DeepVul: A Multi-Task Transformer Model for Joint Prediction of Gene Essentiality and Drug Response
Jararweh, A.; Arredondo, D.; Macaulay, O.; Dicome, M.; Tafoya, L.; Hu, Y.; Virupakshappa, K.; Boland, G.; Flaherty, K.; Sahu, A.
Show abstract
Despite their potential, current precision oncology approaches benefit only a small fraction of patients due to their limited focus on actionable genomic alterations. To expand its applicability, we propose DeepVul, a multi-task transformer-based model designed to predict gene essentiality and drug response from cancer transcriptome data. DeepVul aligns gene expressions, gene perturbations, and drug perturbations into a latent space, enabling simultaneous and accurate prediction of cancer cell vulnerabilities to numerous genes and drugs. Benchmarking against existing precision oncology approaches revealed that Deep-Vul not only matches but also complements oncogene-defined precision methods. Through interpretability analyses, DeepVul identifies underlying mechanisms of treatment response and resistance, as demonstrated with BRAF vulnerability prediction. By leveraging whole-genome transcriptome data, DeepVul enhances the clinical actionability of precision oncology, aiding in the identification of optimal treatments across a broader range of cancer patients. DeepVul is publicly available at https://github.com/alaaj27/DeepVul.git.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- TUGDA: Task uncertainty guided domain adaptation for robust generalization of cancer drug response prediction from in vitro to in vivo settings 97%
- Looking at the BiG picture: Incorporating bipartite graphs in drug response prediction 96%
- AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics 96%
Similar papers in this journal
- Highly Accurate Cancer Phenotype Prediction with AKLIMATE, a Stacked Kernel Learner Integrating Multimodal Genomic Data and Pathway Knowledge 96%
- Monotherapy cancer drug-blind response prediction is limited to intraclass generalization 95%
- Tissue-guided LASSO for prediction of clinical drug response using preclinical samples 95%
Similar papers in this journal
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 96%
- Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study 95%
- Bi-level Graph Learning Unveils Prognosis-Relevant Tumor Microenvironment Patterns in Breast Multiplexed Digital Pathology 94%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.