Synergistic drug combinations prediction by integrating pharmacological data

AttenSyn: An Attention-Based Deep Graph Neural Network for Anticancer Synergistic Drug Combination Prediction

Identifying synergistic drug combinations is fundamentally important to treat a variety of complex diseases while avoiding severe adverse drug-drug interactions. Although several computational methods have been proposed, they highly rely on handcrafted feature engineering and cannot learn better interactive information between drug pairs, easily resulting in relatively low performance. Recently, deep-learning methods, especially graph neural networks, have been widely developed in this area and demonstrated their ability to address complex biological problems. In this study, we proposed AttenSyn, an attention-based deep graph neural network for accurately predicting synergistic drug combinations. In particular, we adopted a graph neural network module to extract high-latent features based on the molecular graphs only and exploited the attention-based pooling module to learn interactive information between drug pairs to strengthen the representations of drug pairs. Comparative results on the benchmark datasets demonstrated that our AttenSyn performs better than the state-of-the-art methods in the prediction of anticancer synergistic drug combinations. Additionally, to provide good interpretability of our model, we explored and visualized some crucial substructures in drugs through attention mechanisms. Furthermore, we also verified the effectiveness of our proposed AttenSyn on two cell lines by visualizing the features of drug combinations learnt from our model, exhibiting satisfactory generalization ability.

DeepTraSynergy: drug combinations using multimodal deep learning with transformers

MOTIVATION

Screening bioactive compounds in cancer cell lines receive more attention. Multidisciplinary drugs or drug combinations have a more effective role in treatments and selectively inhibit the growth of cancer cells.

RESULTS

Hence, we propose a new deep learning-based approach for drug combination synergy prediction called DeepTraSynergy. Our proposed approach utilizes multimodal input including drug-target interaction, protein-protein interaction, and cell-target interaction to predict drug combination synergy. To learn the feature representation of drugs, we have utilized transformers. It is worth noting that our approach is a multitask approach that predicts three outputs including the drug-target interaction, its toxic effect, and drug combination synergy. In our approach, drug combination synergy is the main task and the two other ones are the auxiliary tasks that help the approach to learn a better model. In the proposed approach three loss functions are defined: synergy loss, toxic loss, and drug-protein interaction loss. The last two loss functions are designed as auxiliary losses to help learn a better solution. DeepTraSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the two latest drug combination datasets. The DeepTraSynergy algorithm achieves accuracy values of 0.7715 and 0.8052 (an improvement over other approaches) on the DrugCombDB and Oncology-Screen datasets, respectively. Also, we evaluate the contribution of each component of DeepTraSynergy to show its effectiveness in the proposed method. The introduction of the relation between proteins (PPI networks) and drug-protein interaction significantly improves the prediction of synergistic drug combinations.

AVAILABILITY AND IMPLEMENTATION

The source code and data are available at https://github.com/fatemeh-rafiei/DeepTraSynergy.

Explainable Drug Repurposing Approach From Biased Random Walks

Drug repurposing is a highly active research area, aiming at finding novel uses for drugs that have been previously developed for other therapeutic purposes. Despite the flourishing of methodologies, success is still partial, and different approaches offer, each, peculiar advantages. In this composite landscape, we present a novel methodology focusing on an efficient mathematical procedure based on gene similarity scores and biased random walks which rely on robust drug-gene-disease association data sets. The recommendation mechanism is further unveiled by means of the Markov chain underlying the random walk process, hence providing explainability about how findings are suggested. Performances evaluation and the analysis of a case study on rheumatoid arthritis show that our approach is accurate in providing useful recommendations and is computationally efficient, compared to the state of the art of drug repurposing approaches.

Differential tissue distribution of discrete typing units after drug combination therapy in experimental Trypanosoma cruzi mixed infection

The aim of the present work was to evaluate the distribution of the different clones of the parasite prevailing after treatment with benznidazole (BZ) and clomipramine (CLO), in mice infected with Trypanosoma cruzi, Casibla isolate which consists of a mixture of two discrete typing units (DTUs). Albino Swiss mice were infected and treated with high and low concentrations of BZ (100 or 6.25 mg/kg), CLO (5 or 1.25 mg/kg), or the combination of both low doses (BZ6.25 + CLO1.25), during the acute phase of experimental infection. Treatment efficacy was evaluated by comparing parasitaemia, survival and tissular parasite presence. For DTUs genotyping, blood, skeletal and cardiac muscle samples were analysed by multiplex quantitative polymerase chain reaction. The combined treatment had similar outcomes to BZ6.25; BZ100 was the most effective treatment, but it failed to reach parasite clearance and produced greater histological alterations. Non-treated mice and the ones treated with monotherapies showed both DTUs while BZ6.25 + CLO1.25 treated mice showed only TcVI parasites in all the tissues studied. These findings suggest that the treatment may modify the distribution of infecting DTUs in host tissues. Coinfection with T. cruzi clones belonging to different DTUs reveals a complex scenario for the treatment of Chagas disease and search for new therapies.

