The National Cancer Institute ALMANAC: A Comprehensive Screening Resource for the Detection of Anticancer Drug Pairs with Enhanced Therapeutic Activity

Association of changes in expression of HDAC and SIRT genes after drug treatment with cancer cell line sensitivity to kinase inhibitors

Histone deacetylases (HDACs) and sirtuins (SIRTs) are important epigenetic regulators of cancer pathways. There is a limited understanding of how transcriptional regulation of their genes is affected by chemotherapeutic agents, and how such transcriptional changes affect tumour sensitivity to drug treatment. We investigated the concerted transcriptional response of HDAC and SIRT genes to 15 approved antitumor agents in the NCI-60 cancer cell line panel. Antitumor agents with diverse mechanisms of action induced upregulation or downregulation of multiple HDAC and SIRT genes. HDAC5 was upregulated by dasatinib and erlotinib in the majority of the cell lines. Tumour cell line sensitivity to kinase inhibitors was associated with upregulation of HDAC5, HDAC1, and several SIRT genes. We confirmed changes in HDAC and SIRT expression in independent datasets. We also experimentally validated the upregulation of HDAC5 mRNA and protein expression by dasatinib in the highly sensitive IGROV1 cell line. HDAC5 was not upregulated in the UACC-257 cell line resistant to dasatinib. The effects of cancer drug treatment on expression of HDAC and SIRT genes may influence chemosensitivity and may need to be considered during chemotherapy.

Autoencoder-based drug synergy framework for malignant diseases

Drug combination emerges as a viable option for the treatment of malignant diseases. Drug combination outperforms monotherapy by improving therapeutic efficacy, reducing toxicity, and overcoming drug resistance. To find viable drug combinations it is difficult to traverse empirically because of enormous combinational space. Machine learning and deep learning approaches are used to uncover novel synergistic drug combinations in enormous combinational space. Here, AESyn, a novel autoencoder-based drug synergy framework for malignant diseases using a bag of words encoding is proposed. The bag of word encoding technique is used to extract drug-targeted genes. The framework utilized screening data from NCI-ALMANAC, and O'Neil datasets. Autoencoders take drug embeddings with drug-targeted genes as input for processing. The autoencoder in the proposed framework is used to extract drug features. The proposed framework is evaluated on classification and regression metrics. The performance of the proposed framework is compared with existing methods of drug synergy. According to the findings, the proposed framework achieved high performance with an accuracy of 95%, AUROC of 94.2%, and MAPE of 7.2. The autoencoder-based framework for malignant diseases using an encoding technique provides a stable, order-independent drug synergy prediction.

Single-cell transcriptomes identify patient-tailored therapies for selective co-inhibition of cancer clones

Intratumoral cellular heterogeneity necessitates multi-targeting therapies for improved clinical benefits in advanced malignancies. However, systematic identification of patient-specific treatments that selectively co-inhibit cancerous cell populations poses a combinatorial challenge, since the number of possible drug-dose combinations vastly exceeds what could be tested in patient cells. Here, we describe a machine learning approach, scTherapy, which leverages single-cell transcriptomic profiles to prioritize multi-targeting treatment options for individual patients with hematological cancers or solid tumors. Patient-specific treatments reveal a wide spectrum of co-inhibitors of multiple biological pathways predicted for primary cells from heterogenous cohorts of patients with acute myeloid leukemia and high-grade serous ovarian carcinoma, each with unique resistance patterns and synergy mechanisms. Experimental validations confirm that 96% of the multi-targeting treatments exhibit selective efficacy or synergy, and 83% demonstrate low toxicity to normal cells, highlighting their potential for therapeutic efficacy and safety. In a pan-cancer analysis across five cancer types, 25% of the predicted treatments are shared among the patients of the same tumor type, while 19% of the treatments are patient-specific. Our approach provides a widely-applicable strategy to identify personalized treatment regimens that selectively co-inhibit malignant cells and avoid inhibition of non-cancerous cells, thereby increasing their likelihood for clinical success.

Dual-view jointly learning improves personalized drug synergy prediction

MOTIVATION

Accurate and robust estimation of the synergistic drug combination is important for medicine precision. Although some computational methods have been developed, some predictions are still unreliable especially for the cross-dataset predictions, due to the complex mechanism of drug combinations and heterogeneity of cancer samples.

RESULTS

We have proposed JointSyn that utilizes dual-view jointly learning to predict sample-specific effects of drug combination from drug and cell features. JointSyn outperforms existing state-of-the-art methods in predictive accuracy and robustness across various benchmarks. Each view of JointSyn captures drug synergy-related characteristics and makes complementary contributes to the final prediction of the drug combination. Moreover, JointSyn with fine-tuning improves its generalization ability to predict a novel drug combination or cancer sample using a small number of experimental measurements. We also used JointSyn to generate an estimated atlas of drug synergy for pan-cancer and explored the differential pattern among cancers. These results demonstrate the potential of JointSyn to predict drug synergy, supporting the development of personalized combinatorial therapies.

AVAILABILITY AND IMPLEMENTATION

Source code and data are available at https://github.com/LiHongCSBLab/JointSyn.

M3NetFlow: A novel multi-scale multi-hop graph AI model for integrative multi-omic data analysis

Multi-omic data-driven studies, characterizing complex disease signaling system from multiple levels, are at the forefront of precision medicine and healthcare. The integration and interpretation of multi-omic data are essential for identifying molecular targets and deciphering core signaling pathways of complex diseases. However, it remains an open problem due the large number of biomarkers and complex interactions among them. In this study, we propose a novel Multi-scale Multi-hop Multi-omic graph model, M3NetFlow, to facilitate generic multi-omic data analysis to rank targets and infer core signaling flows/pathways. To evaluate M3NetFlow, we applied it in two independent multi-omic case studies: 1) uncovering mechanisms of synergistic drug combination response (defined as anchor-target guided learning), and 2) identifying biomarkers and pathways of Alzheimer 's disease (AD). The evaluation and comparison results showed M3NetFlow achieves the best prediction accuracy (accurate), and identifies a set of essential targets and core signaling pathways (interpretable). The model can be directly applied to other multi-omic data-driven studies. The code is publicly accessible at: https://github.com/FuhaiLiAiLab/M3NetFlow.

Combination therapy synergism prediction for virus treatment using machine learning models

Combining different drugs synergistically is an essential aspect of developing effective treatments. Although there is a plethora of research on computational prediction for new combination therapies, there is limited to no research on combination therapies in the treatment of viral diseases. This paper proposes AI-based models for predicting novel antiviral combinations to treat virus diseases synergistically. To do this, we assembled a comprehensive dataset comprising information on viral strains, drug compounds, and their known interactions. As far as we know, this is the first dataset and learning model on combination therapy for viruses. Our proposal includes using a random forest model, an SVM model, and a deep model to train viral combination therapy. The machine learning models showed the highest performance, and the predicted values were validated by a t-test, indicating the effectiveness of the proposed methods. One of the predicted combinations of acyclovir and ribavirin has been experimentally confirmed to have a synergistic antiviral effect against herpes simplex type-1 virus, as described in the literature.

AI-powered omics-based drug pair discovery for pyroptosis therapy targeting triple-negative breast cancer

Due to low success rates and long cycles of traditional drug development, the clinical tendency is to apply omics techniques to reveal patient-level disease characteristics and individualized responses to treatment. However, the heterogeneous form of data and uneven distribution of targets make drug discovery and precision medicine a non-trivial task. This study takes pyroptosis therapy for triple-negative breast cancer (TNBC) as a paradigm and uses data mining of a large TNBC cohort and drug databases to establish a biofactor-regulated neural network for rapidly screening and optimizing compound pyroptosis drug pairs. Subsequently, biomimetic nanococrystals are prepared using the preferred combination of mitoxantrone and gambogic acid for rational drug delivery. The unique mechanism of obtained nanococrystals regulating pyroptosis genes through ribosomal stress and triggering pyroptosis cascade immune effects are revealed in TNBC models. In this work, a target omics-based intelligent compound drug discovery framework explores an innovative drug development paradigm, which repurposes existing drugs and enables precise treatment of refractory diseases.

Using DeepSignalingFlow to mine signaling flows interpreting mechanism of synergy of cocktails

Complex signaling pathways are believed to be responsible for drug resistance. Drug combinations perturbing multiple signaling targets have the potential to reduce drug resistance. The large-scale multi-omic datasets and experimental drug combination synergistic score data are valuable resources to study mechanisms of synergy (MoS) to guide the development of precision drug combinations. However, signaling patterns of MoS are complex and remain unclear, and thus it is challenging to identify synergistic drug combinations in clinical. Herein, we proposed a novel integrative and interpretable graph AI model, DeepSignalingFlow, to uncover the MoS by integrating and mining multi-omic data. The major innovation is that we uncover MoS by modeling the signaling flow from multi-omic features of essential disease proteins to the drug targets, which has not been introduced by the existing models. The model performance was assessed utilizing four distinct drug combination synergy evaluation datasets, i.e., NCI ALMANAC, O'Neil, DrugComb, and DrugCombDB. The comparison results showed that the proposed model outperformed existing graph AI models in terms of synergy score prediction, and can interpret MoS using the core signaling flows. The code is publicly accessible via Github: https://github.com/FuhaiLiAiLab/DeepSignalingFlow.

A pan-cancer screen identifies drug combination benefit in cancer cell lines at the individual and population level

Combining drugs can enhance their clinical efficacy, but the number of possible combinations and inter-tumor heterogeneity make identifying effective combinations challenging, while existing approaches often overlook clinically relevant activity. We screen one of the largest cell line panels (N = 757) with 51 clinically relevant combinations and identify responses at the level of individual cell lines and tissue populations. We establish three response classes to model cellular effects beyond monotherapy: synergy, Bliss additivity, and independent drug action (IDA). Synergy is rare (11% of responses) and frequently efficacious (>50% viability reduction), whereas Bliss and IDA are more frequent but less frequently efficacious. We introduce "efficacious combination benefit" (ECB) to describe high-efficacy responses classified as either synergy, Bliss, or IDA. We identify ECB biomarkers in vitro and show that ECB predicts response in patient-derived xenografts better than synergy alone. Our work here provides a valuable resource and framework for preclinical evaluation and the development of combination treatments.

HTS384 NCI60: The Next Phase of the NCI60 Screen

The NCI60 human tumor cell line screen has been in operation as a service to the cancer research community for more than 30 years. The screen operated with 96-well plates, a 2-day exposure period to test agents, and following cell fixation, a visible absorbance endpoint by the protein-staining dye sulforhodamine B. In this study, we describe the next phase of this important cancer research tool, the HTS384 NCI60 screen. Although the cell lines remain the same, the updated screen is performed with 384-well plates, a 3-day exposure period to test agents, and a luminescent endpoint to measure cell viability based upon cellular ATP content. In this study, a library of 1,003 FDA-approved and investigational small-molecule anticancer agents was screened by the two NCI60 assays. The datasets were compared with a focus on targeted agents with at least six representatives in the library. For many agents, including inhibitors of EGFR, BRAF, MEK, ERK, and PI3K, the patterns of GI50 values were very similar between the screens with strong correlations between those patterns within the dataset from each screen. However, for some groups of targeted agents, including mTOR, BET bromodomain, and NAMPRTase inhibitors, there were limited or no correlations between the two datasets, although the patterns of GI50 values and correlations between those patterns within each dataset were apparent. Beginning in January 2024, the HTS384 NCI60 screen became the free screening service of the NCI to facilitate drug discovery by the cancer research community. Significance: The new NCI60 cell line screen HTS384 shows robust patterns of response to oncology agents and substantial overlap with the classic screen, providing an updated tool for studying therapeutic agents. See related commentary by Colombo and Corsello, p. 2397.

SAFER: sub-hypergraph attention-based neural network for predicting effective responses to dose combinations

BACKGROUND

The potential benefits of drug combination synergy in cancer medicine are significant, yet the risks must be carefully managed due to the possibility of increased toxicity. Although artificial intelligence applications have demonstrated notable success in predicting drug combination synergy, several key challenges persist: (1) Existing models often predict average synergy values across a restricted range of testing dosages, neglecting crucial dose amounts and the mechanisms of action of the drugs involved. (2) Many graph-based models rely on static protein-protein interactions, failing to adapt to dynamic and higher-order relationships. These limitations constrain the applicability of current methods.

RESULTS

We introduce SAFER, a Sub-hypergraph Attention-based graph model, addressing these issues by incorporating complex relationships among biological knowledge networks and considering dosing effects on subject-specific networks. SAFER outperformed previous models on the benchmark and the independent test set. The analysis of subgraph attention weight for the lung cancer cell line highlighted JAK-STAT signaling pathway, PRDM12, ZNF781, and CDC5L that have been implicated in lung fibrosis.

CONCLUSIONS

SAFER presents an interpretable framework designed to identify drug-responsive signals. Tailored for comprehending dose effects on subject-specific molecular contexts, our model uniquely captures dose-level drug combination responses. This capability unlocks previously inaccessible avenues of investigation compared to earlier models. Furthermore, the SAFER framework can be leveraged by future inquiries to investigate molecular networks that uniquely characterize individual patients and can be applied to prioritize personalized effective treatment based on safe dose combinations.

Stereoselective Asymmetric Syntheses of Molecules with a 4,5-Dihydro-1H-[1,2,4]-Triazoline Core Possessing an Acetylated Carbohydrate Appendage: Crystal Structure, Spectroscopy, and Pharmacology

A new series of chiral 4,5-dihydro-1H-[1,2,4]-triazoline molecules, featuring a β-ᴅ-glucopyranoside appendage, were synthesized via a 1,3-dipolar cycloaddition reaction between various hydrazonyl chlorides and carbohydrate Schiff bases. The isolated enantiopure triazolines (8a-j) were identified through high-resolution mass spectrometry (HRMS) and vibrational spectroscopy. Subsequently, their solution structures were elucidated through NMR spectroscopic techniques. Single-crystal X-ray analysis of derivative 8b provided definitive evidence for the 3-D structure of this compound and revealed important intermolecular forces in the crystal lattice. Moreover, it confirmed the (S)-configuration at the newly generated stereo-center. Selected target compounds were investigated for anti-tumor activity in 60 cancer cell lines, with derivative 8c showing the highest potency, particularly against leukemia. Additionally, substituent-dependent anti-fungal and anti-bacterial behavior was observed.

New methods for drug synergy prediction: A mini-review

In this mini-review, we explore the new prediction methods for drug combination synergy relying on high-throughput combinatorial screens. The fast progress of the field is witnessed in the more than thirty original machine learning methods published since 2021, a clear majority of them based on deep learning techniques. We aim to put these articles under a unifying lens by highlighting the core technologies, the data sources, the input data types and synergy scores used in the methods, as well as the prediction scenarios and evaluation protocols that the articles deal with. Our finding is that the best methods accurately solve the synergy prediction scenarios involving known drugs or cell lines while the scenarios involving new drugs or cell lines still fall short of an accurate prediction level.

