Accelerating Multicomponent Phase-Coexistence Calculations with Physics-informed Neural Networks DOI Creative Commons

Satyen Dhamankar,

Shengli Jiang, Michael Webb

и другие.

Molecular Systems Design & Engineering, Год журнала: 2024, Номер 10(2), С. 89 - 101

Опубликована: Дек. 24, 2024

We develop a physics-informed machine learning workflow that accelerates multicomponent phase-coexistence calculations on the number, composition, and abundance of phases. The is demonstrated for systems described by Flory–Huggins theory.

Язык: Английский

Fluctuating Chromatin Facilitates Enhancer–Promoter Communication by Regulating Transcriptional Clustering Dynamics DOI

Tao Zhu,

Chunhe Li, Xiakun Chu

и другие.

The Journal of Physical Chemistry Letters, Год журнала: 2024, Номер 15(45), С. 11428 - 11436

Опубликована: Ноя. 7, 2024

Enhancers regulate gene expression by forming contacts with distant promoters. Phase-separated condensates or clusters formed transcription factors (TFs) and cofactors are thought to facilitate these enhancer-promoter (E-P) interactions. Using polymer physics, we developed distinct coarse-grained chromatin models that produce similar ensemble-averaged Hi-C maps but "stable" "dynamic" characteristics. Our findings, consistent recent experiments, reveal a multistep E-P communication process. The dynamic model facilitates proximity enhancing TF clustering subsequently promotes direct interactions destabilizing the through chain flexibility. study physical understanding of molecular mechanisms governing in transcriptional regulation.

Язык: Английский

Процитировано

0

Data efficiency of classification strategies for chemical and materials design DOI Creative Commons

Quinn Gallagher,

Michael Webb

Digital Discovery, Год журнала: 2024, Номер unknown

Опубликована: Янв. 1, 2024

We benchmark the performance of space-filling and active learning algorithms on classification problems in materials science, revealing trends optimally data-efficient algorithms.

Язык: Английский

Процитировано

0

Accelerating Multicomponent Phase-Coexistence Calculations with Physics-informed Neural Networks DOI Creative Commons

Satyen Dhamankar,

Shengli Jiang, Michael Webb

и другие.

Molecular Systems Design & Engineering, Год журнала: 2024, Номер 10(2), С. 89 - 101

Опубликована: Дек. 24, 2024

We develop a physics-informed machine learning workflow that accelerates multicomponent phase-coexistence calculations on the number, composition, and abundance of phases. The is demonstrated for systems described by Flory–Huggins theory.

Язык: Английский

Процитировано

0