Machine learning methods, databases and tools for drug combination prediction

Combination therapy has shown an obvious efficacy on complex diseases and can greatly reduce the development of drug resistance. However, even with high-throughput screens, experimental methods are insufficient to explore novel drug combinations. In order to reduce the search space of drug combinations, there is an urgent need to develop more efficient computational methods to predict novel drug combinations. In recent decades, more and more machine learning (ML) algorithms have been applied to improve the predictive performance. The object of this study is to introduce and discuss the recent applications of ML methods and the widely used databases in drug combination prediction. In this study, we first describe the concept and controversy of synergism between drug combinations. Then, we investigate various publicly available data resources and tools for prediction tasks. Next, ML methods including classic ML and deep learning methods applied in drug combination prediction are introduced. Finally, we summarize the challenges to ML methods in prediction tasks and provide a discussion on future work.

Machine learning liver-injuring drug interactions with non-steroidal anti-inflammatory drugs (NSAIDs) from a retrospective electronic health record (EHR) cohort

Drug-drug interactions account for up to 30% of adverse drug reactions. Increasing prevalence of electronic health records (EHRs) offers a unique opportunity to build machine learning algorithms to identify drug-drug interactions that drive adverse events. In this study, we investigated hospitalizations' data to study drug interactions with non-steroidal anti-inflammatory drugs (NSAIDS) that result in drug-induced liver injury (DILI). We propose a logistic regression based machine learning algorithm that unearths several known interactions from an EHR dataset of about 400,000 hospitalization. Our proposed modeling framework is successful in detecting 87.5% of the positive controls, which are defined by drugs known to interact with diclofenac causing an increased risk of DILI, and correctly ranks aggregate risk of DILI for eight commonly prescribed NSAIDs. We found that our modeling framework is particularly successful in inferring associations of drug-drug interactions from relatively small EHR datasets. Furthermore, we have identified a novel and potentially hepatotoxic interaction that might occur during concomitant use of meloxicam and esomeprazole, which are commonly prescribed together to allay NSAID-induced gastrointestinal (GI) bleeding. Empirically, we validate our approach against prior methods for signal detection on EHR datasets, in which our proposed approach outperforms all the compared methods across most metrics, such as area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC).

Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions

Neurological disorders significantly outnumber diseases in other therapeutic areas. However, developing drugs for central nervous system (CNS) disorders remains the most challenging area in drug discovery, accompanied with the long timelines and high attrition rates. With the rapid growth of biomedical data enabled by advanced experimental technologies, artificial intelligence (AI) and machine learning (ML) have emerged as an indispensable tool to draw meaningful insights and improve decision making in drug discovery. Thanks to the advancements in AI and ML algorithms, now the AI/ML-driven solutions have an unprecedented potential to accelerate the process of CNS drug discovery with better success rate. In this review, we comprehensively summarize AI/ML-powered pharmaceutical discovery efforts and their implementations in the CNS area. After introducing the AI/ML models as well as the conceptualization and data preparation, we outline the applications of AI/ML technologies to several key procedures in drug discovery, including target identification, compound screening, hit/lead generation and optimization, drug response and synergy prediction, de novo drug design, and drug repurposing. We review the current state-of-the-art of AI/ML-guided CNS drug discovery, focusing on blood-brain barrier permeability prediction and implementation into therapeutic discovery for neurological diseases. Finally, we discuss the major challenges and limitations of current approaches and possible future directions that may provide resolutions to these difficulties.

Mapping drug-target interactions and synergy in multi-molecular therapeutics for pressure-overload cardiac hypertrophy

Advancements in systems biology have resulted in the development of network pharmacology, leading to a paradigm shift from "one-target, one-drug" to "target-network, multi-component therapeutics". We employ a chimeric approach involving in-vivo assays, gene expression analysis, cheminformatics, and network biology to deduce the regulatory actions of a multi-constituent Ayurvedic concoction, Amalaki Rasayana (AR) in animal models for its effect in pressure-overload cardiac hypertrophy. The proteomics analysis of in-vivo assays for Aorta Constricted and Biologically Aged rat models identify proteins expressed under each condition. Network analysis mapping protein-protein interactions and synergistic actions of AR using multi-component networks reveal drug targets such as ACADM, COX4I1, COX6B1, HBB, MYH14, and SLC25A4, as potential pharmacological co-targets for cardiac hypertrophy. Further, five out of eighteen AR constituents potentially target these proteins. We propose a distinct prospective strategy for the discovery of network pharmacological therapies and repositioning of existing drug molecules for treating pressure-overload cardiac hypertrophy.

Anticancer drug synergy prediction in understudied tissues using transfer learning

OBJECTIVE

Drug combination screening has advantages in identifying cancer treatment options with higher efficacy without degradation in terms of safety. A key challenge is that the accumulated number of observations in in-vitro drug responses varies greatly among different cancer types, where some tissues are more understudied than the others. Thus, we aim to develop a drug synergy prediction model for understudied tissues as a way of overcoming data scarcity problems.

MATERIALS AND METHODS

We collected a comprehensive set of genetic, molecular, phenotypic features for cancer cell lines. We developed a drug synergy prediction model based on multitask deep neural networks to integrate multimodal input and multiple output. We also utilized transfer learning from data-rich tissues to data-poor tissues.

RESULTS

We showed improved accuracy in predicting synergy in both data-rich tissues and understudied tissues. In data-rich tissue, the prediction model accuracy was 0.9577 AUROC for binarized classification task and 174.3 mean squared error for regression task. We observed that an adequate transfer learning strategy significantly increases accuracy in the understudied tissues.

CONCLUSIONS

Our synergy prediction model can be used to rank synergistic drug combinations in understudied tissues and thus help to prioritize future in-vitro experiments. Code is available at https://github.com/yejinjkim/synergy-transfer.

Folic acid-sulfonamide conjugates as antibacterial agents: design, synthesis and molecular docking studies

Dihydrofolate reductase (DHFR) inhibitors, as antibacterial agents, contain pyrimidine, pteridine, and azine moieties among many other scaffolds. Folic acid (FA), with a pteridine ring and amine group, was used as our focus scaffold, which was then conjugated with sulfonamides to develop new conjugates. The novel synthesized conjugates were characterized using infrared spectroscopy, and ¹H and ¹³C nuclear magnetic resonance (NMR) spectral studies and consequently screened for antimicrobial activities against bacterial strains with ampicillin as a positive control. Compound DS2 has the highest zone of inhibition (36.6 mm) with a percentage activity index (%AI) value of 122.8% against S. aureus and a minimum inhibitory concentration (MIC) of 15.63 μg mL^-1. DHFR enzyme inhibition was also evaluated using the synthesized conjugates through in vitro studies, and inhibition assays revealed that compound DS2 exhibited a 75.4 ± 0.12% (mean ± standard error of the mean (SEM)) inhibition, which is comparable with the standard DHFR inhibitor trimethoprim (74.6 ± 0.09%). The compounds attached to the unsubstituted aryl moiety of the sulfonamides revealed better inhibition against the bacterial strains as compared to the methyl substituted aryl sulfonamides. Molecular docking studies of the novel synthesized conjugates were also performed on the DHFR enzyme to identify the plausible binding modes to explore the binding mechanisms of these conjugates.

Essentiality and Transcriptome-Enriched Pathway Scores Predict Drug-Combination Synergy

In the prediction of the synergy of drug combinations, systems pharmacology models expand the scope of experiment screening and overcome the limitations of current computational models posed by their lack of mechanical interpretation and integration of gene essentiality. We therefore investigated the synergy of drug combinations for cancer therapies utilizing records in NCI ALMANAC, and we employed logistic regression to test the statistical significance of gene and pathway features in that interaction. We trained our predictive models using 43 NCI-60 cell lines, 165 KEGG pathways, and 114 drug pairs. Scores of drug-combination synergies showed a stronger correlation with pathway than gene features in overall trend analysis and a significant association with both genes and pathways in genome-wide association analyses. However, we observed little overlap of significant gene expressions and essentialities and no significant evidence that associated target and non-target genes and their pathways. We were able to validate four drug-combination pathways between two drug combinations, Nelarabine-Exemestane and Docetaxel-Vermurafenib, and two signaling pathways, PI3K-AKT and AMPK, in 16 cell lines. In conclusion, pathways significantly outperformed genes in predicting drug-combination synergy, and because they have very different mechanisms, gene expression and essentiality should be considered in combination rather than individually to improve this prediction.