DeepSynergy: predicting anti-cancer drug synergy with Deep Learning.

Motivation: While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies. Results: DeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations. Availability and implementation: DeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy. Contact: klambauer@bioinf.jku.at. Supplementary information: Supplementary data are available at Bioinformatics online.

Correction: Competitor analysis of functional group H-bond donor and acceptor properties using the Cambridge Structural Database.

Correction for 'Competitor analysis of functional group H-bond donor and acceptor properties using the Cambridge Structural Database' by James McKenzie et al., Phys. Chem. Chem. Phys., 2018, 20, 25324-25334.

Competitor analysis of functional group H-bond donor and acceptor properties using the Cambridge Structural Database.

Intermolecular interactions found in the Cambridge Structural Database (CSD) are analysed as the outcomes of competitions between the different functional groups that are present in each structure: the most energetically favourable interactions are expected to win more often than weaker interactions. Tracking winners and losers through each crystal structure in the CSD provides data that can be analysed using paired comparison algorithms to rank functional group H-bonding properties based on how frequently they outcompete other functional groups in the crystal. This treatment is superior to simple statistical analyses of whether functional groups H-bond or not, because the distribution of H-bond donors and acceptors in the structures of the molecules found in the CSD is non-random. Most organic molecules contain more acceptors than donors, so that all H-bond donors are almost always H-bonded in all crystal structures, and most acceptors are not. The rankings of H-bond acceptors obtained by applying the TrueSkill paired comparison algorithm to the CSD agree well with the corresponding experimentally determined solution phase H-bond acceptor parameters ß, but there is insufficient data to corroborate H-bond donor rankings calculated in the same way. The method is used to make predictions of the H-bond acceptor properties of functional groups for which solution phase measurements are not available.

Using Machine Learning to Predict Synergistic Antimalarial Compound Combinations With Novel Structures.

The parasite Plasmodium falciparum is the most lethal species of Plasmodium to cause serious malaria infection in humans, and with resistance developing rapidly novel treatment modalities are currently being sought, one of which being combinations of existing compounds. The discovery of combinations of antimalarial drugs that act synergistically with one another is hence of great importance; however an exhaustive experimental screen of large drug space in a pairwise manner is not an option. In this study we apply our machine learning approach, Combination Synergy Estimation (CoSynE), which can predict novel synergistic drug interactions using only prior experimental combination screening data and knowledge of compound molecular structures, to a dataset of 1,540 antimalarial drug combinations in which 22.2% were synergistic. Cross validation of our model showed that synergistic CoSynE predictions are enriched 2.74 × compared to random selection when both compounds in a predicted combination are known from other combinations among the training data, 2.36 × when only one compound is known from the training data, and 1.5 × for entirely novel combinations. We prospectively validated our model by making predictions for 185 combinations of 23 entirely novel compounds. CoSynE predicted 20 combinations to be synergistic, which was experimentally validated for nine of them (45%), corresponding to an enrichment of 1.70 × compared to random selection from this prospective data set. Such enrichment corresponds to a 41% reduction in experimental effort. Interestingly, we found that pairwise screening of the compounds CoSynE individually predicted to be synergistic would result in an enrichment of 1.36 × compared to random selection, indicating that synergy among compound combinations is not a random event. The nine novel and correctly predicted synergistic compound combinations mainly (where sufficient bioactivity information is available) consist of efflux or transporter inhibitors (such as hydroxyzine), combined with compounds exhibiting antimalarial activity alone (such as sorafenib, apicidin, or dihydroergotamine). However, not all compound synergies could be rationalized easily in this way. Overall, this study highlights the potential for predictive modeling to expedite the discovery of novel drug combinations in fight against antimalarial resistance, while the underlying approach is also generally applicable.

Modelling of compound combination effects and applications to efficacy and toxicity: state-of-the-art, challenges and perspectives.

The development of treatments involving combinations of drugs is a promising approach towards combating complex or multifactorial disorders. However, the large number of compound combinations that can be generated, even from small compound collections, means that exhaustive experimental testing is infeasible. The ability to predict the behaviour of compound combinations in biological systems, whittling down the number of combinations to be tested, is therefore crucial. Here, we review the current state-of-the-art in the field of compound combination modelling, with the aim to support the development of approaches that, as we hope, will finally lead to an integration of chemical with systems-level biological information for predicting the effect of chemical mixtures.