A Computational Approach for Identifying Synergistic Drug Combinations

A novel mathematical model for studying antimicrobial interactions against viable but non-culturable Campylobacter jejuni in the poultry product processing environment

Campylobacter jejuni is a major pathogen associated with gastrointestinal illness and is frequently detected in poultry products. Its ability to enter the viable but non-culturable (VBNC) state is an adaptive survival strategy triggered by adverse conditions. Consequently, the processing conditions involved in poultry production can potentially induce C. jejuni into the VBNC state, posing risks to food safety and public health. This study aimed to evaluate the antimicrobial effectiveness of carvacrol, diallyl sulfide, and Al2O3 nanoparticles (NPs) and investigate their synergistic interactions against VBNC C. jejuni under simulated poultry processing conditions. The time-kill assay demonstrated that Al₂O₃ NPs achieved >1 log CFU/mL reductions at 0.3 mg/mL, while carvacrol and diallyl sulfide required higher concentrations (0.8 mg/mL and 1.6 mg/mL, respectively) to achieve comparable reductions. While additive effects were observed for all combinations, the interactions were further examined using the combination index. The mathematical model effectively simulated the antimicrobial effects and interactions across varying levels of inhibition, confirming the potent antimicrobial activity of Al2O3 NPs. While carvacrol and diallyl sulfide exhibited additive effects in combination, synergistic interactions (combination index <1) were identified for binary and ternary combinations with Al₂O₃ NPs, including carvacrol/Al₂O₃ NPs, diallyl sulfide/Al₂O₃ NPs, and carvacrol/diallyl sulfide/Al₂O₃ NPs. These findings underscore the potential of Al₂O₃ NPs, individually or in combination with plant-based antimicrobials, to mitigate VBNC C. jejuni and improve food safety. The mathematical model presents an alternative approach to developing novel antimicrobial strategies.

Optimizing drug synergy prediction through categorical embeddings in deep neural networks

Cancer treatments often lose effectiveness as tumors develop resistance to single-agent therapies. Combination treatments can overcome this limitation, but the overwhelming combinatorial space of drug-dose interactions makes exhaustive experimental testing impractical. Data-driven methods, such as machine and deep learning, have emerged as promising tools to predict synergistic drug combinations. In this work, we systematically investigate the use of categorical embeddings within Deep Neural Networks to enhance drug synergy predictions. These learned and transferable encodings capture similarities between the elements of each category, demonstrating particular utility in scarce data scenarios.

Drug repositioning as a promising approach for the eradication of emerging and re-emerging viral agents

The global impact of emerging and re-emerging viral agents during epidemics and pandemics leads to serious health and economic burdens. Among the major emerging or re-emerging viruses include SARS-CoV-2, Ebola virus (EBOV), Monkeypox virus (Mpox), Hepatitis viruses, Zika virus, Avian flu, Influenza virus, Chikungunya virus (CHIKV), Dengue fever virus (DENV), West Nile virus, Rhabdovirus, Sandfly fever virus, Crimean-Congo hemorrhagic fever (CCHF) virus, and Rift Valley fever virus (RVFV). A comprehensive literature search was performed to identify existing studies, clinical trials, and reviews that discuss drug repositioning strategies for the treatment of emerging and re-emerging viral infections using databases, such as PubMed, Scholar Google, Scopus, and Web of Science. By utilizing drug repositioning, pharmaceutical companies can take advantage of a cost-effective, accelerated, and effective strategy, which in turn leads to the discovery of innovative treatment options for patients. In light of antiviral drug resistance and the high costs of developing novel antivirals, drug repositioning holds great promise for more rapid substitution of approved drugs. Main repositioned drugs have included chloroquine, ivermectin, dexamethasone, Baricitinib, tocilizumab, Mab114 (Ebanga™), ZMapp (pharming), Artesunate, imiquimod, saquinavir, capmatinib, naldemedine, Trametinib, statins, celecoxib, naproxen, metformin, ruxolitinib, nitazoxanide, gemcitabine, Dorzolamide, Midodrine, Diltiazem, zinc acetate, suramin, 5-fluorouracil, quinine, minocycline, trifluoperazine, paracetamol, berbamine, Nifedipine, and chlorpromazine. This succinct review will delve into the topic of repositioned drugs that have been utilized to combat emerging and re-emerging viral pathogens.

Advancing personalized cancer therapy: Onko_DrugCombScreen-a novel Shiny app for precision drug combination screening

Identifying and validating genotype-guided drug combinations for a specific molecular subtype in cancer therapy represents an unmet medical need and is important in enhancing efficacy and reducing toxicity. However, the exponential increase in combinatorial possibilities constrains the ability to identify and validate effective drug combinations. In this context, we have developed Onko_DrugCombScreen, an innovative tool aiming at advancing precision medicine based on identifying significant drug combination candidates in a target cancer cohort compared to a comparison cohort. Onko_DrugCombScreen, inspired by the molecular tumor board process, synergizes drug knowledgebase analysis with various statistical methodologies and data visualization techniques to pinpoint drug combination candidates. Validated through a TCGA-BRCA case study, Onko_DrugCombScreen has demonstrated its proficiency in discerning established drug combinations in a specific cancer type and in revealing potential novel drug combinations. By enhancing the capability of drug combination discovery through drug knowledgebases, Onko_DrugCombScreen represents a significant advancement in personalized cancer treatment by identifying promising drug combinations, setting the stage for the development of more precise and potent combination treatments in cancer care. The Onko_DrugCombScreen Shiny app is available at https://rshiny.gwdg.de/apps/onko_drugcombscreen/. The Git repository can be accessed at https://gitlab.gwdg.de/MedBioinf/mtb/onko_drugcombscreen.

Omics-Based Interaction Analysis Reveals Interplay of Chemical Pollutant (Ozone) and Photoradiation (UVSSR) Stressors in Skin Damage

The skin acts as the first line of defense against various environmental stressors, such as solar ultraviolet radiation, visible light, pollution particles and ozone. Simultaneous exposure to different stressors is common in everyday life but has been less studied than exposure to single stressors. Herein, the combined effects of a chemical pollutant (ozone) and a UV radiation stressor (UVSSR) were investigated on a 3D pigmented living skin equivalent model. Our results demonstrate that skin lightness (L* value) was significantly decreased by exposure to either UVSSR or ozone alone and that co-exposure to UVSSR and ozone further exacerbated surface darkness, suggesting that these stressors had a significant joint effect. Conventional differential expression analysis showed that, among exposure groups, co-exposure dysregulated the most genes, followed by ozone and UVSSR alone. Omics-based interaction framework (OBIF) analysis showed that most interactive genes following ozone and UVSSR exposure displayed a cooperative effect and had functions related to the skin barrier; these genes with synergistic effects were enriched in biological pathways such as the chronic inflammatory response and the apoptotic signaling pathway. In summary, exposure to ozone in combination with UVSSR showed a joint effect on UVSSR-induced phenotypic changes in the skin; the underlying mechanism was determined by using transcriptome analysis, showing the additive impacts of ozone on UVSSR-induced skin damage, such as cellular stress and inflammatory responses. These findings shed light on how ozone exacerbates UVSSR damage and indicate that the synergistic response genes identified using OBIF analysis may drive the progression of skin damage induced by chemical/photoradiation stress co-exposure.

