DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Interpretable artificial intelligence and exascale molecular dynamics simulations to reveal kinetics: Applications to Alzheimer's disease

Abstract

The rapid increase in computing power, especially with the integration of graphics processing units, has dramatically increased the capabilities of molecular dynamics simulations. To date, these capabilities extend from running very long simulations (tens to hundreds of microseconds) to thousands of short simulations. However, the expansive data generated in these simulations must be made interpretable not only by the investigator who performs them but also by others as well. Here, we demonstrate how integrating learning techniques, such as artificial intelligence, machine learning, and neural networks, into analysis pipelines can reveal the kinetics of Alzheimer's disease (AD) protein aggregation. Finally, we review select AD targets, describe current simulation methods, and introduce learning concepts and their application in AD, highlighting limitations and potential solutions.

Authors:
ORCiD logo [1];  [2];  [3];  [4]; ORCiD logo [5]
  1. Cleveland Clinic, OH (United States)
  2. Univ. of Virginia, Charlottesville, VA (United States)
  3. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  4. National Cancer Institute, Frederick, MD (United States); Tel Aviv Univ., Tel Aviv (Israel)
  5. Cleveland Clinic, OH (United States); Case Western Reserve Univ., Cleveland, OH (United States)
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA); National Institute of Aging; National Heart, Lung, and Blood Institute; National Institutes of Health (NIH)
OSTI Identifier:
1832329
Report Number(s):
LLNL-JRNL-827311
Journal ID: ISSN 0959-440X; 1042416
Grant/Contract Number:  
AC52-07NA27344; R01AG066707; 3R01AG066707-01S1; R00HL138272; HHSN261200800001E
Resource Type:
Accepted Manuscript
Journal Name:
Current Opinion in Structural Biology
Additional Journal Information:
Journal Volume: 72; Journal Issue: na; Journal ID: ISSN 0959-440X
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; Biological and medical sciences

Citation Formats

Martin, William, Sheynkman, Gloria, Lightstone, Felice C., Nussinov, Ruth, and Cheng, Feixiong. Interpretable artificial intelligence and exascale molecular dynamics simulations to reveal kinetics: Applications to Alzheimer's disease. United States: N. p., 2021. Web. doi:10.1016/j.sbi.2021.09.001.
Martin, William, Sheynkman, Gloria, Lightstone, Felice C., Nussinov, Ruth, & Cheng, Feixiong. Interpretable artificial intelligence and exascale molecular dynamics simulations to reveal kinetics: Applications to Alzheimer's disease. United States. https://doi.org/10.1016/j.sbi.2021.09.001
Martin, William, Sheynkman, Gloria, Lightstone, Felice C., Nussinov, Ruth, and Cheng, Feixiong. Thu . "Interpretable artificial intelligence and exascale molecular dynamics simulations to reveal kinetics: Applications to Alzheimer's disease". United States. https://doi.org/10.1016/j.sbi.2021.09.001. https://www.osti.gov/servlets/purl/1832329.
@article{osti_1832329,
title = {Interpretable artificial intelligence and exascale molecular dynamics simulations to reveal kinetics: Applications to Alzheimer's disease},
author = {Martin, William and Sheynkman, Gloria and Lightstone, Felice C. and Nussinov, Ruth and Cheng, Feixiong},
abstractNote = {The rapid increase in computing power, especially with the integration of graphics processing units, has dramatically increased the capabilities of molecular dynamics simulations. To date, these capabilities extend from running very long simulations (tens to hundreds of microseconds) to thousands of short simulations. However, the expansive data generated in these simulations must be made interpretable not only by the investigator who performs them but also by others as well. Here, we demonstrate how integrating learning techniques, such as artificial intelligence, machine learning, and neural networks, into analysis pipelines can reveal the kinetics of Alzheimer's disease (AD) protein aggregation. Finally, we review select AD targets, describe current simulation methods, and introduce learning concepts and their application in AD, highlighting limitations and potential solutions.},
doi = {10.1016/j.sbi.2021.09.001},
journal = {Current Opinion in Structural Biology},
number = na,
volume = 72,
place = {United States},
year = {Thu Oct 07 00:00:00 EDT 2021},
month = {Thu Oct 07 00:00:00 EDT 2021}
}

Works referenced in this record:

Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
journal, January 2017


Synergy between amyloid-β and tau in Alzheimer’s disease
journal, August 2020


Novel tau filament fold in chronic traumatic encephalopathy encloses hydrophobic molecules
journal, March 2019


A new era for understanding amyloid structures and disease
journal, September 2018

