Abstract
Combinatorial drug therapy can improve the therapeutic effect and reduce the corresponding adverse events. In silico strategies to classify synergistic vs. antagonistic drug pairs is more efficient than experimental strategies. However, most of the developed methods have been applied only to cancer therapies. In this study, we introduce a novel method, XGBoost, based on five features of drugs and biomolecular networks of their targets, to classify synergistic vs. antagonistic drug combinations from different drug categories. We found that XGBoost outperformed other classifiers in both stratified fivefold cross-validation (CV) and independent validation. For example, XGBoost achieved higher predictive accuracy than other models (0.86, 0.78, 0.78, and 0.83 for XGBoost, logistic regression, naïve Bayesian, and random forest, respectively) for an independent validation set. We also found that the five-feature XGBoost model is much more effective at predicting combinatorial therapies that have synergistic effects than those with antagonistic effects. The five-feature XGBoost model was also validated on TCGA data with accuracy of 0.79 among the 61 tested drug pairs, which is comparable to that of DeepSynergy. Among the 14 main anatomical/pharmacological groups classified according to WHO Anatomic Therapeutic Class, for drugs belonging to five groups, their prediction accuracy was significantly increased (odds ratio < 1) or reduced (odds ratio > 1) (Fisher’s exact test, p < 0.05). This study concludes that our five-feature XGBoost model has significant benefits for classifying synergistic vs. antagonistic drug combinations.
Highlights
The de novo drug discovery paradigm of “one drug, one target, and one disease” has been greatly challenged by the increasing rate of drug attrition in clinical trials and drug withdrawal due to severe adverse drug reactions (ADRs) at the post-marketing stage (Wood, 2006)
The performance of all XGBoost models roughly tend to be stable after the size of features combination reached five; further increasing the number of features did not change the model performance or slightly decreased the performance
Similar to the findings described in the previous section, the XGBoost model achieved the best performance in permutation tests
Summary
The de novo drug discovery paradigm of “one drug, one target, and one disease” has been greatly challenged by the increasing rate of drug attrition in clinical trials and drug withdrawal due to severe adverse drug reactions (ADRs) at the post-marketing stage (Wood, 2006). Drug combinations have been widely used to counter drug resistance in cancer therapy (Webster, 2016). One example of this is the combination of docetaxel with two HER2 inhibitors (i.e., pertuzumab and trastuzumab) for treating HER2-positive metastatic breast cancer, which achieved an approximately 16month improvement in overall survival (OS) compared with the conventional single treatment option (Swain et al, 2015). The use of drug combinations has been applied to alleviate ADRs. One example is fixeddose combination therapies for treating type 2 diabetes, which effectively eliminated the side effects of diabetes drugs such as cardiovascular toxicity and enhanced the efficacy (Bell, 2013).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
