Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL
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 th...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-06-01
|
| Series: | Genomics, Proteomics & Bioinformatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1672022923000323 |
| _version_ | 1797372058729971712 |
|---|---|
| author | David Earl Hostallero Lixuan Wei Liewei Wang Junmei Cairns Amin Emad |
| author_facet | David Earl Hostallero Lixuan Wei Liewei Wang Junmei Cairns Amin Emad |
| author_sort | David Earl Hostallero |
| collection | DOAJ |
| description | 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 CCLs and patient tumors. Moreover, by making the deep learning black box interpretable, this model identifies a small set of genes whose expression levels are predictive of drug response in the trained model, enabling identification of biomarkers of drug response. Using data from two large databases of CCLs and cancer tumors, we showed that this model can distinguish between sensitive and resistant tumors for 10 (out of 14) drugs, outperforming various other machine learning models. In addition, our small interfering RNA (siRNA) knockdown experiments on 10 genes identified by this model for one of the drugs (tamoxifen) confirmed that tamoxifen sensitivity is substantially influenced by all of these genes in MCF7 cells, and seven of these genes in T47D cells. Furthermore, genes implicated for multiple drugs pointed to shared mechanism of action among drugs and suggested several important signaling pathways. In summary, this study provides a powerful deep learning framework for prediction of drug response and identification of biomarkers of drug response in cancer. The code can be accessed at https://github.com/ddhostallero/tindl. |
| first_indexed | 2024-03-08T18:29:56Z |
| format | Article |
| id | doaj.art-a5a8bc59c73b4a1eb766852882461bc4 |
| institution | Directory Open Access Journal |
| issn | 1672-0229 |
| language | English |
| last_indexed | 2024-03-08T18:29:56Z |
| publishDate | 2023-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Genomics, Proteomics & Bioinformatics |
| spelling | doaj.art-a5a8bc59c73b4a1eb766852882461bc42023-12-30T04:42:58ZengElsevierGenomics, Proteomics & Bioinformatics1672-02292023-06-01213535550Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDLDavid Earl Hostallero0Lixuan Wei1Liewei Wang2Junmei Cairns3Amin Emad4Department of Electrical and Computer Engineering, McGill University, Montreal, QC H3A, Canada; Mila – Quebec Artificial Intelligence Institute, Montreal, QC H2S, CanadaDepartment of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN 55905, USADepartment of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN 55905, USADepartment of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN 55905, USA; Corresponding authors.Department of Electrical and Computer Engineering, McGill University, Montreal, QC H3A, Canada; Mila – Quebec Artificial Intelligence Institute, Montreal, QC H2S, Canada; The Rosalind and Morris Goodman Cancer Institute, McGill University, Montreal, QC H3A, Canada; Corresponding authors.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 CCLs and patient tumors. Moreover, by making the deep learning black box interpretable, this model identifies a small set of genes whose expression levels are predictive of drug response in the trained model, enabling identification of biomarkers of drug response. Using data from two large databases of CCLs and cancer tumors, we showed that this model can distinguish between sensitive and resistant tumors for 10 (out of 14) drugs, outperforming various other machine learning models. In addition, our small interfering RNA (siRNA) knockdown experiments on 10 genes identified by this model for one of the drugs (tamoxifen) confirmed that tamoxifen sensitivity is substantially influenced by all of these genes in MCF7 cells, and seven of these genes in T47D cells. Furthermore, genes implicated for multiple drugs pointed to shared mechanism of action among drugs and suggested several important signaling pathways. In summary, this study provides a powerful deep learning framework for prediction of drug response and identification of biomarkers of drug response in cancer. The code can be accessed at https://github.com/ddhostallero/tindl.http://www.sciencedirect.com/science/article/pii/S1672022923000323Drug responseDeep learningExplainable AICancerGene knockdown experiment |
| spellingShingle | David Earl Hostallero Lixuan Wei Liewei Wang Junmei Cairns Amin Emad Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL Genomics, Proteomics & Bioinformatics Drug response Deep learning Explainable AI Cancer Gene knockdown experiment |
| title | Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL |
| title_full | Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL |
| title_fullStr | Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL |
| title_full_unstemmed | Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL |
| title_short | Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL |
| title_sort | preclinical to clinical anti cancer drug response prediction and biomarker identification using tindl |
| topic | Drug response Deep learning Explainable AI Cancer Gene knockdown experiment |
| url | http://www.sciencedirect.com/science/article/pii/S1672022923000323 |
| work_keys_str_mv | AT davidearlhostallero preclinicaltoclinicalanticancerdrugresponsepredictionandbiomarkeridentificationusingtindl AT lixuanwei preclinicaltoclinicalanticancerdrugresponsepredictionandbiomarkeridentificationusingtindl AT lieweiwang preclinicaltoclinicalanticancerdrugresponsepredictionandbiomarkeridentificationusingtindl AT junmeicairns preclinicaltoclinicalanticancerdrugresponsepredictionandbiomarkeridentificationusingtindl AT aminemad preclinicaltoclinicalanticancerdrugresponsepredictionandbiomarkeridentificationusingtindl |