Multitask Matrix Completion for Learning Protein Interactions Across Diseases

Abstract

Disease-causing pathogens such as viruses introduce their proteins into the host cells in which they interact with the host's proteins, enabling the virus to replicate inside the host. These interactions between pathogen and host proteins are key to understanding infectious diseases. Often multiple diseases involve phylogenetically related or biologically similar pathogens. Here we present a multitask learning method to jointly model interactions between human proteins and three different but related viruses: Hepatitis C, Ebola virus, and Influenza A. Our multitask matrix completion-based model uses a shared low-rank structure in addition to a task-specific sparse structure to incorporate the various interactions. We obtain between 7 and 39 percentage points improvement in predictive performance over prior state-of-the-art models. We show how our model's parameters can be interpreted to reveal both general and specific interaction-relevant characteristics of the viruses. Our code is available online.

APEX2S: A two‐layer machine learning model for discovery of host‐pathogen protein‐protein interactions on cloud‐based multiomics data

“…Although the coordination for multiomics databases is somehow hampered and the amount of accumulated data between different databases are not level, the multimics databases have shown some benefits on building powerful computational models toward the analysis of infectious diseases and improving the performance of protein related prediction task 9,17,49‐51 . Thus, the prospects of using multiomics databases for HP‐PPIs prediction task in Figure 1 is designed, which solicits future work from different disciplines to acquire more data.…”

DeepVir - Graphical Deep Matrix Factorization for In Silico Antiviral Repositioning: Application to COVID-19

“…• Protein-protein interaction prediction: Interactions are estimated in a protein-protein network [77,38]. Kshirsagar et al [38] deploy a matrix completion variant to model interactions between host (human here) proteins and pathogen (viruses causing infectious diseases here) proteins.…”

“…• Protein-protein interaction prediction: Interactions are estimated in a protein-protein network [77,38]. Kshirsagar et al [38] deploy a matrix completion variant to model interactions between host (human here) proteins and pathogen (viruses causing infectious diseases here) proteins. This helps identifying the interaction between viral proteins and the human proteins, enabling deeper understanding of infectious diseases (which may involve biologically similar pathogens).…”

Review of computational methods for virus–host protein interaction prediction: a case study on novel Ebola–human interactions

“…In contrast, prediction of inter-species (virus-host) PPI is relatively young field of study, which requires new model-based approaches. To tackle the problem of data scarcity, eliciting and transferring data from related domains to a desired formulation can be a promising solution [26,27]. Multitask learning [28][29][30] uses relationship among different domains and learns the problem simultaneously, which leads to a better performance rather conducting learning task on individual domain.…”