Synergistic drug combination prediction software tools | Drug discovery data analysis
Recent success in the study of synergistic combinations, such as the use of CHK1 inhibitors in combination with several DNA damaging agents or of the PARP inhibitor olaparib in combination with the PI3K inhibitor BKM120, have generated significant interest in the systematic screening of compound pairs to identify synergistic pairs for combination therapy.
Performs prediction of drug synergism. TAIJI is based on the winning algorithm in the AstraZeneca-Sanger Drug Combination Prediction DREAM Challenge. It utilizes both the pharmacological monotherapy results and cell line-specific molecular profiles. This software can be used by computational biologists and pharmacologists for estimating the drug combinatorial effects and guiding experimental and clinical trial design.
Measures synergistic agent combinations. NIMS addresses the network target-based virtual screen and assesses the synergistic strength of multicomponent therapeutics. It captures the node importance from different aspects by integrating the three measures Betweenness, Closeness and PageRank. The tool was used to prioritize synergistic agent pairs from 63 manually collected agents and estimated their effects on angiogenesis.
Predicts drug combinations targeting multiple signaling modules of cancer-specific networks. DrugComboRanker selects combinations targeting the alternative and complementary signaling modules of disease. It can provide insights into mechanism of actions of drug combinations by mapping the predicted drug targets on the disease signaling network.
Predicts the synergistic potential of the available anticancer drugs. RACS improves drug synergy prediction for guiding experimental searching despite of the unclear synergistic mechanism. It aims to address the limited positive/labelled samples and the large set of unknown/unlabelled combinations. The tool was evaluated using the endocrine receptor (ER)-positive breast cancer cell line MCF7.
Predict drug combination effects. DIGRE models the drug response dynamics and gene expression changes after individual drug treatments. It takes into account the sequential effect of the treatment, in agreement with many observations that the sequencing of drug treatment matters to patients’ outcomes. The tool uses a mathematical model of the drug response estimates the genomic residual effect.
Conducts computational ‘screens’. NLLSS integrates several types of information such as known synergistic drug combinations, unlabeled combinations, drug-target interactions, and drug chemical structures. It is an efficient way to find potential synergistic antifungal combinations by exploring new indications of existing antifungal drugs. The tool is based on the framework of Laplacian Regularized Least Square (LapRLS).
Predicts possible drug combinations. DCPred aims to facilitate the in-silico identification of effective drug combinations and speed up the future discovery process. It was used to predict and rank all the possible drug combinations. The tool is decomposed in three models that were applied to rank drug combinations and found that the top ranked combinations are more likely to be effective combinations.