MMSyn: A New Multimodal Deep Learning Framework for Enhanced Prediction of Synergistic Drug Combinations

Combination therapy is a promising strategy for the successful treatment of cancer. The large number of possible combinations, however, mean that it is laborious and expensive to screen for synergistic drug combinations in vitro. Nevertheless, because of the availability of high-throughput screening data and advances in computational techniques, deep learning (DL) can be a useful tool for the prediction of synergistic drug combinations. In this study, we proposed a multimodal DL framework, MMSyn, for the prediction of synergistic drug combinations. First, features embedded in the drug molecules were extracted: structure, fingerprint, and string encoding. Then, gene expression data, DNA copy number, and pathway activity were used to describe cancer cell lines. Finally, these processed features were integrated using an attention mechanism and an interaction module and then input into a multilayer perceptron to predict drug synergy. Experimental results showed that our method outperformed five state-of-the-art DL methods and three traditional machine learning models for drug combination prediction. We verified that MMSyn achieved superior performance in stratified cross-validation settings using both the drug combination and cell line data. Moreover, we performed a set of ablation experiments to illustrate the effectiveness of each component and the efficacy of our model. In addition, our visual representation and case studies further confirmed the effectiveness of our model. All results showed that MMSyn can be used as a powerful tool for the prediction of synergistic drug combinations.

Optimized models and deep learning methods for drug response prediction in cancer treatments: a review

Recent advancements in deep learning (DL) have played a crucial role in aiding experts to develop personalized healthcare services, particularly in drug response prediction (DRP) for cancer patients. The DL's techniques contribution to this field is significant, and they have proven indispensable in the medical field. This review aims to analyze the diverse effectiveness of various DL models in making these predictions, drawing on research published from 2017 to 2023. We utilized the VOS-Viewer 1.6.18 software to create a word cloud from the titles and abstracts of the selected studies. This study offers insights into the focus areas within DL models used for drug response. The word cloud revealed a strong link between certain keywords and grouped themes, highlighting terms such as deep learning, machine learning, precision medicine, precision oncology, drug response prediction, and personalized medicine. In order to achieve an advance in DRP using DL, the researchers need to work on enhancing the models' generalizability and interoperability. It is also crucial to develop models that not only accurately represent various architectures but also simplify these architectures, balancing the complexity with the predictive capabilities. In the future, researchers should try to combine methods that make DL models easier to understand; this will make DRP reviews more open and help doctors trust the decisions made by DL models in cancer DRP.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

Enhanced SREBP2-driven cholesterol biosynthesis by PKCλ/ι deficiency in intestinal epithelial cells promotes aggressive serrated tumorigenesis

The metabolic and signaling pathways regulating aggressive mesenchymal colorectal cancer (CRC) initiation and progression through the serrated route are largely unknown. Although relatively well characterized as BRAF mutant cancers, their poor response to current targeted therapy, difficult preneoplastic detection, and challenging endoscopic resection make the identification of their metabolic requirements a priority. Here, we demonstrate that the phosphorylation of SCAP by the atypical PKC (aPKC), PKCλ/ι promotes its degradation and inhibits the processing and activation of SREBP2, the master regulator of cholesterol biosynthesis. We show that the upregulation of SREBP2 and cholesterol by reduced aPKC levels is essential for controlling metaplasia and generating the most aggressive cell subpopulation in serrated tumors in mice and humans. Since these alterations are also detected prior to neoplastic transformation, together with the sensitivity of these tumors to cholesterol metabolism inhibitors, our data indicate that targeting cholesterol biosynthesis is a potential mechanism for serrated chemoprevention.

Flubendazole Enhances the Inhibitory Effect of Paclitaxel via HIF1α/PI3K/AKT Signaling Pathways in Breast Cancer

Paclitaxel, a natural anticancer drug, is widely recognized and extensively utilized in the treatment of breast cancer (BC). However, it may lead to certain side effects or drug resistance. Fortunately, combination therapy with another anti-tumor agent has been explored as an option to improve the efficacy of paclitaxel in the treatment of BC. Herein, we first evaluated the synergistic effects of paclitaxel and flubendazole through combination index (CI) calculations. Secondly, flubendazole was demonstrated to synergize paclitaxel-mediated BC cell killing in vitro and in vivo. Moreover, we discovered that flubendazole could reverse the drug resistance of paclitaxel-resistant BC cells. Mechanistically, flubendazole was demonstrated to enhance the inhibitory effect of paclitaxel via HIF1α/PI3K/AKT signaling pathways. Collectively, our findings demonstrate the effectiveness of flubendazole in combination with paclitaxel for treating BC, providing an insight into exploiting more novel combination therapies for BC in the future.

Drug combinations identified by high-throughput screening promote cell cycle transition and upregulate Smad pathways in myeloma

Drug resistance and disease progression are common in multiple myeloma (MM) patients, underscoring the need for new therapeutic combinations. A high-throughput drug screen in 47 MM cell lines and in silico Huber robust regression analysis of drug responses revealed 43 potentially synergistic combinations. We hypothesized that effective combinations would reduce MYC expression and enhance p16 activity. Six combinations cooperatively reduced MYC protein, frequently over-expressed in MM and also cooperatively increased p16 expression, frequently downregulated in MM. Synergistic reductions in viability were observed with top combinations in proteasome inhibitor-resistant and sensitive MM cell lines, while sparing fibroblasts. Three combinations significantly prolonged survival in a transplantable Ras-driven allograft model of advanced MM closely recapitulating high-risk/refractory myeloma in humans and reduced viability of ex vivo treated patient cells. Common genetic pathways similarly downregulated by these combinations promoted cell cycle transition, whereas pathways most upregulated were involved in TGFβ/SMAD signaling. These preclinical data identify potentially useful drug combinations for evaluation in drug-resistant MM and reveal potential mechanisms of combined drug sensitivity.

ACDA: implementation of an augmented drug synergy prediction algorithm

Motivation

Drug synergy prediction is approached with machine learning techniques using molecular and pharmacological data. The published Cancer Drug Atlas (CDA) predicts a synergy outcome in cell-line models from drug target information, gene mutations and the models' monotherapy drug sensitivity. We observed low performance of the CDA, 0.339, measured by Pearson correlation of predicted versus measured sensitivity on DrugComb datasets.

Results

We augmented the approach CDA by applying a random forest regression and optimization via cross-validation hyper-parameter tuning and named it Augmented CDA (ACDA). We benchmarked the ACDA's performance, which is 68% higher than that of the CDA when trained and validated on the same dataset spanning 10 tissues. We compared the performance of ACDA to one of the winning methods of the DREAM Drug Combination Prediction Challenge, the performance of which was lower than ACDA in 16 out of 19 cases. We further trained the ACDA on Novartis Institutes for BioMedical Research PDX encyclopedia data and generated sensitivity predictions for PDX models. Finally, we developed a novel approach to visualize synergy-prediction data.

Availability and implementation

The source code is available at https://github.com/TheJacksonLaboratory/drug-synergy and the software package at PyPI.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer

One of the main obstacles to the successful treatment of cancer is the phenomenon of drug resistance. A common strategy to overcome resistance is the use of combination therapies. However, the space of possibilities is huge and efficient search strategies are required. Machine Learning (ML) can be a useful tool for the discovery of novel, clinically relevant anti-cancer drug combinations. In particular, deep learning (DL) has become a popular choice for modeling drug combination effects. Here, we set out to examine the impact of different methodological choices on the performance of multimodal DL-based drug synergy prediction methods, including the use of different input data types, preprocessing steps and model architectures. Focusing on the NCI ALMANAC dataset, we found that feature selection based on prior biological knowledge has a positive impact-limiting gene expression data to cancer or drug response-specific genes improved performance. Drug features appeared to be more predictive of drug response, with a 41% increase in coefficient of determination (R2) and 26% increase in Spearman correlation relative to a baseline model that used only cell line and drug identifiers. Molecular fingerprint-based drug representations performed slightly better than learned representations-ECFP4 fingerprints increased R2 by 5.3% and Spearman correlation by 2.8% w.r.t the best learned representations. In general, fully connected feature-encoding subnetworks outperformed other architectures. DL outperformed other ML methods by more than 35% (R2) and 14% (Spearman). Additionally, an ensemble combining the top DL and ML models improved performance by about 6.5% (R2) and 4% (Spearman). Using a state-of-the-art interpretability method, we showed that DL models can learn to associate drug and cell line features with drug response in a biologically meaningful way. The strategies explored in this study will help to improve the development of computational methods for the rational design of effective drug combinations for cancer therapy.

MGAE-DC: Predicting the synergistic effects of drug combinations through multi-channel graph autoencoders

Accurate prediction of synergistic effects of drug combinations can reduce the experimental costs for drug development and facilitate the discovery of novel efficacious combination therapies for clinical studies. The drug combinations with high synergy scores are regarded as synergistic ones, while those with moderate or low synergy scores are additive or antagonistic ones. The existing methods usually exploit the synergy data from the aspect of synergistic drug combinations, paying little attention to the additive or antagonistic ones. Also, they usually do not leverage the common patterns of drug combinations across different cell lines. In this paper, we propose a multi-channel graph autoencoder (MGAE)-based method for predicting the synergistic effects of drug combinations (DC), and shortly denote it as MGAE-DC. A MGAE model is built to learn the drug embeddings by considering not only synergistic combinations but also additive and antagonistic ones as three input channels. The later two channels guide the model to explicitly characterize the features of non-synergistic combinations through an encoder-decoder learning process, and thus the drug embeddings become more discriminative between synergistic and non-synergistic combinations. In addition, an attention mechanism is incorporated to fuse each cell-line's drug embeddings across various cell lines, and a common drug embedding is extracted to capture the invariant patterns by developing a set of cell-line shared decoders. The generalization performance of our model is further improved with the invariant patterns. With the cell-line specific and common drug embeddings, our method is extended to predict the synergy scores of drug combinations by a neural network module. Experiments on four benchmark datasets demonstrate that MGAE-DC consistently outperforms the state-of-the-art methods. In-depth literature survey is conducted to find that many drug combinations predicted by MGAE-DC are supported by previous experimental studies. The source code and data are available at https://github.com/yushenshashen/MGAE-DC.

Building a knowledge graph to enable precision medicine

Developing personalized diagnostic strategies and targeted treatments requires a deep understanding of disease biology and the ability to dissect the relationship between molecular and genetic factors and their phenotypic consequences. However, such knowledge is fragmented across publications, non-standardized repositories, and evolving ontologies describing various scales of biological organization between genotypes and clinical phenotypes. Here, we present PrimeKG, a multimodal knowledge graph for precision medicine analyses. PrimeKG integrates 20 high-quality resources to describe 17,080 diseases with 4,050,249 relationships representing ten major biological scales, including disease-associated protein perturbations, biological processes and pathways, anatomical and phenotypic scales, and the entire range of approved drugs with their therapeutic action, considerably expanding previous efforts in disease-rooted knowledge graphs. PrimeKG contains an abundance of 'indications', 'contradictions', and 'off-label use' drug-disease edges that lack in other knowledge graphs and can support AI analyses of how drugs affect disease-associated networks. We supplement PrimeKG's graph structure with language descriptions of clinical guidelines to enable multimodal analyses and provide instructions for continual updates of PrimeKG as new data become available.

SNRMPACDC: computational model focused on Siamese network and random matrix projection for anticancer synergistic drug combination prediction

Synergistic drug combinations can improve the therapeutic effect and reduce the drug dosage to avoid toxicity. In previous years, an in vitro approach was utilized to screen synergistic drug combinations. However, the in vitro method is time-consuming and expensive. With the rapid growth of high-throughput data, computational methods are becoming efficient tools to predict potential synergistic drug combinations. Considering the limitations of the previous computational methods, we developed a new model named Siamese Network and Random Matrix Projection for AntiCancer Drug Combination prediction (SNRMPACDC). Firstly, the Siamese convolutional network and random matrix projection were used to process the features of the two drugs into drug combination features. Then, the features of the cancer cell line were processed through the convolutional network. Finally, the processed features were integrated and input into the multi-layer perceptron network to get the predicted score. Compared with the traditional method of splicing drug features into drug combination features, SNRMPACDC improved the interpretability of drug combination features to a certain extent. In addition, the introduction of convolutional networks can better extract the potential information in the features. SNRMPACDC achieved the root mean-squared error of 15.01 and the Pearson correlation coefficient of 0.75 in 5-fold cross-validation of regression prediction for response data. In addition, SNRMPACDC achieved the AUC of 0.91 ± 0.03 and the AUPR of 0.62 ± 0.05 in 5-fold cross-validation of classification prediction of synergistic or not. These results are almost better than all the previous models. SNRMPACDC would be an effective approach to infer potential anticancer synergistic drug combinations.

Application of artificial intelligence to the public health education

With the global outbreak of coronavirus disease 2019 (COVID-19), public health has received unprecedented attention. The cultivation of emergency and compound professionals is the general trend through public health education. However, current public health education is limited to traditional teaching models that struggle to balance theory and practice. Fortunately, the development of artificial intelligence (AI) has entered the stage of intelligent cognition. The introduction of AI in education has opened a new era of computer-assisted education, which brought new possibilities for teaching and learning in public health education. AI-based on big data not only provides abundant resources for public health research and management but also brings convenience for students to obtain public health data and information, which is conducive to the construction of introductory professional courses for students. In this review, we elaborated on the current status and limitations of public health education, summarized the application of AI in public health practice, and further proposed a framework for how to integrate AI into public health education curriculum. With the rapid technological advancements, we believe that AI will revolutionize the education paradigm of public health and help respond to public health emergencies.

Deep learning-based multi-drug synergy prediction model for individually tailored anti-cancer therapies

While synergistic drug combinations are more effective at fighting tumors with complex pathophysiology, preference compensating mechanisms, and drug resistance, the identification of novel synergistic drug combinations, especially complex higher-order combinations, remains challenging due to the size of combination space. Even though certain computational methods have been used to identify synergistic drug combinations in lieu of traditional in vitro and in vivo screening tests, the majority of previously published work has focused on predicting synergistic drug pairs for specific types of cancer and paid little attention to the sophisticated high-order combinations. The main objective of this study is to develop a deep learning-based approach that integrated multi-omics data to predict novel synergistic multi-drug combinations (DeepMDS) in a given cell line. To develop this approach, we firstly created a dataset comprising of gene expression profiles of cancer cell lines, target information of anti-cancer drugs, and drug response against a large variety of cancer cell lines. Based on the principle of a fully connected feed forward Deep Neural Network, the proposed model was constructed using this dataset, which achieved a high performance with a Mean Square Error (MSE) of 2.50 and a Root Mean Squared Error (RMSE) of 1.58 in the regression task, and gave the best classification accuracy of 0.94, an area under the Receiver Operating Characteristic curve (AUC) of 0.97, a sensitivity of 0.95, and a specificity of 0.93. Furthermore, we utilized three breast cancer cell subtypes (MCF-7, MDA-MD-468 and MDA-MB-231) and one lung cancer cell line A549 to validate the predicted results of our model, showing that the predicted top-ranked multi-drug combinations had superior anti-cancer effects to other combinations, particularly those that were widely used in clinical treatment. Our model has the potential to increase the practicality of expanding the drug combinational space and to leverage its capacity to prioritize the most effective multi-drug combinational therapy for precision oncology applications.

Computational pharmacogenomic screen identifies drugs that potentiate the anti-breast cancer activity of statins

Statins, a family of FDA-approved cholesterol-lowering drugs that inhibit the rate-limiting enzyme of the mevalonate metabolic pathway, have demonstrated anticancer activity. Evidence shows that dipyridamole potentiates statin-induced cancer cell death by blocking a restorative feedback loop triggered by statin treatment. Leveraging this knowledge, we develop an integrative pharmacogenomics pipeline to identify compounds similar to dipyridamole at the level of drug structure, cell sensitivity and molecular perturbation. To overcome the complex polypharmacology of dipyridamole, we focus our pharmacogenomics pipeline on mevalonate pathway genes, which we name mevalonate drug-network fusion (MVA-DNF). We validate top-ranked compounds, nelfinavir and honokiol, and identify that low expression of the canonical epithelial cell marker, E-cadherin, is associated with statin-compound synergy. Analysis of remaining prioritized hits led to the validation of additional compounds, clotrimazole and vemurafenib. Thus, our computational pharmacogenomic approach identifies actionable compounds with pathway-specific activities.

Predicting Drug Synergism by Means of Non-Negative Matrix Tri-Factorization

Traditional drug experiments to find synergistic drug pairs are time-consuming and expensive due to the numerous possible combinations of drugs that have to be examined. Thus, computational methods that can give suggestions for synergistic drug investigations are of great interest. Here, we propose a Non-negative Matrix Tri-Factorization (NMTF) based approach that leverages the integration of different data types for predicting synergistic drug pairs in multiple specific cell lines. Our computational framework relies on a network-based representation of available data about drug synergism, which also allows integrating genomic information about cell lines. We computationally evaluate the performances of our method in finding missing relationships between synergistic drug pairs and cell lines, and in computing synergy scores between drug pairs in a specific cell line, as well as we estimate the benefit of adding cell line genomic data to the network. Our approach obtains very good performance (Average Precision Score equal to 0.937, Pearson's correlation coefficient equal to 0.760) when cell line genomic data and rich data about synergistic drugs in a cell line are considered. Finally, we systematically searched our top-scored predictions in the available literature and in the NCI ALMANAC, a well-known database of drug combination experiments, proving the goodness of our findings.

Identification of Synergistic Drug Combinations to Target KRAS-Driven Chemoradioresistant Cancers Utilizing Tumoroid Models of Colorectal Adenocarcinoma and Recurrent Glioblastoma

Treatment resistance is observed in all advanced cancers. Colorectal cancer (CRC) presenting as colorectal adenocarcinoma (COAD) is the second leading cause of cancer deaths worldwide. Multimodality treatment includes surgery, chemotherapy, and targeted therapies with selective utilization of immunotherapy and radiation therapy. Despite the early success of anti-epidermal growth factor receptor (anti-EGFR) therapy, treatment resistance is common and often driven by mutations in APC, KRAS, RAF, and PI3K/mTOR and positive feedback between activated KRAS and WNT effectors. Challenges in the direct targeting of WNT regulators and KRAS have caused alternative actionable targets to gain recent attention. Utilizing an unbiased drug screen, we identified combinatorial targeting of DDR1/BCR-ABL signaling axis with small-molecule inhibitors of EGFR-ERBB2 to be potentially cytotoxic against multicellular spheroids obtained from WNT-activated and KRAS-mutant COAD lines (HCT116, DLD1, and SW480) independent of their KRAS mutation type. Based on the data-driven approach using available patient datasets (The Cancer Genome Atlas (TCGA)), we constructed transcriptomic correlations between gene DDR1, with an expression of genes for EGFR, ERBB2-4, mitogen-activated protein kinase (MAPK) pathway intermediates, BCR, and ABL and genes for cancer stem cell reactivation, cell polarity, and adhesion; we identified a positive association of DDR1 with EGFR, ERBB2, BRAF, SOX9, and VANGL2 in Pan-Cancer. The evaluation of the pathway network using the STRING database and Pathway Commons database revealed DDR1 protein to relay its signaling via adaptor proteins (SHC1, GRB2, and SOS1) and BCR axis to contribute to the KRAS-PI3K-AKT signaling cascade, which was confirmed by Western blotting. We further confirmed the cytotoxic potential of our lead combination involving EGFR/ERBB2 inhibitor (lapatinib) with DDR1/BCR-ABL inhibitor (nilotinib) in radioresistant spheroids of HCT116 (COAD) and, in an additional devastating primary cancer model, glioblastoma (GBM). GBMs overexpress DDR1 and share some common genomic features with COAD like EGFR amplification and WNT activation. Moreover, genetic alterations in genes like NF1 make GBMs have an intrinsically high KRAS activity. We show the combination of nilotinib plus lapatinib to exhibit more potent cytotoxic efficacy than either of the drugs administered alone in tumoroids of patient-derived recurrent GBMs. Collectively, our findings suggest that combinatorial targeting of DDR1/BCR-ABL with EGFR-ERBB2 signaling may offer a therapeutic strategy against stem-like KRAS-driven chemoradioresistant tumors of COAD and GBM, widening the window for its applications in mainstream cancer therapeutics.

