Sergio Doria-Belenguer1, Alexandros Xenos1, Gaia Ceddia1, Noël Malod-Dognin1 and Nataša Pržulj1,2,3,*
1 Barcelona Supercomputing Center (BSC), Barcelona, Spain
2 Department of Computer Science, University College London, London, United Kingdom
3 ICREA, Pg. Lluís Companys 23, Barcelona, Spain
natasha [at] bsc.es
Abstract
Common approaches for deciphering biological networks involve network embedding algorithms. These approaches strictly focus on clustering the genes’ embedding vectors and interpreting such clusters to reveal the hidden information of the networks. However, the difficulty to unambiguously cluster the embeddings of genes in space and the limitations of the functional annotations’ resources hinder the identification of the currently unknown cell’s functioning mechanisms from the gene clusters.
We propose a new approach that shifts this functional exploration from the embedding vectors of genes in space to the axes of the space itself. We assign interpretable and fine-grained semantic meanings to the axes (basis vectors) that span the embedding space to identify the functional mechanisms of a cell.
Our axes-based methodology captures 1.32 times more functional information (GO BP terms associated with the axes) from the embedding spaces than the standard gene-centric approach (GO BP terms enriched in at least one gene cluster). This captured information is also better stratified, as GO BP terms associated with the same axis are, on average, 1.42 times more semantically coherent than those enriched in the same gene cluster. Moreover, it uncovers new data-driven functional interactions that are unregistered in the functional ontologies, but biologically coherent. We exploit these interactions to define new higher-level annotations that we validate through literature curation. Finally, we leverage our methodology to discover evolutionary connections between cellular functions and the evolution of species.
Keywords: Network Biology, Network Embedding, AI
Acknowledgement: This work is supported by the European Research Council (ERC) Consolidator Grant 770827, the Spanish State Research Agency and the Ministry of Science and Innovation MCIN grant PID2022-141920NBI00 / AEI /10.13039/501100011033/ FEDER, UE, and the Department of Research and Universities of the Generalitat de Catalunya code 2021 SGR01536.