Multitask learning for host–pathogen protein interactions

By Meghana Kshirsagar, Jaime G. Carbonell, Judith Klein-Seetharaman. 2013

83 citations recorded by the source corpus.

Motivation: An important aspect of infectious disease research involves understanding the differences and commonalities in the infection mechanisms underlying various diseases. Systems biology-based approaches study infectious diseases by analyzing the interactions between the host species and the pathogen organisms. This work aims to combine the knowledge from experimental studies of host–pathogen interactions in several diseases to build stronger predictive models. Our approach is based on a formalism from machine learning called ‘multitask learning’, which considers the problem of building models across tasks that are related to each other. A ‘task’ in our scenario is the set of host–pathogen protein interactions involved in one disease. To integrate interactions from several tasks (i.e. diseases), our method exploits the similarity in the infection process across the diseases. In particular, we use the biological hypothesis that similar pathogens target the same critical biological processes in the host, in defining a common structure across the tasks. Results: Our current work on host–pathogen protein interaction prediction focuses on human as the host, and four bacterial species as pathogens. The multitask learning technique we develop uses a task-based regularization approach. We find that the resulting optimization problem is a difference of convex (DC) functions. To optimize, we implement a Convex–Concave procedure-based algorithm. We compare our integrative approach to baseline methods that build models on a single host–pathogen protein interaction dataset. Our results show that our approach outperforms the baselines on the training data. We further analyze the protein interaction predictions generated by the models, and find some interesting insights. Availability: The predictions and code are available at: http://www.cs.cmu.edu/∼mkshirsa/ismb2013_paper320.html Contact: j.klein-seetharaman@warwick.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

A Survey on Multi-Task Learning (2017, methodology): “Task Relation Learning Protein subcellular location prediction [194] Sentiment classification [230] Web search ranking [231] Localization [203] Organism modeling [232] Collaborative filtering [233] Robotics [234], [235] MHC-I binding prediction [236] Display advertising [237] Trajectory regression [”
Multitask Matrix Completion for Learning Protein Interactions Across Diseases (2016, methodology): “[13] develop a task regularization based framework that incorporates the similarity in biological pathways targeted by various diseases.”
Multi-Task Multiple Kernel Relationship Learning (2016, background): “Unfortunately, such prior knowledge is not easily available in many applications either because it is time-consuming or it is expensive to elicit.”
Inductive matrix completion for predicting gene–disease associations (2014, methodology): “We refer the reader to the excellent survey articles by Moreau and Tranchevent [2012] and by Piro and Di Cunto [2012] for a near-comprehensive treatment of different classes of methods, contexts in which they are best-suited and what sources of data they integrate.”