Dataset Information

Linking drug target and pathway activation for effective therapy using multi-task learning.

ABSTRACT: Despite the abundance of large-scale molecular and drug-response data, the insights gained about the mechanisms underlying treatment efficacy in cancer has been in general limited. Machine learning algorithms applied to those datasets most often are used to provide predictions without interpretation, or reveal single drug-gene association and fail to derive robust insights. We propose to use Macau, a bayesian multitask multi-relational algorithm to generalize from individual drugs and genes and explore the interactions between the drug targets and signaling pathways' activation. A typical insight would be: "Activation of pathway Y will confer sensitivity to any drug targeting protein X". We applied our methodology to the Genomics of Drug Sensitivity in Cancer (GDSC) screening, using gene expression of 990 cancer cell lines, activity scores of 11 signaling pathways derived from the tool PROGENy as cell line input and 228 nominal targets for 265 drugs as drug input. These interactions can guide a tissue-specific combination treatment strategy, for example suggesting to modulate a certain pathway to maximize the drug response for a given tissue. We confirmed in literature drug combination strategies derived from our result for brain, skin and stomach tissues. Such an analysis of interactions across tissues might help target discovery, drug repurposing and patient stratification strategies.

SUBMITTER: Yang M

PROVIDER: S-EPMC5974390 | biostudies-literature | 2018 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Linking drug target and pathway activation for effective therapy using multi-task learning.

Yang Mi M Simm Jaak J Lam Chi Chung CC Zakeri Pooya P van Westen Gerard J P GJP Moreau Yves Y Saez-Rodriguez Julio J

Scientific reports 20180529 1

Despite the abundance of large-scale molecular and drug-response data, the insights gained about the mechanisms underlying treatment efficacy in cancer has been in general limited. Machine learning algorithms applied to those datasets most often are used to provide predictions without interpretation, or reveal single drug-gene association and fail to derive robust insights. We propose to use Macau, a bayesian multitask multi-relational algorithm to generalize from individual drugs and genes and ...[more]

PMID: 29844324

Similar Datasets

Project description:Osteosarcoma (OS) is the most common bone tumor in children. Polyamines (PAs) are ubiquitous cations involved in many cell processes including tumor development, invasion and metastasis. In other pediatric cancer models, inhibition of the PA biosynthesis pathway with ornithine decarboxylase (ODC) inhibitor alpha-difluoromethylornithine (DFMO) results in decreased cell proliferation and differentiation. In OS, the PA pathway has not been evaluated. DFMO is an attractive, orally administered drug, is well tolerated, can be given for prolonged periods, and is already used in pediatric patients. Three OS cell lines were used to study the cellular effects of PA inhibition with DFMO: MG-63, U-2 OS and Saos-2. Effects on proliferation were analyzed by cell count, flow cytometry-based cell cycle analysis and RealTime-Glo™ MT Cell Viability assays. Intracellular PA levels were measured with high-performance liquid chromatography (HPLC). Western blot analysis was used to evaluate cell differentiation. DFMO exposure resulted in significantly decreased cell proliferation in all cell lines. After treatment, intracellular spermidine levels were drastically decreased. Cell cycle arrest at G₂/M was observed in U-2 OS and Saos-2. Cell differentiation was most prominent in MG-63 and U-2 OS as determined by increases in the terminal differentiation markers osteopontin and collagen 1a1. Cell proliferation continued to be suppressed for several days after removal of DFMO. Based on our findings, DFMO is a promising new adjunct to current osteosarcoma therapy in patients at high risk of relapse, such as those with poor necrosis at resection or those with metastatic or recurrent osteosarcoma. It is a well-tolerated oral drug that is currently in phase II clinical trials in pediatric neuroblastoma patients as a maintenance therapy. The same type of regimen may also improve outcomes in osteosarcoma patients in whom there have been essentially no medical advances in the last 30 years.

Dataset Information

Linking drug target and pathway activation for effective therapy using multi-task learning.

Publications

Linking drug target and pathway activation for effective therapy using multi-task learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets