Prediction of synergistic drug combinations

Scaling up drug combination surface prediction

Drug combinations are required to treat advanced cancers and other complex diseases. Compared with monotherapy, combination treatments can enhance efficacy and reduce toxicity by lowering the doses of single drugs-and there especially synergistic combinations are of interest. Since drug combination screening experiments are costly and time-consuming, reliable machine learning models are needed for prioritizing potential combinations for further studies. Most of the current machine learning models are based on scalar-valued approaches, which predict individual response values or synergy scores for drug combinations. We take a functional output prediction approach, in which full, continuous dose-response combination surfaces are predicted for each drug combination on the cell lines. We investigate the predictive power of the recently proposed comboKR method, which is based on a powerful input-output kernel regression technique and functional modeling of the response surface. In this work, we develop a scaled-up formulation of the comboKR, which also implements improved modeling choices: we (1) incorporate new modeling choices for the output drug combination response surfaces to the comboKR framework, and (2) propose a projected gradient descent method to solve the challenging pre-image problem that is traditionally solved with simple candidate set approaches. We provide thorough experimental analysis of comboKR 2.0 with three real-word datasets within various challenging experimental settings, including cases where drugs or cell lines have not been encountered in the training data. Our comparison with synergy score prediction methods further highlights the relevance of dose-response prediction approaches, instead of relying on simple scoring methods.

Role of artificial intelligence in early diagnosis and treatment of infectious diseases

Infectious diseases remain a global health challenge, necessitating innovative approaches for their early diagnosis and effective treatment. Artificial Intelligence (AI) has emerged as a transformative force in healthcare, offering promising solutions to address this challenge. This review article provides a comprehensive overview of the pivotal role AI can play in the early diagnosis and treatment of infectious diseases. It explores how AI-driven diagnostic tools, including machine learning algorithms, deep learning, and image recognition systems, enhance the accuracy and efficiency of disease detection and surveillance. Furthermore, it delves into the potential of AI to predict disease outbreaks, optimise treatment strategies, and personalise interventions based on individual patient data and how AI can be used to gear up the drug discovery and development (D3) process.The ethical considerations, challenges, and limitations associated with the integration of AI in infectious disease management are also examined. By harnessing the capabilities of AI, healthcare systems can significantly improve their preparedness, responsiveness, and outcomes in the battle against infectious diseases.

The synthesis, thermal behaviour, spectral and structural characterization, and in silico prediction of pharmacokinetic parameters of tetraalkylammonium salts of non-steroidal anti-inflammatory drug nimesulide

The synthesis, spectral properties, thermal analysis, structural characterization and in silico prediction of pharmacokinetic parameters of tetramethylammonium (compound 1) and tetraethylammonium (compound 2) salt of nimesulide were described in this article. Both compounds crystallize in the monoclinic P21/n space group, with one tetraalkylammonium cation and one nimesulide anion in the asymmetric unit and their crystal structures are stabilized by C-H···O hydrogen bonds between ions. Additionally, structures of title compounds are stabilized by π-π interactions (compound 1), or C-H···π interactions (compound 2) between nimesulide anions. The TG and DSC measurements show that compound 1 melts at a temperature higher than nimesulide, whereas the compound 2 melts at a temperature lower than nimesulide. The MALDI-TOF, 1H NMR, 13C NMR and ATR-FTIR analyses confirm the SCXRD study, that in compounds 1 and 2 nimesulide exists in an ionized form. Studies performed by SWISS ADME and ProTOX II tools, predict to be oral bioavailability of both salts obtained, and one of them (compound 1) is predicted to be well-absorbed by digestive system, while both compounds obtained are classified into toxicity class 4.

[Application areas of artificial intelligence in the context of One Health with a focus on antimicrobial resistance]

Societal health is facing a number of new challenges, largely driven by ongoing climate change, demographic ageing, and globalization. The One Health approach links human, animal, and environmental sectors with the goal of achieving a holistic understanding of health in general. To implement this approach, diverse and heterogeneous data streams and types must be combined and analyzed. To this end, artificial intelligence (AI) techniques offer new opportunities for cross-sectoral assessment of current and future health threats. Using the example of antimicrobial resistance as a global threat in the One Health context, we demonstrate potential applications and challenges of AI techniques.This article provides an overview of different applications of AI techniques in the context of One Health and highlights their challenges. Using the spread of antimicrobial resistance (AMR), an increasing global threat, as an example, existing and future AI-based approaches to AMR containment and prevention are described. These range from novel drug development and personalized therapy, to targeted monitoring of antibiotic use in livestock and agriculture, to comprehensive environmental surveillance.

Artificial Intelligence for Antimicrobial Resistance Prediction: Challenges and Opportunities towards Practical Implementation

Antimicrobial resistance (AMR) is emerging as a potential threat to many lives worldwide. It is very important to understand and apply effective strategies to counter the impact of AMR and its mutation from a medical treatment point of view. The intersection of artificial intelligence (AI), especially deep learning/machine learning, has led to a new direction in antimicrobial identification. Furthermore, presently, the availability of huge amounts of data from multiple sources has made it more effective to use these artificial intelligence techniques to identify interesting insights into AMR genes such as new genes, mutations, drug identification, conditions favorable to spread, and so on. Therefore, this paper presents a review of state-of-the-art challenges and opportunities. These include interesting input features posing challenges in use, state-of-the-art deep-learning/machine-learning models for robustness and high accuracy, challenges, and prospects to apply these techniques for practical purposes. The paper concludes with the encouragement to apply AI to the AMR sector with the intention of practical diagnosis and treatment, since presently most studies are at early stages with minimal application in the practice of diagnosis and treatment of disease.

Disrupting the ArcA Regulatory Network Amplifies the Fitness Cost of Tetracycline Resistance in Escherichia coli

There is an urgent need for strategies to discover secondary drugs to prevent or disrupt antimicrobial resistance (AMR), which is causing >700,000 deaths annually. Here, we demonstrate that tetracycline-resistant (TetR) Escherichia coli undergoes global transcriptional and metabolic remodeling, including downregulation of tricarboxylic acid cycle and disruption of redox homeostasis, to support consumption of the proton motive force for tetracycline efflux. Using a pooled genome-wide library of single-gene deletion strains, at least 308 genes, including four transcriptional regulators identified by our network analysis, were confirmed as essential for restoring the fitness of TetR E. coli during treatment with tetracycline. Targeted knockout of ArcA, identified by network analysis as a master regulator of this new compensatory physiological state, significantly compromised fitness of TetR E. coli during tetracycline treatment. A drug, sertraline, which generated a similar metabolome profile as the arcA knockout strain, also resensitized TetR E. coli to tetracycline. We discovered that the potentiating effect of sertraline was eliminated upon knocking out arcA, demonstrating that the mechanism of potential synergy was through action of sertraline on the tetracycline-induced ArcA network in the TetR strain. Our findings demonstrate that therapies that target mechanistic drivers of compensatory physiological states could resensitize AMR pathogens to lost antibiotics. IMPORTANCE Antimicrobial resistance (AMR) is projected to be the cause of >10 million deaths annually by 2050. While efforts to find new potent antibiotics are effective, they are expensive and outpaced by the rate at which new resistant strains emerge. There is desperate need for a rational approach to accelerate the discovery of drugs and drug combinations that effectively clear AMR pathogens and even prevent the emergence of new resistant strains. Using tetracycline-resistant (TetR) Escherichia coli, we demonstrate that gaining resistance is accompanied by loss of fitness, which is restored by compensatory physiological changes. We demonstrate that transcriptional regulators of the compensatory physiologic state are promising drug targets because their disruption increases the susceptibility of TetR E. coli to tetracycline. Thus, we describe a generalizable systems biology approach to identify new vulnerabilities within AMR strains to rationally accelerate the discovery of therapeutics that extend the life span of existing antibiotics.

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.

Computational models, databases and tools for antibiotic combinations

Antibiotic combination is a promising strategy to extend the lifetime of antibiotics and thereby combat antimicrobial resistance. However, screening for new antibiotic combinations is both time-consuming and labor-intensive. In recent years, an increasing number of researchers have used computational models to predict effective antibiotic combinations. In this review, we summarized existing computational models for antibiotic combinations and discussed the limitations and challenges of these models in detail. In addition, we also collected and summarized available data resources and tools for antibiotic combinations. This study aims to help computational biologists design more accurate and interpretable computational models.

Craft of Co-encapsulation in Nanomedicine: A Struggle To Achieve Synergy through Reciprocity

Achieving synergism, often by combination therapy via codelivery of chemotherapeutic agents, remains the mainstay of treating multidrug-resistance cases in cancer and microbial strains. With a typical core-shell architecture and surface functionalization to ensure facilitated targeting of tissues, nanocarriers are emerging as a promising platform toward gaining such synergism. Co-encapsulation of disparate theranostic agents in nanocarriers-from chemotherapeutic molecules to imaging or photothermal modalities-can not only address the issue of protecting the labile drug payload from a hostile biochemical environment but may also ensure optimized drug release as a mainstay of synergistic effect. However, the fate of co-encapsulated molecules, influenced by temporospatial proximity, remains unpredictable and marred with events with deleterious impact on therapeutic efficacy, including molecular rearrangement, aggregation, and denaturation. Thus, more than just an art of confining multiple therapeutics into a 3D nanoscale space, a co-encapsulated nanocarrier, while aiming for synergism, should strive toward achieving a harmonious cohabitation of the encapsulated molecules that, despite proximity and opportunities for interaction, remain innocuous toward each other and ensure molecular integrity. This account will inspect the current progress in co-encapsulation in nanocarriers and distill out the key points toward accomplishing such synergism through reciprocity.