  • Iadanza, Matthew G.; Jackson, Matthew P.; Hewitt, Eric W.
  • Nature Reviews Molecular Cell Biology, Vol. 19, Issue 12
  • DOI: 10.1038/s41580-018-0060-8

A kinetic ensemble of the Alzheimer’s Aβ peptide
journal, January 2021

  • Löhr, Thomas; Kohlhoff, Kai; Heller, Gabriella T.
  • Nature Computational Science, Vol. 1, Issue 1
  • DOI: 10.1038/s43588-020-00003-w

Least squares quantization in PCM
journal, March 1982


The amyloid hypothesis on trial
journal, July 2018


Mixing Aβ(1–40) and Aβ(1–42) peptides generates unique amyloid fibrils
journal, January 2020

  • Cerofolini, Linda; Ravera, Enrico; Bologna, Sara
  • Chemical Communications, Vol. 56, Issue 62
  • DOI: 10.1039/D0CC02463E

Scalable molecular dynamics with NAMD
journal, January 2005

  • Phillips, James C.; Braun, Rosemary; Wang, Wei
  • Journal of Computational Chemistry, Vol. 26, Issue 16, p. 1781-1802
  • DOI: 10.1002/jcc.20289

The Amber biomolecular simulation programs
journal, January 2005

  • Case, David A.; Cheatham, Thomas E.; Darden, Tom
  • Journal of Computational Chemistry, Vol. 26, Issue 16
  • DOI: 10.1002/jcc.20290

The BioGRID database: A comprehensive biomedical resource of curated protein, genetic, and chemical interactions
journal, November 2020

  • Oughtred, Rose; Rust, Jennifer; Chang, Christie
  • Protein Science, Vol. 30, Issue 1
  • DOI: 10.1002/pro.3978

A Community Letter Regarding Sharing Biomolecular Simulation Data for COVID-19
journal, April 2020

  • Amaro, Rommie E.; Mulholland, Adrian J.
  • Journal of Chemical Information and Modeling, Vol. 60, Issue 6
  • DOI: 10.1021/acs.jcim.0c00319

Molecular basis for the loss-of-function effects of the Alzheimer's disease–associated R47H variant of the immune receptor TREM2
journal, August 2018

  • Sudom, Athena; Talreja, Santosh; Danao, Jean
  • Journal of Biological Chemistry, Vol. 293, Issue 32
  • DOI: 10.1074/jbc.RA118.002352

Bringing Molecular Dynamics Simulation Data into View
journal, November 2019

  • Hildebrand, Peter W.; Rose, Alexander S.; Tiemann, Johanna K. S.
  • Trends in Biochemical Sciences, Vol. 44, Issue 11
  • DOI: 10.1016/j.tibs.2019.06.004

Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995


Accurate prediction of protein structures and interactions using a three-track neural network
journal, July 2021


Unsupervised Learning Methods for Molecular Simulation Data
journal, May 2021


Cryo-EM structure and polymorphism of Aβ amyloid fibrils purified from Alzheimer’s brain tissue
journal, October 2019


MSMBuilder: Statistical Models for Biomolecular Dynamics
journal, January 2017

  • Harrigan, Matthew P.; Sultan, Mohammad M.; Hernández, Carlos X.
  • Biophysical Journal, Vol. 112, Issue 1
  • DOI: 10.1016/j.bpj.2016.10.042

GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers
journal, September 2015


Highly accurate protein structure prediction with AlphaFold
journal, July 2021


The misfolding mechanism of the key fragment R3 of tau protein: a combined molecular dynamics simulation and Markov state model study
journal, January 2020

  • Liu, Hongli; Zhong, Haiyang; Xu, Zerong
  • Physical Chemistry Chemical Physics, Vol. 22, Issue 19
  • DOI: 10.1039/C9CP06954B

Neurodegenerative Disease–Associated Variants in TREM2 Destabilize the Apical Ligand-Binding Region of the Immunoglobulin Domain
journal, November 2019


ApoE Lipidation as a Therapeutic Target in Alzheimer’s Disease
journal, September 2020

  • Lanfranco, Maria Fe; Ng, Christi Anne; Rebeck, G. William
  • International Journal of Molecular Sciences, Vol. 21, Issue 17
  • DOI: 10.3390/ijms21176336

STRING v11: protein–protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets
journal, November 2018

  • Szklarczyk, Damian; Gable, Annika L.; Lyon, David
  • Nucleic Acids Research, Vol. 47, Issue D1
  • DOI: 10.1093/nar/gky1131

Markov State Models: From an Art to a Science
journal, February 2018

  • Husic, Brooke E.; Pande, Vijay S.
  • Journal of the American Chemical Society, Vol. 140, Issue 7
  • DOI: 10.1021/jacs.7b12191

