Repositorio Digital de la UPF
Publicación
Artículo científico (JournalArticle)
NetActivity enhances transcriptional signals by combining gene expression into robust gene set activity scores through interpretable autoencoders
Grouping gene expression into gene set activity scores (GSAS) provides better biological insights than studying individual genes. However, existing gene set projection methods cannot return representative, robust, and interpretable GSAS. We developed NetActivity, a machine learning framework that generates GSAS based on a sparsely-connected autoencoder, where each neuron in the inner layer represents a gene set. We proposed a three-tier training that yielded representative, robust, and interpretable GSAS. NetActivity model was trained with 1518 GO biological processes terms and KEGG pathways and all GTEx samples. NetActivity generates GSAS robust to the initialization parameters and representative of the original transcriptome, and assigned higher importance to more biologically relevant genes. Moreover, NetActivity returns GSAS with a more consistent definition and higher interpretability than GSVA and hipathia, state-of-the-art gene set projection methods. Finally, NetActivity enables combining bulk RNA-seq and microarray datasets in a meta-analysis of prostate cancer progression, highlighting gene sets related to cell division, key for disease progression. When applied to metastatic prostate cancer, gene sets associated with cancer progression were also altered due to drug resistance, while a classical enrichment analysis identified gene sets irrelevant to the phenotype. NetActivity is publicly available in Bioconductor and GitHub., MCIN/AEI/10.13039/501100011033 [TED2021-131300B-I00 C. Ruiz-Arenas, M. Hernaez]; Scientific Foundation of the Spanish Association Against Cancer [POSTD235059RUIZ to C. Ruiz-Arenas]; MCIN/AEI/10.13039/501100011033 and “European UnionNextGenerationEU/PRTR” [PID2020‐114394RA‐C33 to M. Hernaez], MCIN/AEI/10.13039/501100011033 [RYC2021- 033127-I to M. Hernaez]; Department of Defense of the US—Congressionally Directed Medical Research Programs [W81XWH-20–1-0262 to L. Wang, M. Hernaez] (in part); Mayo Clinic Center for Individualized Medicine [MC1351 to L. Wang] (in part); A.T. Suharya and D.H. Ghan (to L. Wang); Ayudas Predoctorales Gobierno de Navarra [0011-0537–2021-000106 to I. Marín-Goñi]; MCIN/AEI/10.13039/501100011033 [RYC2019-028578-I to I. Ochoa]; Gipuzkoa Fellows [2022-FELL-000003-01 to I. Ochoa]; MCIN/AEI/10.13039/501100011033 [PID2021-126718OA-I00 to I. Ochoa]. Funding for open access charge: Congressionally Directed Medical Research Programs.