SNSynergy: Similarity network-based machine learning framework for synergy prediction towards new cell lines and new anticancer drug combinations

The computational method has been proven to be a promising means for pre-screening large-scale anticancer drug combinations to support precision oncology applications. Pioneering efforts have been made to develop machine learning technology for predicting drug synergy, but high computational cost for training models as well as great diversity and limited size in screening data escalate the difficulty of prediction. To address this challenge, we propose a simple machine learning framework, namely Similarity Network-based Synergy prediction (SNSynergy), for predicting synergistic effects towards new cell lines and new drug combinations by two locally weighted models CLSN and DCSN. This framework only requires a small amount of auxiliary data, like genomics information of cell lines and the molecular fingerprints or targets of drugs. Based on the assumption that similar cell lines and similar drug combinations have similar synergistic effects, CLSN and DCSN predict synergy scores through capturing individual synergy contributions of nearest cell line and drug combination neighbors, respectively. High correlations between predicted and measured synergy scores on two leading cancer cell line pharmacogenomic screening datasets (the O'Neil dataset and the NCI-ALMANAC dataset) demonstrate the effectiveness and robustness of SNSynergy. Many of the identified drug combinations are consistent with previous studies, or have been explored in clinical settings against the specific cancer type, showing that SNSynergy has the potential to supply cost-saving and effective high-throughput screening for prioritizing the most applicable cell lines and the most promising drug combinations.

ReCorDE: a framework for identifying drug classes targeting shared vulnerabilities with applications to synergistic drug discovery

Cancer is typically treated with combinatorial therapy, and such combinations may be synergistic. However, discovery of these combinations has proven difficult as brute force combinatorial screening approaches are both logistically complex and resource-intensive. Therefore, computational approaches to augment synergistic drug discovery are of interest, but current approaches are limited by their dependencies on combinatorial drug screening training data or molecular profiling data. These dataset dependencies can limit the number and diversity of drugs for which these approaches can make inferences. Herein, we describe a novel computational framework, ReCorDE (Recurrent Correlation of Drugs with Enrichment), that uses publicly-available cell line-derived monotherapy cytotoxicity datasets to identify drug classes targeting shared vulnerabilities across multiple cancer lineages; and we show how these inferences can be used to augment synergistic drug combination discovery. Additionally, we demonstrate in preclinical models that a drug class combination predicted by ReCorDE to target shared vulnerabilities (PARP inhibitors and Aurora kinase inhibitors) exhibits class-class synergy across lineages. ReCorDE functions independently of combinatorial drug screening and molecular profiling data, using only extensive monotherapy cytotoxicity datasets as its input. This allows ReCorDE to make robust inferences for a large, diverse array of drugs. In conclusion, we have described a novel framework for the identification of drug classes targeting shared vulnerabilities using monotherapy cytotoxicity datasets, and we showed how these inferences can be used to aid discovery of novel synergistic drug combinations.

Large-scale Pan-cancer Cell Line Screening Identifies Actionable and Effective Drug Combinations

Oncology drug combinations can improve therapeutic responses and increase treatment options for patients. The number of possible combinations is vast and responses can be context-specific. Systematic screens can identify clinically relevant, actionable combinations in defined patient subtypes. We present data for 109 anticancer drug combinations from AstraZeneca's oncology small molecule portfolio screened in 755 pan-cancer cell lines. Combinations were screened in a 7 × 7 concentration matrix, with more than 4 million measurements of sensitivity, producing an exceptionally data-rich resource. We implement a new approach using combination Emax (viability effect) and highest single agent (HSA) to assess combination benefit. We designed a clinical translatability workflow to identify combinations with clearly defined patient populations, rationale for tolerability based on tumor type and combination-specific "emergent" biomarkers, and exposures relevant to clinical doses. We describe three actionable combinations in defined cancer types, confirmed in vitro and in vivo, with a focus on hematologic cancers and apoptotic targets.

SIGNIFICANCE

We present the largest cancer drug combination screen published to date with 7 × 7 concentration response matrices for 109 combinations in more than 750 cell lines, complemented by multi-omics predictors of response and identification of "emergent" combination biomarkers. We prioritize hits to optimize clinical translatability, and experimentally validate novel combination hypotheses. This article is featured in Selected Articles from This Issue, p. 695.

SAFER: sub-hypergraph attention-based neural network for predicting effective responses to dose combinations

Background

The potential benefits of drug combination synergy in cancer medicine are significant, yet the risks must be carefully managed due to the possibility of increased toxicity. Although artificial intelligence applications have demonstrated notable success in predicting drug combination synergy, several key challenges persist: (1) Existing models often predict average synergy values across a restricted range of testing dosages, neglecting crucial dose amounts and the mechanisms of action of the drugs involved. (2) Many graph-based models rely on static protein-protein interactions, failing to adapt to dynamic and context-dependent networks. This limitation constrains the applicability of current methods.

Results

We introduced SAFER, a Sub-hypergraph Attention-based graph model, addressing these issues by incorporating complex relationships among biological knowledge networks and considering dosing effects on subject-specific networks. SAFER outperformed previous models on the benchmark and the independent test set. The analysis of subgraph attention weight for the lung cancer cell line highlighted JAK-STAT signaling pathway, PRDM12, ZNF781, and CDC5L that have been implicated in lung fibrosis.

Conclusions

SAFER presents an interpretable framework designed to identify drug-responsive signals. Tailored for comprehending dose effects on subject-specific molecular contexts, our model uniquely captures dose-level drug combination responses. This capability unlocks previously inaccessible avenues of investigation compared to earlier models. Finally, the SAFER framework can be leveraged by future inquiries to investigate molecular networks that uniquely characterize individual patients.

PermuteDDS: a permutable feature fusion network for drug-drug synergy prediction

MOTIVATION

Drug combination therapies have shown promise in clinical cancer treatments. However, it is hard to experimentally identify all drug combinations for synergistic interaction even with high-throughput screening due to the vast space of potential combinations. Although a number of computational methods for drug synergy prediction have proven successful in narrowing down this space, fusing drug pairs and cell line features effectively still lacks study, hindering current algorithms from understanding the complex interaction between drugs and cell lines.

RESULTS

In this paper, we proposed a Permutable feature fusion network for Drug-Drug Synergy prediction, named PermuteDDS. PermuteDDS takes multiple representations of drugs and cell lines as input and employs a permutable fusion mechanism to combine drug and cell line features. In experiments, PermuteDDS exhibits state-of-the-art performance on two benchmark data sets. Additionally, the results on independent test set grouped by different tissues reveal that PermuteDDS has good generalization performance. We believed that PermuteDDS is an effective and valuable tool for identifying synergistic drug combinations. It is publicly available at https://github.com/littlewei-lazy/PermuteDDS .

SCIENTIFIC CONTRIBUTION

First, this paper proposes a permutable feature fusion network for predicting drug synergy termed PermuteDDS, which extract diverse information from multiple drug representations and cell line representations. Second, the permutable fusion mechanism combine the drug and cell line features by integrating information of different channels, enabling the utilization of complex relationships between drugs and cell lines. Third, comparative and ablation experiments provide evidence of the efficacy of PermuteDDS in predicting drug-drug synergy.

