Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality
Abstract Background Synthetic lethality describes a genetic interaction between two perturbations, leading to cell death, whereas neither event alone has a significant effect on cell viability. This concept can be exploited to specifically target tumor cells. CRISPR viability screens have been widel...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-08-01
|
| Series: | Molecular Cancer |
| Online Access: | https://doi.org/10.1186/s12943-021-01405-8 |
| _version_ | 1818909435208138752 |
|---|---|
| author | Salvatore Benfatto Özdemirhan Serçin Francesca R. Dejure Amir Abdollahi Frank T. Zenke Balca R. Mardin |
| author_facet | Salvatore Benfatto Özdemirhan Serçin Francesca R. Dejure Amir Abdollahi Frank T. Zenke Balca R. Mardin |
| author_sort | Salvatore Benfatto |
| collection | DOAJ |
| description | Abstract Background Synthetic lethality describes a genetic interaction between two perturbations, leading to cell death, whereas neither event alone has a significant effect on cell viability. This concept can be exploited to specifically target tumor cells. CRISPR viability screens have been widely employed to identify cancer vulnerabilities. However, an approach to systematically infer genetic interactions from viability screens is missing. Methods Here we describe PAn-canceR Inferred Synthetic lethalities (PARIS), a machine learning approach to identify cancer vulnerabilities. PARIS predicts synthetic lethal (SL) interactions by combining CRISPR viability screens with genomics and transcriptomics data across hundreds of cancer cell lines profiled within the Cancer Dependency Map. Results Using PARIS, we predicted 15 high confidence SL interactions within 549 DNA damage repair (DDR) genes. We show experimental validation of an SL interaction between the tumor suppressor CDKN2A, thymidine phosphorylase (TYMP) and the thymidylate synthase (TYMS), which may allow stratifying patients for treatment with TYMS inhibitors. Using genome-wide mapping of SL interactions for DDR genes, we unraveled a dependency between the aldehyde dehydrogenase ALDH2 and the BRCA-interacting protein BRIP1. Our results suggest BRIP1 as a potential therapeutic target in ~ 30% of all tumors, which express low levels of ALDH2. Conclusions PARIS is an unbiased, scalable and easy to adapt platform to identify SL interactions that should aid in improving cancer therapy with increased availability of cancer genomics data. |
| first_indexed | 2024-12-19T22:26:52Z |
| format | Article |
| id | doaj.art-ff8c47867c32418e8423c70dbf2b4ab1 |
| institution | Directory Open Access Journal |
| issn | 1476-4598 |
| language | English |
| last_indexed | 2024-12-19T22:26:52Z |
| publishDate | 2021-08-01 |
| publisher | BMC |
| record_format | Article |
| series | Molecular Cancer |
| spelling | doaj.art-ff8c47867c32418e8423c70dbf2b4ab12022-12-21T20:03:29ZengBMCMolecular Cancer1476-45982021-08-0120112210.1186/s12943-021-01405-8Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethalitySalvatore Benfatto0Özdemirhan Serçin1Francesca R. Dejure2Amir Abdollahi3Frank T. Zenke4Balca R. Mardin5BioMed X Institute (GmbH)BioMed X Institute (GmbH)BioMed X Institute (GmbH)Division of Molecular and Translational Radiation Oncology, National Centre for Tumour Diseases (NCT), Heidelberg University HospitalTranslational Innovation Platform Oncology & Immuno-OncologyBioMed X Institute (GmbH)Abstract Background Synthetic lethality describes a genetic interaction between two perturbations, leading to cell death, whereas neither event alone has a significant effect on cell viability. This concept can be exploited to specifically target tumor cells. CRISPR viability screens have been widely employed to identify cancer vulnerabilities. However, an approach to systematically infer genetic interactions from viability screens is missing. Methods Here we describe PAn-canceR Inferred Synthetic lethalities (PARIS), a machine learning approach to identify cancer vulnerabilities. PARIS predicts synthetic lethal (SL) interactions by combining CRISPR viability screens with genomics and transcriptomics data across hundreds of cancer cell lines profiled within the Cancer Dependency Map. Results Using PARIS, we predicted 15 high confidence SL interactions within 549 DNA damage repair (DDR) genes. We show experimental validation of an SL interaction between the tumor suppressor CDKN2A, thymidine phosphorylase (TYMP) and the thymidylate synthase (TYMS), which may allow stratifying patients for treatment with TYMS inhibitors. Using genome-wide mapping of SL interactions for DDR genes, we unraveled a dependency between the aldehyde dehydrogenase ALDH2 and the BRCA-interacting protein BRIP1. Our results suggest BRIP1 as a potential therapeutic target in ~ 30% of all tumors, which express low levels of ALDH2. Conclusions PARIS is an unbiased, scalable and easy to adapt platform to identify SL interactions that should aid in improving cancer therapy with increased availability of cancer genomics data.https://doi.org/10.1186/s12943-021-01405-8 |
| spellingShingle | Salvatore Benfatto Özdemirhan Serçin Francesca R. Dejure Amir Abdollahi Frank T. Zenke Balca R. Mardin Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality Molecular Cancer |
| title | Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality |
| title_full | Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality |
| title_fullStr | Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality |
| title_full_unstemmed | Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality |
| title_short | Uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality |
| title_sort | uncovering cancer vulnerabilities by machine learning prediction of synthetic lethality |
| url | https://doi.org/10.1186/s12943-021-01405-8 |
| work_keys_str_mv | AT salvatorebenfatto uncoveringcancervulnerabilitiesbymachinelearningpredictionofsyntheticlethality AT ozdemirhansercin uncoveringcancervulnerabilitiesbymachinelearningpredictionofsyntheticlethality AT francescardejure uncoveringcancervulnerabilitiesbymachinelearningpredictionofsyntheticlethality AT amirabdollahi uncoveringcancervulnerabilitiesbymachinelearningpredictionofsyntheticlethality AT franktzenke uncoveringcancervulnerabilitiesbymachinelearningpredictionofsyntheticlethality AT balcarmardin uncoveringcancervulnerabilitiesbymachinelearningpredictionofsyntheticlethality |