Special Issue: Machine Learning, Mathematical and Statistical Modeling for Systems Biology

Guest Editors

Prof. Wandi Ding
Department of Mathematical Sciences, Computational and Data Science Program, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Email: wding@mtsu.edu


Prof. Joshua L. Phillips
Department of Computer Science, Computational and Data Science Program, Middle Tennessee State University, Murfreesboro, TN 37132, USA
Email: Joshua.Phillips@mtsu.edu


Prof. Zhuolin Qu
Department of Mathematics, University of Texas, San Antonio, TX, 78249, USA
Email: zhuolin.qu@utsa.edu


Prof. Russell Zaretzki
Business Analytics and Statistics, University of Tennessee, Knoxville, TN 37996, USA
Email: rzaretzk@utk.edu

Manuscript Topics


This special issue focuses on recent advances using machine learning, deep learning, statistical modeling, mathematical modeling (agent/individual-based modeling, ordinary and partial differential equations and difference equations), and hybrid systems in the design, modeling, validation, and control for infectious diseases. The topic includes both human diseases such as malaria, Zika, dengue, West Nile Virus, TB, HIV, etc., and various zoonotic diseases. We expect it to provide a deeper insight into data curation and assembly, the development of new theories that connect the subdisciplines, new predictive and interpretable machine/deep learning models that are better suited to biological applications than existing techniques. It will require strong collaborations between computational biologists and applied mathematicians. This special issue will provide a vision using the above techniques for infectious diseases modeling and control, and it will highlight some challenges as well.


Machine learning techniques specifically adapted for biological applications will help to enable the reintegration of biology, modeling, and computation. It will allow us not only to collect, connect, and analyze data at unparalleled scales, but also to build predictive models that span diverse topics. Especially the use of deep learning, e.g., convolutional neural networks, recurrent neural networks, graph neural networks, generative adversarial networks, autoencoder models, and reinforcement learning, which have recently obtained unprecedented achievements in computer vision, classification, and prediction.


Learning hidden patterns and extracting information from large-scale data arising from many applications is the aim of the modern field of data science. We invite manuscripts from pattern recognition and predictive analytics based on large-scale data. A common thread in the research is to resort to mathematical methods, probability theory, entropy (information theory), and algorithms, or develop new algorithms and theories to solve various problems. Neural networks have produced amazingly good results, but the mathematical theory is lacking. We would like to see contributions in this field too.


Differential equation-based models using ordinary and partial differential equations are classical modeling methods for studying biological systems when the environment/conditions are homogeneous. With the rich analytical theory, such as dynamical systems, they can be used to gain qualitative insights into the system. Investigations of heterogeneous models arising in epidemiology are welcome to submit.


Agent-based modeling is a powerful computational tool that allows great complexity in the description of the system across spatial and temporal scales. It has rising applications in interdisciplinary fields, such as epidemiology, ecology, biology, and psychology. The models simulate the stochastic actions and interactions between individuals to recreate the macroscopic phenomena and quantitatively predict the collective behavior of complex systems.


For over 100 years, statistical methods have been a fundamental tool in the mathematical modeling of biological systems. Statistical principles and tools remain a very core component of epidemiology and the scientific modeling of disease. In this special issue, we look forward to exploring cutting-edge methodologies that will advance our knowledge of the spatial, temporal, and graphical processes that govern the spread of disease in various populations. Furthermore, we also look forward to contributions that highlight causal techniques that help us to understand risk factors of disease in observational data along with experimental and quasi-experimental methods that serve as the foundation for the dynamics explored in more complex and prescriptive mathematical models.


Our special issue will use machine learning, deep learning, mathematical and statistical modeling techniques to tackle problems with temporal and spatial components, age and stage structures, different transmission mechanisms within and between humans and vectors, climate change, environmental factors, antibiotic resistance, the complex ecological and evolutionary dynamics pertaining to the adaptive biological systems. Different control measures will be explored via systematic control and optimal control theory to develop effective strategies for disease prevention and control.


Key words: machine learning; deep learning; agent/individual-based modeling; ordinary and partial differential equations; statistical modeling; computational biology; systems biology


Instructions for authors
https://www.aimspress.com/mbe/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/

Paper Submission

All manuscripts will be peer-reviewed before their acceptance for publication. The deadline for manuscript submission is 31 December 2022

Published Papers({{count}})

Special Issue Topical Section Recurring Topics Special Issue
{{author.authorNameEn}}
{{article.year}}, Volume {{article.volume}}, Issue {{article.issue}}: {{article.fpage | processPage:article.lpage:6}}. doi: {{article.doi}}
{{article.articleStateNameEn}}Available online{{article.preferredDate | date:'yyyy-MM-dd'}} doi: {{article.doi}}
Abstract Abstract HTML HTML PDF Cited ({{article.citedByCount}}) Viewed ({{article.visitArticleCount}})