Prediction of Synergistic Antibiotic Combinations by Graph Learning

Antibiotic resistance is a major public health concern. Antibiotic combinations, offering better efficacy at lower doses, are a useful way to handle this problem. However, it is difficult for us to find effective antibiotic combinations in the vast chemical space. Herein, we propose a graph learning framework to predict synergistic antibiotic combinations. In this model, a network proximity method combined with network propagation was used to quantify the relationships of drug pairs, and we found that synergistic antibiotic combinations tend to have smaller network proximity. Therefore, network proximity can be used for building an affinity matrix. Subsequently, the affinity matrix was fed into a graph regularization model to predict potential synergistic antibiotic combinations. Compared with existing methods, our model shows a better performance in the prediction of synergistic antibiotic combinations and interpretability.

No population left behind: Improving paediatric drug safety using informatics and systems biology

Adverse drugs effects (ADEs) in children are common and may result in disability and death. The current paediatric drug safety landscape, including clinical trials, is limited as it rarely includes children and relies on extrapolation from adults. Children are not small adults but go through an evolutionarily conserved and physiologically dynamic process of growth and maturation. Novel quantitative approaches, integrating observations from clinical trials and drug safety databases with dynamic mechanisms, can be used to systematically identify ADEs unique to childhood. In this perspective, we discuss three critical research directions using systems biology methodologies and novel informatics to improve paediatric drug safety, namely child versus adult drug safety profiles, age-dependent drug toxicities and genetic susceptibility of ADEs across childhood. We argue that a data-driven framework that leverages observational data, biomedical knowledge and systems biology modelling will reveal previously unknown mechanisms of pediatric adverse drug events and lead to improved paediatric drug safety.

Computationally predicting clinical drug combination efficacy with cancer cell line screens and independent drug action

Evidence has recently emerged that many clinical cancer drug combinations may derive their efficacy from independent drug action (IDA), where patients only receive benefit from the single most effective drug in a drug combination. Here we present IDACombo, an IDA based method to predict the efficacy of drug combinations using monotherapy data from high-throughput cancer cell line screens. We show that IDACombo predictions closely agree with measured drug combination efficacies both in vitro (Pearson's correlation = 0.93 when comparing predicted efficacies to measured efficacies for >5000 combinations) and in a systematically selected set of clinical trials (accuracy > 84% for predicting statistically significant improvements in patient outcomes for 26 first line therapy trials). Finally, we demonstrate how IDACombo can be used to systematically prioritize combinations for development in specific cancer settings, providing a framework for quickly translating existing monotherapy cell line data into clinically meaningful predictions of drug combination efficacy.

Predicting drug synergy for precision medicine using network biology and machine learning

Identification of effective drug combinations for patients is an expensive and time-consuming procedure, especially for in vitro experiments. To accelerate the synergistic drug discovery process, we present a new classification model to identify more effective anti-cancer drug pairs using in silico network biology approach. Based on the hypotheses that the drug synergy comes from the collective effects on the biological network, therefore, we developed six network biology features, including overlap and distance of drug perturbation network, that were derived by using individual drug-perturbed transcriptome profiles and the relevant biological network analysis. Using publicly available drug synergy databases and three machine-learning (ML) methods, the model was trained to discriminate the positive (synergistic) and negative (nonsynergistic) drug combinations. The proposed models were evaluated on the test cases to predict the most promising network biology feature, which is the network degree activity, i.e. the synergistic effect between drug pairs is mainly accounted by the complementary signaling pathways or molecular networks from two drugs.

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.

Prediction of drug combination effects with a minimal set of experiments

High-throughput drug combination screening provides a systematic strategy to discover unexpected combinatorial synergies in pre-clinical cell models. However, phenotypic combinatorial screening with multi-dose matrix assays is experimentally expensive, especially when the aim is to identify selective combination synergies across a large panel of cell lines or patient samples. Here we implemented DECREASE, an efficient machine learning model that requires only a limited set of pairwise dose-response measurements for accurate prediction of drug combination synergy and antagonism. Using a compendium of 23,595 drug combination matrices tested in various cancer cell lines, and malaria and Ebola infection models, we demonstrate how cost-effective experimental designs with DECREASE capture almost the same degree of information for synergy and antagonism detection as the fully-measured dose-response matrices. Measuring only the diagonal of the matrix provides an accurate and practical option for combinatorial screening. The open-source web-implementation enables applications of DECREASE to both pre-clinical and translational studies.

A self-assembled, ROS-responsive Janus-prodrug for targeted therapy of inflammatory bowel disease

A self-assembled and oxidation-degradable Janus-prodrug, termed as Bud-ATK-Tem (B-ATK-T), was fabricated by ROS-responsive aromatized thioketal (ATK) linked anti-inflammatory drug budesonide (Bud) and antioxidant tempol (Tem). Benefiting from the hydrophobic interactions and π-π stacking interactions of ATK, prodrug B-ATK-T could self-assemble into nanoparticles (NP) in water containing lecithin and DSPE-PEG_2K. The morphology of B-ATK-T NP (approximate 100-120nm) was confirmed to be regular spherical by transmission electron microscope. B-ATK-T NP was endowed high drug loading content with 41.23% for Bud and 15.55% for Tem. The rapid drug release from B-ATK-T NP proceeded in an extensive reactive oxygen species (ROS)-dependent manner. More than 98% of Bud and Tem in B-ATK-T NP could release in the mimic inflammation microenvironment or phorbol-12-myristate-13-acetate (PMA)-stimulated macrophages within short time. The release of drugs in a simultaneous and proportional manner ensures that B-ATK-T NP can increase the combined efficacy of anti-inflammation and anti-oxidation. It is worth noting that B-ATK-T NP could be passively accumulated and dramatically increasing the maximum drugs concentration in the inflamed colon of mice with inflammatory bowel disease (IBD) by oral route, and avoiding potential systemic side effects. B-ATK-T NP could not only relieve colitis via inhibiting the expression of oxidative and proinflammatory mediators more than combination of free drugs, but also significantly reduce colitis-caused death. Taken together, the self-assembled, Janus-prodrug B-ATK-T NP is a promising candidate therapies for IBD, even for other inflammatory diseases.

Response envelope analysis for quantitative evaluation of drug combinations

MOTIVATION

The concept of synergy between two agents, over a century old, is important to the fields of biology, chemistry, pharmacology and medicine. A key step in drug combination analysis is the selection of an additivity model to identify combination effects including synergy, additivity and antagonism. Existing methods for identifying and interpreting those combination effects have limitations.

RESULTS

We present here a computational framework, termed response envelope analysis (REA), that makes use of 3D response surfaces formed by generalized Loewe Additivity and Bliss Independence models of interaction to evaluate drug combination effects. Because the two models imply two extreme limits of drug interaction (mutually exclusive and mutually non-exclusive), a response envelope defined by them provides a quantitatively stringent additivity model for identifying combination effects without knowing the inhibition mechanism. As a demonstration, we apply REA to representative published data from large screens of anticancer and antibiotic combinations. We show that REA is more accurate than existing methods and provides more consistent results in the context of cross-experiment evaluation.

AVAILABILITY AND IMPLEMENTATION

The open-source software package associated with REA is available at: https://github.com/4dsoftware/rea.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Use of genetic and chemical synthetic lethality as probes of complexity in bacterial cell systems

Different conditions and genomic contexts are known to have an impact on gene essentiality and interactions. Synthetic lethal interactions occur when a combination of perturbations, either genetic or chemical, result in a more profound fitness defect than expected based on the effect of each perturbation alone. Synthetic lethality in bacterial systems has long been studied; however, during the past decade, the emerging fields of genomics and chemical genomics have led to an increase in the scale and throughput of these studies. Here, we review the concepts of genomics and chemical genomics in the context of synthetic lethality and their revolutionary roles in uncovering novel biology such as the characterization of genes of unknown function and in antibacterial drug discovery. We provide an overview of the methodologies, examples and challenges of both genetic and chemical synthetic lethal screening platforms. Finally, we discuss how to apply genetic and chemical synthetic lethal approaches to rationalize the synergies of drugs, screen for new and improved antibacterial therapies and predict drug mechanism of action.

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.

Modeling the impact of drug interactions on therapeutic selectivity

Combination therapies that produce synergistic growth inhibition are widely sought after for the pharmacotherapy of many pathological conditions. Therapeutic selectivity, however, depends on the difference between potency on disease-causing cells and potency on non-target cell types that cause toxic side effects. Here, we examine a model system of antimicrobial compound combinations applied to two highly diverged yeast species. We find that even though the drug interactions correlate between the two species, cell-type-specific differences in drug interactions are common and can dramatically alter the selectivity of compounds when applied in combination vs. single-drug activity-enhancing, diminishing, or inverting therapeutic windows. This study identifies drug combinations with enhanced cell-type-selectivity with a range of interaction types, which we experimentally validate using multiplexed drug-interaction assays for heterogeneous cell cultures. This analysis presents a model framework for evaluating drug combinations with increased efficacy and selectivity against pathogens or tumors.