Extracting functional insights from loss-of-function screens using deep link prediction
- Author
- Pieter-Paul Strybol (UGent) , Maarten Larmuseau (UGent) , Louise de Schaetzen van Brienen (UGent) , Tim Van den Bulcke and Kathleen Marchal (UGent)
- Organization
- Project
-
- The importance of epistasis and network rewiring in determining the adaptive outcome of bacterial populations subjected to antibiotic gradients
- Leveraging comprehensive cancer systems genetic data to uncover the modus operandi of driver mutations
- A data-driven integrative framework for the identification of cancer driver pathways and their mode of action.
- Abstract
- We present deep link prediction (DLP), a method for the interpretation of loss-of-function screens. Our approach uses representation-based link prediction to reprioritize phenotypic readouts by integrating screening experiments with gene-gene interaction networks. We validate on 2 different loss-of-function technologies, RNAi and CRISPR, using datasets obtained from DepMap. Extensive benchmarking shows that DLP-DeepWalk outperforms other methods in recovering cell-specific dependencies, achieving an average precision well above 90% across 7 different cancer types and on both RNAi and CRISPR data. We show that the genes ranked highest by DLP-DeepWalk are appreciably more enriched in drug targets compared to the ranking based on original screening scores. Interestingly, this enrichment is more pronounced on RNAi data compared to CRISPR data, consistent with the greater inherent noise of RNAi screens. Finally, we demonstrate how DLP-DeepWalk can infer the molecular mechanism through which putative targets trigger cell line mortality.
- Keywords
- LARGE-SCALE, CANCER, DEPENDENCIES, TARGETS, CELLS, RNAI
Downloads
-
8069.pdf
- full text (Published version)
- |
- open access
- |
- |
- 2.04 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01GR8SJ8ZN2QFTSTSW0ENR9VSG
- MLA
- Strybol, Pieter-Paul, et al. “Extracting Functional Insights from Loss-of-Function Screens Using Deep Link Prediction.” CELL REPORTS METHODS, vol. 2, no. 2, 2022, doi:10.1016/j.crmeth.2022.100171.
- APA
- Strybol, P.-P., Larmuseau, M., de Schaetzen van Brienen, L., Van den Bulcke, T., & Marchal, K. (2022). Extracting functional insights from loss-of-function screens using deep link prediction. CELL REPORTS METHODS, 2(2). https://doi.org/10.1016/j.crmeth.2022.100171
- Chicago author-date
- Strybol, Pieter-Paul, Maarten Larmuseau, Louise de Schaetzen van Brienen, Tim Van den Bulcke, and Kathleen Marchal. 2022. “Extracting Functional Insights from Loss-of-Function Screens Using Deep Link Prediction.” CELL REPORTS METHODS 2 (2). https://doi.org/10.1016/j.crmeth.2022.100171.
- Chicago author-date (all authors)
- Strybol, Pieter-Paul, Maarten Larmuseau, Louise de Schaetzen van Brienen, Tim Van den Bulcke, and Kathleen Marchal. 2022. “Extracting Functional Insights from Loss-of-Function Screens Using Deep Link Prediction.” CELL REPORTS METHODS 2 (2). doi:10.1016/j.crmeth.2022.100171.
- Vancouver
- 1.Strybol P-P, Larmuseau M, de Schaetzen van Brienen L, Van den Bulcke T, Marchal K. Extracting functional insights from loss-of-function screens using deep link prediction. CELL REPORTS METHODS. 2022;2(2).
- IEEE
- [1]P.-P. Strybol, M. Larmuseau, L. de Schaetzen van Brienen, T. Van den Bulcke, and K. Marchal, “Extracting functional insights from loss-of-function screens using deep link prediction,” CELL REPORTS METHODS, vol. 2, no. 2, 2022.
@article{01GR8SJ8ZN2QFTSTSW0ENR9VSG,
abstract = {{We present deep link prediction (DLP), a method for the interpretation of loss-of-function screens. Our approach uses representation-based link prediction to reprioritize phenotypic readouts by integrating screening experiments with gene-gene interaction networks. We validate on 2 different loss-of-function technologies, RNAi and CRISPR, using datasets obtained from DepMap. Extensive benchmarking shows that DLP-DeepWalk outperforms other methods in recovering cell-specific dependencies, achieving an average precision well above 90% across 7 different cancer types and on both RNAi and CRISPR data. We show that the genes ranked highest by DLP-DeepWalk are appreciably more enriched in drug targets compared to the ranking based on original screening scores. Interestingly, this enrichment is more pronounced on RNAi data compared to CRISPR data, consistent with the greater inherent noise of RNAi screens. Finally, we demonstrate how DLP-DeepWalk can infer the molecular mechanism through which putative targets trigger cell line mortality.}},
articleno = {{100171}},
author = {{Strybol, Pieter-Paul and Larmuseau, Maarten and de Schaetzen van Brienen, Louise and Van den Bulcke, Tim and Marchal, Kathleen}},
issn = {{2667-2375}},
journal = {{CELL REPORTS METHODS}},
keywords = {{LARGE-SCALE,CANCER,DEPENDENCIES,TARGETS,CELLS,RNAI}},
language = {{eng}},
number = {{2}},
pages = {{11}},
title = {{Extracting functional insights from loss-of-function screens using deep link prediction}},
url = {{http://doi.org/10.1016/j.crmeth.2022.100171}},
volume = {{2}},
year = {{2022}},
}
- Altmetric
- View in Altmetric