Modeling drug combination effects via latent tensor reconstruction

Motivation: Combination therapies have emerged as a powerful treatment modality to overcome drug resistance and improve treatment efficacy. However, the number of possible drug combinations increases very rapidly with the number of individual drugs in consideration which makes the comprehensive experimental screening infeasible in practice. Machine learning models offer time- and cost-efficient means to aid this process by prioritising the most effective drug combinations for further pre-clinical and clinical validation. However, the complexity of the underlying interaction patterns across multiple drug doses and in different cellular contexts poses challenges to the predictive modelling of drug combination effects. Results: We introduce comboLTR, highly time-efficient method for learning complex, nonlinear target functions for describing the responses of therapeutic agent combinations in various doses and cancer cell-contexts. The method is based on a polynomial regression via powerful latent tensor reconstruction. It uses a combination of recommender system-style features indexing the data tensor of response values in different contexts, and chemical and multi-omics features as inputs. We demonstrate that comboLTR outperforms state-of-the-art methods in terms of predictive performance and running time, and produces highly accurate results even in the challenging and practical inference scenario where full dose-response matrices are predicted for completely new drug combinations with no available combination and monotherapy response measurements in any training cell line.

Download Full-text

Survey of ex vivo drug combination effects in chronic lymphocytic leukemia reveals synergistic drug effects and genetic dependencies

Leukemia ◽

10.1038/s41375-020-0846-5 ◽

2020 ◽

Vol 34 (11) ◽

pp. 2934-2950

Author(s):

Marina Lukas ◽

Britta Velten ◽

Leopold Sellner ◽

Katarzyna Tomska ◽

Jennifer Hüellein ◽

...

Keyword(s):

Chronic Lymphocytic Leukemia ◽

Drug Combination ◽

Ex Vivo ◽

Drug Effects ◽

Cell Receptor ◽

Drug Combinations ◽

Lymphocytic Leukemia ◽

Critical Pathways ◽

Combination Effects ◽

Synergistic Interactions

Abstract Drug combinations that target critical pathways are a mainstay of cancer care. To improve current approaches to combination treatment of chronic lymphocytic leukemia (CLL) and gain insights into the underlying biology, we studied the effect of 352 drug combination pairs in multiple concentrations by analysing ex vivo drug response of 52 primary CLL samples, which were characterized by “omics” profiling. Known synergistic interactions were confirmed for B-cell receptor (BCR) inhibitors with Bcl-2 inhibitors and with chemotherapeutic drugs, suggesting that this approach can identify clinically useful combinations. Moreover, we uncovered synergistic interactions between BCR inhibitors and afatinib, which we attribute to BCR activation by afatinib through BLK upstream of BTK and PI3K. Combinations of multiple inhibitors of BCR components (e.g., BTK, PI3K, SYK) had effects similar to the single agents. While PI3K and BTK inhibitors produced overall similar effects in combinations with other drugs, we uncovered a larger response heterogeneity of combinations including PI3K inhibitors, predominantly in CLL with mutated IGHV, which we attribute to the target’s position within the BCR-signaling pathway. Taken together, our study shows that drug combination effects can be effectively queried in primary cancer cells, which could aid discovery, triage and clinical development of drug combinations.

Download Full-text

Machine learning methods, databases and tools for drug combination prediction

Briefings in Bioinformatics ◽

10.1093/bib/bbab355 ◽

2021 ◽

Author(s):

Lianlian Wu ◽

Yuqi Wen ◽

Dongjin Leng ◽

Qinglong Zhang ◽

Chong Dai ◽

...

Keyword(s):

Machine Learning ◽

Drug Combination ◽

Predictive Performance ◽

Search Space ◽

Drug Combinations ◽

Learning Methods ◽

Machine Learning Methods ◽

High Throughput Screens ◽

Novel Drug ◽

Future Work

Abstract 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.

