About this Research Topic
The cell is like a densely populated city of molecular interactions. Most of drug discovery is based on compounds that target these interactions because many disease states are associated with loss of interaction regulation. The latest advances in structural biology, sequencing technologies, and high throughput methods (such as mass spectroscopy) have created an explosion in the amount of available data.
This increase in data in publicly available databases has made the application of computational methodologies more reliable. Simultaneously, machine learning methodologies have become not only more powerful but also more robust and more interpretable. The advances on these fronts have accelerated research in the application of machine learning methodologies for understanding, analyzing, and predicting how biomolecules interact.
This Research Topic will cover the application of machine learning approaches to study molecular interactions. Specific topics may include, but are not limited to the analysis and prediction of:
• Interactions between proteins, DNA, RNA, small molecule ligands, peptides, lipids and other biomolecules
• Biomolecular interactions related to complex disease states such as neurodegenerative diseases, cancer and inflammatory diseases
• Crosstalk among cellular pathways in complex disease states
• Host pathogen interactions in infectious diseases focusing on viral and bacterial infections
• Novel molecules that target protein(s) and/or cells/tissues of interest
• Using supervised and unsupervised machine learning/deep learning techniques including the approaches generally applied to natural language processing, computer vision, image and speech recognition, and generative modeling
We also invite articles that focus on methodological advances in areas such as:
• De novo construction of small molecules and peptides with desired properties and interactions
• New ways of featurizing (bio)molecules and their interactions including graph-based approaches, and trainable/learnt representations
• Machine learning applications to aid conventional structure-based interaction analysis approaches such as docking and molecular dynamics
This Research Topic welcomes submissions in the form of original research articles (describing new algorithms, computational tools, methods and their applications, databases and datasets), reviews, and perspectives.
Dr. Elif Ozkirimli is a full time employee of F. Hoffmann-La Roche AG, Switzerland and Dr. Artur Yakimovich is a full time employee of Roche Products Limited, UK. All other Topic Editors declare no competing interests with regards to the Research Topic.
Keywords: Molecular interactions, interaction databases, benchmark datasets, feature engineering, machine learning, natural language processing, text mining, relation extraction, generative models, graph theory, drug discovery, repurposing
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.