Online Machine Learning for Accelerating Molecular Dynamics Modeling of Cells

Zhang, Ziji; Zhang, Peng; Han, Changnian; Cong, Guojing; Yang, Chulho; Deng, Yuefan

doi:10.3389/fmolb.2021.812248

Cited by 7 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the simulation speed, a multiscale model concurrently considering components at their own characteristic scales ( Zhu et al, 2021 ) and an intelligent time-stepping algorithm ( Han et al, 2021 ) can effectively relieve the computing load and shorten the simulation time. Advances on machine learning based techniques also have been made towards intelligent image processing for simulation parameter determination ( Zhang et al, 2021b ; Sheriff et al, 2021 ) and dynamics prediction ( Zhang et al, 2021a ), which enables long-term study with affordable efforts.…”

Section: Discussionmentioning

confidence: 99%

Modeling of the thermal properties of SARS-CoV-2 S-protein

Niu

Hasegawa²,

Deng³

et al. 2022

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

We calculate the thermal and conformational states of the spike glycoprotein (S-protein) of SARS-CoV-2 at seven temperatures ranging from 3°C to 95°C by all-atom molecular dynamics (MD) µs-scale simulations with the objectives to understand the structural variations on the temperatures and to determine the potential phase transition while trying to correlate such findings of the S-protein with the observed properties of the SARS-CoV2. Our simulations revealed the following thermal properties of the S-protein: 1) It is structurally stable at 3°C, agreeing with observations that the virus stays active for more than two weeks in the cold supply chain; 2) Its structure varies more significantly at temperature values of 60°C–80°C; 3) The sharpest structural variations occur near 60°C, signaling a plausible critical temperature nearby; 4) The maximum deviation of the receptor-binding domain at 37°C, corroborating the anecdotal observations that the virus is most infective at 37°C; 5) The in silico data agree with reported experiments of the SARS-CoV-2 survival times from weeks to seconds by our clustering approach analysis. Our MD simulations at µs scales demonstrated the S-protein’s thermodynamics of the critical states at around 60°C, and the stable and denatured states for temperatures below and above this value, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Modeling of the thermal properties of SARS-CoV-2 S-protein

Niu

Hasegawa²,

Deng³

et al. 2022

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Using a convolutional neural network (CNN) to identify subtle morphological features, Zhou et al classified platelet aggregates activated by different agonists [135], while Kempster et al used a CNN to automate analysis of spreading platelets captured under differential interference contrast (DIC) microscopy [136]. Semi-unsupervised learning based on CNN has been used to categorize morphology from platelets dynamics in microchannels [46,[137][138][139]. Several researchers have attempted to classify cellular information using features from diverse data types.…”

Section: Platelet Mechanobiology Modelling In the Age Of Datamentioning

confidence: 99%

Platelet Biorheology and Mechanobiology in Thrombosis: In Silico Perspectives

Tuna,

Yi,

Crespo Cruz

et al. 2024

Preprint

View full text Add to dashboard Cite

Thrombosis is the pathological clot formation under abnormal hemodynamic conditions, which can result in vascular obstruction, causing ischemic strokes and myocardial infarction. Thrombus growth under moderate to low shear (10,000 s$^{-1}$) is predominantly driven by unactivated platelet binding and aggregating mediated by von Willebrand factor (VWF), while platelet activation and coagulation are secondary in supporting and reinforcing the thrombus. Given the molecular and cellular level information it can access, multiscale computational modelling informed by biology can provide new pathological mechanisms that are otherwise not accessible experimentally, holding promise for novel first principle based therapeutics. In this review, we summarize the key aspects of platelet mechanobiology, focusing on the molecular and cellular scale events and how they build up all the way to thrombosis through platelet adhesion and aggregation in the presence or absence of platelet activation. In particular, we highlight the recent advancements in multiscale modelling of platelet biorheology and mechanobiology and their role in predicting thrombus formation. Recent applications of artificial intelligence in modelling platelet mechanobiology and thrombosis have also been briefly discussed.

show abstract

“…This gap has recently been noticed and addressed across multiple fields. The two types of models that are usually studied in isolation were integrated into a single framework for applications that include The two traditionally separate model types have been integrated into a unified framework for multiple applications, including Biology [4][5][6], Physics [7][8][9], Chemistry [10], Energy [11], and transportation [12]. In spite of that, there are still many unexplored aspects of this field [13].…”

Section: Introductionmentioning

confidence: 99%

A machine learning approach to predict gene expression levels based on stochastic simulation

taweraqi,

King

2024

Preprint

View full text Add to dashboard Cite

Purpose: Genes are key players in cellular systems as they control different aspects of cell behaviour and progression. Abnormalities in gene activities are indicators of cancer development and pathogenesis. However, despite the many advances in prediction tools and algorithms, predicting gene expression levels is considered challenging due to the noisy measurements of genes and the high complexity of the cellar networks. This study highlights the role of literature knowledge represented as signalling pathways in improving machine learning models' performance as they predict changes in gene expression levels. Methods: In this work, we introduce simulation-based machine learning models, where we combine stochastic simulation models with multi-target machine learning models to predict gene expression levels.Prior knowledge of gene activities is used to run simulations to infer gene similarities based on their activities.Then these similarities are used to build the machine learning models. Results: The results show that our method significantly outperforms the baseline, which does not include the literature knowledge.Moreover, It turns out that models of multi-target regression are sensitive to the number of included targets.Also, these models manage to capture the relationship between different targets even if their performance varies in the level of individual genes.

show abstract

Online Machine Learning for Accelerating Molecular Dynamics Modeling of Cells

Cited by 7 publications

References 40 publications

Modeling of the thermal properties of SARS-CoV-2 S-protein

Modeling of the thermal properties of SARS-CoV-2 S-protein

Platelet Biorheology and Mechanobiology in Thrombosis: In Silico Perspectives

A machine learning approach to predict gene expression levels based on stochastic simulation

Contact Info

Product

Resources

About