Download Full-text

Rationale and Technique for Single and Multiple Drug Combinations in Long-term Intrathecal Infusions

Pain Practice ◽

10.1046/j.1533-2500.2001.01010.x ◽

2001 ◽

Vol 1 (1) ◽

pp. 68-80 ◽

Cited By ~ 3

Author(s):

Leland Lou ◽

Mauricio Orbegozo ◽

Casey L. King

Keyword(s):

Drug Combinations ◽

Multiple Drug

Download Full-text

Biomolecular Network-Based Synergistic Drug Combination Discovery

BioMed Research International ◽

10.1155/2016/8518945 ◽

2016 ◽

Vol 2016 ◽

pp. 1-11 ◽

Cited By ~ 6

Author(s):

Xiangyi Li ◽

Guangrong Qin ◽

Qingmin Yang ◽

Lanming Chen ◽

Lu Xie

Keyword(s):

Drug Combination ◽

Complex Disease ◽

Recent Decade ◽

Drug Combinations ◽

Network Medicine ◽

Disease Therapy ◽

Biomolecular Network ◽

Disease Related Genes ◽

Disease Specific ◽

Synergistic Drug Combinations

Drug combination is a powerful and promising approach for complex disease therapy such as cancer and cardiovascular disease. However, the number of synergistic drug combinations approved by the Food and Drug Administration is very small. To bridge the gap between urgent need and low yield, researchers have constructed various models to identify synergistic drug combinations. Among these models, biomolecular network-based model is outstanding because of its ability to reflect and illustrate the relationships among drugs, disease-related genes, therapeutic targets, and disease-specific signaling pathways as a system. In this review, we analyzed and classified models for synergistic drug combination prediction in recent decade according to their respective algorithms. Besides, we collected useful resources including databases and analysis tools for synergistic drug combination prediction. It should provide a quick resource for computational biologists who work with network medicine or synergistic drug combination designing.

Download Full-text

Using Yeast Synthetic Lethality To Inform Drug Combination for Malaria

Antimicrobial Agents and Chemotherapy ◽

10.1128/aac.01533-17 ◽

2018 ◽

Vol 62 (4) ◽

Author(s):

Suvitha Subramaniam ◽

Christoph D. Schmid ◽

Xue Li Guan ◽

Pascal Mäser

Keyword(s):

Plasmodium Falciparum ◽

Drug Combination ◽

Synthetic Lethality ◽

Drug Combinations ◽

Synthetic Lethal Interaction ◽

Content Type ◽

Synthetic Lethal ◽

Gene Pairs ◽

Phosphatidylinositol 4

ABSTRACT Combinatorial chemotherapy is necessary for the treatment of malaria. However, finding a suitable partner drug for a new candidate is challenging. Here we develop an algorithm that identifies all of the gene pairs of Plasmodium falciparum that possess orthologues in yeast that have a synthetic lethal interaction but are absent in humans. This suggests new options for drug combinations, particularly for inhibitors of targets such as P. falciparum calcineurin, cation ATPase 4, or phosphatidylinositol 4-kinase.

Download Full-text

The IDentif.AI 2.0 Pandemic Readiness Platform: Rapid Prioritization of Optimized COVID-19 Combination Therapy Regimens

10.1101/2021.06.23.21259321 ◽

2021 ◽

Author(s):

Agata Blasiak ◽

Anh TL Truong ◽

Alexandria Remus ◽

Lissa Hooi ◽

Shirley Gek Kheng Seah ◽

...

Keyword(s):

Combination Therapy ◽

Drug Efficacy ◽

Drug Combinations ◽

Multiple Drug ◽

Original Strain ◽

Live Virus ◽

Drug Synergy ◽

Positive Treatment ◽

Strong Candidate ◽

Combination Regimens

Objectives: We aimed to harness IDentif.AI 2.0, a clinically actionable AI platform to rapidly pinpoint and prioritize optimal combination therapy regimens against COVID-19. Methods: A pool of starting candidate therapies was developed in collaboration with a community of infectious disease clinicians and included EIDD-1931 (metabolite of EIDD-2801), baricitinib, ebselen, selinexor, masitinib, nafamostat mesylate, telaprevir (VX-950), SN-38 (metabolite of irinotecan), imatinib mesylate, remdesivir, lopinavir, and ritonavir. Following the initial drug pool assessment, a focused, 6-drug pool was interrogated at 3 dosing levels per drug representing nearly 10,000 possible combination regimens. IDentif.AI 2.0 paired prospective, experimental validation of multi-drug efficacy on a SARS-CoV-2 live virus (propagated, original strain and B.1.351 variant) and Vero E6 assay with a quadratic optimization workflow. Results: Within 3 weeks, IDentif.AI 2.0 realized a list of combination regimens, ranked by efficacy, for clinical go/no-go regimen recommendations. IDentif.AI 2.0 revealed EIDD-1931 to be a strong candidate upon which multiple drug combinations can be derived. Conclusions: IDentif.AI 2.0 rapidly revealed promising drug combinations for a clinical translation. It pinpointed dose-dependent drug synergy behavior to play a role in trial design and realizing positive treatment outcomes. IDentif.AI 2.0 represents an actionable path towards rapidly optimizing combination therapy following pandemic emergence.

