Dear Colleagues,

Both, artificial intelligence and/or machine learning (AI/ML) and complex networks algorithms are important tools in the computational study of molecular systems. Some of these methods are artificial neural networks (ANNs), deep learning networks, support vector machines (SVMs), random forests (RFs), genetic algorithms (GAs), deep neural networks (DNNs), deep belief networks (DBNs), recurrent neural networks (RNNs), convolutional neural networks (CNNs), etc. We can use structural parameters, molecular descriptors, experimental conditions, chemometrics measurements, etc., as inputs to train these AI/ML algorithms. As a result, we can obtain predictive models for drug discovery, vaccine design, nanotechnology, etc.

On the other hand, complex networks are particularly useful in the study of complex bio-molecular systems. We can use complex networks to represent complex structural–function patterns in complex molecular bio-systems. This includes, but is not limited to, the structures of chemical compounds, synthetic chemical reaction routes, proteins, polymers, viral structures, RNA secondary structures, etc. This method is highly flexible; therefore, we can also represent larger bio-systems such as metabolic pathways, protein interaction networks (PINs), gene regulatory networks, brain cortexes, ecosystems, the internet, markets, social networks, etc. Within this approach, parts of a system (atoms, amino acids, monomers, proteins, reactions, neurons, organisms, etc.) are commonly represented as nodes, and the structure–function relationships among them (chemical bonds, hydrogen bonds, reactions, activation, co-expression, etc.) are represented as edges or links. This paves the way for the study of complex bio-molecular systems with graphs and the complex network theory. As a consequence, we can calculate multiple graph invariants (numeric parameters), which are useful to quantify the complex structure of these systems. This includes software/algorithms for the representation and study of distributions, emergent properties, transport phenomena, multiplex networks, dynamic systems properties, etc. In addition, although not mandatory, we can also train AI/ML algorithms using the numerical parameters of complex networks and bio-molecular systems as input in order to predict structure–function relationships and, as a consequence, the properties of these systems.

This framework opens the door to the development of new methods, algorithms, databases, and software for the study of complex bio-molecular systems using AI/ML and/or complex network algorithms. Consequently, the title of this issue is: “Complex Networks, Bio-Molecular Systems, and Machine Learning.” Authors are welcome to submit papers that utilize AI/ML algorithms alone, and we also welcome papers that utilize complex network algorithms alone. Overall, we especially welcome papers that combine both AI/ML and complex networks.

Prof. Dr. Humberto González-Díaz
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Molecular Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. There is an Article Processing Charge (APC) for publication in this open access journal. For details about the APC please see here. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• complex networks
• bio-molecular systems
• protein interaction networks (PINs)
• metabolic pathway networks
• brain networks
• social, financial, and legal networks
• machine learning
• bioinformatics
• cheminformatics and drug discovery
• graph theory
• artificial neural networks
• support vector machines
• deep learning