A Deep Neural Network for Predicting Synergistic Drug Combinations on Cancer

The exploration of drug combinations presents an opportunity to amplify therapeutic effectiveness while alleviating undesirable side effects. Nevertheless, the extensive array of potential combinations poses challenges in terms of cost and time constraints for experimental screening. Thus, it is crucial to narrow down the search space. Deep learning approaches have gained widespread popularity in predicting synergistic drug combinations tailored for specific cell lines in vitro settings. In the present study, we introduce a novel method termed GTextSyn, which utilizes the integration of gene expression data and chemical structure information for the prediction of synergistic effects in drug combinations. GTextSyn employs a sentence classification model within the domain of Natural Language Processing (NLP), wherein drugs and cell lines are regarded as entities possessing biochemical relevance. Meanwhile, combinations of drug pairs and cell lines are construed as sentences with biochemical relational significance. To assess the efficacy of GTextSyn, we conduct a comparative analysis with alternative deep learning approaches using a standard benchmark dataset. The results from a five-fold cross-validation demonstrate a 49.5% reduction in Mean Square Error (MSE) achieved by GTextSyn, surpassing the performance of the next best method in the regression task. Furthermore, we conduct a comprehensive literature survey on the predicted novel drug combinations and find substantial support from prior experimental studies for many of the combinations identified by GTextSyn.

Synergistic Drug Combinations Promote the Development of Resistance in Acute Myeloid Leukemia

Combination therapy is an important part of cancer treatment and is often employed to overcome or prevent drug resistance. Preclinical screening strategies often prioritize synergistic drug combinations; however, studies of antibiotic combinations show that synergistic drug interactions can accelerate the emergence of resistance because resistance to one drug depletes the effect of both. In this study, we aimed to determine whether synergy drives the development of resistance in cancer cell lines using live-cell imaging. Consistent with prior models of tumor evolution, we found that when controlling for activity, drug synergy is associated with increased probability of developing drug resistance. We demonstrate that these observations are an expected consequence of synergy: the fitness benefit of resisting a drug in a combination is greater in synergistic combinations than in nonsynergistic combinations. These data have important implications for preclinical strategies aiming to develop novel combinations of cancer therapies with robust and durable efficacy.

SIGNIFICANCE

Preclinical strategies to identify combinations for cancer treatment often focus on identifying synergistic combinations. This study shows that in AML cells combinations that rely on synergy can increase the likelihood of developing resistance, suggesting that combination screening strategies may benefit from a more holistic approach rather than focusing on drug synergy. See related commentary by Bhola and Letai, p. 81. This article is featured in Selected Articles from This Issue, p. 80.

Ex vivo discovery of synergistic drug combinations for hematologic malignancies

Combination therapies have improved outcomes for patients with acute myeloid leukemia (AML). However, these patients still have poor overall survival. Although many combination therapies are identified with high-throughput screening (HTS), these approaches are constrained to disease models that can be grown in large volumes (e.g., immortalized cell lines), which have limited translational utility. To identify more effective and personalized treatments, we need better strategies for screening and exploring potential combination therapies. Our objective was to develop an HTS platform for identifying effective combination therapies with highly translatable ex vivo disease models that use size-limited, primary samples from patients with leukemia (AML and myelodysplastic syndrome). We developed a system, ComboFlow, that comprises three main components: MiniFlow, ComboPooler, and AutoGater. MiniFlow conducts ex vivo drug screening with a miniaturized flow-cytometry assay that uses minimal amounts of patient sample to maximize throughput. ComboPooler incorporates computational methods to design efficient screens of pooled drug combinations. AutoGater is an automated gating classifier for flow cytometry that uses machine learning to rapidly analyze the large datasets generated by the assay. We used ComboFlow to efficiently screen more than 3000 drug combinations across 20 patient samples using only 6 million cells per patient sample. In this screen, ComboFlow identified the known synergistic combination of bortezomib and panobinostat. ComboFlow also identified a novel drug combination, dactinomycin and fludarabine, that synergistically killed leukemic cells in 35 % of AML samples. This combination also had limited effects in normal, hematopoietic progenitors. In conclusion, ComboFlow enables exploration of massive landscapes of drug combinations that were previously inaccessible in ex vivo models. We envision that ComboFlow can be used to discover more effective and personalized combination therapies for cancers amenable to ex vivo models.

Harnessing machine learning to find synergistic combinations for FDA-approved cancer drugs

Combination therapy is a fundamental strategy in cancer chemotherapy. It involves administering two or more anti-cancer agents to increase efficacy and overcome multidrug resistance compared to monotherapy. However, drug combinations can exhibit synergy, additivity, or antagonism. This study presents a machine learning framework to classify and predict cancer drug combinations. The framework utilizes several key steps including data collection and annotation from the O'Neil drug interaction dataset, data preprocessing, stratified splitting into training and test sets, construction and evaluation of classification models to categorize combinations as synergistic, additive, or antagonistic, application of regression models to predict combination sensitivity scores for enhanced predictions compared to prior work, and the last step is examination of drug features and mechanisms of action to understand synergy behaviors for optimal combinations. The models identified combination pairs most likely to synergize against different cancers. Kinase inhibitors combined with mTOR inhibitors, DNA damage-inducing drugs or HDAC inhibitors showed benefit, particularly for ovarian, melanoma, prostate, lung and colorectal carcinomas. Analysis highlighted Gemcitabine, MK-8776 and AZD1775 as frequently synergizing across cancer types. This machine learning framework provides a valuable approach to uncover more effective multi-drug regimens.

SynergyX: a multi-modality mutual attention network for interpretable drug synergy prediction

Discovering effective anti-tumor drug combinations is crucial for advancing cancer therapy. Taking full account of intricate biological interactions is highly important in accurately predicting drug synergy. However, the extremely limited prior knowledge poses great challenges in developing current computational methods. To address this, we introduce SynergyX, a multi-modality mutual attention network to improve anti-tumor drug synergy prediction. It dynamically captures cross-modal interactions, allowing for the modeling of complex biological networks and drug interactions. A convolution-augmented attention structure is adopted to integrate multi-omic data in this framework effectively. Compared with other state-of-the-art models, SynergyX demonstrates superior predictive accuracy in both the General Test and Blind Test and cross-dataset validation. By exhaustively screening combinations of approved drugs, SynergyX reveals its ability to identify promising drug combination candidates for potential lung cancer treatment. Another notable advantage lies in its multidimensional interpretability. Taking Sorafenib and Vorinostat as an example, SynergyX serves as a powerful tool for uncovering drug-gene interactions and deciphering cell selectivity mechanisms. In summary, SynergyX provides an illuminating and interpretable framework, poised to catalyze the expedition of drug synergy discovery and deepen our comprehension of rational combination therapy.

Augmented drug combination dataset to improve the performance of machine learning models predicting synergistic anticancer effects

Combination therapy has gained popularity in cancer treatment as it enhances the treatment efficacy and overcomes drug resistance. Although machine learning (ML) techniques have become an indispensable tool for discovering new drug combinations, the data on drug combination therapy currently available may be insufficient to build high-precision models. We developed a data augmentation protocol to unbiasedly scale up the existing anti-cancer drug synergy dataset. Using a new drug similarity metric, we augmented the synergy data by substituting a compound in a drug combination instance with another molecule that exhibits highly similar pharmacological effects. Using this protocol, we were able to upscale the AZ-DREAM Challenges dataset from 8798 to 6,016,697 drug combinations. Comprehensive performance evaluations show that ML models trained on the augmented data consistently achieve higher accuracy than those trained solely on the original dataset. Our data augmentation protocol provides a systematic and unbiased approach to generating more diverse and larger-scale drug combination datasets, enabling the development of more precise and effective ML models. The protocol presented in this study could serve as a foundation for future research aimed at discovering novel and effective drug combinations for cancer treatment.

