On the analysis of the human immunome via an information theoretical approach Online publication date: Wed, 31-Mar-2021
by Maciej Pietrzak; Gerard Lozanski; Michael Grever; Leslie Andritsos; James Blachly; Kerry Rogers; Michal Seweryn
International Journal of Computational Biology and Drug Design (IJCBDD), Vol. 13, No. 5/6, 2020
Abstract: Deep phenotyping of the cellular components of the immune system (the immunome) enables to decompose the multilayer immune network in health and disease. Analysis of immunome data requires computational approaches that allow to detect consistent differences in the non-abundant components and relations between them. In this note we develop an algorithm that scores cell populations by quantifying the amount of information that it carries about the case/control status in the context of the entire immunome. We show that the information-based similarity measures we use are able to detect overlap between rare cell populations in the immunomes and the feature selection algorithm is at least as sensitive to signal as other machine learning tools. We also demonstrate, that we are able to identify a set of positive controls in a real-life immunome data from Hairy Cell Leukemia patients and detect other, biologically relevant cell populations in this context.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Biology and Drug Design (IJCBDD):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com
Our Blog 
Follow us on Twitter 
Visit us on Facebook