using a topology‐aware machine learning (ML) model that integrates structural, chemical, pore‐size, and topological descriptors. Top‐performing MOFs exhibit aromatic‐enriched cavities and open metal sites that enable π–π and C–H···π interactions, serving as ...
Yu Li, Honglin Li, Jialu Li, Wan‐Lu Li
wiley   +1 more source

Machine Learning-Based QSAR Models for Discovery of Inhibitors Targeting <i>Leishmania infantum</i> Amastigotes. [PDF]

open access: yesPharmaceuticals (Basel)
Flores-Balmaseda N   +5 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy