Results 201 to 210 of about 266,738 (314)

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

Try the Monte Carlo Method

open access: yes, 2019
summary:Stochastická metoda Monte Carlo (tedy kombinující pravděpodobnost a statistiku) nachází uplatnění v mnoha oblastech: jaderná a částicová fyzika [Frýbort, J.: Monte Carlo není jenom hazard, Rozhledy matematicko-fyzikální, 86 (2011), 3, 4–12 ...
Dvořáková, Ľubomíra
core  

Interpretable Machine Learning for Solvent‐Dependent Carrier Mobility in Solution‐Processed Organic Thin Films

open access: yesAdvanced Intelligent Discovery, EarlyView.
This work establishes a correlation between solvent properties and the charge transport performance of solution‐processed organic thin films through interpretable machine learning. Strong dispersion interactions (δD), moderate hydrogen bonding (δH), closely matching and compatible with the solute (quadruple thiophene), and a small molar volume (MolVol)
Tianhao Tan, Lian Duan, Dong Wang
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

Home - About - Disclaimer - Privacy