Abstract
BackgroundTranslating in vitro results to clinical tests is a major challenge in systems biology. Here we present a new Multi-Task learning framework which integrates thousands of cell line expression experiments to reconstruct drug specific response networks in cancer.ResultsThe reconstructed networks correctly identify several shared key proteins and pathways while simultaneously highlighting many cell type specific proteins. We used top proteins from each drug network to predict survival for patients prescribed the drug.ConclusionsPredictions based on proteins from the in-vitro derived networks significantly outperformed predictions based on known cancer genes indicating that Multi-Task learning can indeed identify accurate drug response networks.
Highlights
Translating in vitro results to clinical tests is a major challenge in systems biology
We developed a new Multi-Task (MT) learning formulation for integrating expression experiments across different types of drugs administered to cancer cell lines (Fig. 1)
Following our assumption that most drugs activate the same pathways across different tissues / cancer types, the joint (MT) learning framework is used to constrain the set of paths in the resulting networks by encouraging compact solutions that are shared across the different tasks
Summary
Translating in vitro results to clinical tests is a major challenge in systems biology. Recent efforts aimed at inferring cellular response networks that are activated by such perturbations have utilized in vitro cell lines Such cell lines have been derived for several different types of cancer [3,4,5,6,7] and these have been extensively used to study potential treatments and mutants. Over the last decade several methods have been developed for reconstructing molecular response networks [10,11,12,13] These methods often combine general interaction and sequence data with condition specific data to model pathways that are activated as part of the biological process being studied. Since the number of parameters is often greater than the effective
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