Network Control Models With Personalized Genomics Data for Understanding Tumor Heterogeneity in Cancer

Due to rapid development of high-throughput sequencing and biotechnology, it has brought new opportunities and challenges in developing efficient computational methods for exploring personalized genomics data of cancer patients. Because of the high-dimension and small sample size characteristics of these personalized genomics data, it is difficult for excavating effective information by using traditional statistical methods. In the past few years, network control methods have been proposed to solve networked system with high-dimension and small sample size. Researchers have made progress in the design and optimization of network control principles. However, there are few studies comprehensively surveying network control methods to analyze the biomolecular network data of individual patients. To address this problem, here we comprehensively surveyed complex network control methods on personalized omics data for understanding tumor heterogeneity in precision medicine of individual patients with cancer.

Integrated Network Pharmacology Approach for Drug Combination Discovery: A Multi-Cancer Case Study

Despite remarkable efforts of computational and predictive pharmacology to improve therapeutic strategies for complex diseases, only in a few cases have the predictions been eventually employed in the clinics. One of the reasons behind this drawback is that current predictive approaches are based only on the integration of molecular perturbation of a certain disease with drug sensitivity signatures, neglecting intrinsic properties of the drugs. Here we integrate mechanistic and chemocentric approaches to drug repositioning by developing an innovative network pharmacology strategy. We developed a multilayer network-based computational framework integrating perturbational signatures of the disease as well as intrinsic characteristics of the drugs, such as their mechanism of action and chemical structure. We present five case studies carried out on public data from The Cancer Genome Atlas, including invasive breast cancer, colon adenocarcinoma, lung squamous cell carcinoma, hepatocellular carcinoma and prostate adenocarcinoma. Our results highlight paclitaxel as a suitable drug for combination therapy for many of the considered cancer types. In addition, several non-cancer-related genes representing unusual drug targets were identified as potential candidates for pharmacological treatment of cancer.

Fully connected autoencoder and convolutional neural network with attention-based method for inferring disease-related lncRNAs

Since abnormal expression of long noncoding RNAs (lncRNAs) is often closely related to various human diseases, identification of disease-associated lncRNAs is helpful for exploring the complex pathogenesis. Most of recent methods concentrate on exploiting multiple kinds of data related to lncRNAs and diseases for predicting candidate disease-related lncRNAs. These methods, however, failed to deeply integrate the topology information from the meta-paths that are composed of lncRNA, disease and microRNA (miRNA) nodes. We proposed a new method based on fully connected autoencoders and convolutional neural networks, called ACLDA, for inferring potential disease-related lncRNA candidates. A heterogeneous graph that consists of lncRNA, disease and miRNA nodes were firstly constructed to integrate similarities, associations and interactions among them. Fully connected autoencoder-based module was established to extract the low-dimensional features of lncRNA, disease and miRNA nodes in the heterogeneous graph. We designed the attention mechanisms at the node feature level and at the meta-path level to learn more informative features and meta-paths. A module based on convolutional neural networks was constructed to encode the local topologies of lncRNA and disease nodes from multiple meta-path perspectives. The comprehensive experimental results demonstrated ACLDA achieves superior performance than several state-of-the-art prediction methods. Case studies on breast, lung and colon cancers demonstrated that ACLDA is able to discover the potential disease-related lncRNAs.

Predicting Anticancer Drug Resistance Mediated by Mutations

Cancer drug resistance presents a challenge for precision medicine. Drug-resistant mutations are always emerging. In this study, we explored the relationship between drug-resistant mutations and drug resistance from the perspective of protein structure. By combining data from previously identified drug-resistant mutations and information of protein structure and function, we used machine learning-based methods to build models to predict cancer drug resistance mutations. The performance of our combined model achieved an accuracy of 86%, a Matthews correlation coefficient score of 0.57, and an F1 score of 0.66. We have constructed a fast, reliable method that predicts and investigates cancer drug resistance in a protein structure. Nonetheless, more information is needed concerning drug resistance and, in particular, clarification is needed about the relationships between the drug and the drug resistance mutations in proteins. Highly accurate predictions regarding drug resistance mutations can be helpful for developing new strategies with personalized cancer treatments. Our novel concept, which combines protein structure information, has the potential to elucidate physiological mechanisms of cancer drug resistance.

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.

PRODeepSyn: predicting anticancer synergistic drug combinations by embedding cell lines with protein–protein interaction network

Although drug combinations in cancer treatment appear to be a promising therapeutic strategy with respect to monotherapy, it is arduous to discover new synergistic drug combinations due to the combinatorial explosion. Deep learning technology holds immense promise for better prediction of in vitro synergistic drug combinations for certain cell lines. In methods applying such technology, omics data are widely adopted to construct cell line features. However, biological network data are rarely considered yet, which is worthy of in-depth study. In this study, we propose a novel deep learning method, termed PRODeepSyn, for predicting anticancer synergistic drug combinations. By leveraging the Graph Convolutional Network, PRODeepSyn integrates the protein–protein interaction (PPI) network with omics data to construct low-dimensional dense embeddings for cell lines. PRODeepSyn then builds a deep neural network with the Batch Normalization mechanism to predict synergy scores using the cell line embeddings and drug features. PRODeepSyn achieves the lowest root mean square error of 15.08 and the highest Pearson correlation coefficient of 0.75, outperforming two deep learning methods and four machine learning methods. On the classification task, PRODeepSyn achieves an area under the receiver operator characteristics curve of 0.90, an area under the precision–recall curve of 0.63 and a Cohen’s Kappa of 0.53. In the ablation study, we find that using the multi-omics data and the integrated PPI network’s information both can improve the prediction results. Additionally, the case study demonstrates the consistency between PRODeepSyn and previous studies.

Combination treatment optimization using a pan-cancer pathway model

The design of efficient combination therapies is a difficult key challenge in the treatment of complex diseases such as cancers. The large heterogeneity of cancers and the large number of available drugs renders exhaustive in vivo or even in vitro investigation of possible treatments impractical. In recent years, sophisticated mechanistic, ordinary differential equation-based pathways models that can predict treatment responses at a molecular level have been developed. However, surprisingly little effort has been put into leveraging these models to find novel therapies. In this paper we use for the first time, to our knowledge, a large-scale state-of-the-art pan-cancer signaling pathway model to identify candidates for novel combination therapies to treat individual cancer cell lines from various tissues (e.g., minimizing proliferation while keeping dosage low to avoid adverse side effects) and populations of heterogeneous cancer cell lines (e.g., minimizing the maximum or average proliferation across the cell lines while keeping dosage low). We also show how our method can be used to optimize the drug combinations used in sequential treatment plans-that is, optimized sequences of potentially different drug combinations-providing additional benefits. In order to solve the treatment optimization problems, we combine the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) algorithm with a significantly more scalable sampling scheme for truncated Gaussian distributions, based on a Hamiltonian Monte-Carlo method. These optimization techniques are independent of the signaling pathway model, and can thus be adapted to find treatment candidates for other complex diseases than cancers as well, as long as a suitable predictive model is available.

Artificial intelligence in cancer research, diagnosis and therapy

Artificial intelligence and machine learning techniques are breaking into biomedical research and health care, which importantly includes cancer research and oncology, where the potential applications are vast. These include detection and diagnosis of cancer, subtype classification, optimization of cancer treatment and identification of new therapeutic targets in drug discovery. While big data used to train machine learning models may already exist, leveraging this opportunity to realize the full promise of artificial intelligence in both the cancer research space and the clinical space will first require significant obstacles to be surmounted. In this Viewpoint article, we asked four experts for their opinions on how we can begin to implement artificial intelligence while ensuring standards are maintained so as transform cancer diagnosis and the prognosis and treatment of patients with cancer and to drive biological discovery.

Machine learning approaches for drug combination therapies

Drug combination therapy is a promising strategy to treat complex diseases such as cancer and infectious diseases. However, current knowledge of drug combination therapies, especially in cancer patients, is limited because of adverse drug effects, toxicity and cell line heterogeneity. Screening new drug combinations requires substantial efforts since considering all possible combinations between drugs is infeasible and expensive. Therefore, building computational approaches, particularly machine learning methods, could provide an effective strategy to overcome drug resistance and improve therapeutic efficacy. In this review, we group the state-of-the-art machine learning approaches to analyze personalized drug combination therapies into three categories and discuss each method in each category. We also present a short description of relevant databases used as a benchmark in drug combination therapies and provide a list of well-known, publicly available interactive data analysis portals. We highlight the importance of data integration on the identification of drug combinations. Finally, we address the advantages of combining multiple data sources on drug combination analysis by showing an experimental comparison.

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.

Extending the lymphoblastoid cell line model for drug combination pharmacogenomics

Combination drug therapies have become an integral part of precision oncology, and while evidence of clinical effectiveness continues to grow, the underlying mechanisms supporting synergy are poorly understood. Immortalized human lymphoblastoid cell lines (LCLs) have been proven as a particularly useful, scalable and low-cost model in pharmacogenetics research, and are suitable for elucidating the molecular mechanisms of synergistic combination therapies. In this review, we cover the advantages of LCLs in synergy pharmacogenomics and consider recent studies providing initial evidence of the utility of LCLs in synergy research. We also discuss several opportunities for LCL-based systems to address gaps in the research through the expansion of testing regimens, assessment of new drug classes and higher-order combinations, and utilization of integrated omics technologies.

Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data

BACKGROUND

Predicting the drug response of a patient is important for precision oncology. In recent studies, multi-omics data have been used to improve the prediction accuracy of drug response. Although multi-omics data are good resources for drug response prediction, the large dimension of data tends to hinder performance improvement. In this study, we aimed to develop a new method, which can effectively reduce the large dimension of data, based on the supervised deep learning model for predicting drug response.

RESULTS

We proposed a novel method called Supervised Feature Extraction Learning using Triplet loss (Super.FELT) for drug response prediction. Super.FELT consists of three stages, namely, feature selection, feature encoding using a supervised method, and binary classification of drug response (sensitive or resistant). We used multi-omics data including mutation, copy number aberration, and gene expression, and these were obtained from cell lines [Genomics of Drug Sensitivity in Cancer (GDSC), Cancer Cell Line Encyclopedia (CCLE), and Cancer Therapeutics Response Portal (CTRP)], patient-derived tumor xenografts (PDX), and The Cancer Genome Atlas (TCGA). GDSC was used for training and cross-validation tests, and CCLE, CTRP, PDX, and TCGA were used for external validation. We performed ablation studies for the three stages and verified that the use of multi-omics data guarantees better performance of drug response prediction. Our results verified that Super.FELT outperformed the other methods at external validation on PDX and TCGA and was good at cross-validation on GDSC and external validation on CCLE and CTRP. In addition, through our experiments, we confirmed that using multi-omics data is useful for external non-cell line data.

CONCLUSION

By separating the three stages, Super.FELT achieved better performance than the other methods. Through our results, we found that it is important to train encoders and a classifier independently, especially for external test on PDX and TCGA. Moreover, although gene expression is the most powerful data on cell line data, multi-omics promises better performance for external validation on non-cell line data than gene expression data. Source codes of Super.FELT are available at  https://github.com/DMCB-GIST/Super.FELT .

Synergistic potential of dual andrographolide and melatonin targeting of metastatic colon cancer cells: Using the Chou-Talalay combination index method

Colorectal cancer (CRC) mortality has diminished for decades due to new and improved treatment profiles. However, CRC still ranks as the third most diagnosed cancer in the US. Therefore, a new therapeutic approach is needed to overcome colospheroids inhibition and drug resistance. It is well documented that andrographolide (AGP) and melatonin (MLT) have anti-carcinogenic properties. Our goal was to evaluate their synergistic effects on metastatic colon cancer cells (mCRC) and colospheroids. HT-29 and HCT-15 mCRC cells were simultaneously treated with serial dilutions of AGP and MLT for 24, 48 and 72 h. Cell viability was monitored using the MTT assay. The Chou-Talalay method for drug combination is based on the median effect equation, providing a theoretical basis for the combination index and the isobologram equation. This allows quantitative determination of drug interactions using the CompuSyn software, where CI < 1, = 1, and >1 indicates synergistic, additive, and antagonistic effects respectively. Our results demonstrate that AGP and MLT in combination show synergism with CI values of 0.35293 and 0.34152 for HT-29 and HCT-15 respectively and a fractional inhibition of Fa = 0.50-0.90, as shown by the Fa-CI plot and isobologram. The synergism value was validated in colospheroids (HT-29-s and HCT-15-s) based on morphology, viability, and colony formation and in 5-FU drug resistant cell (HT-29R and HCT-116R) viability. The mechanism(s) of decreased cell viability are due to the induction of ER stress proteins and angiogenic inhibition. Our results provide rationale for using AGP in combination with MLT on mCRC.

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.

Sepsis in the era of data-driven medicine: personalizing risks, diagnoses, treatments and prognoses

Sepsis is a series of clinical syndromes caused by the immunological response to infection. The clinical evidence for sepsis could typically attribute to bacterial infection or bacterial endotoxins, but infections due to viruses, fungi or parasites could also lead to sepsis. Regardless of the etiology, rapid clinical deterioration, prolonged stay in intensive care units and high risk for mortality correlate with the incidence of sepsis. Despite its prevalence and morbidity, improvement in sepsis outcomes has remained limited. In this comprehensive review, we summarize the current landscape of risk estimation, diagnosis, treatment and prognosis strategies in the setting of sepsis and discuss future challenges. We argue that the advent of modern technologies such as in-depth molecular profiling, biomedical big data and machine intelligence methods will augment the treatment and prevention of sepsis. The volume, variety, veracity and velocity of heterogeneous data generated as part of healthcare delivery and recent advances in biotechnology-driven therapeutics and companion diagnostics may provide a new wave of approaches to identify the most at-risk sepsis patients and reduce the symptom burden in patients within shorter turnaround times. Developing novel therapies by leveraging modern drug discovery strategies including computational drug repositioning, cell and gene-therapy, clustered regularly interspaced short palindromic repeats -based genetic editing systems, immunotherapy, microbiome restoration, nanomaterial-based therapy and phage therapy may help to develop treatments to target sepsis. We also provide empirical evidence for potential new sepsis targets including FER and STARD3NL. Implementing data-driven methods that use real-time collection and analysis of clinical variables to trace, track and treat sepsis-related adverse outcomes will be key. Understanding the root and route of sepsis and its comorbid conditions that complicate treatment outcomes and lead to organ dysfunction may help to facilitate identification of most at-risk patients and prevent further deterioration. To conclude, leveraging the advances in precision medicine, biomedical data science and translational bioinformatics approaches may help to develop better strategies to diagnose and treat sepsis in the next decade.

Machine learning approaches to drug response prediction: challenges and recent progress

Cancer is a leading cause of death worldwide. Identifying the best treatment using computational models to personalize drug response prediction holds great promise to improve patient's chances of successful recovery. Unfortunately, the computational task of predicting drug response is very challenging, partially due to the limitations of the available data and partially due to algorithmic shortcomings. The recent advances in deep learning may open a new chapter in the search for computational drug response prediction models and ultimately result in more accurate tools for therapy response. This review provides an overview of the computational challenges and advances in drug response prediction, and focuses on comparing the machine learning techniques to be of utmost practical use for clinicians and machine learning non-experts. The incorporation of new data modalities such as single-cell profiling, along with techniques that rapidly find effective drug combinations will likely be instrumental in improving cancer care.

A cancer drug atlas enables synergistic targeting of independent drug vulnerabilities

Personalized cancer treatments using combinations of drugs with a synergistic effect is attractive but proves to be highly challenging. Here we present an approach to uncover the efficacy of drug combinations based on the analysis of mono-drug effects. For this we used dose-response data from pharmacogenomic encyclopedias and represent these as a drug atlas. The drug atlas represents the relations between drug effects and allows to identify independent processes for which the tumor might be particularly vulnerable when attacked by two drugs. Our approach enables the prediction of combination-therapy which can be linked to tumor-driving mutations. By using this strategy, we can uncover potential effective drug combinations on a pan-cancer scale. Predicted synergies are provided and have been validated in glioblastoma, breast cancer, melanoma and leukemia mouse-models, resulting in therapeutic synergy in 75% of the tested models. This indicates that we can accurately predict effective drug combinations with translational value.

Attentional multi-level representation encoding based on convolutional and variance autoencoders for lncRNA-disease association prediction

As the abnormalities of long non-coding RNAs (lncRNAs) are closely related to various human diseases, identifying disease-related lncRNAs is important for understanding the pathogenesis of complex diseases. Most of current data-driven methods for disease-related lncRNA candidate prediction are based on diseases and lncRNAs. Those methods, however, fail to consider the deeply embedded node attributes of lncRNA-disease pairs, which contain multiple relations and representations across lncRNAs, diseases and miRNAs. Moreover, the low-dimensional feature distribution at the pairwise level has not been taken into account. We propose a prediction model, VADLP, to extract, encode and adaptively integrate multi-level representations. Firstly, a triple-layer heterogeneous graph is constructed with weighted inter-layer and intra-layer edges to integrate the similarities and correlations among lncRNAs, diseases and miRNAs. We then define three representations including node attributes, pairwise topology and feature distribution. Node attributes are derived from the graph by an embedding strategy to represent the lncRNA-disease associations, which are inferred via their common lncRNAs, diseases and miRNAs. Pairwise topology is formulated by random walk algorithm and encoded by a convolutional autoencoder to represent the hidden topological structural relations between a pair of lncRNA and disease. The new feature distribution is modeled by a variance autoencoder to reveal the underlying lncRNA-disease relationship. Finally, an attentional representation-level integration module is constructed to adaptively fuse the three representations for lncRNA-disease association prediction. The proposed model is tested over a public dataset with a comprehensive list of evaluations. Our model outperforms six state-of-the-art lncRNA-disease prediction models with statistical significance. The ablation study showed the important contributions of three representations. In particular, the improved recall rates under different top $k$ values demonstrate that our model is powerful in discovering true disease-related lncRNAs in the top-ranked candidates. Case studies of three cancers further proved the capacity of our model to discover potential disease-related lncRNAs.

Deep learning for drug response prediction in cancer

Predicting the sensitivity of tumors to specific anti-cancer treatments is a challenge of paramount importance for precision medicine. Machine learning(ML) algorithms can be trained on high-throughput screening data to develop models that are able to predict the response of cancer cell lines and patients to novel drugs or drug combinations. Deep learning (DL) refers to a distinct class of ML algorithms that have achieved top-level performance in a variety of fields, including drug discovery. These types of models have unique characteristics that may make them more suitable for the complex task of modeling drug response based on both biological and chemical data, but the application of DL to drug response prediction has been unexplored until very recently. The few studies that have been published have shown promising results, and the use of DL for drug response prediction is beginning to attract greater interest from researchers in the field. In this article, we critically review recently published studies that have employed DL methods to predict drug response in cancer cell lines. We also provide a brief description of DL and the main types of architectures that have been used in these studies. Additionally, we present a selection of publicly available drug screening data resources that can be used to develop drug response prediction models. Finally, we also address the limitations of these approaches and provide a discussion on possible paths for further improvement. Contact:  mrocha@di.uminho.pt.

Signal flow control of complex signaling networks

Complex disease such as cancer is often caused by genetic mutations that eventually alter the signal flow in the intra-cellular signaling network and result in different cell fate. Therefore, it is crucial to identify control targets that can most effectively block such unwanted signal flow. For this purpose, systems biological analysis provides a useful framework, but mathematical modeling of complicated signaling networks requires massive time-series measurements of signaling protein activity levels for accurate estimation of kinetic parameter values or regulatory logics. Here, we present a novel method, called SFC (Signal Flow Control), for identifying control targets without the information of kinetic parameter values or regulatory logics. Our method requires only the structural information of a signaling network and is based on the topological estimation of signal flow through the network. SFC will be particularly useful for a large-scale signaling network to which parameter estimation or inference of regulatory logics is no longer applicable in practice. The identified control targets have significant implication in drug development as they can be putative drug targets.

