Systems biology is an interdisciplinary field of study in which biological systems are explored by holistic quantitative approaches in an attempt to discover how the collective behaviors of these systems emerge from the complex interactions among their components. The molecular systems biology in particular deals with the emergence of behaviors from the complex interactions among biomolecules such as DNA, RNA, proteins, metabolites and so on.
To pursue a holistic analysis of molecular biological systems, in general these systems are first modeled as graphs in which vertices or nodes are the biomolecules and edges are the interactions among these biomolecules. These graphs are widely known as molecular biological networks and the relationships among their biomolecules can be quantitatively analyzed so that their topological properties can then be correlated with the emergence of biological phenomena of interest.
Among the holistic quantitative approaches in use in molecular systems biology are the machine learning-based approaches. Machine learning is a branch of the artificial intelligence that encompass techniques used to learn and extract knowledge from raw data. Machine learning techniques are able to extract patterns hidden in a given data set and make use of these patterns to make accurate predictions on future data. Thus, considering a given biological system, the application of machine learning techniques can reveal how the relationships among the biocomponents can originate a collective behavior of interest of the biological system under study.
In this Research Topic we intend to introduce some fundamentals of systems biology and machine learning and present a current state of the art of the machine learning applied to molecular systems biology. For this purpose, we welcome contributors that use machine learning techniques to explore biological systems, particularly biomolecular systems, in the following aspects of this research field:
1. Network-based identification and prediction of novel drug targets, druggable protein-protein interactions and essential and disease genes;
2. Reconstruction and inference of gene regulatory, metabolic and protein-protein interaction networks;
3. Network-based prediction of gene and protein functions;
4. Network-based analysis of gene expression data;
5. Molecular systems biology of cancer.
However, these subjects are not exclusive and only represent the core of the themes that can be considered for publication.
Systems biology is an interdisciplinary field of study in which biological systems are explored by holistic quantitative approaches in an attempt to discover how the collective behaviors of these systems emerge from the complex interactions among their components. The molecular systems biology in particular deals with the emergence of behaviors from the complex interactions among biomolecules such as DNA, RNA, proteins, metabolites and so on.
To pursue a holistic analysis of molecular biological systems, in general these systems are first modeled as graphs in which vertices or nodes are the biomolecules and edges are the interactions among these biomolecules. These graphs are widely known as molecular biological networks and the relationships among their biomolecules can be quantitatively analyzed so that their topological properties can then be correlated with the emergence of biological phenomena of interest.
Among the holistic quantitative approaches in use in molecular systems biology are the machine learning-based approaches. Machine learning is a branch of the artificial intelligence that encompass techniques used to learn and extract knowledge from raw data. Machine learning techniques are able to extract patterns hidden in a given data set and make use of these patterns to make accurate predictions on future data. Thus, considering a given biological system, the application of machine learning techniques can reveal how the relationships among the biocomponents can originate a collective behavior of interest of the biological system under study.
In this Research Topic we intend to introduce some fundamentals of systems biology and machine learning and present a current state of the art of the machine learning applied to molecular systems biology. For this purpose, we welcome contributors that use machine learning techniques to explore biological systems, particularly biomolecular systems, in the following aspects of this research field:
1. Network-based identification and prediction of novel drug targets, druggable protein-protein interactions and essential and disease genes;
2. Reconstruction and inference of gene regulatory, metabolic and protein-protein interaction networks;
3. Network-based prediction of gene and protein functions;
4. Network-based analysis of gene expression data;
5. Molecular systems biology of cancer.
However, these subjects are not exclusive and only represent the core of the themes that can be considered for publication.
