Preclinical-to-Clinical Anti-Cancer Drug Response Prediction and Biomarker Identification Using TINDL

Hostallero, David Earl; Wei, Lixuan; Wang, Liewei; Cairns, Junmei; Emad, Amin

doi:10.1016/j.gpb.2023.01.006

Cited by 3 publications

(3 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the distinct molecular and clinical characteristics of cancer types, it is necessary to evaluate the response of cancer cells to different treatments and treatment strategies in each cancer type. The curation of molecular profiles of cancer cell lines (CCLs) and their response to monotherapies in large databases such as the Cancer Cell Line Encyclopedia (CCLE) ( Barretina et al 2012 ) and Genomics of Drug Sensitivity in Cancer (GDSC) ( Yang et al 2013 ) initiated the development of various computational models for prediction of single drug response in CCLs ( Costello et al 2014 ; Hostallero et al 2022 ) and patient tumors ( Huang et al 2020 ; Hostallero et al 2023 ). More recently, large databases of synergy scores of drug combinations (mainly drug pairs) in CCLs such as DrugComb ( Zagidullin et al 2019 ) have been curated based on the results of many high-throughput drug screening studies.…”

Section: Introductionmentioning

confidence: 99%

MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores

2023

Self Cite

View full text Add to dashboard Cite

Motivation Combination therapies have emerged as a treatment strategy for cancers to reduce the probability of drug resistance and to improve outcome. Large databases curating the results of many drug screening studies on preclinical cancer cell lines have been developed, capturing the synergistic and antagonistic effects of combination of drugs in different cell lines. However, due to the high cost of drug screening experiments and the sheer size of possible drug combinations, these databases are quite sparse. This necessitates the development of transductive computational models to accurately impute these missing values. Results Here, we developed MARSY, a deep learning multi-task model that incorporates information on gene expression profile of cancer cell lines, as well as the differential expression signature induced by each drug to predict drug-pair synergy scores. By utilizing two encoders to capture the interplay between the drug-pairs, as well as the drug-pairs and cell lines, and by adding auxiliary tasks in the predictor, MARSY learns latent embeddings that improve the prediction performance compared to state-of-the-art and traditional machine learning models. Using MARSY, we then predicted the synergy scores of 133,722 new drug-pair cell line combinations, which we have made available to the community as part of this study. Moreover, we validated various insights obtained from these novel predictions using independent studies, confirming the ability of MARSY in making accurate novel predictions. Availability and implementation An implementation of the algorithms in Python and cleaned input datasets are provided in https://github.com/Emad-COMBINE-lab/MARSY. Supplementary information Online-only supplementary data are available at Bioinformatics online.

show abstract

Section: Introductionmentioning

confidence: 99%

MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…cancer cell lines (CCLs) or tumors], drug representations, and network information ( Adam et al 2020 , Guvenc Paltun et al 2021 , Ballester et al 2022 ). In recent years, various models have been proposed using deep learning (DL) for DRP ( Baptista et al 2021 , Chen and Zhang 2022 , Hostallero et al 2022 , El Khili et al 2023 , Hostallero et al 2023 ). In spite of their success in their perspective tasks, most DL models are considered as “black-boxes” with inner operations that are difficult to interpret.…”

Section: Introductionmentioning

confidence: 99%

“…using post hoc feature importance methods). While we and others have successfully used the former strategy in DRP ( Hostallero et al 2022 , Hostallero et al 2023 ) and other applications ( Caruana et al 2015 , Che et al 2016 ), the latter strategy can potentially allow the interpretability to go one step further to provide systems biology insights regarding the mechanisms involved in response to drug treatments. Incorporating prior information such as biological pathway and subsystem information allows the model embeddings to reflect subsystem activities and state changes, which can then be computationally or experimentally investigated to reveal different biological mechanisms that confer specific drug sensitivities ( Kuenzi et al 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?

Hostallero

Emad

2023

Bioinformatics

Self Cite

View full text Add to dashboard Cite

Motivation Interpretable deep learning (DL) models that can provide biological insights, in addition to accurate predictions, are of great interest to the biomedical community. Recently, interpretable DL models that incorporate signaling pathways have been proposed for drug response prediction. While these models improve interpretability, it is unclear whether this comes at the cost of less accurate drug response predictions, or a prediction improvement can also be obtained. Results We comprehensively and systematically assessed four state-of-the-art interpretable DL models using three pathway collections to assess their ability in making accurate predictions on unseen samples from the same dataset, as well as their generalizability to an independent dataset. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. However, in most evaluation setups, the best performance was achieved using a black-box multi-layer perceptron, and the performance of a random forests baseline was comparable to those of the interpretable models. Replacing the signaling pathways with randomly generated pathways showed a comparable performance for the majority of the models. Finally, the performance of all models deteriorated when applied to an independent dataset. These results highlight the importance of systematic evaluation of newly proposed models using carefully selected baselines. We provide different evaluation setups and baseline models that can be used to achieve this goal. Availability Implemented models and datasets are provided in https://doi.org/10.5281/zenodo.7787178 and https://doi.org/10.5281/zenodo.7101665, respectively. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

TheMarker: a comprehensive database of therapeutic biomarkers

Zhang,

Zhou,

Zhou

et al. 2023

Nucleic Acids Research

View full text Add to dashboard Cite

Distinct from the traditional diagnostic/prognostic biomarker (adopted as the indicator of disease state/process), the therapeutic biomarker (ThMAR) has emerged to be very crucial in the clinical development and clinical practice of all therapies. There are five types of ThMAR that have been found to play indispensable roles in various stages of drug discovery, such as: Pharmacodynamic Biomarker essential for guaranteeing the pharmacological effects of a therapy, Safety Biomarker critical for assessing the extent or likelihood of therapy-induced toxicity, Monitoring Biomarker indispensable for guiding clinical management by serially measuring patients’ status, Predictive Biomarker crucial for maximizing the clinical outcome of a therapy for specific individuals, and Surrogate Endpoint fundamental for accelerating the approval of a therapy. However, these data of ThMARs has not been comprehensively described by any of the existing databases. Herein, a database, named ‘TheMarker’, was therefore constructed to (a) systematically offer all five types of ThMAR used at different stages of drug development, (b) comprehensively describe ThMAR information for the largest number of drugs among available databases, (c) extensively cover the widest disease classes by not just focusing on anticancer therapies. These data in TheMarker are expected to have great implication and significant impact on drug discovery and clinical practice, and it is freely accessible without any login requirement at: https://idrblab.org/themarker.

show abstract

Preclinical-to-Clinical Anti-Cancer Drug Response Prediction and Biomarker Identification Using TINDL

Cited by 3 publications

References 83 publications

MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores

MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores

Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?

TheMarker: a comprehensive database of therapeutic biomarkers

Contact Info

Product

Resources

About