Results 251 to 260 of about 252,758 (328)

Benchmarking Large Language Models for Polymer Property Predictions

open access: yesMacromolecular Rapid Communications, EarlyView.
Large language models (LLMs) are fine‐tuned on polymer thermal property datasets to directly predict glass transition, melting, and decomposition temperatures from SMILES inputs. Compared to state‐of‐the‐art models such as Polymer Genome, polyGNN, and polyBERT, LLMs achieve competitive yet lower accuracy.
Sonakshi Gupta   +3 more
wiley   +1 more source

Role of High Fidelity Vs. Low Fidelity Experimental Data in Machine Learning Model Performance for Predicting Polymer Solubility

open access: yesMacromolecular Rapid Communications, EarlyView.
The performance of machine learning models for classifying polymer solubility improves when a high‐fidelity experimental dataset is used compared to a low‐fidelity experimental dataset. This has important implications for justifying the value of spending additional time and resources preparing detailed experimental datasets.
Mona Amrihesari   +3 more
wiley   +1 more source

Uncovering Key Characteristics of Antibacterial Peptides through Machine Learning

open access: yesMacromolecular Rapid Communications, EarlyView.
Machine‐learning (ML) techniques using random forest classification models revealed key characteristics that predict effective antimicrobial peptides (AMPs) targeting Gram‐negative bacteria, Gram‐positive bacteria, and mycobacteria. The ideal cLogP (<$ < $−6) and net‐charge (≤+4) threshold was the same for all three targets with variations in the ...
Jooyoung Roh   +2 more
wiley   +1 more source

Structure‐Aware Machine Learning for Polymers: A Hierarchical Graph Network for Predicting Properties From Statistical Ensembles

open access: yesMacromolecular Rapid Communications, EarlyView.
This work presents a structure‐aware graph convolutional network that models polymers as statistical ensembles to predict macroscopic properties. By combining topologically realistic graphs generated via kinetic Monte Carlo simulations with explicit molar mass distributions, the framework achieves high accuracy in classifying architectures and ...
Julian Kimmig   +7 more
wiley   +1 more source

ChemFM as a scaling law guided foundation model pre-trained on informative chemicals. [PDF]

open access: yesCommun Chem
Cai F   +8 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy