Prediction of Synergism from Chemical-Genetic Interactions by Machine Learning

A Bayesian active learning platform for scalable combination drug screens

Large-scale combination drug screens are generally considered intractable due to the immense number of possible combinations. Existing approaches use ad hoc fixed experimental designs then train machine learning models to impute unobserved combinations. Here we propose BATCHIE, an orthogonal approach that conducts experiments dynamically in batches. BATCHIE uses information theory and probabilistic modeling to design each batch to be maximally informative based on the results of previous experiments. On retrospective experiments from previous large-scale screens, BATCHIE designs rapidly discover highly effective and synergistic combinations. In a prospective combination screen of a library of 206 drugs on a collection of pediatric cancer cell lines, the BATCHIE model accurately predicts unseen combinations and detects synergies after exploring only 4% of the 1.4M possible experiments. Further, the model identifies a panel of top combinations for Ewing sarcomas, which follow-up validation experiments confirm to be effective, including the rational and translatable top hit of PARP plus topoisomerase I inhibition. These results demonstrate that adaptive experiments can enable large-scale unbiased combination drug screens with a relatively small number of experiments. BATCHIE is open source and publicly available ( https://github.com/tansey-lab/batchie ).

Role of Artificial Intelligence in Drug Discovery to Revolutionize the Pharmaceutical Industry: Resources, Methods and Applications

Traditional drug discovery methods such as wet-lab testing, validations, and synthetic techniques are time-consuming and expensive. Artificial Intelligence (AI) approaches have progressed to the point where they can have a significant impact on the drug discovery process. Using massive volumes of open data, artificial intelligence methods are revolutionizing the pharmaceutical industry. In the last few decades, many AI-based models have been developed and implemented in many areas of the drug development process. These models have been used as a supplement to conventional research to uncover superior pharmaceuticals expeditiously. AI's involvement in the pharmaceutical industry was used mostly for reverse engineering of existing patents and the invention of new synthesis pathways. Drug research and development to repurposing and productivity benefits in the pharmaceutical business through clinical trials. AI is studied in this article for its numerous potential uses. We have discussed how AI can be put to use in the pharmaceutical sector, specifically for predicting a drug's toxicity, bioactivity, and physicochemical characteristics, among other things. In this review article, we have discussed its application to a variety of problems, including de novo drug discovery, target structure prediction, interaction prediction, and binding affinity prediction. AI for predicting drug interactions and nanomedicines were also considered.

Ultra-high-throughput screening of antimicrobial combination therapies using a two-stage transparent machine learning model

Here, we present M2D2, a two-stage machine learning (ML) pipeline that identifies promising antimicrobial drug combinations, which are crucial for combating drug resistance. M2D2 addresses key challenges in drug combination discovery by predicting drug synergies using computationally generated drug-protein interaction data, thereby circumventing the need for expensive omics data. The model improves the accuracy of drug target identification using high-throughput experimental and computational methods via feedback between ML stages. M2D2's transparent framework provides mechanistic insights into drug interactions and was benchmarked against chemogenomics, transcriptomics, and metabolomics datasets. We experimentally validated M2D2 using high-throughput screening of 946 combinations of Food and Drug Administration (FDA)- approved drugs and antibiotics against Escherichia coli . We discovered synergy between a cerebrovascular drug and a widely used penicillin antibiotic and validated predicted mechanisms of action using genome-wide CRISPR inhibition screens. M2D2 offers a transparent ML tool for rapidly designing combination therapies and guides repurposing efforts while providing mechanistic insights.

Analysis of Co-localized Biosynthetic Gene Clusters Identifies a Membrane-Permeabilizing Natural Product

Combination therapy is an effective strategy to combat antibiotic resistance. Multiple synergistic antimicrobial combinations are produced by enzymes encoded in biosynthetic gene clusters (BGCs) that co-localize on the bacterial genome. This phenomenon led to the hypothesis that mining co-localized BGCs will reveal new synergistic combinations of natural products. Here, we bioinformatically identified 38 pairs of co-localized BGCs, which we predict to produce natural products that are related to known compounds, including polycyclic tetramate macrolactams (PoTeMs). We further showed that ikarugamycin, a PoTeM, increases the membrane permeability of Acinetobacter baumannii and Staphylococcus aureus, which suggests that ikarugamycin might be an adjuvant that facilitates the entry of other natural products. Our work outlines a promising avenue to discover synergistic combinations of natural products by mining bacterial genomes.

Hybrid deep learning technique for COX-2 inhibition bioactivity detection against breast cancer disease

This study addresses detecting COX-2 inhibition in breast cancer, targeting its role in tumor growth. The primary goal is to develop an efficient technique for precise COX-2 inhibition bioactivity detection, with implications for identifying anti-cancer compounds and advancing breast cancer therapies. The proposed methodology uses the UNet architecture for feature extraction, enhancing accuracy. A modified chicken swarm optimization (MCSO) algorithm addresses data dimensionality, optimizing features. An improved Laguerre neural network (ILNN) classifies COX-2 inhibition bioactivity. Validation is performed using the ChEMBL database. The research evaluates the accuracy, precision, recall, F-measure, Matthews' correlation coefficient (MCC), and Dice coefficient of the proposed method. These metrics are compared against those of contemporary methods to assess the efficiency and effectiveness of the developed technique. The study underscores the hybrid deep learning method's significance in accurately detecting COX-2 inhibition bioactivity against breast cancer. Results highlight its potential as a valuable tool in breast cancer drug discovery.

Transfer learning predicts species-specific drug interactions in emerging pathogens

Machine learning (ML) algorithms are necessary to efficiently identify potent drug combinations within a large candidate space to combat drug resistance. However, existing ML approaches cannot be applied to emerging and under-studied pathogens with limited training data. To address this, we developed a transfer learning and crowdsourcing framework (TACTIC) to train ML models on data from multiple bacteria. TACTIC was built using 2,965 drug interactions from 12 bacterial strains and outperformed traditional ML models in predicting drug interaction outcomes for species that lack training data. Top TACTIC model features revealed genetic and metabolic factors that influence cross-species and species-specific drug interaction outcomes. Upon analyzing ~600,000 predicted drug interactions across 9 metabolic environments and 18 bacterial strains, we identified a small set of drug interactions that are selectively synergistic against Gram-negative (e.g., A. baumannii) and non-tuberculous mycobacteria (NTM) pathogens. We experimentally validated synergistic drug combinations containing clarithromycin, ampicillin, and mecillinam against M. abscessus, an emerging pathogen with growing levels of antibiotic resistance. Lastly, we leveraged TACTIC to propose selectively synergistic drug combinations to treat bacterial eye infections (endophthalmitis).

Piquing artificial intelligence towards drug discovery: Tools, techniques, and applications

The purpose of this study was to discuss how artificial intelligence (AI) methods have affected the field of drug development. It looks at how AI models and data resources are reshaping the drug development process by offering more affordable and expedient options to conventional approaches. The paper opens with an overview of well-known information sources for drug development. The discussion then moves on to molecular representation techniques that make it possible to convert data into representations that computers can understand. The paper also gives a general overview of the algorithms used in the creation of drug discovery models based on AI. In particular, the paper looks at how AI algorithms might be used to forecast drug toxicity, drug bioactivity, and drug physicochemical properties. De novo drug design, binding affinity prediction, and other AI-based models for drug-target interaction were covered in deeper detail. Modern applications of AI in nanomedicine design and pharmacological synergism/antagonism prediction were also covered. The potential advantages of AI in drug development are highlighted as the evaluation comes to a close. It underlines how AI may greatly speed up and improve the efficiency of drug discovery, resulting in the creation of new and better medicines. To fully realize the promise of AI in drug discovery, the review acknowledges the difficulties that come with its uses in this field and advocates for more study and development.

SynerGNet: A Graph Neural Network Model to Predict Anticancer Drug Synergy

Drug combination therapy shows promise in cancer treatment by addressing drug resistance, reducing toxicity, and enhancing therapeutic efficacy. However, the intricate and dynamic nature of biological systems makes identifying potential synergistic drugs a costly and time-consuming endeavor. To facilitate the development of combination therapy, techniques employing artificial intelligence have emerged as a transformative solution, providing a sophisticated avenue for advancing existing therapeutic approaches. In this study, we developed SynerGNet, a graph neural network model designed to accurately predict the synergistic effect of drug pairs against cancer cell lines. SynerGNet utilizes cancer-specific featured graphs created by integrating heterogeneous biological features into the human protein-protein interaction network, followed by a reduction process to enhance topological diversity. Leveraging synergy data provided by AZ-DREAM Challenges, the model yields a balanced accuracy of 0.68, significantly outperforming traditional machine learning. Encouragingly, augmenting the training data with carefully constructed synthetic instances improved the balanced accuracy of SynerGNet to 0.73. Finally, the results of an independent validation conducted against DrugCombDB demonstrated that it exhibits a strong performance when applied to unseen data. SynerGNet shows a great potential in detecting drug synergy, positioning itself as a valuable tool that could contribute to the advancement of combination therapy for cancer treatment.

RECOVER identifies synergistic drug combinations in vitro through sequential model optimization

For large libraries of small molecules, exhaustive combinatorial chemical screens become infeasible to perform when considering a range of disease models, assay conditions, and dose ranges. Deep learning models have achieved state-of-the-art results in silico for the prediction of synergy scores. However, databases of drug combinations are biased toward synergistic agents and results do not generalize out of distribution. During 5 rounds of experimentation, we employ sequential model optimization with a deep learning model to select drug combinations increasingly enriched for synergism and active against a cancer cell line-evaluating only ∼5% of the total search space. Moreover, we find that learned drug embeddings (using structural information) begin to reflect biological mechanisms. In silico benchmarking suggests search queries are ∼5-10× enriched for highly synergistic drug combinations by using sequential rounds of evaluation when compared with random selection or ∼3× when using a pretrained model.

Confronting antifungal resistance, tolerance, and persistence: Advances in drug target discovery and delivery systems

Human pathogenic fungi pose a serious threat to human health and safety. Unfortunately, the limited number of antifungal options is exacerbated by the continuous emergence of drug-resistant variants, leading to frequent drug treatment failures. Recent studies have also highlighted the clinical importance of other modes of fungal survival of antifungal treatment, including drug tolerance and persistence, pointing to the complexity of the fungal response to antifungal drugs. A lack of understanding of the fungal drug response has hampered the identification of new targets, the development of alternative antifungal strategies and the design of appropriate delivery systems. In this review we summarize recent advances in the study of antifungal resistance, tolerance and persistence, with an emphasis on promising drug targets and drug delivery systems that may yield important insights into the development of new or improved antifungal therapies against fungal infections.

Advances in the Applications of Bioinformatics and Chemoinformatics

Chemoinformatics involves integrating the principles of physical chemistry with computer-based and information science methodologies, commonly referred to as "in silico techniques", in order to address a wide range of descriptive and prescriptive chemistry issues, including applications to biology, drug discovery, and related molecular areas. On the other hand, the incorporation of machine learning has been considered of high importance in the field of drug design, enabling the extraction of chemical data from enormous compound databases to develop drugs endowed with significant biological features. The present review discusses the field of cheminformatics and proposes the use of virtual chemical libraries in virtual screening methods to increase the probability of discovering novel hit chemicals. The virtual libraries address the need to increase the quality of the compounds as well as discover promising ones. On the other hand, various applications of bioinformatics in disease classification, diagnosis, and identification of multidrug-resistant organisms were discussed. The use of ensemble models and brute-force feature selection methodology has resulted in high accuracy rates for heart disease and COVID-19 diagnosis, along with the role of special formulations for targeting meningitis and Alzheimer's disease. Additionally, the correlation between genomic variations and disease states such as obesity and chronic progressive external ophthalmoplegia, the investigation of the antibacterial activity of pyrazole and benzimidazole-based compounds against resistant microorganisms, and its applications in chemoinformatics for the prediction of drug properties and toxicity-all the previously mentioned-were presented in the current review.

Understanding multimorbidity requires sign-disease networks and higher-order interactions, a perspective

Background

Count scores, disease clustering, and pairwise associations between diseases remain ubiquitous in multimorbidity research despite two major shortcomings: they yield no insight into plausible mechanisms underlying multimorbidity, and they ignore higher-order interactions such as effect modification.

Objectives

We argue that two components are currently missing but vital to develop novel multimorbidity metrics. Firstly, networks should be constructed which consists simultaneously of signs, symptoms, and diseases, since only then could they yield insight into plausible shared biological mechanisms underlying diseases.Secondly, learning pairwise associations is insufficient to fully characterize the correlations in a system. That is, synergistic (e.g., cooperative or antagonistic) effects are widespread in complex systems, where two or more elements combined give a larger or smaller effect than the sum of their individual effects. It can even occur that pairs of symptoms have no pairwise associations whatsoever, but in combination have a significant association. Therefore, higher-order interactions should be included in networks used to study multimorbidity, resulting in so-called hypergraphs.

Methods

We illustrate our argument using a synthetic Bayesian Network model of symptoms, signs and diseases, composed of pairwise and higher-order interactions. We simulate network interventions on both individual and population levels and compare the ground-truth outcomes with the predictions from pairwise associations.

Conclusion

We find that, when judged purely from the pairwise associations, interventions can have unexpected 'side-effects' or the most opportune intervention could be missed. The hypergraph uncovers links missed in pairwise networks, giving a more complete overview of sign and disease associations.

New antifungal strategies: drug combination and co-delivery

The growing occurrence of invasive fungal infections and the mounting rates of drug resistance constitute a significant menace to human health. Antifungal drug combinations have garnered substantial interest for their potential to improve therapeutic efficacy, reduce drug doses, reverse, or ameliorate drug resistance. A thorough understanding of the molecular mechanisms underlying antifungal drug resistance and drug combination is key to developing new drug combinations. Here we discuss the mechanisms of antifungal drug resistance and elucidate how to discover potent drug combinations to surmount resistance. We also examine the challenges encountered in developing such combinations and discuss prospects, including advanced drug delivery strategies.

KGANSynergy: knowledge graph attention network for drug synergy prediction

Combination therapy is widely used to treat complex diseases, particularly in patients who respond poorly to monotherapy. For example, compared with the use of a single drug, drug combinations can reduce drug resistance and improve the efficacy of cancer treatment. Thus, it is vital for researchers and society to help develop effective combination therapies through clinical trials. However, high-throughput synergistic drug combination screening remains challenging and expensive in the large combinational space, where an array of compounds are used. To solve this problem, various computational approaches have been proposed to effectively identify drug combinations by utilizing drug-related biomedical information. In this study, considering the implications of various types of neighbor information of drug entities, we propose a novel end-to-end Knowledge Graph Attention Network to predict drug synergy (KGANSynergy), which utilizes neighbor information of known drugs/cell lines effectively. KGANSynergy uses knowledge graph (KG) hierarchical propagation to find multi-source neighbor nodes for drugs and cell lines. The knowledge graph attention network is designed to distinguish the importance of neighbors in a KG through a multi-attention mechanism and then aggregate the entity's neighbor node information to enrich the entity. Finally, the learned drug and cell line embeddings can be utilized to predict the synergy of drug combinations. Experiments demonstrated that our method outperformed several other competing methods, indicating that our method is effective in identifying drug combinations.

A compact review of progress and prospects of deep learning in drug discovery

BACKGROUND

Drug discovery processes, such as new drug development, drug synergy, and drug repurposing, consume significant yearly resources. Computer-aided drug discovery can effectively improve the efficiency of drug discovery. Traditional computer methods such as virtual screening and molecular docking have achieved many gratifying results in drug development. However, with the rapid growth of computer science, data structures have changed considerably; with more extensive and dimensional data and more significant amounts of data, traditional computer methods can no longer be applied well. Deep learning methods are based on deep neural network structures that can handle high-dimensional data very well, so they are used in current drug development.

RESULTS

This review summarized the applications of deep learning methods in drug discovery, such as drug target discovery, drug de novo design, drug recommendation, drug synergy, and drug response prediction. While applying deep learning methods to drug discovery suffers from a lack of data, transfer learning is an excellent solution to this problem. Furthermore, deep learning methods can extract deeper features and have higher predictive power than other machine learning methods. Deep learning methods have great potential in drug discovery and are expected to facilitate drug discovery development.

Predicting Drug Synergy and Discovering New Drug Combinations Based on a Graph Autoencoder and Convolutional Neural Network

Drug synergy is a crucial component in drug reuse since it solves the problem of sluggish drug development and the absence of corresponding drugs for several diseases. Predicting drug synergistic relationships can screen drug combinations in advance and reduce the waste of laboratory resources. In this research, we proposed a model that utilizes graph autoencoder and convolutional neural networks to predict drug synergy (GAECDS). Our methods include a graph convolutional neural network as an encoder to encode drug features and use a matrix factorization method as a decoder. Multilayer perceptron (MLP) was applied to process cell line features and combine them with drug features. Furthermore, the latent vectors generated during the encoding process are being used to predict drug synergistic scores using a convolutional neural network. By measuring prediction performance using AUC, AUPR, and F1 score, GAECDS superior to other state-of-the-art models. In addition, four pairs of the predicted top 10 drug combinations were found to work well enough for evaluation. The case study shows that the GAECDS approach is useful for identifying potential drug synergy.

Artificial intelligence for drug discovery: Resources, methods, and applications

Conventional wet laboratory testing, validations, and synthetic procedures are costly and time-consuming for drug discovery. Advancements in artificial intelligence (AI) techniques have revolutionized their applications to drug discovery. Combined with accessible data resources, AI techniques are changing the landscape of drug discovery. In the past decades, a series of AI-based models have been developed for various steps of drug discovery. These models have been used as complements of conventional experiments and have accelerated the drug discovery process. In this review, we first introduced the widely used data resources in drug discovery, such as ChEMBL and DrugBank, followed by the molecular representation schemes that convert data into computer-readable formats. Meanwhile, we summarized the algorithms used to develop AI-based models for drug discovery. Subsequently, we discussed the applications of AI techniques in pharmaceutical analysis including predicting drug toxicity, drug bioactivity, and drug physicochemical property. Furthermore, we introduced the AI-based models for de novo drug design, drug-target structure prediction, drug-target interaction, and binding affinity prediction. Moreover, we also highlighted the advanced applications of AI in drug synergism/antagonism prediction and nanomedicine design. Finally, we discussed the challenges and future perspectives on the applications of AI to drug discovery.

High-Resolution Bacterial Cytological Profiling Reveals Intrapopulation Morphological Variations upon Antibiotic Exposure

Phenotypic heterogeneity is crucial to bacterial survival and could provide insights into the mechanism of action (MOA) of antibiotics, especially those with polypharmacological actions. Although phenotypic changes among individual cells could be detected by existing profiling methods, due to the data complexity, only population average data were commonly used, thereby overlooking the heterogeneity. In this study, we developed a high-resolution bacterial cytological profiling method that can capture morphological variations of bacteria upon antibiotic treatment. With an unprecedented single-cell resolution, this method classifies morphological changes of individual cells into known MOAs with an overall accuracy above 90%. We next showed that combinations of two antibiotics induce altered cell morphologies that are either unique or similar to that of an antibiotic in the combinations. With these combinatorial profiles, this method successfully revealed multiple cytological changes caused by a natural product-derived compound that, by itself, is inactive against Acinetobacter baumannii but synergistically exerts its multiple antibacterial activities in the presence of colistin. The findings have paved the way for future single-cell profiling in bacteria and have highlighted previously underappreciated intrapopulation variations caused by antibiotic perturbation.

Antibiotic discovery in the artificial intelligence era

As the global burden of antibiotic resistance continues to grow, creative approaches to antibiotic discovery are needed to accelerate the development of novel medicines. A rapidly progressing computational revolution-artificial intelligence-offers an optimistic path forward due to its ability to alleviate bottlenecks in the antibiotic discovery pipeline. In this review, we discuss how advancements in artificial intelligence are reinvigorating the adoption of past antibiotic discovery models-namely natural product exploration and small molecule screening. We then explore the application of contemporary machine learning approaches to emerging areas of antibiotic discovery, including antibacterial systems biology, drug combination development, antimicrobial peptide discovery, and mechanism of action prediction. Lastly, we propose a call to action for open access of high-quality screening datasets and interdisciplinary collaboration to accelerate the rate at which machine learning models can be trained and new antibiotic drugs can be developed.

Drepmel-A Multi-Omics Melanoma Drug Repurposing Resource for Prioritizing Drug Combinations and Understanding Tumor Microenvironment

Although substantial progress has been made in treating patients with advanced melanoma with targeted and immuno-therapies, de novo and acquired resistance is commonplace. After treatment failure, therapeutic options are very limited and novel strategies are urgently needed. Combination therapies are often more effective than single agents and are now widely used in clinical practice. Thus, there is a strong need for a comprehensive computational resource to define rational combination therapies. We developed a Shiny app, DRepMel to provide rational combination treatment predictions for melanoma patients from seventy-three thousand combinations based on a multi-omics drug repurposing computational approach using whole exome sequencing and RNA-seq data in bulk samples from two independent patient cohorts. DRepMel provides robust predictions as a resource and also identifies potential treatment effects on the tumor microenvironment (TME) using single-cell RNA-seq data from melanoma patients. Availability: DRepMel is accessible online.

The past, present, and future of antibiotics

Antibiotics have transformed modern medicine. They are essential for treating infectious diseases and enable vital therapies and procedures. However, despite this success, their continued use in the 21st century is imperiled by two orthogonal challenges. The first is that the microbes targeted by these drugs evolve resistance to them over time. The second is that antibiotic discovery and development are no longer cost-effective using traditional reimbursement models. Consequently, there are a dwindling number of companies and laboratories dedicated to delivering new antibiotics, resulting in an anemic pipeline that threatens our control of infections. The future of antibiotics requires innovation in a field that has relied on highly traditional methods of discovery and development. This will require substantial changes in policy, quantitative understanding of the societal value of these drugs, and investment in alternatives to traditional antibiotics. These include narrow-spectrum drugs, bacteriophage, monoclonal antibodies, and vaccines, coupled with highly effective diagnostics. Addressing the antibiotic crisis to meet our future needs requires considerable investment in both research and development, along with ensuring a viable marketplace that encourages innovation. This review explores the past, present, and future of antimicrobial therapy.

A New Estimation Method for the Biological Interaction Predicting Problems

For the past decades, computational methods have been developed to predict various interactions in biological problems. Usually these methods treated the predicting problems as semi-supervised problem or positive-unlabeled(PU) learning problem. Researchers focused on the prediction of unlabeled samples and hoped to find novel interactions in the datasets they collected. However, most of the computational methods could only predict a small proportion of undiscovered interactions and the total number was unknown. In this paper, we developed an estimation method with deep learning to calculate the number of undiscovered interactions in the unlabeled samples, derived its asymptotic interval estimation, and applied it to the compound synergism dataset, drug-target interaction(DTI) dataset and MicroRNA-disease interaction dataset successfully. Moreover, this method could reveal which dataset contained more undiscovered interactions and would be a guidance for the experimental validation. Furthermore, we compared our method with some mixture proportion estimators and demonstarted the efficacy of our method. Finally, we proved that AUC and AUPR were related with the number of undiscovered interactions, which was regarded as another evaluation indicator for the computational methods.

An enhanced cascade-based deep forest model for drug combination prediction

Combination therapy has shown an obvious curative effect on complex diseases, whereas the search space of drug combinations is too large to be validated experimentally even with high-throughput screens. With the increase of the number of drugs, artificial intelligence techniques, especially machine learning methods, have become applicable for the discovery of synergistic drug combinations to significantly reduce the experimental workload. In this study, in order to predict novel synergistic drug combinations in various cancer cell lines, the cell line-specific drug-induced gene expression profile (GP) is added as a new feature type to capture the cellular response of drugs and reveal the biological mechanism of synergistic effect. Then, an enhanced cascade-based deep forest regressor (EC-DFR) is innovatively presented to apply the new small-scale drug combination dataset involving chemical, physical and biological (GP) properties of drugs and cells. Verified by the dataset, EC-DFR outperforms two state-of-the-art deep neural network-based methods and several advanced classical machine learning algorithms. Biological experimental validation performed subsequently on a set of previously untested drug combinations further confirms the performance of EC-DFR. What is more prominent is that EC-DFR can distinguish the most important features, making it more interpretable. By evaluating the contribution of each feature type, GP feature contributes 82.40%, showing the cellular responses of drugs may play crucial roles in synergism prediction. The analysis based on the top contributing genes in GP further demonstrates some potential relationships between the transcriptomic levels of key genes under drug regulation and the synergism of drug combinations.

From cell lines to cancer patients: personalized drug synergy prediction

MOTIVATION

Combination drug therapies are effective treatments for cancer. However, the genetic heterogeneity of the patients and exponentially large space of drug pairings pose significant challenges for finding the right combination for a specific patient. Current in silico prediction methods can be instrumental in reducing the vast number of candidate drug combinations. However, existing powerful methods are trained with cancer cell line gene expression data, which limits their applicability in clinical settings. While synergy measurements on cell line models are available at large scale, patient-derived samples are too few to train a complex model. On the other hand, patient-specific single-drug response data are relatively more available.

RESULTS

In this work, we propose a deep learning framework, Personalized Deep Synergy Predictor (PDSP), that enables us to use the patient-specific single drug response data for customizing patient drug synergy predictions. PDSP is first trained to learn synergy scores of drug pairs and their single drug responses for a given cell line using drug structures and large scale cell line gene expression data. Then, the model is fine-tuned for patients with their patient gene expression data and associated single drug response measured on the patient ex vivo samples. In this study, we evaluate PDSP on data from three leukemia patients and observe that it improves the prediction accuracy by 27% compared to models trained on cancer cell line data.

AVAILABILITY AND IMPLEMENTATION

PDSP is available at https://github.com/hikuru/PDSP.

Prediction of synergistic drug combinations using PCA-initialized deep learning

Background

Cancer is one of the main causes of death worldwide. Combination drug therapy has been a mainstay of cancer treatment for decades and has been shown to reduce host toxicity and prevent the development of acquired drug resistance. However, the immense number of possible drug combinations and large synergistic space makes it infeasible to screen all effective drug pairs experimentally. Therefore, it is crucial to develop computational approaches to predict drug synergy and guide experimental design for the discovery of rational combinations for therapy.

Results

We present a new deep learning approach to predict synergistic drug combinations by integrating gene expression profiles from cell lines and chemical structure data. Specifically, we use principal component analysis (PCA) to reduce the dimensionality of the chemical descriptor data and gene expression data. We then propagate the low-dimensional data through a neural network to predict drug synergy values. We apply our method to O’Neil’s high-throughput drug combination screening data as well as a dataset from the AstraZeneca-Sanger Drug Combination Prediction DREAM Challenge. We compare the neural network approach with and without dimension reduction. Additionally, we demonstrate the effectiveness of our deep learning approach and compare its performance with three state-of-the-art machine learning methods: Random Forests, XGBoost, and elastic net, with and without PCA-based dimensionality reduction.

Conclusions

Our developed approach outperforms other machine learning methods, and the use of dimension reduction dramatically decreases the computation time without sacrificing accuracy.

GraphSynergy: a network-inspired deep learning model for anticancer drug combination prediction

OBJECTIVE

To develop an end-to-end deep learning framework based on a protein-protein interaction (PPI) network to make synergistic anticancer drug combination predictions.

MATERIALS AND METHODS

We propose a deep learning framework named Graph Convolutional Network for Drug Synergy (GraphSynergy). GraphSynergy adapts a spatial-based Graph Convolutional Network component to encode the high-order topological relationships in the PPI network of protein modules targeted by a pair of drugs, as well as the protein modules associated with a specific cancer cell line. The pharmacological effects of drug combinations are explicitly evaluated by their therapy and toxicity scores. An attention component is also introduced in GraphSynergy, which aims to capture the pivotal proteins that play a part in both PPI network and biomolecular interactions between drug combinations and cancer cell lines.

RESULTS

GraphSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the 2 latest drug combination datasets. Specifically, GraphSynergy achieves accuracy values of 0.7553 (11.94% improvement compared to DeepSynergy, the latest published drug combination prediction algorithm) and 0.7557 (10.95% improvement compared to DeepSynergy) on DrugCombDB and Oncology-Screen datasets, respectively. Furthermore, the proteins allocated with high contribution weights during the training of GraphSynergy are proved to play a role in view of molecular functions and biological processes, such as transcription and transcription regulation.

CONCLUSION

The introduction of topological relations between drug combination and cell line within the PPI network can significantly improve the capability of synergistic drug combination identification.

Machine learning applications for therapeutic tasks with genomics data

Thanks to the increasing availability of genomics and other biomedical data, many machine learning algorithms have been proposed for a wide range of therapeutic discovery and development tasks. In this survey, we review the literature on machine learning applications for genomics through the lens of therapeutic development. We investigate the interplay among genomics, compounds, proteins, electronic health records, cellular images, and clinical texts. We identify 22 machine learning in genomics applications that span the whole therapeutics pipeline, from discovering novel targets, personalizing medicine, developing gene-editing tools, all the way to facilitating clinical trials and post-market studies. We also pinpoint seven key challenges in this field with potentials for expansion and impact. This survey examines recent research at the intersection of machine learning, genomics, and therapeutic development.

Deep learning identifies synergistic drug combinations for treating COVID-19

Effective treatments for COVID-19 are urgently needed. However, discovering single-agent therapies with activity against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been challenging. Combination therapies play an important role in antiviral therapies, due to their improved efficacy and reduced toxicity. Recent approaches have applied deep learning to identify synergistic drug combinations for diseases with vast preexisting datasets, but these are not applicable to new diseases with limited combination data, such as COVID-19. Given that drug synergy often occurs through inhibition of discrete biological targets, here we propose a neural network architecture that jointly learns drug-target interaction and drug-drug synergy. The model consists of two parts: a drug-target interaction module and a target-disease association module. This design enables the model to utilize drug-target interaction data and single-agent antiviral activity data, in addition to available drug-drug combination datasets, which may be small in nature. By incorporating additional biological information, our model performs significantly better in synergy prediction accuracy than previous methods with limited drug combination training data. We empirically validated our model predictions and discovered two drug combinations, remdesivir and reserpine as well as remdesivir and IQ-1S, which display strong antiviral SARS-CoV-2 synergy in vitro. Our approach, which was applied here to address the urgent threat of COVID-19, can be readily extended to other diseases for which a dearth of chemical-chemical combination data exists.

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 in the prediction of cancer therapy

Resistance to therapy remains a major cause of cancer treatment failures, resulting in many cancer-related deaths. Resistance can occur at any time during the treatment, even at the beginning. The current treatment plan is dependent mainly on cancer subtypes and the presence of genetic mutations. Evidently, the presence of a genetic mutation does not always predict the therapeutic response and can vary for different cancer subtypes. Therefore, there is an unmet need for predictive models to match a cancer patient with a specific drug or drug combination. Recent advancements in predictive models using artificial intelligence have shown great promise in preclinical settings. However, despite massive improvements in computational power, building clinically useable models remains challenging due to a lack of clinically meaningful pharmacogenomic data. In this review, we provide an overview of recent advancements in therapeutic response prediction using machine learning, which is the most widely used branch of artificial intelligence. We describe the basics of machine learning algorithms, illustrate their use, and highlight the current challenges in therapy response prediction for clinical practice.

Integration and interplay of machine learning and bioinformatics approach to identify genetic interaction related to ovarian cancer chemoresistance

Although chemotherapy is the first-line treatment for ovarian cancer (OCa) patients, chemoresistance (CR) decreases their progression-free survival. This paper investigates the genetic interaction (GI) related to OCa-CR. To decrease the complexity of establishing gene networks, individual signature genes related to OCa-CR are identified using a gradient boosting decision tree algorithm. Additionally, the genetic interaction coefficient (GIC) is proposed to measure the correlation of two signature genes quantitatively and explain their joint influence on OCa-CR. Gene pair that possesses high GIC is identified as signature pair. A total of 24 signature gene pairs are selected that include 10 individual signature genes and the influence of signature gene pairs on OCa-CR is explored. Finally, a signature gene pair-based prediction of OCa-CR is identified. The area under curve (AUC) is a widely used performance measure for machine learning prediction. The AUC of signature gene pair reaches 0.9658, whereas the AUC of individual signature gene-based prediction is 0.6823 only. The identified signature gene pairs not only build an efficient GI network of OCa-CR but also provide an interesting way for OCa-CR prediction. This improvement shows that our proposed method is a useful tool to investigate GI related to OCa-CR.

