AI-aided multiscale modeling of physiologically-significant blood clots

Yicong Zhu; Changnian Han; Peng Zhang; Guojing Cong; James R. Kozloski; Chih Chieh Yang; Leili Zhang; Yuefan Deng

doi:10.1016/j.cpc.2023.108718

AI-aided multiscale modeling of physiologically-significant blood clots

Yicong Zhu
, Changnian Han
, Peng Zhang
, Guojing Cong
, James R. Kozloski
, Chih Chieh Yang
, Leili Zhang
, Yuefan Deng

Applied Mathematics and Statistics

Stony Brook University
Oak Ridge National Laboratory
IBM

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

We have developed an AI-aided multiple time stepping (AI-MTS) algorithm and multiscale modeling framework (AI-MSM) and implemented them on the AiMOS supercomputer. AI-MSM is the first of its kind to integrate multi-physics, including intra-platelet, inter-platelet, and fluid-platelet interactions, into one system. It has simulated a record-setting multiscale blood clotting model of 102 million particles, of which 70 flowing and 180 aggregating platelets, under dissipative particle dynamics to coarse-grained molecular dynamics. By adaptively adjusting timestep sizes to match the characteristic time scales of the underlying dynamics, AI-MTS optimally balances speeds and accuracies of the simulations.

Original language	English
Article number	108718
Journal	Computer Physics Communications
Volume	287
DOIs	https://doi.org/10.1016/j.cpc.2023.108718
State	Published - Jun 2023

Keywords

Artificial intelligence
Blood clotting
HPC
Multiscale modeling

Access to Document

10.1016/j.cpc.2023.108718

Cite this

@article{0e1bccd1fe8e4e30a277183eb15eecb1,

title = "AI-aided multiscale modeling of physiologically-significant blood clots",

abstract = "We have developed an AI-aided multiple time stepping (AI-MTS) algorithm and multiscale modeling framework (AI-MSM) and implemented them on the AiMOS supercomputer. AI-MSM is the first of its kind to integrate multi-physics, including intra-platelet, inter-platelet, and fluid-platelet interactions, into one system. It has simulated a record-setting multiscale blood clotting model of 102 million particles, of which 70 flowing and 180 aggregating platelets, under dissipative particle dynamics to coarse-grained molecular dynamics. By adaptively adjusting timestep sizes to match the characteristic time scales of the underlying dynamics, AI-MTS optimally balances speeds and accuracies of the simulations.",

keywords = "Artificial intelligence, Blood clotting, HPC, Multiscale modeling",

author = "Yicong Zhu and Changnian Han and Peng Zhang and Guojing Cong and Kozloski, \{James R.\} and Yang, \{Chih Chieh\} and Leili Zhang and Yuefan Deng",

note = "Publisher Copyright: {\textcopyright} 2023 Elsevier B.V.",

year = "2023",

month = jun,

doi = "10.1016/j.cpc.2023.108718",

language = "English",

volume = "287",

journal = "Computer Physics Communications",

issn = "0010-4655",

}

TY - JOUR

T1 - AI-aided multiscale modeling of physiologically-significant blood clots

AU - Zhu, Yicong

AU - Han, Changnian

AU - Zhang, Peng

AU - Cong, Guojing

AU - Kozloski, James R.

AU - Yang, Chih Chieh

AU - Zhang, Leili

AU - Deng, Yuefan

PY - 2023/6

Y1 - 2023/6

N2 - We have developed an AI-aided multiple time stepping (AI-MTS) algorithm and multiscale modeling framework (AI-MSM) and implemented them on the AiMOS supercomputer. AI-MSM is the first of its kind to integrate multi-physics, including intra-platelet, inter-platelet, and fluid-platelet interactions, into one system. It has simulated a record-setting multiscale blood clotting model of 102 million particles, of which 70 flowing and 180 aggregating platelets, under dissipative particle dynamics to coarse-grained molecular dynamics. By adaptively adjusting timestep sizes to match the characteristic time scales of the underlying dynamics, AI-MTS optimally balances speeds and accuracies of the simulations.

AB - We have developed an AI-aided multiple time stepping (AI-MTS) algorithm and multiscale modeling framework (AI-MSM) and implemented them on the AiMOS supercomputer. AI-MSM is the first of its kind to integrate multi-physics, including intra-platelet, inter-platelet, and fluid-platelet interactions, into one system. It has simulated a record-setting multiscale blood clotting model of 102 million particles, of which 70 flowing and 180 aggregating platelets, under dissipative particle dynamics to coarse-grained molecular dynamics. By adaptively adjusting timestep sizes to match the characteristic time scales of the underlying dynamics, AI-MTS optimally balances speeds and accuracies of the simulations.

KW - Artificial intelligence

KW - Blood clotting

KW - HPC

KW - Multiscale modeling

UR - https://www.scopus.com/pages/publications/85150048557

U2 - 10.1016/j.cpc.2023.108718

DO - 10.1016/j.cpc.2023.108718

M3 - Article

AN - SCOPUS:85150048557

SN - 0010-4655

VL - 287

JO - Computer Physics Communications

JF - Computer Physics Communications

M1 - 108718

ER -

AI-aided multiscale modeling of physiologically-significant blood clots

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this