Using ontology embeddings for structural inductive bias in gene expression data analysis
| Title: | Using ontology embeddings for structural inductive bias in gene expression data analysis |
|---|---|
| Authors: | Trębacz, Maja, Shams, Zohreh, Jamnik, Mateja, Scherer, Paul, Simidjievski, Nikola, Terre, Helena Andres, Liò, Pietro |
| Publication Year: | 2020 |
| Collection: | Computer Science Quantitative Biology |
| Subject Terms: | Quantitative Biology - Genomics, Computer Science - Machine Learning |
| More Details: | Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning. However, such data is extremely highly dimensional as it contains expression values for over 20000 genes per patient, and the number of samples in the datasets is low. To deal with such settings, we propose to incorporate prior biological knowledge about genes from ontologies into the machine learning system for the task of patient classification given their gene expression data. We use ontology embeddings that capture the semantic similarities between the genes to direct a Graph Convolutional Network, and therefore sparsify the network connections. We show this approach provides an advantage for predicting clinical targets from high-dimensional low-sample data. Comment: 4 pages + 2 page references, 15th Machine Learning in Computational Biology (MLCB) meeting, 2020 |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2011.10998 |
| Accession Number: | edsarx.2011.10998 |
| Database: | arXiv |
| Description not available. |