Bruton's tyrosine kinase is at the crossroads of metabolic adaptation in primary malignant human lymphocytes

In this work we explored metabolic aspects of human primary leukemic lymphocytes that hold a potential impact on the treatment of Bruton tyrosine kinase (BTK)-driven diseases. Our results suggest that there is crosstalk between Bruton tyrosine kinase (BTK) signaling and bioenergetic stress responses. In primary chronic lymphocytic leukemia (CLL) lymphocytes, pharmacological interference with mitochondrial ATP synthesis or glucose metabolism affects BTK activity. Conversely, an inhibitor of BTK used clinically (ibrutinib) induces bioenergetic stress responses that in turn affect ibrutinib resistance. Although the detailed molecular mechanisms are still to be defined, our work shows for the first time that in primary B cells, metabolic stressors enhance BTK signaling and suggest that metabolic rewiring to hyperglycemia affects ibrutinib resistance in TP53 deficient chronic lymphocytic leukemia (CLL) lymphocytes.

Kinase inhibitor library screening identifies synergistic drug combinations effective in sensitive and resistant melanoma cells

Background

Melanoma is the most aggressive and deadly form of skin cancer with increasing case numbers worldwide. The development of inhibitors targeting mutated BRAF (found in around 60% of melanoma patients) has markedly improved overall survival of patients with late-stage tumors, even more so when combined with MEK inhibitors targeting the same signaling pathway. However, invariably patients become resistant to this targeted therapy resulting in rapid progression with treatment-refractory disease. The purpose of this study was the identification of new kinase inhibitors that do not lead to the development of resistance in combination with BRAF inhibitors (BRAFi), or that could be of clinical benefit as a 2nd line treatment for late-stage melanoma patients that have already developed resistance.

Methods

We have screened a 274-compound kinase inhibitor library in 3 BRAF mutant melanoma cell lines (each one sensitive or made resistant to 2 distinct BRAFi). The screening results were validated by dose-response studies and confirmed the killing efficacies of many kinase inhibitors. Two different tools were applied to investigate and quantify potential synergistic effects of drug combinations: the Chou-Talalay method and the Synergyfinder application. In order to exclude that resistance to the new treatments might occur at later time points, synergistic combinations were administered to fluorescently labelled parental and resistant cells over a period of > 10 weeks.

Results

Eight inhibitors targeting Wee1, Checkpoint kinase 1/2, Aurora kinase, MEK, Polo-like kinase, PI3K and Focal adhesion kinase killed melanoma cells synergistically when combined with a BRAFi. Additionally, combination of a Wee1 and Chk inhibitor showed synergistic killing effects not only on sensitive cell lines, but also on intrinsically BRAFi- and treatment induced-resistant melanoma cells. First in vivo studies confirmed these observations. Interestingly, continuous treatment with several of these drugs, alone or in combination, did not lead to emergence of resistance.

Conclusions

Here, we have identified new, previously unexplored (in the framework of BRAFi resistance) inhibitors that have an effect not only on sensitive but also on BRAFi-resistant cells. These promising combinations together with the new immunotherapies could be an important step towards improved 1st and 2nd line treatments for late-stage melanoma patients.

Electronic supplementary material

The online version of this article (10.1186/s13046-019-1038-x) contains supplementary material, which is available to authorized users.

On-demand serum-free media formulations for human hematopoietic cell expansion using a high dimensional search algorithm

Substitution of serum and other clinically incompatible reagents is requisite for controlling product quality in a therapeutic cell manufacturing process. However, substitution with chemically defined compounds creates a complex, large-scale optimization problem due to the large number of possible factors and dose levels, making conventional process optimization methods ineffective. We present a framework for high-dimensional optimization of serum-free formulations for the expansion of human hematopoietic cells. Our model-free approach utilizes evolutionary computing principles to drive an experiment-based feedback control platform. We validate this method by optimizing serum-free formulations for first, TF-1 cells and second, primary T-cells. For each cell type, we successfully identify a set of serum-free formulations that support cell expansions similar to the serum-containing conditions commonly used to culture these cells, by experimentally testing less than 1 × 10-5 % of the total search space. We also demonstrate how this iterative search process can provide insights into factor interactions that contribute to supporting cell expansion.

What Makes Species Productive of Anti-Cancer Drugs? Clues from Drugs' Species Origin, Druglikeness, Target and Pathway

BACKGROUND

Despite the substantial contribution of natural products to the FDA drug approval list, the discovery of anti-cancer drugs from the huge amount of species on the planet remains looking for a needle in a haystack.

OBJECTIVE

Drug-productive clusters in the phylogenetic tree are thus proposed to narrow the searching scope by focusing on much smaller amount of species within each cluster, which enable prioritized and rational bioprospecting for novel drug-like scaffolds. However, the way anti-cancer nature-derived drugs distribute in phylogenetic tree has not been reported, and it is oversimplified to just focus anti-cancer drug discovery on the drug-productive clusters, since the number of species in each cluster remains too large to be managed.

METHODS

In this study, 260 anti-cancer drugs approved in the past 70 years were comprehensively analyzed by hierarchical clustering of phylogenetic distribution.

RESULTS

207 out of these 260 drugs were derived from or inspired by the natural products isolated from 58 species. Phylogenetic distribution of those drugs further revealed that nature-derived anti-cancer drugs originated mostly from drug-productive families that tend to be clustered rather than scattered on the phylogenetic tree. Moreover, based on their productivity, drug-producing species were categorized into productive (CPS), newly emerging (CNS) and lessproductive (CLS). Statistical significances in druglikeness between drugs from CPS and CLS were observed, and drugs from CNS were found to share similar drug-like properties to those from CPS.

CONCLUSION

This finding indicated a great raise in drug approval standard, which suggested us to focus bioprospecting on the species yielding multiple drugs and keeping productive for long period of time.

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.

SynAggreg: A Multifunctional High-Throughput Technology for Precision Study of Amyloid Aggregation and Systematic Discovery of Synergistic Inhibitor Compounds

Numerous proteins can coalesce into amyloid self-assemblies, which are responsible for a class of diseases called amyloidoses, but which can also fulfill important biological functions and are of great interest for biotechnology. Amyloid aggregation is a complex multi-step process, poorly prone to detailed structural studies. Therefore, small molecules interacting with amyloids are often used as tools to probe the amyloid aggregation pathway and in some cases to treat amyloidoses as they prevent pathogenic protein aggregation. Here, we report on SynAggreg, an in vitro high-throughput (HT) platform dedicated to the precision study of amyloid aggregation and the effect of modulator compounds. SynAggreg relies on an accurate bi-fluorescent amyloid-tracer readout that overcomes some limitations of existing HT methods. It allows addressing diverse aspects of aggregation modulation that are critical for pathomechanistic studies, such as the specificity of compounds toward various amyloids and their effects on aggregation kinetics, as well as the co-assembly propensity of distinct amyloids and the influence of prion-like seeding on self-assembly. Furthermore, SynAggreg is the first HT technology that integrates tailored methodology to systematically identify synergistic compound combinations-an emerging strategy to improve fatal amyloidoses by targeting multiple steps of the aggregation pathway. To this end, we apply analytical combinatorial scores to rank the inhibition efficiency of couples of compounds and to readily detect synergism. Finally, the SynAggreg platform should be suited for the characterization of a broad class of amyloids, whether of interest for drug development purposes, for fundamental research on amyloid functions, or for biotechnological applications.