Home // BIOTECHNO 2022, The Fourteenth International Conference on Bioinformatics, Biocomputational Systems and Biotechnologies // View article
Authors:
Luca Giudice
Claudia Mengoni
Rosalba Giugno
Keywords: Pathway-based classification; Network-based propagation; Patient similarity network; Subgroup cohesive algorithm.
Abstract:
Patient classifiers should be able to rely on the strength of machine learning methodologies while not losing biological interpretability. So far, most of the developed methods lack in one of the two aspects. We propose Simpati, a pathway-based tool for patient classification, which enables accurate classification focusing on the detection of relevant biological features and patient cohesive communities. The tool makes it possible to classify patients and investigate the features which were mostly representative of each class. It presents ad-hoc algorithms for the processing of patient similarity networks and proposes an effective simulation strategy as a recommender system to predict a patient's class based on graph topology. Its computational performance, classification performance and biological validation were performed on genetic data from different types of cancer and compared favorably with state-of-the-art competitors.
Pages: 20 to 25
Copyright: Copyright (c) IARIA, 2022
Publication date: May 22, 2022
Published in: conference
ISSN: 2308-4383
ISBN: 978-1-61208-971-3
Location: Venice, Italy
Dates: from May 22, 2022 to May 26, 2022