CHARMM: The biomolecular simulation program
journal, July 2009

  • Brooks, B. R.; Brooks, C. L.; Mackerell, A. D.
  • Journal of Computational Chemistry, Vol. 30, Issue 10
  • DOI: 10.1002/jcc.21287

Comprehensive characterization of protein–protein interactions perturbed by disease mutations
journal, February 2021


Interactome3D: adding structural details to protein networks
journal, January 2013

  • Mosca, Roberto; Céol, Arnaud; Aloy, Patrick
  • Nature Methods, Vol. 10, Issue 1
  • DOI: 10.1038/nmeth.2289

Using Dimensionality Reduction to Analyze Protein Trajectories
journal, June 2019


Molecular structure of a prevalent amyloid-β fibril polymorph from Alzheimer's disease brain tissue
journal, January 2021

  • Ghosh, Ujjayini; Thurber, Kent R.; Yau, Wai-Ming
  • Proceedings of the National Academy of Sciences, Vol. 118, Issue 4
  • DOI: 10.1073/pnas.2023089118

Tau Assembly: The Dominant Role of PHF6 (VQIVYK) in Microtubule Binding Region Repeat R3
journal, March 2015

  • Ganguly, Pritam; Do, Thanh D.; Larini, Luca
  • The Journal of Physical Chemistry B, Vol. 119, Issue 13
  • DOI: 10.1021/acs.jpcb.5b00175

Chemical Kinetics for Bridging Molecular Mechanisms and Macroscopic Measurements of Amyloid Fibril Formation
journal, April 2018


UCSF Chimera?A visualization system for exploratory research and analysis
journal, January 2004

  • Pettersen, Eric F.; Goddard, Thomas D.; Huang, Conrad C.
  • Journal of Computational Chemistry, Vol. 25, Issue 13
  • DOI: 10.1002/jcc.20084

PyEMMA 2: A Software Package for Estimation, Validation, and Analysis of Markov Models
journal, October 2015

  • Scherer, Martin K.; Trendelkamp-Schroer, Benjamin; Paul, Fabian
  • Journal of Chemical Theory and Computation, Vol. 11, Issue 11
  • DOI: 10.1021/acs.jctc.5b00743

Reconsideration of Amyloid Hypothesis and Tau Hypothesis in Alzheimer's Disease
journal, January 2018


Thermodynamics and kinetics of the amyloid-β peptide revealed by Markov state models based on MD data in agreement with experiment
journal, January 2021

  • Paul, Arghadwip; Samantray, Suman; Anteghini, Marco
  • Chemical Science, Vol. 12, Issue 19
  • DOI: 10.1039/D0SC04657D

Fibril structure of amyloid-β(1–42) by cryo–electron microscopy
journal, September 2017


Mechanism of Prion Propagation: Amyloid Growth Occurs by Monomer Addition
journal, September 2004


A Supervised Molecular Dynamics Approach to Unbiased Ligand–Protein Unbinding
journal, March 2020

  • Deganutti, Giuseppe; Moro, Stefano; Reynolds, Christopher A.
  • Journal of Chemical Information and Modeling, Vol. 60, Issue 3
  • DOI: 10.1021/acs.jcim.9b01094

Cryo-EM structures of tau filaments from Alzheimer’s disease with PET ligand APN-1607
journal, March 2021


Apolipoprotein E: From lipid transport to neurobiology
journal, January 2011


Principles of protein structural ensemble determination
journal, February 2017

  • Bonomi, Massimiliano; Heller, Gabriella T.; Camilloni, Carlo
  • Current Opinion in Structural Biology, Vol. 42
  • DOI: 10.1016/j.sbi.2016.12.004

EMDB Web Resources
journal, March 2018

  • Abbott, Sanja; Iudin, Andrii; Korir, Paul K.
  • Current Protocols in Bioinformatics, Vol. 61, Issue 1
  • DOI: 10.1002/cpbi.48

Apolipoprotein E and Alzheimer disease: pathobiology and targeting strategies
journal, July 2019


Molecular Dynamics Simulation for All
journal, September 2018


γ‐Secretase cleavage of the Alzheimer risk factor TREM 2 is determined by its intrinsic structural dynamics
journal, August 2020


PDBe: Protein Data Bank in Europe
journal, November 2010

  • Velankar, S.; Alhroub, Y.; Alili, A.
  • Nucleic Acids Research, Vol. 39, Issue Database
  • DOI: 10.1093/nar/gkq985

Reducing acetylated tau is neuroprotective in brain injury
journal, May 2021


Swarm Learning for decentralized and confidential clinical machine learning
journal, May 2021

  • Warnat-Herresthal, Stefanie; Schultze, Hartmut; Shastry, Krishnaprasad Lingadahalli
  • Nature, Vol. 594, Issue 7862
  • DOI: 10.1038/s41586-021-03583-3

Complete protein–protein association kinetics in atomic detail revealed by molecular dynamics simulations and Markov modelling
journal, June 2017

  • Plattner, Nuria; Doerr, Stefan; De Fabritiis, Gianni
  • Nature Chemistry, Vol. 9, Issue 10
  • DOI: 10.1038/nchem.2785

Apolipoprotein E: Structural Insights and Links to Alzheimer Disease Pathogenesis
journal, January 2021


Developing a molecular dynamics force field for both folded and disordered protein states
journal, May 2018

  • Robustelli, Paul; Piana, Stefano; Shaw, David E.
  • Proceedings of the National Academy of Sciences, Vol. 115, Issue 21
  • DOI: 10.1073/pnas.1800690115

APOE-amyloid interaction: Therapeutic targets
journal, May 2020


INstruct: a database of high-quality 3D structurally resolved protein interactome networks
journal, May 2013


Salt bridge relay triggers defective LDL receptor binding by a mutant apolipoprotein
journal, August 1994


Tau Pathology in Parkinson's Disease
journal, October 2018


Human apolipoprotein E. Role of arginine 61 in mediating the lipoprotein preferences of the E3 and E4 isoforms.
journal, September 1994


The HADDOCK2.2 Web Server: User-Friendly Integrative Modeling of Biomolecular Complexes
journal, February 2016

  • van Zundert, G. C. P.; Rodrigues, J. P. G. L. M.; Trellet, M.
  • Journal of Molecular Biology, Vol. 428, Issue 4
  • DOI: 10.1016/j.jmb.2015.09.014

Three-dimensional structure of the LDL receptor-binding domain of human apolipoprotein E
journal, June 1991


Amyloid assembly is dominated by misregistered kinetic traps on an unbiased energy landscape
journal, April 2020

  • Jia, Zhiguang; Schmit, Jeremy D.; Chen, Jianhan
  • Proceedings of the National Academy of Sciences, Vol. 117, Issue 19
  • DOI: 10.1073/pnas.1911153117

Conformation Determines the Seeding Potencies of Native and Recombinant Tau Aggregates
journal, January 2015

  • Falcon, Benjamin; Cavallini, Annalisa; Angers, Rachel
  • Journal of Biological Chemistry, Vol. 290, Issue 2
  • DOI: 10.1074/jbc.M114.589309

Tau Pathology in Chronic Traumatic Encephalopathy and Alzheimer's Disease: Similarities and Differences
journal, September 2019


ApoE attenuates unresolvable inflammation by complex formation with activated C1q
journal, January 2019


SWISS-MODEL: homology modelling of protein structures and complexes
journal, May 2018

  • Waterhouse, Andrew; Bertoni, Martino; Bienert, Stefan
  • Nucleic Acids Research, Vol. 46, Issue W1
  • DOI: 10.1093/nar/gky427

The Protein Data Bank
journal, January 2000


Structural Evolution of Iowa Mutant β-Amyloid Fibrils from Polymorphic to Homogeneous States under Repeated Seeded Growth
journal, February 2011

  • Qiang, Wei; Yau, Wai-Ming; Tycko, Robert
  • Journal of the American Chemical Society, Vol. 133, Issue 11
  • DOI: 10.1021/ja109679q

Separation of a mixture of independent signals using time delayed correlations
journal, June 1994


APOE and Alzheimer's disease: advances in genetics, pathophysiology, and therapeutic approaches
journal, January 2021


OpenMM 7: Rapid development of high performance algorithms for molecular dynamics
journal, July 2017


Atomistic Insights into Structural Differences between E3 and E4 Isoforms of Apolipoprotein E
journal, December 2017


Topology of human apolipoprotein E3 uniquely regulates its diverse biological functions
journal, August 2011

  • Chen, J.; Li, Q.; Wang, J.
  • Proceedings of the National Academy of Sciences, Vol. 108, Issue 36
  • DOI: 10.1073/pnas.1106420108

PED in 2021: a major update of the protein ensemble database for intrinsically disordered proteins
journal, December 2020

  • Lazar, Tamas; Martínez-Pérez, Elizabeth; Quaglia, Federica
  • Nucleic Acids Research, Vol. 49, Issue D1
  • DOI: 10.1093/nar/gkaa1021