Prediction of Drug Combinations by Integrating Molecular and Pharmacological Data

By Xingming Zhao, Murat Iskar, Georg Zeller, Michael Kuhn, Vera van Noort, Peer Bork. 2011

195 citations recorded by the source corpus.

Combinatorial therapy is a promising strategy for combating complex disorders due to improved efficacy and reduced side effects. However, screening new drug combinations exhaustively is impractical considering all possible combinations between drugs. Here, we present a novel computational approach to predict drug combinations by integrating molecular and pharmacological data. Specifically, drugs are represented by a set of their properties, such as their targets or indications. By integrating several of these features, we show that feature patterns enriched in approved drug combinations are not only predictive for new drug combinations but also provide insights into mechanisms underlying combinatorial therapy. Further analysis confirmed that among our top ranked predictions of effective combinations, 69% are supported by literature, while the others represent novel potential drug combinations. We believe that our proposed approach can help to limit the search space of drug combinations and provide a new way to effectively utilize existing drugs for new purposes.

Subfields: Computational Theory and Mathematics, Molecular Biology, Pharmacology

How researchers see this paper

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

In Computational Theory and Mathematics

In Molecular Biology

In Pharmacology

Citations in the corpus

Modeling polypharmacy side effects with graph convolutional networks (2018, methodology): “The ﬁnal network after linking entity vocabularies used by different databases has 645 drug and 19,085 protein nodes connected by 715,612 protein-protein, 4,651,131 drug-drug, and 18,596 drug-protein edges.”
A community computational challenge to predict the activity of pairs of compounds (2014, methodology): “” Due to the limited number of synergistic (16) and antagonistic (36) compound pairs, we could not divide the gold standard data set into three subsets (S1, S2 and S3) to train and evaluate the performance of aggregating predictions by various methods on these metrics.”
Synergy Maps: exploring compound combinations using network-based visualization (2015, background): “Enrichment analysis of molecular and pharmacological properties predicted several combinations to be synergistic, 69% of which were subsequently verified in the literature [12].”
DrugComboRanker: drug combination discovery based on target network analysis (2014, methodology): “The novel method was evaluated on lung adenocarcinoma and endocrine receptor positive breast cancer, and compared with other drug combination approaches.”
Prediction of synergistic anti-cancer drug combinations based on drug target network and drug induced gene expression profiles (2017, background): “rug combinations with enrichment score above a certain threshld would be more likely to be new drug combinations [8].”
Combining genomic and network characteristics for extended capability in predicting synergistic drugs for cancer (2015, unknown): “…combinations on different cancers, which facilitates the statistic derivation of a whole set of signiﬁcant features for further model formulation and the incorporation of the drug targeting network to describe the MOA of drugs, which covers complementary and non-complementary mechanisms 3,7,11,12 .”
Predicting combinative drug pairs towards realistic screening via integrating heterogeneous features (2017, methodology): “Then, varied computational models are built by supervised learning (e.g. frequency-based lazy learning [5] and logistic regression [7]) to predict unknown drug pairs.”
Systematic prediction of drug combinations based on clinical side-effects (2014, methodology): “Therefore, computational methods 10–13 have been developed to predict new drug combinations.”
Structure and dynamics of molecular networks: A novel paradigm of drug discovery: A comprehensive review (2012, methodology): “…iterative algorithms were developed to find optimal target combinations restricting the search to a few combinations out of the potential search space of severalmillions to billions of combinations (Calzolari et al., 2008;Wong et al., 2008; Small et al., 2011; Yoon, 2011; Zhao et al., 2011a).”