Predicting effective drug combinations using gradient tree boosting based on features extracted from drug-protein heterogeneous network

Abstract

BackgroundAlthough targeted drugs have contributed to impressive advances in the treatment of cancer patients, their clinical benefits on tumor therapies are greatly limited due to intrinsic and acquired resistance of cancer cells against such drugs. Drug combinations synergistically interfere with protein networks to inhibit the activity level of carcinogenic genes more effectively, and therefore play an increasingly important role in the treatment of complex disease.ResultsIn this paper, we combined the drug similarity network, protein similarity network and known drug-protein associations into a drug-protein heterogenous network. Next, we ran random walk with restart (RWR) on the heterogenous network using the combinatorial drug targets as the initial probability, and obtained the converged probability distribution as the feature vector of each drug combination. Taking these feature vectors as input, we trained a gradient tree boosting (GTB) classifier to predict new drug combinations. We conducted performance evaluation on the widely used drug combination data set derived from the DCDB database. The experimental results show that our method outperforms seven typical classifiers and traditional boosting algorithms.ConclusionsThe heterogeneous network-derived features introduced in our method are more informative and enriching compared to the primary ontology features, which results in better performance. In addition, from the perspective of network pharmacology, our method effectively exploits the topological attributes and interactions of drug targets in the overall biological network, which proves to be a systematic and reliable approach for drug discovery.

Pathway-guided deep neural network toward interpretable and predictive modeling of drug sensitivity

“…Last but not least, single-drug treatments often fail to inhibit the carcinogenic pathways in cancer cells, due to the intrinsic compensatory mechanism and cross-talk among cellular pathways. Combination drugs have demonstrated high sensitivities and low side effects in cancer therapies, and thus have drawn intensive attention from both the academical and industrial community [33,34,35]. It is crucial to develop in-silico methods that can dissect the mechanism of drug action from the perspective of pathways in modeling drug sensitivity to cancer.…”

Machine learning approaches for drug combination therapies

“…Gradient tree boosting (GTB) was utilized by a heterogeneous network-based inference to classify efficacious drug combinations using features derived from drug–protein heterogeneous network [ 54 ]. Protein networks play an essential role in treating complex diseases, and therefore they might be applied to decrease the activity level of carcinogenic genes while developing drug combinations.…”

“…DTF [ 78 ] and DeepSynergy [ 37 ] are both competitive based on the results and the predictions from the two approaches are complementary. The best performance was by GTB of [ 54 ], but all methods achieved around 90% or more of AUC, which implies the data was too easy to evaluate the method, and more tough data would be good to be used for evaluation. Besides, training the drug combination prediction problem as a classification problem might underestimate the actual situation.…”

An In Silico Method for Predicting Drug Synergy Based on Multitask Learning

“…Therefore, due to the enormous screening space, some in silico methods have recently been proposed to improve clinical trials [9,10]. Various patterns, including pharmacological features [11], and network topological features [12][13][14], are enriched in a large number of effective drug combinations; these patterns were used to build a statistical learning model. Then, computational models to calculate a synergy score can effectively screen drug combinations from the many potential drug combinations based on numerical features extracted from these distinguished features.…”