Cargando…
Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles
(1) Background: Inter-tumour heterogeneity is one of cancer’s most fundamental features. Patient stratification based on drug response prediction is hence needed for effective anti-cancer therapy. However, single-gene markers of response are rare and/or may fail to achieve a significant impact in th...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8533095/ https://www.ncbi.nlm.nih.gov/pubmed/34680436 http://dx.doi.org/10.3390/biomedicines9101319 |
_version_ | 1784587228938240000 |
---|---|
author | Nguyen, Linh C. Naulaerts, Stefan Bruna, Alejandra Ghislat, Ghita Ballester, Pedro J. |
author_facet | Nguyen, Linh C. Naulaerts, Stefan Bruna, Alejandra Ghislat, Ghita Ballester, Pedro J. |
author_sort | Nguyen, Linh C. |
collection | PubMed |
description | (1) Background: Inter-tumour heterogeneity is one of cancer’s most fundamental features. Patient stratification based on drug response prediction is hence needed for effective anti-cancer therapy. However, single-gene markers of response are rare and/or may fail to achieve a significant impact in the clinic. Machine Learning (ML) is emerging as a particularly promising complementary approach to precision oncology. (2) Methods: Here we leverage comprehensive Patient-Derived Xenograft (PDX) pharmacogenomic data sets with dimensionality-reducing ML algorithms with this purpose. (3) Results: Combining multiple gene alterations via ML leads to better discrimination between sensitive and resistant PDXs in 19 of the 26 analysed cases. Highly predictive ML models employing concise gene lists were found for three cases: paclitaxel (breast cancer), binimetinib (breast cancer) and cetuximab (colorectal cancer). Interestingly, each of these multi-gene ML models identifies some treatment-responsive PDXs not harbouring the best actionable mutation for that case. Thus, ML multi-gene predictors generally have much fewer false negatives than the corresponding single-gene marker. (4) Conclusions: As PDXs often recapitulate clinical outcomes, these results suggest that many more patients could benefit from precision oncology if ML algorithms were also applied to existing clinical pharmacogenomics data, especially those algorithms generating classifiers combining data-selected gene alterations. |
format | Online Article Text |
id | pubmed-8533095 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-85330952021-10-23 Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles Nguyen, Linh C. Naulaerts, Stefan Bruna, Alejandra Ghislat, Ghita Ballester, Pedro J. Biomedicines Article (1) Background: Inter-tumour heterogeneity is one of cancer’s most fundamental features. Patient stratification based on drug response prediction is hence needed for effective anti-cancer therapy. However, single-gene markers of response are rare and/or may fail to achieve a significant impact in the clinic. Machine Learning (ML) is emerging as a particularly promising complementary approach to precision oncology. (2) Methods: Here we leverage comprehensive Patient-Derived Xenograft (PDX) pharmacogenomic data sets with dimensionality-reducing ML algorithms with this purpose. (3) Results: Combining multiple gene alterations via ML leads to better discrimination between sensitive and resistant PDXs in 19 of the 26 analysed cases. Highly predictive ML models employing concise gene lists were found for three cases: paclitaxel (breast cancer), binimetinib (breast cancer) and cetuximab (colorectal cancer). Interestingly, each of these multi-gene ML models identifies some treatment-responsive PDXs not harbouring the best actionable mutation for that case. Thus, ML multi-gene predictors generally have much fewer false negatives than the corresponding single-gene marker. (4) Conclusions: As PDXs often recapitulate clinical outcomes, these results suggest that many more patients could benefit from precision oncology if ML algorithms were also applied to existing clinical pharmacogenomics data, especially those algorithms generating classifiers combining data-selected gene alterations. MDPI 2021-09-26 /pmc/articles/PMC8533095/ /pubmed/34680436 http://dx.doi.org/10.3390/biomedicines9101319 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Nguyen, Linh C. Naulaerts, Stefan Bruna, Alejandra Ghislat, Ghita Ballester, Pedro J. Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles |
title | Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles |
title_full | Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles |
title_fullStr | Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles |
title_full_unstemmed | Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles |
title_short | Predicting Cancer Drug Response In Vivo by Learning an Optimal Feature Selection of Tumour Molecular Profiles |
title_sort | predicting cancer drug response in vivo by learning an optimal feature selection of tumour molecular profiles |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8533095/ https://www.ncbi.nlm.nih.gov/pubmed/34680436 http://dx.doi.org/10.3390/biomedicines9101319 |
work_keys_str_mv | AT nguyenlinhc predictingcancerdrugresponseinvivobylearninganoptimalfeatureselectionoftumourmolecularprofiles AT naulaertsstefan predictingcancerdrugresponseinvivobylearninganoptimalfeatureselectionoftumourmolecularprofiles AT brunaalejandra predictingcancerdrugresponseinvivobylearninganoptimalfeatureselectionoftumourmolecularprofiles AT ghislatghita predictingcancerdrugresponseinvivobylearninganoptimalfeatureselectionoftumourmolecularprofiles AT ballesterpedroj predictingcancerdrugresponseinvivobylearninganoptimalfeatureselectionoftumourmolecularprofiles |