Reconstructing cancer drug response networks using multitask learning

Translating 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. The reconstructed networks correctly id...

Full description

Saved in:
Bibliographic Details
Published in:BMC systems biology 2017-10, Vol.11 (1), p.96-96, Article 96
Main Authors: Ruffalo, Matthew, Stojanov, Petar, Pillutla, Venkata Krishna, Varma, Rohan, Bar-Joseph, Ziv
Format: Article
Language:English
Subjects:
Antineoplastic Agents - pharmacology
Antineoplastic Agents - therapeutic use
Apoptosis
Breast cancer
Cancer
Cell growth
Computational Biology - methods
Drugs
Experiments
Gene expression
Genomes
Kinases
Learning
Machine Learning
Melanoma
Methods
Neoplasms - drug therapy
Neoplasms - genetics
Networks
Prostate cancer
Proteins
Survival Analysis
Treatment Outcome
Usability
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Translating 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. The 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. Predictions 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.
ISSN:1752-0509
1752-0509
DOI:10.1186/s12918-017-0471-8