2023
DOI: 10.1016/j.gpb.2023.01.006
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: Prediction of the response of cancer patients to different treatments and identification of biomarkers of drug response are two major goals of individualized medicine. Here, we developed a deep learning framework called TINDL, completely trained on preclinical cancer cell lines (CCLs), to predict the response of cancer patients to different treatments. TINDL utilizes a tissue-informed normalization to account for the tissue type and cancer type of the tumors and to reduce the statistical discrepancies between … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3

Citation Types

0
3
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
3

Relationship

2
1

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 83 publications
0
3
0
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%
“…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%
“…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%