Mapping combinatorial drug effects to DNA damage response kinase inhibitors

One fundamental principle that underlies various cancer treatments, such as traditional chemotherapy and radiotherapy, involves the induction of catastrophic DNA damage, leading to the apoptosis of cancer cells. In our study, we conduct a comprehensive dose-response combination screening focused on inhibitors that target key kinases involved in the DNA damage response (DDR): ATR, ATM, and DNA-PK. This screening involves 87 anti-cancer agents, including six DDR inhibitors, and encompasses 62 different cell lines spanning 12 types of tumors, resulting in a total of 17,912 combination treatment experiments. Within these combinations, we analyze the most effective and synergistic drug pairs across all tested cell lines, considering the variations among cancers originating from different tissues. Our analysis reveals inhibitors of five DDR-related pathways (DNA topoisomerase, PLK1 kinase, p53-inducible ribonucleotide reductase, PARP, and cell cycle checkpoint proteins) that exhibit strong combinatorial efficacy and synergy when used alongside ATM/ATR/DNA-PK inhibitors.

Logic-based modeling and drug repurposing for the prediction of novel therapeutic targets and combination regimens against E2F1-driven melanoma progression

Melanoma presents increasing prevalence and poor outcomes. Progression to aggressive stages is characterized by overexpression of the transcription factor E2F1 and activation of downstream prometastatic gene regulatory networks (GRNs). Appropriate therapeutic manipulation of the E2F1-governed GRNs holds the potential to prevent metastasis however, these networks entail complex feedback and feedforward regulatory motifs among various regulatory layers, which make it difficult to identify druggable components. To this end, computational approaches such as mathematical modeling and virtual screening are important tools to unveil the dynamics of these signaling networks and identify critical components that could be further explored as therapeutic targets. Herein, we integrated a well-established E2F1-mediated epithelial-mesenchymal transition (EMT) map with transcriptomics data from E2F1-expressing melanoma cells to reconstruct a core regulatory network underlying aggressive melanoma. Using logic-based in silico perturbation experiments of a core regulatory network, we identified that simultaneous perturbation of Protein kinase B (AKT1) and oncoprotein murine double minute 2 (MDM2) drastically reduces EMT in melanoma. Using the structures of the two protein signatures, virtual screening strategies were performed with the FDA-approved drug library. Furthermore, by combining drug repurposing and computer-aided drug design techniques, followed by molecular dynamics simulation analysis, we identified two potent drugs (Tadalafil and Finasteride) that can efficiently inhibit AKT1 and MDM2 proteins. We propose that these two drugs could be considered for the development of therapeutic strategies for the management of aggressive melanoma.

A granularity-level information fusion strategy on hypergraph transformer for predicting synergistic effects of anticancer drugs

Combination therapy has exhibited substantial potential compared to monotherapy. However, due to the explosive growth in the number of cancer drugs, the screening of synergistic drug combinations has become both expensive and time-consuming. Synergistic drug combinations refer to the concurrent use of two or more drugs to enhance treatment efficacy. Currently, numerous computational methods have been developed to predict the synergistic effects of anticancer drugs. However, there has been insufficient exploration of how to mine drug and cell line data at different granularity levels for predicting synergistic anticancer drug combinations. Therefore, this study proposes a granularity-level information fusion strategy based on the hypergraph transformer, named HypertranSynergy, to predict synergistic effects of anticancer drugs. HypertranSynergy introduces synergistic connections between cancer cell lines and drug combinations using hypergraph. Then, the Coarse-grained Information Extraction (CIE) module merges the hypergraph with a transformer for node embeddings. In the CIE module, Contranorm is a normalization layer that mitigates over-smoothing, while Gaussian noise addresses local information gaps. Additionally, the Fine-grained Information Extraction (FIE) module assesses fine-grained information's impact on predictions by employing similarity-aware matrices from drug/cell line features. Both CIE and FIE modules are integrated into HypertranSynergy. In addition, HypertranSynergy achieved the AUC of 0.93${\pm }$0.01 and the AUPR of 0.69${\pm }$0.02 in 5-fold cross-validation of classification task, and the RMSE of 13.77${\pm }$0.07 and the PCC of 0.81${\pm }$0.02 in 5-fold cross-validation of regression task. These results are better than most of the state-of-the-art models.

A CRISPR-drug perturbational map for identifying compounds to combine with commonly used chemotherapeutics

Combination chemotherapy is crucial for successfully treating cancer. However, the enormous number of possible drug combinations means discovering safe and effective combinations remains a significant challenge. To improve this process, we conduct large-scale targeted CRISPR knockout screens in drug-treated cells, creating a genetic map of druggable genes that sensitize cells to commonly used chemotherapeutics. We prioritize neuroblastoma, the most common extracranial pediatric solid tumor, where ~50% of high-risk patients do not survive. Our screen examines all druggable gene knockouts in 18 cell lines (10 neuroblastoma, 8 others) treated with 8 widely used drugs, resulting in 94,320 unique combination-cell line perturbations, which is comparable to the largest existing drug combination screens. Using dense drug-drug rescreening, we find that the top CRISPR-nominated drug combinations are more synergistic than standard-of-care combinations, suggesting existing combinations could be improved. As proof of principle, we discover that inhibition of PRKDC, a component of the non-homologous end-joining pathway, sensitizes high-risk neuroblastoma cells to the standard-of-care drug doxorubicin in vitro and in vivo using patient-derived xenograft (PDX) models. Our findings provide a valuable resource and demonstrate the feasibility of using targeted CRISPR knockout to discover combinations with common chemotherapeutics, a methodology with application across all cancers.

SynAI: an AI-driven cancer drugs synergism prediction platform

Summary

The SynAI solution is a flexible AI-driven drug synergism prediction solution aiming to discover potential therapeutic value of compounds in early stage. Rather than providing a finite choice of drug combination or cell lines, SynAI is capable of predicting potential drug synergism/antagonism using in silico compound SMILE (Simplified Molecular Input Line Entry System) sequences. The AI core of SynAI platform has been trained against cell lines and compound pairs listed by NCI (National Cancer Institute)-Almanac and DurgCombDB datasets. In total, the training data consists of over 1 200 000 in vitro synergism tests on 150 cancer cell lines of different organ origins. Each cell line is tested against over 6000 pairs of FDA (Food and Drug Administration) approved compound combinations. Given one or both candidate compound in SMILE sequence, SynAI is able to predict the potential Bliss score of the combined compound test with the designated cell line without the needs of compound synthetization or structural analysis; thus can significantly reduce the candidate screening costs during the compound development. SynAI platform demonstrates a comparable performance to existing methods but offers more flexibilities for data input.

Availability and implementation

The evaluation version of SynAI is freely accessible online at https://synai.crownbio.com.

Targeted Investigational Oncology Agents in the NCI-60: A Phenotypic Systems-based Resource

The NCI-60 human tumor cell line panel has proved to be a useful tool for the global cancer research community in the search for novel chemotherapeutics. The publicly available cell line characterization and compound screening data from the NCI-60 assay have significantly contributed to the understanding of cellular mechanisms targeted by new oncology agents. Signature sensitivity/resistance patterns generated for a given chemotherapeutic agent against the NCI-60 panel have long served as fingerprint presentations that encompass target information and the mechanism of action associated with the tested agent. We report the establishment of a new public NCI-60 resource based on the cell line screening of a large and growing set of 175 FDA-approved oncology drugs (AOD) plus >825 clinical and investigational oncology agents (IOA), representing a diverse set (>250) of therapeutic targets and mechanisms. This data resource is available to the public (https://ioa.cancer.gov) and includes the raw data from the screening of the IOA and AOD collection along with an extensive set of visualization and analysis tools to allow for comparative study of individual test compounds and multiple compound sets.

Potent Personalized Venetoclax Partners for Acute Myeloid Leukemia Identified by Ex Vivo Drug Screening

SUMMARY

High-throughput screens (HTS) have been utilized to assess the efficacy of single drugs against patient tumor samples with the purpose of optimizing precision therapy, but testing the synergy of drug combinations can identify the ideal second drug to add. With novel sophisticated HTS, effective venetoclax combinations can be revealed that provide the cell state, phenotype, and molecular features of the susceptible and resistant cell populations. See related article by Eide, Kurtz et al., p. 452 (14) .

Augmented drug combination dataset to improve the performance of machine learning models predicting synergistic anticancer effects

Combination therapy has gained popularity in cancer treatment as it enhances the treatment efficacy and overcomes drug resistance. Although machine learning (ML) techniques have become an indispensable tool for discovering new drug combinations, the data on drug combination therapy currently available may be insufficient to build high-precision models. We developed a data augmentation protocol to unbiasedly scale up the existing anti-cancer drug synergy dataset. Using a new drug similarity metric, we augmented the synergy data by substituting a compound in a drug combination instance with another molecule that exhibits highly similar pharmacological effects. Using this protocol, we were able to upscale the AZ-DREAM Challenges dataset from 8,798 to 6,016,697 drug combinations. Comprehensive performance evaluations show that Random Forest and Gradient Boosting Trees models trained on the augmented data achieve higher accuracy than those trained solely on the original dataset. Our data augmentation protocol provides a systematic and unbiased approach to generating more diverse and larger-scale drug combination datasets, enabling the development of more precise and effective ML models. The protocol presented in this study could serve as a foundation for future research aimed at discovering novel and effective drug combinations for cancer treatment.

Statistical Assessment of Drug Synergy from In Vivo Combination Studies Using Mouse Tumor Models

Drug combination therapy is a promising strategy for treating cancer; however, its efficacy and synergy require rigorous evaluation in preclinical studies before going to clinical trials. Existing methods have limited power to detect synergy in animal studies. Here, we introduce a novel approach to assess in vivo drug synergy with high sensitivity and low false discovery rate. It can accurately estimate combination index and synergy score under the Bliss independence model and the highest single agent (HSA) model without any assumption on tumor growth kinetics, study duration, data completeness and balance for tumor volume measurement. We show that our method can effectively validate in vitro drug synergy discovered from cell line assays in in vivo xenograft experiments, and can help to elucidate the mechanism of action for immune checkpoint inhibitors in syngeneic mouse models by combining an anti-PD-1 antibody and several tumor-infiltrating leukocytes depletion treatments. We provide a unified view of in vitro and in vivo synergy by presenting a parallelism between the fixed-dose in vitro and the 4-group in vivo combination studies, so they can be better designed, analyzed, and compared. We emphasize that combination index, when defined here via relative survival of tumor cells, is both dose and time dependent, and give guidelines on designing informative in vivo combination studies. We explain how to interpret and apply Bliss and HSA synergies. Finally, we provide an open-source software package named invivoSyn that enables automated analysis of in vivo synergy using our method and several other existing methods.

SIGNIFICANCE

This work presents a general solution to reliably determine in vivo drug synergy in single-dose 4-group animal combination studies.

RECOVER identifies synergistic drug combinations in vitro through sequential model optimization

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

Inhibitory Mechanisms of Lekethromycin in Dog Liver Cytochrome P450 Enzymes Based on UPLC-MS/MS Cocktail Method

Lekethromycin (LKMS) is a synthetic macrolide compound derivative intended for use as a veterinary medicine. Since there have been no in vitro studies evaluating its potential for drug-drug interactions related to cytochrome P450 (CYP450) enzymes, the effect of the inhibitory mechanisms of LKMS on CYP450 enzymes is still unclear. Thus, this study aimed to evaluate the inhibitory effects of LKMS on dog CYP450 enzymes. A cocktail approach using ultra-performance liquid chromatography-tandem mass spectrometry was conducted to investigate the inhibitory effect of LKMS on canine CYP450 enzymes. Typical probe substrates of phenacetin, coumarin, bupropion, tolbutamide, dextromethorphan, chlorzoxazone, and testosterone were used for CYP1A2, CYP2A6, CYP2B6, CYP2C9, CYP2D6, CYP2E1, and CYP3A4, respectively. This study showed that LKMS might not be a time-dependent inhibitor. LKMS inhibited CYP2A6, CYP2B6, and CYP2D6 via mixed inhibition. LKMS exhibited mixed-type inhibition against the activity of CYP2A6 with an inhibition constant (Ki) value of 135.6 μΜ. LKMS inhibited CYP2B6 in a mixed way, with Ki values of 59.44 μM. A phenotyping study based on an inhibition assay indicated that CYP2D6 contributes to the biotransformation of LKMS. A mixed inhibition of CYP2D6 with Ki values of 64.87 μM was also observed. Given that this study was performed in vitro, further in vivo studies should be conducted to identify the interaction between LKMS and canine CYP450 enzymes to provide data support for the clinical application of LKMS and the avoidance of adverse interactions between other drugs.

Inhibition of GCN2 Reveals Synergy with Cell-Cycle Regulation and Proteostasis

The integrated stress response is a signaling network comprising four branches, each sensing different cellular stressors, converging on the phosphorylation of eIF2α to downregulate global translation and initiate recovery. One of these branches includes GCN2, which senses cellular amino acid insufficiency and participates in maintaining amino acid homeostasis. Previous studies have shown that GCN2 is a viable cancer target when amino acid stress is induced by inhibiting an additional target. In this light, we screened numerous drugs for their potential to synergize with the GCN2 inhibitor TAP20. The drug sensitivity of six cancer cell lines to a panel of 25 compounds was assessed. Each compound was then combined with TAP20 at concentrations below their IC50, and the impact on cell growth was evaluated. The strongly synergistic combinations were further characterized using synergy analyses and matrix-dependent invasion assays. Inhibitors of proteostasis and the MEK-ERK pathway, as well as the pan-CDK inhibitors, flavopiridol, and seliciclib, were potently synergistic with TAP20 in two cell lines. Among their common CDK targets was CDK7, which was more selectively targeted by THZ-1 and synergized with TAP20. Moreover, these combinations were partially synergistic when assessed using matrix-dependent invasion assays. However, TAP20 alone was sufficient to restrict invasion at concentrations well below its growth-inhibitory IC50. We conclude that GCN2 inhibition can be further explored in vivo as a cancer target.

A model-agnostic framework to enhance knowledge graph-based drug combination prediction with drug-drug interaction data and supervised contrastive learning

Combination therapies have brought significant advancements to the treatment of various diseases in the medical field. However, searching for effective drug combinations remains a major challenge due to the vast number of possible combinations. Biomedical knowledge graph (KG)-based methods have shown potential in predicting effective combinations for wide spectrum of diseases, but the lack of credible negative samples has limited the prediction performance of machine learning models. To address this issue, we propose a novel model-agnostic framework that leverages existing drug-drug interaction (DDI) data as a reliable negative dataset and employs supervised contrastive learning (SCL) to transform drug embedding vectors to be more suitable for drug combination prediction. We conducted extensive experiments using various network embedding algorithms, including random walk and graph neural networks, on a biomedical KG. Our framework significantly improved performance metrics compared to the baseline framework. We also provide embedding space visualizations and case studies that demonstrate the effectiveness of our approach. This work highlights the potential of using DDI data and SCL in finding tighter decision boundaries for predicting effective drug combinations.

Review of Predicting Synergistic Drug Combinations

The prediction of drug combinations is of great clinical significance. In many diseases, such as high blood pressure, diabetes, and stomach ulcers, the simultaneous use of two or more drugs has shown clear efficacy. It has greatly reduced the progression of drug resistance. This review presents the latest applications of methods for predicting the effects of drug combinations and the bioactivity databases commonly used in drug combination prediction. These studies have played a significant role in developing precision therapy. We first describe the concept of synergy. we study various publicly available databases for drug combination prediction tasks. Next, we introduce five algorithms applied to drug combinatorial prediction, which include traditional machine learning methods, deep learning methods, mathematical methods, systems biology methods and search algorithms. In the end, we sum up the difficulties encountered in prediction models.

Interpreting the Mechanism of Synergism for Drug Combinations Using Attention-Based Hierarchical Graph Pooling

Synergistic drug combinations provide huge potentials to enhance therapeutic efficacy and to reduce adverse reactions. However, effective and synergistic drug combination prediction remains an open question because of the unknown causal disease signaling pathways. Though various deep learning (AI) models have been proposed to quantitatively predict the synergism of drug combinations, the major limitation of existing deep learning methods is that they are inherently not interpretable, which makes the conclusions of AI models untransparent to human experts, henceforth limiting the robustness of the model conclusion and the implementation ability of these models in real-world human-AI healthcare. In this paper, we develop an interpretable graph neural network (GNN) that reveals the underlying essential therapeutic targets and the mechanism of the synergy (MoS) by mining the sub-molecular network of great importance. The key point of the interpretable GNN prediction model is a novel graph pooling layer, a self-attention-based node and edge pool (henceforth SANEpool), that can compute the attention score (importance) of genes and connections based on the genomic features and topology. As such, the proposed GNN model provides a systematic way to predict and interpret the drug combination synergism based on the detected crucial sub-molecular network. Experiments on various well-adopted drug-synergy-prediction datasets demonstrate that (1) the SANEpool model has superior predictive ability to generate accurate synergy score prediction, and (2) the sub-molecular networks detected by the SANEpool are self-explainable and salient for identifying synergistic drug combinations.

Transcriptional Response to Standard AML Drugs Identifies Synergistic Combinations

Unlike genomic alterations, gene expression profiles have not been widely used to refine cancer therapies. We analyzed transcriptional changes in acute myeloid leukemia (AML) cell lines in response to standard first-line AML drugs cytarabine and daunorubicin by means of RNA sequencing. Those changes were highly cell- and treatment-specific. By comparing the changes unique to treatment-sensitive and treatment-resistant AML cells, we enriched for treatment-relevant genes. Those genes were associated with drug response-specific pathways, including calcium ion-dependent exocytosis and chromatin remodeling. Pharmacological mimicking of those changes using EGFR and MEK inhibitors enhanced the response to daunorubicin with minimum standalone cytotoxicity. The synergistic response was observed even in the cell lines beyond those used for the discovery, including a primary AML sample. Additionally, publicly available cytotoxicity data confirmed the synergistic effect of EGFR inhibitors in combination with daunorubicin in all 60 investigated cancer cell lines. In conclusion, we demonstrate the utility of treatment-evoked gene expression changes to formulate rational drug combinations. This approach could improve the standard AML therapy, especially in older patients.

Challenges and Opportunities in Developing Targeted Therapies for Triple Negative Breast Cancer

Triple negative breast cancer (TNBC) is a heterogeneous group of breast cancers characterized by their lack of estrogen receptors, progesterone receptors, and the HER2 receptor. They are more aggressive than other breast cancer subtypes, with a higher mean tumor size, higher tumor grade, the worst five-year overall survival, and the highest rates of recurrence and metastasis. Developing targeted therapies for TNBC has been a major challenge due to its heterogeneity, and its treatment still largely relies on surgery, radiation therapy, and chemotherapy. In this review article, we review the efforts in developing targeted therapies for TNBC, discuss insights gained from these efforts, and highlight potential opportunities going forward. Accumulating evidence supports TNBCs as multi-driver cancers, in which multiple oncogenic drivers promote cell proliferation and survival. In such multi-driver cancers, targeted therapies would require drug combinations that simultaneously block multiple oncogenic drivers. A strategy designed to generate mechanism-based combination targeted therapies for TNBC is discussed.

Pharmacokinetic and Pharmacodynamic Drug-Drug Interactions: Research Methods and Applications

Because of the high research and development cost of new drugs, the long development process of new drugs, and the high failure rate at later stages, combining past drugs has gradually become a more economical and attractive alternative. However, the ensuing problem of drug-drug interactions (DDIs) urgently need to be solved, and combination has attracted a lot of attention from pharmaceutical researchers. At present, DDI is often evaluated and investigated from two perspectives: pharmacodynamics and pharmacokinetics. However, in some special cases, DDI cannot be accurately evaluated from a single perspective. Therefore, this review describes and compares the current DDI evaluation methods based on two aspects: pharmacokinetic interaction and pharmacodynamic interaction. The methods summarized in this paper mainly include probe drug cocktail methods, liver microsome and hepatocyte models, static models, physiologically based pharmacokinetic models, machine learning models, in vivo comparative efficacy studies, and in vitro static and dynamic tests. This review aims to serve as a useful guide for interested researchers to promote more scientific accuracy and clinical practical use of DDI studies.

Heterocyclic Iminoquinones and Quinones from the National Cancer Institute (NCI, USA) COMPARE Analysis

This review uses the National Cancer Institute (NCI) COMPARE program to establish an extensive list of heterocyclic iminoquinones and quinones with similarities in differential growth inhibition patterns across the 60-cell line panel of the NCI Developmental Therapeutics Program (DTP). Many natural products and synthetic analogues are revealed as potential NAD(P)H:quinone oxidoreductase 1 (NQO1) substrates, through correlations to dipyridoimidazo[5,4-f]benzimidazoleiminoquinone (DPIQ), and as potential thioredoxin reductase (TrxR) inhibitors, through correlations to benzo[1,2,4]triazin-7-ones and pleurotin. The strong correlation to NQO1 infers the enzyme has a major influence on the amount of the active compound with benzo[e]perimidines, phenoxazinones, benz[f]pyrido[1,2-a]indole-6,11-quinones, seriniquinones, kalasinamide, indolequinones, and furano[2,3-b]naphthoquinones, hypothesised as prodrugs. Compounds with very strong correlations to known TrxR inhibitors had inverse correlations to the expression of both reductase enzymes, NQO1 and TrxR, including naphtho[2,3-b][1,4]oxazepane-6,11-diones, benzo[a]carbazole-1,4-diones, pyranonaphthoquinones (including kalafungin, nanaomycin A, and analogues of griseusin A), and discorhabdin C. Quinoline-5,8-dione scaffolds based on streptonigrin and lavendamycin can correlate to either reductase. Inhibitors of TrxR are not necessarily (imino)quinones, e.g., parthenolides, while oxidising moieties are essential for correlations to NQO1, as with the mitosenes. Herein, an overview of synthetic methods and biological activity of each family of heterocyclic imino(quinone) is provided.

SynBa: improved estimation of drug combination synergies with uncertainty quantification

MOTIVATION

There exists a range of different quantification frameworks to estimate the synergistic effect of drug combinations. The diversity and disagreement in estimates make it challenging to determine which combinations from a large drug screening should be proceeded with. Furthermore, the lack of accurate uncertainty quantification for those estimates precludes the choice of optimal drug combinations based on the most favourable synergistic effect.

RESULTS

In this work, we propose SynBa, a flexible Bayesian approach to estimate the uncertainty of the synergistic efficacy and potency of drug combinations, so that actionable decisions can be derived from the model outputs. The actionability is enabled by incorporating the Hill equation into SynBa, so that the parameters representing the potency and the efficacy can be preserved. Existing knowledge may be conveniently inserted due to the flexibility of the prior, as shown by the empirical Beta prior defined for the normalized maximal inhibition. Through experiments on large combination screenings and comparison against benchmark methods, we show that SynBa provides improved accuracy of dose-response predictions and better-calibrated uncertainty estimation for the parameters and the predictions.

AVAILABILITY AND IMPLEMENTATION

The code for SynBa is available at https://github.com/HaotingZhang1/SynBa. The datasets are publicly available (DOI of DREAM: 10.7303/syn4231880; DOI of the NCI-ALMANAC subset: 10.5281/zenodo.4135059).

A Comprehensive Review of Interventional Clinical Trials in Patients with Bone Metastases

Bone metastasis is one of the most important factors associated with poor prognosis for patients with prostate, breast, thyroid, and lung cancer. In the past two decades, 651 clinical trials, including 554 interventional trials, were being registered in ClinicalTrials.gov and pharma.id.informa.com to combat bone metastases from different perspectives. In this review, we comprehensively analyzed, regrouped, and discussed all the interventional trials on bone metastases. Clinical trials were re-grouped into bone-targeting agents, radiotherapy, small molecule targeted therapy, combination therapy, and others, based on the different mechanisms of action including modifying the bone microenvironment and preventing the growth of cancer cells. We also discussed the potential strategies that might improve overall survival and progression-free survival of patients with bone metastases in the future.

A landscape of response to drug combinations in non-small cell lung cancer

Combination of anti-cancer drugs is broadly seen as way to overcome the often-limited efficacy of single agents. The design and testing of combinations are however very challenging. Here we present a uniquely large dataset screening over 5000 targeted agent combinations across 81 non-small cell lung cancer cell lines. Our analysis reveals a profound heterogeneity of response across the tumor models. Notably, combinations very rarely result in a strong gain in efficacy over the range of response observable with single agents. Importantly, gain of activity over single agents is more often seen when co-targeting functionally proximal genes, offering a strategy for designing more efficient combinations. Because combinatorial effect is strongly context specific, tumor specificity should be achievable. The resource provided, together with an additional validation screen sheds light on major challenges and opportunities in building efficacious combinations against cancer and provides an opportunity for training computational models for synergy prediction.

[SMILESynergy: Anticancer drug synergy prediction based on Transformer pre-trained model]

The synergistic effect of drug combinations can solve the problem of acquired resistance to single drug therapy and has great potential for the treatment of complex diseases such as cancer. In this study, to explore the impact of interactions between different drug molecules on the effect of anticancer drugs, we proposed a Transformer-based deep learning prediction model-SMILESynergy. First, the drug text data-simplified molecular input line entry system (SMILES) were used to represent the drug molecules, and drug molecule isomers were generated through SMILES Enumeration for data augmentation. Then, the attention mechanism in the Transformer was used to encode and decode the drug molecules after data augmentation, and finally, a multi-layer perceptron (MLP) was connected to obtain the synergy value of the drugs. Experimental results showed that our model had a mean squared error of 51.34 in regression analysis, an accuracy of 0.97 in classification analysis, and better predictive performance than the DeepSynergy and MulinputSynergy models. SMILESynergy offers improved predictive performance to assist researchers in rapidly screening optimal drug combinations to improve cancer treatment outcomes.

CellMinerCDB: NCATS Is a Web-Based Portal Integrating Public Cancer Cell Line Databases for Pharmacogenomic Explorations

Major advances have been made in the field of precision medicine for treating cancer. However, many open questions remain that need to be answered to realize the goal of matching every patient with cancer to the most efficacious therapy. To facilitate these efforts, we have developed CellMinerCDB: National Center for Advancing Translational Sciences (NCATS; https://discover.nci.nih.gov/rsconnect/cellminercdb_ncats/), which makes available activity information for 2,675 drugs and compounds, including multiple nononcology drugs and 1,866 drugs and compounds unique to the NCATS. CellMinerCDB: NCATS comprises 183 cancer cell lines, with 72 unique to NCATS, including some from previously understudied tissues of origin. Multiple forms of data from different institutes are integrated, including single and combination drug activity, DNA copy number, methylation and mutation, transcriptome, protein levels, histone acetylation and methylation, metabolites, CRISPR, and miscellaneous signatures. Curation of cell lines and drug names enables cross-database (CDB) analyses. Comparison of the datasets is made possible by the overlap between cell lines and drugs across databases. Multiple univariate and multivariate analysis tools are built-in, including linear regression and LASSO. Examples have been presented here for the clinical topoisomerase I (TOP1) inhibitors topotecan and irinotecan/SN-38. This web application provides both substantial new data and significant pharmacogenomic integration, allowing exploration of interrelationships.

SIGNIFICANCE

CellMinerCDB: NCATS provides activity information for 2,675 drugs in 183 cancer cell lines and analysis tools to facilitate pharmacogenomic research and to identify determinants of response.

Analysis and modeling of cancer drug responses using cell cycle phase-specific rate effects

Identifying effective therapeutic treatment strategies is a major challenge to improving outcomes for patients with breast cancer. To gain a comprehensive understanding of how clinically relevant anti-cancer agents modulate cell cycle progression, here we use genetically engineered breast cancer cell lines to track drug-induced changes in cell number and cell cycle phase to reveal drug-specific cell cycle effects that vary across time. We use a linear chain trick (LCT) computational model, which faithfully captures drug-induced dynamic responses, correctly infers drug effects, and reproduces influences on specific cell cycle phases. We use the LCT model to predict the effects of unseen drug combinations and confirm these in independent validation experiments. Our integrated experimental and modeling approach opens avenues to assess drug responses, predict effective drug combinations, and identify optimal drug sequencing strategies.

The recent progress of deep-learning-based in silico prediction of drug combination

Drug combination therapy has become a common strategy for the treatment of complex diseases. There is an urgent need for computational methods to efficiently identify appropriate drug combinations owing to the high cost of experimental screening. In recent years, deep learning has been widely used in the field of drug discovery. Here, we provide a comprehensive review on deep-learning-based drug combination prediction algorithms from multiple aspects. Current studies highlight the flexibility of this technology in integrating multimodal data and the ability to achieve state-of-art performance; it is expected that deep-learning-based prediction of drug combinations should play an important part in future drug discovery.