Pan-cancer prediction of cell-line drug sensitivity using network-based methods
Pan-cancer prediction of cell-line drug sensitivity using network-based methods
The development of reliable predictive models for individual cancer cell lines to identify an optimal cancer drug is a crucial step to accelerate personalized medicine, but vast differences in cancer cell lines and drug characteristics make it quite challenging to develop predictive models that result in high predictive power and explain the similarity of cell lines or drugs. Our study proposes a novel network-based methodology that breaks the problem into smaller, more interpretable problems to improve the predictive power of anti-cancer drug responses in cell lines. For the drug-sensitivity study, we used the GDSC database for 915 cell lines and 200 drugs. The theory of optimal mass transport was first used to separately cluster cell lines and drugs, using gene-expression profiles and extensive cheminformatic drug features, represented in a form of data networks. To predict cell-line specific drug responses, random forest regression modeling was separately performed for each cell-line drug cluster pair. Post-modeling biological analysis was further performed to identify potential biological correlates associated with drug responses. The network-based clustering method resulted in 30 distinct cell-line drug cluster pairs. Predictive modeling on each cell-line-drug cluster outperformed alternative computational methods in predicting drug responses. We found that among the four drugs top-ranked with respect to prediction performance, three targeted the PI3K/mTOR signaling pathway. Predictive modeling on clustered subsets of cell lines and drugs improved the prediction accuracy of cell-line specific drug responses. Post-modeling analysis identified plausible biological processes associated with drug responses.
Pouryahya, Maryam
1e19637a-c44f-423d-9476-760d76809224
Oh, Jung Hun
753e9122-1405-4aa4-ac1a-e3d64f76a2eb
Mathews, James C.
7987e961-1e4c-4ad1-8eae-5fc51e64a741
Belkhatir, Zehor
de90d742-a58f-4425-837c-20ff960fb9b6
Moosmueller, Caroline
012ab5cc-36d5-4d64-9003-dcaf075eb199
Deasy, Joseph O.
b7de1a95-3c23-47d7-9652-55a2a18f47bd
Tannenbaum, Allen R.
8c08f40e-6f54-4ed7-9de4-c1347d60c7db
19 January 2022
Pouryahya, Maryam
1e19637a-c44f-423d-9476-760d76809224
Oh, Jung Hun
753e9122-1405-4aa4-ac1a-e3d64f76a2eb
Mathews, James C.
7987e961-1e4c-4ad1-8eae-5fc51e64a741
Belkhatir, Zehor
de90d742-a58f-4425-837c-20ff960fb9b6
Moosmueller, Caroline
012ab5cc-36d5-4d64-9003-dcaf075eb199
Deasy, Joseph O.
b7de1a95-3c23-47d7-9652-55a2a18f47bd
Tannenbaum, Allen R.
8c08f40e-6f54-4ed7-9de4-c1347d60c7db
Pouryahya, Maryam, Oh, Jung Hun, Mathews, James C., Belkhatir, Zehor, Moosmueller, Caroline, Deasy, Joseph O. and Tannenbaum, Allen R.
(2022)
Pan-cancer prediction of cell-line drug sensitivity using network-based methods.
International Journal of Molecular Sciences, 23 (3), [1074].
(doi:10.3390/ijms23031074).
Abstract
The development of reliable predictive models for individual cancer cell lines to identify an optimal cancer drug is a crucial step to accelerate personalized medicine, but vast differences in cancer cell lines and drug characteristics make it quite challenging to develop predictive models that result in high predictive power and explain the similarity of cell lines or drugs. Our study proposes a novel network-based methodology that breaks the problem into smaller, more interpretable problems to improve the predictive power of anti-cancer drug responses in cell lines. For the drug-sensitivity study, we used the GDSC database for 915 cell lines and 200 drugs. The theory of optimal mass transport was first used to separately cluster cell lines and drugs, using gene-expression profiles and extensive cheminformatic drug features, represented in a form of data networks. To predict cell-line specific drug responses, random forest regression modeling was separately performed for each cell-line drug cluster pair. Post-modeling biological analysis was further performed to identify potential biological correlates associated with drug responses. The network-based clustering method resulted in 30 distinct cell-line drug cluster pairs. Predictive modeling on each cell-line-drug cluster outperformed alternative computational methods in predicting drug responses. We found that among the four drugs top-ranked with respect to prediction performance, three targeted the PI3K/mTOR signaling pathway. Predictive modeling on clustered subsets of cell lines and drugs improved the prediction accuracy of cell-line specific drug responses. Post-modeling analysis identified plausible biological processes associated with drug responses.
Text
ijms-23-01074
- Version of Record
More information
Accepted/In Press date: 17 January 2022
Published date: 19 January 2022
Identifiers
Local EPrints ID: 501847
URI: http://eprints.soton.ac.uk/id/eprint/501847
ISSN: 1422-0067
PURE UUID: f3948c42-277a-497a-8ad4-9828cd2edf35
Catalogue record
Date deposited: 11 Jun 2025 16:30
Last modified: 22 Aug 2025 02:38
Export record
Altmetrics
Contributors
Author:
Maryam Pouryahya
Author:
Jung Hun Oh
Author:
James C. Mathews
Author:
Zehor Belkhatir
Author:
Caroline Moosmueller
Author:
Joseph O. Deasy
Author:
Allen R. Tannenbaum
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics