Machine Learning Methodologies To Study Molecular Interactions

Machine Learning Methodologies To Study Molecular Interactions

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.

Machine learning for biological sequence analysis

Computational Approaches In Molecular Interaction Analysis: Predicting Protein Complexes, Host-pathogen Interactions, And Protein Function From Interactome Data

This book presents a curated collection of research articles from the Journal of Bioinformatics and Computational Biology, highlighting advances in protein-protein interaction-based computational methods for predicting protein complexes, host-pathogen interactions (HPIs), and protein functions. In Part I, it addresses the dynamic challenges of protein complex prediction using innovative techniques like GECA and IPC-RPIN, which integrate network topology, gene expression, and GO annotations to improve accuracy, especially for small complexes. Part II focuses on HPIs, reviewing computational approaches, predictive models, and tools that enhance understanding of infectious diseases, with a particular emphasis on machine learning applications. Part III delves into protein function prediction, employing PPI networks, multi-label methods, and iterative models that account for dynamic interactions. Collectively, these studies provide a comprehensive resource for advancing computational biology and understanding cellular and disease mechanisms.