Systems-Level Chemical Biology to Accelerate Antibiotic Drug Discovery

Drug-resistant bacterial infections pose an imminent and growing threat to public health. The discovery and development of new antibiotics of novel chemical class and mode of action that are unsusceptible to existing resistance mechanisms is imperative for tackling this threat. Modern industrial drug discovery, however, has failed to provide new drugs of this description, as it is dependent largely on a reductionist genes-to-drugs research paradigm. We posit that the lack of success in new antibiotic drug discovery is due in part to a lack of understanding of the bacterial cell system as whole. A fundamental understanding of the architecture and function of bacterial systems has been elusive but is of critical importance to design strategies to tackle drug-resistant bacterial pathogens.Increasingly, systems-level approaches are rewriting our understanding of the cell, defining a dense network of redundant and interacting components that resist perturbations of all kinds, including by antibiotics. Understanding the network properties of bacterial cells requires integrative, systematic, and genome-scale approaches. These methods strive to understand how the phenotypic behavior of bacteria emerges from the many interactions of individual molecular components that constitute the system. With the ability to examine genomic, transcriptomic, proteomic, and metabolomic consequences of, for example, genetic or chemical perturbations, researchers are increasingly moving away from one-gene-at-a-time studies to consider the system-wide response of the cell. Such measurements are demonstrating promise as quantitative tools, powerful discovery engines, and robust hypothesis generators with great value to antibiotic drug discovery.In this Account, we describe our thinking and findings using systems-level studies aimed at understanding bacterial physiology broadly and in uncovering new antibacterial chemical matter of novel mechanism. We share our systems-level toolkit and detail recent technological developments that have enabled unprecedented acquisition of genome-wide interaction data. We focus on three types of interactions: gene-gene, chemical-gene, and chemical-chemical. We provide examples of their use in understanding cell networks and how these insights might be harnessed for new antibiotic discovery. By example, we show the application of these principles in mapping genetic networks that underpin phenotypes of interest, characterizing genes of unknown function, validating small-molecule screening platforms, uncovering novel chemical probes and antibacterial leads, and delineating the mode of action of antibacterial chemicals. We also discuss the importance of computation to these approaches and its probable dominance as a tool for systems approaches in the future. In all, we advocate for the use of systems-based approaches as discovery engines in antibacterial research, both as powerful tools and to stimulate innovation.

Incorporating Machine Learning into Established Bioinformatics Frameworks

The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.

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.

Leveraging multi-way interactions for systematic prediction of pre-clinical drug combination effects

We present comboFM, a machine learning framework for predicting the responses of drug combinations in pre-clinical studies, such as those based on cell lines or patient-derived cells. comboFM models the cell context-specific drug interactions through higher-order tensors, and efficiently learns latent factors of the tensor using powerful factorization machines. The approach enables comboFM to leverage information from previous experiments performed on similar drugs and cells when predicting responses of new combinations in so far untested cells; thereby, it achieves highly accurate predictions despite sparsely populated data tensors. We demonstrate high predictive performance of comboFM in various prediction scenarios using data from cancer cell line pharmacogenomic screens. Subsequent experimental validation of a set of previously untested drug combinations further supports the practical and robust applicability of comboFM. For instance, we confirm a novel synergy between anaplastic lymphoma kinase (ALK) inhibitor crizotinib and proteasome inhibitor bortezomib in lymphoma cells. Overall, our results demonstrate that comboFM provides an effective means for systematic pre-screening of drug combinations to support precision oncology applications.

Combinatorial treatments have become a standard of care for various complex diseases including cancers. Here, the authors show that combinatorial responses of two anticancer drugs can be accurately predicted using factorization machines trained on large-scale pharmacogenomic data for guiding precision oncology studies.

Advances in fungal chemical genomics for the discovery of new antifungal agents

Invasive fungal infections have escalated from a rare curiosity to a major cause of human mortality around the globe. This is in part due to a scarcity in the number of antifungal drugs available to combat mycotic disease, making the discovery of novel bioactive compounds and determining their mode of action of utmost importance. The development and application of chemical genomic assays using the model yeast Saccharomyces cerevisiae has provided powerful methods to identify the mechanism of action of diverse molecules in a living cell. Furthermore, complementary assays are continually being developed in fungal pathogens, most notably Candida albicans and Cryptococcus neoformans, to elucidate compound mechanism of action directly in the pathogen of interest. Collectively, the suite of chemical genetic assays that have been developed in multiple fungal species enables the identification of candidate drug target genes, as well as genes involved in buffering drug target pathways, and genes involved in general cellular responses to small molecules. In this review, we examine current yeast chemical genomic assays and highlight how such resources provide powerful tools that can be utilized to bolster the antifungal pipeline.

TAIJI: approaching experimental replicates-level accuracy for drug synergy prediction

MOTIVATION

Combination therapy is widely used in cancer treatment to overcome drug resistance. High-throughput drug screening is the standard approach to study the drug combination effects, yet it becomes impractical when the number of drugs under consideration is large. Therefore, accurate and fast computational tools for predicting drug synergistic effects are needed to guide experimental design for developing candidate drug pairs.

RESULTS

Here, we present TAIJI, a high-performance software for fast and accurate prediction of drug synergism. It is based on the winning algorithm in the AstraZeneca-Sanger Drug Combination Prediction DREAM Challenge, which is a unique platform to unbiasedly evaluate the performance of current state-of-the-art methods, and includes 160 team-based submission methods. When tested across a broad spectrum of 85 different cancer cell lines and 1089 drug combinations, TAIJI achieved a high prediction correlation (0.53), approaching the accuracy level of experimental replicates (0.56). The runtime is at the scale of minutes to achieve this state-of-the-field performance.

AVAILABILITY AND IMPLEMENTATION

TAIJI is freely available on GitHub (https://github.com/GuanLab/TAIJI). It is functional with built-in Perl and Python.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Synergistic and antagonistic drug interactions in the treatment of systemic fungal infections

Invasive fungal infections cause 1.6 million deaths annually, primarily in immunocompromised individuals. Mortality rates are as high as 90% due to limited treatments. The azole class antifungal, fluconazole, is widely available and has multi-species activity but only inhibits growth instead of killing fungal cells, necessitating long treatments. To improve treatment, we used our novel high-throughput method, the overlap² method (O2M) to identify drugs that interact with fluconazole, either increasing or decreasing efficacy. We identified 40 molecules that act synergistically (amplify activity) and 19 molecules that act antagonistically (decrease efficacy) when combined with fluconazole. We found that critical frontline beta-lactam antibiotics antagonize fluconazole activity. A promising fluconazole-synergizing anticholinergic drug, dicyclomine, increases fungal cell permeability and inhibits nutrient intake when combined with fluconazole. In vivo, this combination doubled the time-to-endpoint of mice with Cryptococcus neoformans meningitis. Thus, our ability to rapidly identify synergistic and antagonistic drug interactions can potentially alter the patient outcomes.

Individuals with weakened immune systems – such as recipients of organ transplants – can fall prey to illnesses caused by fungi that are harmless to most people. These infections are difficult to manage because few treatments exist to fight fungi, and many have severe side effects. Antifungal drugs usually slow the growth of fungi cells rather than kill them, which means that patients must remain under treatment for a long time, or even for life.

One way to boost efficiency and combat resistant infections is to combine antifungal treatments with drugs that work in complementary ways: the drugs strengthen each other’s actions, and together they can potentially kill the fungus rather than slow its progression. However, not all drug combinations are helpful. In fact, certain drugs may interact in ways that make treatment less effective. This is particularly concerning because people with weakened immune systems often take many types of medications.

Here, Wambaugh et al. harnessed a new high-throughput system to screen how 2,000 drugs (many of which already approved to treat other conditions) affected the efficiency of a common antifungal called fluconazole. This highlighted 19 drugs that made fluconazole less effective, some being antibiotics routinely used to treat patients with weakened immune systems.

On the other hand, 40 drugs boosted the efficiency of fluconazole, including dicyclomine, a compound currently used to treat inflammatory bowel syndrome. In fact, pairing dicyclomine and fluconazole more than doubled the survival rate of mice with severe fungal infections. The combined treatment could target many species of harmful fungi, even those that had become resistant to fluconazole alone.

The results by Wambaugh et al. point towards better treatments for individuals with serious fungal infections. Drugs already in circulation for other conditions could be used to boost the efficiency of fluconazole, while antibiotics that do not decrease the efficiency of this medication should be selected to treat at-risk patients.

A Point of Inflection and Reflection on Systems Chemical Biology

For the past several decades, chemical biologists have been leveraging chemical principles for understanding biology, tackling disease, and biomanufacturing, while systems biologists have holistically applied computation and genome-scale experimental tools to the same problems. About a decade ago, the benefit of combining the philosophies of chemical biology with systems biology into systems chemical biology was advocated, with the potential to systematically understand the way small molecules affect biological systems. Recently, there has been an explosion in new technologies that permit massive expansion in the scale of biological experimentation, increase access to more diverse chemical space, and enable powerful computational interpretation of large datasets. Fueled by these rapidly increasing capabilities, systems chemical biology is now at an inflection point, poised to enter a new era of more holistic and integrated scientific discovery. Systems chemical biology is primed to reveal an integrated understanding of fundamental biology and to discover new chemical probes to comprehensively dissect and systematically understand that biology, thereby providing a path to novel strategies for discovering therapeutics, designing drug combinations, avoiding toxicity, and harnessing beneficial polypharmacology. In this Review, we examine the emergence of new capabilities driving us to this inflection point in systems chemical biology, and highlight holistic approaches and opportunities that are arising from integrating chemical biology with a systems-level understanding of the intersection of biology and chemistry.

Retro-2 protects cells from ricin toxicity by inhibiting ASNA1-mediated ER targeting and insertion of tail-anchored proteins

The small molecule Retro-2 prevents ricin toxicity through a poorly-defined mechanism of action (MOA), which involves halting retrograde vesicle transport to the endoplasmic reticulum (ER). CRISPRi genetic interaction analysis revealed Retro-2 activity resembles disruption of the transmembrane domain recognition complex (TRC) pathway, which mediates post-translational ER-targeting and insertion of tail-anchored (TA) proteins, including SNAREs required for retrograde transport. Cell-based and in vitro assays show that Retro-2 blocks delivery of newly-synthesized TA-proteins to the ER-targeting factor ASNA1 (TRC40). An ASNA1 point mutant identified using CRISPR-mediated mutagenesis abolishes both the cytoprotective effect of Retro-2 against ricin and its inhibitory effect on ASNA1-mediated ER-targeting. Together, our work explains how Retro-2 prevents retrograde trafficking of toxins by inhibiting TA-protein targeting, describes a general CRISPR strategy for predicting the MOA of small molecules, and paves the way for drugging the TRC pathway to treat broad classes of viruses known to be inhibited by Retro-2.

Network inference performance complexity: a consequence of topological, experimental and algorithmic determinants

MOTIVATION

Network inference algorithms aim to uncover key regulatory interactions governing cellular decision-making, disease progression and therapeutic interventions. Having an accurate blueprint of this regulation is essential for understanding and controlling cell behavior. However, the utility and impact of these approaches are limited because the ways in which various factors shape inference outcomes remain largely unknown.

RESULTS

We identify and systematically evaluate determinants of performance-including network properties, experimental design choices and data processing-by developing new metrics that quantify confidence across algorithms in comparable terms. We conducted a multifactorial analysis that demonstrates how stimulus target, regulatory kinetics, induction and resolution dynamics, and noise differentially impact widely used algorithms in significant and previously unrecognized ways. The results show how even if high-quality data are paired with high-performing algorithms, inferred models are sometimes susceptible to giving misleading conclusions. Lastly, we validate these findings and the utility of the confidence metrics using realistic in silico gene regulatory networks. This new characterization approach provides a way to more rigorously interpret how algorithms infer regulation from biological datasets.

AVAILABILITY AND IMPLEMENTATION

Code is available at http://github.com/bagherilab/networkinference/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Using BEAN-counter to quantify genetic interactions from multiplexed barcode sequencing experiments

The construction of genome-wide mutant collections has enabled high-throughput, high-dimensional quantitative characterization of gene and chemical function, particularly via genetic and chemical-genetic interaction experiments. As the throughput of such experiments increases with improvements in sequencing technology and sample multiplexing, appropriate tools must be developed to handle the large volume of data produced. Here, we describe how to apply our approach to high-throughput, fitness-based profiling of pooled mutant yeast collections using the BEAN-counter software pipeline (Barcoded Experiment Analysis for Next-generation sequencing) for analysis. The software has also successfully processed data from Schizosaccharomyces pombe, Escherichia coli, and Zymomonas mobilis mutant collections. We provide general recommendations for the design of large-scale, multiplexed barcode sequencing experiments. The procedure outlined here was used to score interactions for ~4 million chemical-by-mutant combinations in our recently published chemical-genetic interaction screen of nearly 14,000 chemical compounds across seven diverse compound collections. Here we selected a representative subset of these data on which to demonstrate our analysis pipeline. BEAN-counter is open source, written in Python, and freely available for academic use. Users should be proficient at the command line; advanced users who wish to analyze larger datasets with hundreds or more conditions should also be familiar with concepts in analysis of high-throughput biological data. BEAN-counter encapsulates the knowledge we have accumulated from, and successfully applied to, our multiplexed, pooled barcode sequencing experiments. This protocol will be useful to those interested in generating their own high-dimensional, quantitative characterizations of gene or chemical function in a high-throughput manner.

Drug combinations: a strategy to extend the life of antibiotics in the 21st century

Antimicrobial resistance threatens a resurgence of life-threatening bacterial infections and the potential demise of many aspects of modern medicine. Despite intensive drug discovery efforts, no new classes of antibiotics have been developed into new medicines for decades, in large part owing to the stringent chemical, biological and pharmacological requisites for effective antibiotic drugs. Combinations of antibiotics and of antibiotics with non-antibiotic activity-enhancing compounds offer a productive strategy to address the widespread emergence of antibiotic-resistant strains. In this Review, we outline a theoretical and practical framework for the development of effective antibiotic combinations.

