Guantes, R. | Search bioRxiv

bioRxiv2024

Optimizing drug synergy prediction through categorical embeddings in Deep Neural Networks

Cancer treatments often lose effectiveness as tumors develop resistance to single-agent therapies. Combination treatments can overcome this limitation, but the overwhelming combinatorial space of drug-dose interactions makes exhaustive experimental testing impractical. Data-driven methods, such as Machine and deep learning, have emerged as promising tools to predict synergistic drug combinations. In this work, we systematically investigate the use of categorical embeddings within Deep Neural Networks to enhance drug synergy predictions. These learned and transferable encodings capture similarities between the elements of each category, demonstrating particular utility in scarce data scenarios.

bioinformatics↗

bioRxiv2023

Virus-host protein co-expression networks reveal temporal organization and strategies of viral infection

Viral replication is a complex dynamical process involving the global remodelling of the host cellular machinery across several stages. In this study, we provide a unified view of the virus-host interaction at the proteome level reconstructing protein co-expression networks from quantitative temporal data of four large DNA viruses. We take advantage of a formal framework, the theory of interacting networks, to describe the viral infection as a dynamical system taking place on a network of networks where perturbations induced by viral proteins spread to hijack the host proteome for the virus benefit. Our methodology demonstrates how the viral replication cycle can be effectively examined as a complex interaction between protein networks, providing useful insights into the viral and hosts temporal organization and strategies, key protein nodes targeted by the virus and dynamical bottlenecks during the course of the infection.

systems biology↗