Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.15646 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909852836560896 |
|---|---|
| author | Bodinier, Barbara Dissez, Gaetan Ter-Minassian, Lucile Bleistein, Linus Codato, Roberta Klein, John Durand, Eric Dauvin, Antonin |
| author_facet | Bodinier, Barbara Dissez, Gaetan Ter-Minassian, Lucile Bleistein, Linus Codato, Roberta Klein, John Durand, Eric Dauvin, Antonin |
| contents | High-throughput preclinical perturbation screens, where the effects of genetic, chemical, or environmental perturbations are systematically tested on disease models, hold significant promise for machine learning-enhanced drug discovery due to their scale and causal nature. Predictive models trained on such datasets can be used to (i) infer perturbation response for previously untested disease models, and (ii) characterise the biological context that affects perturbation response. Existing predictive models suffer from limited reproducibility, generalisability and interpretability. To address these issues, we introduce a framework of Layered Ensemble of Autoencoders and Predictors (LEAP), a general and flexible ensemble strategy to aggregate predictions from multiple regressors trained using diverse gene expression representation models. LEAP consistently improves prediction performances in unscreened cell lines across modelling strategies. In particular, LEAP applied to perturbation-specific LASSO regressors (PS-LASSO) provides a favorable balance between near state-of-the-art performance and low computation time. We also propose an interpretability approach combining model distillation and stability selection to identify important biological pathways for perturbation response prediction in LEAP. Our models have the potential to accelerate the drug discovery pipeline by guiding the prioritisation of preclinical experiments and providing insights into the biological mechanisms involved in perturbation response. The code and datasets used in this work are publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15646 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predicting gene essentiality and drug response from perturbation screens in preclinical cancer models with LEAP: Layered Ensemble of Autoencoders and Predictors Bodinier, Barbara Dissez, Gaetan Ter-Minassian, Lucile Bleistein, Linus Codato, Roberta Klein, John Durand, Eric Dauvin, Antonin Machine Learning High-throughput preclinical perturbation screens, where the effects of genetic, chemical, or environmental perturbations are systematically tested on disease models, hold significant promise for machine learning-enhanced drug discovery due to their scale and causal nature. Predictive models trained on such datasets can be used to (i) infer perturbation response for previously untested disease models, and (ii) characterise the biological context that affects perturbation response. Existing predictive models suffer from limited reproducibility, generalisability and interpretability. To address these issues, we introduce a framework of Layered Ensemble of Autoencoders and Predictors (LEAP), a general and flexible ensemble strategy to aggregate predictions from multiple regressors trained using diverse gene expression representation models. LEAP consistently improves prediction performances in unscreened cell lines across modelling strategies. In particular, LEAP applied to perturbation-specific LASSO regressors (PS-LASSO) provides a favorable balance between near state-of-the-art performance and low computation time. We also propose an interpretability approach combining model distillation and stability selection to identify important biological pathways for perturbation response prediction in LEAP. Our models have the potential to accelerate the drug discovery pipeline by guiding the prioritisation of preclinical experiments and providing insights into the biological mechanisms involved in perturbation response. The code and datasets used in this work are publicly available. |
| title | Predicting gene essentiality and drug response from perturbation screens in preclinical cancer models with LEAP: Layered Ensemble of Autoencoders and Predictors |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.15646 |