Download Full-text

Predictive modelling of hospital readmission: Evaluation of different preprocessing techniques on machine learning classifiers

Intelligent Data Analysis ◽

10.3233/ida-205468 ◽

2021 ◽

Vol 25 (5) ◽

pp. 1073-1098

Author(s):

Nor Hamizah Miswan ◽

Chee Seng Chan ◽

Chong Guan Ng

Keyword(s):

Machine Learning ◽

Hospital Readmission ◽

Performance Metrics ◽

Predictive Performance ◽

Predictive Modelling ◽

Machine Learning Classifiers ◽

Learning Classifiers ◽

Set Up ◽

The Right ◽

The Impact

Hospital readmission is a major cost for healthcare systems worldwide. If patients with a higher potential of readmission could be identified at the start, existing resources could be used more efficiently, and appropriate plans could be implemented to reduce the risk of readmission. Therefore, it is important to predict the right target patients. Medical data is usually noisy, incomplete, and inconsistent. Hence, before developing a prediction model, it is crucial to efficiently set up the predictive model so that improved predictive performance is achieved. The current study aims to analyse the impact of different preprocessing methods on the performance of different machine learning classifiers. The preprocessing applied by previous hospital readmission studies were compared, and the most common approaches highlighted such as missing value imputation, feature selection, data balancing, and feature scaling. The hyperparameters were selected using Bayesian optimisation. The different preprocessing pipelines were assessed using various performance metrics and computational costs. The results indicated that the preprocessing approaches helped improve the model’s prediction of hospital readmission.

Download Full-text

Transcriptomic Signatures Predict Regulators of Drug Synergy and Clinical Regimen Efficacy against Tuberculosis

mBio ◽

10.1128/mbio.02627-19 ◽

2019 ◽

Vol 10 (6) ◽

Cited By ~ 6

Author(s):

Shuyi Ma ◽

Suraj Jaipalli ◽

Jonah Larkins-Ford ◽

Jenny Lohmiller ◽

Bree B. Aldridge ◽

...

Keyword(s):

Clinical Trials ◽

Computational Model ◽

Drug Combinations ◽

Broth Culture ◽

Multiple Drug ◽

Content Type ◽

Drug Synergy ◽

Drug Regimens

ABSTRACT The rapid spread of multidrug-resistant strains has created a pressing need for new drug regimens to treat tuberculosis (TB), which kills 1.8 million people each year. Identifying new regimens has been challenging due to the slow growth of the pathogen Mycobacterium tuberculosis (MTB), coupled with the large number of possible drug combinations. Here we present a computational model (INDIGO-MTB) that identified synergistic regimens featuring existing and emerging anti-TB drugs after screening in silico more than 1 million potential drug combinations using MTB drug transcriptomic profiles. INDIGO-MTB further predicted the gene Rv1353c as a key transcriptional regulator of multiple drug interactions, and we confirmed experimentally that Rv1353c upregulation reduces the antagonism of the bedaquiline-streptomycin combination. A retrospective analysis of 57 clinical trials of TB regimens using INDIGO-MTB revealed that synergistic combinations were significantly more efficacious than antagonistic combinations (P value = 1 × 10−4) based on the percentage of patients with negative sputum cultures after 8 weeks of treatment. Our study establishes a framework for rapid assessment of TB drug combinations and is also applicable to other bacterial pathogens. IMPORTANCE Multidrug combination therapy is an important strategy for treating tuberculosis, the world’s deadliest bacterial infection. Long treatment durations and growing rates of drug resistance have created an urgent need for new approaches to prioritize effective drug regimens. Hence, we developed a computational model called INDIGO-MTB that identifies synergistic drug regimens from an immense set of possible drug combinations using the pathogen response transcriptome elicited by individual drugs. Although the underlying input data for INDIGO-MTB was generated under in vitro broth culture conditions, the predictions from INDIGO-MTB correlated significantly with in vivo drug regimen efficacy from clinical trials. INDIGO-MTB also identified the transcription factor Rv1353c as a regulator of multiple drug interaction outcomes, which could be targeted for rationally enhancing drug synergy.

Download Full-text