Recruiting machine learning methods for molecular simulations of proteins

Mittal, Shriyaa; Shukla, Diwakar

doi:10.1080/08927022.2018.1448976

Cited by 29 publications

(25 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clustering refers to the coarse graining analysis that groups certain datasets based on their similarities, so that macrostates can be formed to be better understood. Commonly used clustering algorithms, such as minibatch k-means [15,33,38], mini-batch k-medoids [39,40] and k-centers [21,41], have shown similar performance when the data is preprocessed with tICA [17][18][19][20]. (4) MSM construction.…”

Section: Theory and Methodsmentioning

confidence: 99%

Automatic Feature Selection in Markov State Models Using Genetic Algorithm

Chen¹,

Feng²,

Mittal³

et al. 2018

JOCSE

Self Cite

View full text Add to dashboard Cite

Markov State Models (MSMs) are a powerful framework to reproduce the long-time conformational dynamics of biomolecules using a set of short Molecular Dynamics (MD) simulations. However, precise kinetics predictions of MSMs heavily rely on the features selected to describe the system. Despite the importance of feature selection for large system, determining an optimal set of features remains a difficult unsolved problem. Here, we introduce an automatic approach to optimize feature selection based on genetic algorithms (GA), which adaptively evolves the most fitted solution according to natural selection laws. The power of the GA-based method is illustrated on long atomistic folding simulations of four proteins, varying in length from 28 to 80 residues. Due to the diversity of tested proteins, we expect that our method will be extensible to other proteins and drive MSM building to a more objective protocol.Additional Key Words and Phrases: Genetic algorithm, feature selection, markov state model, molecular dynamics simulation, generalized matrix Rayleigh quotient 1 arXiv:1806.09723v1 [q-bio.BM]

show abstract

Section: Theory and Methodsmentioning

confidence: 99%

Automatic Feature Selection in Markov State Models Using Genetic Algorithm

Chen¹,

Feng²,

Mittal³

et al. 2018

JOCSE

Self Cite

View full text Add to dashboard Cite

show abstract

“…To further understand the formation and related properties of proteins, nanoengineering combined with ML approach has been applied for the analysis. The application of ML algorithms in protein dynamics studies has been investigated [139,140]. Protein kinase C isoforms, one type of membrane-associated proteins evaluated clinically for the treatment of cancer and Alzheimer's disease and the eradication of HIV/AIDS, is modeled through long-timescale MD simulations integrated with ML optimization, demonstrating different membrane states in biological effects [141].…”

Section: Modeling Approach With MLmentioning

confidence: 99%

Nanoengineering in biomedicine: Current development and future perspectives

Jian

Hui

Lau

2020

Nanotechnology Reviews

View full text Add to dashboard Cite

Recent advances in biomedicine largely rely on the development in nanoengineering. As the access to unique properties in biomaterials is not readily available from traditional techniques, the nanoengineering becomes an effective approach for research and development, by which the performance as well as the functionalities of biomaterials has been greatly improved and enriched. This review focuses on the main materials used in biomedicine, including metallic materials, polymers, and nanocomposites, as well as the major applications of nanoengineering in developing biomedical treatments and techniques. Research that provides an in-depth understanding of material properties and efficient enhancement of material performance using molecular dynamics simulations from the nanoengineering perspective are discussed. The advanced techniques which facilitate nanoengineering in biomedical applications are also presented to inspire further improvement in the future. Furthermore, the potential challenges of nanoengineering in biomedicine are evaluated by summarizing concerned issues and possible solutions.

show abstract

“…Sophisticated statistical machineries have been proposed to analyze those data, such as the Markov state models 59 – 61 , which are constantly updated 62 , to the point of switching “from [being] an Art to [becoming] a Science”, paraphrasing a recent review by Husic and Pande 63 . Interestingly, the specificity of the data generated by molecular simulations has led to the natural adaptation of machine-learning techniques to support their analyses; for a recent review on this topic, see Mittal and Shukla 64 .…”

Section: Physics-based Approaches To Protein Structure Predictionmentioning

confidence: 99%

Combined approaches from physics, statistics, and computer science for ab initio protein structure prediction: ex unitate vires (unity is strength)?

Delarue

Koehl

2018

F1000Res

View full text Add to dashboard Cite

Connecting the dots among the amino acid sequence of a protein, its structure, and its function remains a central theme in molecular biology, as it would have many applications in the treatment of illnesses related to misfolding or protein instability. As a result of high-throughput sequencing methods, biologists currently live in a protein sequence-rich world. However, our knowledge of protein structure based on experimental data remains comparatively limited. As a consequence, protein structure prediction has established itself as a very active field of research to fill in this gap. This field, once thought to be reserved for theoretical biophysicists, is constantly reinventing itself, borrowing ideas informed by an ever-increasing assembly of scientific domains, from biology, chemistry, (statistical) physics, mathematics, computer science, statistics, bioinformatics, and more recently data sciences. We review the recent progress arising from this integration of knowledge, from the development of specific computer architecture to allow for longer timescales in physics-based simulations of protein folding to the recent advances in predicting contacts in proteins based on detection of coevolution using very large data sets of aligned protein sequences.

show abstract

Recruiting machine learning methods for molecular simulations of proteins

Cited by 29 publications

References 127 publications

Automatic Feature Selection in Markov State Models Using Genetic Algorithm

Automatic Feature Selection in Markov State Models Using Genetic Algorithm

Nanoengineering in biomedicine: Current development and future perspectives

Combined approaches from physics, statistics, and computer science for ab initio protein structure prediction: ex unitate vires (unity is strength)?

Contact Info

Product

Resources

About