Machine learning–driven multiscale modeling reveals lipid-dependent dynamics of RAS signaling proteins

Helgi I. Ingolfsson, Chris Neale, Timothy S. Carpenter, Rebika Shrestha, Cesar A. Lopez, Timothy H. Tran, Tomas Oppelstrup, Harsh Bhatia, Liam G. Stanton, Xiaohua Zhang, Shiv Sundram, Francesco Di Natale, Animesh Agarwal, Gautham Dharuman, Sara I.L. Kokkila Schumacher, Thomas Turbyville, Gulcin Gulten, Que N. Van, Debanjan Goswami, Frantz Jean-FrancoisConstance Agamasu, De Chen, Jeevapani J. Hettige, Timothy Travers, Sumantra Sarkar, Michael P. Surh, Yue Yang, Adam Moody, Shusen Liu, Brian C. van Essen, Arthur F. Voter, Arvind Ramanathan, Nicolas W. Hengartner, Dhirendra K. Simanshu, Andrew G. Stephen, Peer Timo Bremer, S. Gnanakaran, James N. Glosli, Felice C. Lightstone, Frank McCormick, Dwight V. Nissley, Frederick H. Streitz

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


RAS is a signaling protein associated with the cell membrane that is mutated in up to 30% of human cancers. RAS signaling has been proposed to be regulated by dynamic heterogeneity of the cell membrane. Investigating such a mechanism requires near-atomistic detail at macroscopic temporal and spatial scales, which is not possible with conventional computational or experimental techniques. We demonstrate here a multiscale simulation infrastructure that uses machine learning to create a scale-bridging ensemble of over 100,000 simulations of active wild-type KRAS on a complex, asymmetric membrane. Initialized and validated with experimental data (including a new structure of active wild-type KRAS), these simulations represent a substantial advance in the ability to characterize RAS-membrane biology. We report distinctive patterns of local lipid composition that correlate with interfacially promiscuous RAS multimerization. These lipid fingerprints are coupled to RAS dynamics, predicted to influence effector binding, and therefore may be a mechanism for regulating cell signaling cascades.

Original languageEnglish (US)
Article numbere2113297119
JournalProceedings of the National Academy of Sciences of the United States of America
Issue number1
StatePublished - Jan 4 2022
Externally publishedYes


  • Massive parallel simulations
  • Multiscale infrastructure
  • Multiscale modeling
  • RAS dynamics
  • RAS-membrane biology

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Machine learning–driven multiscale modeling reveals lipid-dependent dynamics of RAS signaling proteins'. Together they form a unique fingerprint.

Cite this