Synthetic lethal combinations of low-toxicity drugs for breast cancer identified in silico by genetic screens in yeast

In recent years, the concept of synthetic lethality, describing a cellular state where loss of two genes leads to a non-viable phenotype while loss of one gene can be compensated, has emerged as a novel strategy for cancer therapy. Various compounds targeting synthetic lethal pathways are either under clinical investigation or are already routinely used in multiple cancer entities such as breast cancer. Most of them target the well-described synthetic lethal interplay between PARP1 and BRCA1/2. In our study, we investigated, using an in silico methodological approach, clinically utilized drug combinations for breast cancer treatment, by correlating their known molecular targets with known homologous interaction partners that cause synthetic lethality in yeast. Further, by creating a machine-learning algorithm, we were able to suggest novel synthetic lethal drug combinations of low-toxicity drugs in breast cancer and showed their negative effects on cancer cell viability in vitro. Our findings foster the understanding of evolutionarily conserved synthetic lethality in breast cancer cells and might lead to new drug combinations with favorable toxicity profile in this entity.

Predicting bioprocess targets of chemical compounds through integration of chemical-genetic and genetic interactions

Chemical-genetic interactions–observed when the treatment of mutant cells with chemical compounds reveals unexpected phenotypes–contain rich functional information linking compounds to their cellular modes of action. To systematically identify these interactions, an array of mutants is challenged with a compound and monitored for fitness defects, generating a chemical-genetic interaction profile that provides a quantitative, unbiased description of the cellular function(s) perturbed by the compound. Genetic interactions, obtained from genome-wide double-mutant screens, provide a key for interpreting the functional information contained in chemical-genetic interaction profiles. Despite the utility of this approach, integrative analyses of genetic and chemical-genetic interaction networks have not been systematically evaluated. We developed a method, called CG-TARGET (Chemical Genetic Translation via A Reference Genetic nETwork), that integrates large-scale chemical-genetic interaction screening data with a genetic interaction network to predict the biological processes perturbed by compounds. In a recent publication, we applied CG-TARGET to a screen of nearly 14,000 chemical compounds in Saccharomyces cerevisiae, integrating this dataset with the global S. cerevisiae genetic interaction network to prioritize over 1500 compounds with high-confidence biological process predictions for further study. We present here a formal description and rigorous benchmarking of the CG-TARGET method, showing that, compared to alternative enrichment-based approaches, it achieves similar or better accuracy while substantially improving the ability to control the false discovery rate of biological process predictions. Additional investigation of the compatibility of chemical-genetic and genetic interaction profiles revealed that one-third of observed chemical-genetic interactions contributed to the highest-confidence biological process predictions and that negative chemical-genetic interactions overwhelmingly formed the basis of these predictions. We also present experimental validations of CG-TARGET-predicted tubulin polymerization and cell cycle progression inhibitors. Our approach successfully demonstrates the use of genetic interaction networks in the high-throughput functional annotation of compounds to biological processes.

Understanding how chemical compounds affect biological systems is of paramount importance as pharmaceutical companies strive to develop life-saving medicines, governments seek to regulate the safety of consumer products and agrichemicals, and basic scientists continue to study the fundamental inner workings of biological organisms. One powerful approach to characterize the effects of chemical compounds in living cells is chemical-genetic interaction screening. Using this approach, a collection of cells–each with a different defined genetic perturbation–is tested for sensitivity or resistance to the presence of a compound, resulting in a quantitative profile describing the functional effects of that compound on the cells. The work presented here describes our efforts to integrate compounds’ chemical-genetic interaction profiles with reference genetic interaction profiles containing information on gene function to predict the cellular processes perturbed by the compounds. We focused on specifically developing a method that could scale to perform these functional predictions for large collections of thousands of screened compounds and robustly control the false discovery rate. With chemical-genetic and genetic interaction screens now underway in multiple species including human cells, the method described here can be generally applied to enable the characterization of compounds’ effects across the tree of life.

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.

Machine Learning in Agriculture: A Review

Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems. The works analyzed were categorized in (a) crop management, including applications on yield prediction, disease detection, weed detection crop quality, and species recognition; (b) livestock management, including applications on animal welfare and livestock production; (c) water management; and (d) soil management. The filtering and classification of the presented articles demonstrate how agriculture will benefit from machine learning technologies. By applying machine learning to sensor data, farm management systems are evolving into real time artificial intelligence enabled programs that provide rich recommendations and insights for farmer decision support and action.

Species-specific activity of antibacterial drug combinations

The spread of antimicrobial resistance has become a serious public health concern, making once-treatable diseases deadly again and undermining the achievements of modern medicine^1,2. Drug combinations can help to fight multi-drug-resistant bacterial infections, yet they are largely unexplored and rarely used in clinics. Here we profile almost 3,000 dose-resolved combinations of antibiotics, human-targeted drugs and food additives in six strains from three Gram-negative pathogens-Escherichia coli, Salmonella enterica serovar Typhimurium and Pseudomonas aeruginosa-to identify general principles for antibacterial drug combinations and understand their potential. Despite the phylogenetic relatedness of the three species, more than 70% of the drug-drug interactions that we detected are species-specific and 20% display strain specificity, revealing a large potential for narrow-spectrum therapies. Overall, antagonisms are more common than synergies and occur almost exclusively between drugs that target different cellular processes, whereas synergies are more conserved and are enriched in drugs that target the same process. We provide mechanistic insights into this dichotomy and further dissect the interactions of the food additive vanillin. Finally, we demonstrate that several synergies are effective against multi-drug-resistant clinical isolates in vitro and during infections of the larvae of the greater wax moth Galleria mellonella, with one reverting resistance to the last-resort antibiotic colistin.

High-throughput Identification of Synergistic Drug Combinations by the Overlap2 Method

Although antimicrobial drugs have dramatically increased the lifespan and quality of life in the 20^th century, antimicrobial resistance threatens our entire society's ability to treat systemic infections. In the United States alone, antibiotic-resistant infections kill approximately 23,000 people a year and cost around 20 billion USD in additional healthcare. One approach to combat antimicrobial resistance is combination therapy, which is particularly useful in the critical early stage of infection, before the infecting organism and its drug resistance profile have been identified. Many antimicrobial treatments use combination therapies. However, most of these combinations are additive, meaning that the combined efficacy is the same as the sum of the individual antibiotic efficacy. Some combination therapies are synergistic: the combined efficacy is much greater than additive. Synergistic combinations are particularly useful because they can inhibit the growth of antimicrobial drug resistant strains. However, these combinations are rare and difficult to identify. This is due to the sheer number of molecules needed to be tested in a pairwise manner: a library of 1,000 molecules has 1 million potential combinations. Thus, efforts have been made to predict molecules for synergy. This article describes our high-throughput method for predicting synergistic small molecule pairs known as the Overlap² Method (O2M). O2M uses patterns from chemical-genetic datasets to identify mutants that are hypersensitive to each molecule in a synergistic pair but not to other molecules. The Brown lab exploits this growth difference by performing a high-throughput screen for molecules that inhibit the growth of mutant but not wild-type cells. The lab's work previously identified molecules that synergize with the antibiotic trimethoprim and the antifungal drug fluconazole using this strategy. Here, the authors present a method to screen for novel synergistic combinations, which can be altered for multiple microorganisms.