Advertisement
PRMA Consulting - Integrated Evidence Generation 2.0

C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
C-Tech Analytical Solutions
Get a free Nalgene bottle when you send us an enquiry!
Get a free Nalgene bottle when you send us an enquiry!
Get a free Nalgene bottle when you send us an enquiry!
Get a free Nalgene bottle when you send us an enquiry!
Get a free Nalgene bottle when you send us an enquiry!
Get a free Nalgene bottle when you send us an enquiry!
Get a free Nalgene bottle when you send us an enquiry!

Machine Learning Predicts Cancer Subtypes and Progression from Blood Immune Signatures

David A. Simon Davis, Sahngeun Mun, Julianne M. Smith, Dillon Hammill, Jessica Garrett, Katharine Gosling, Jason Price, Hany Elsaleh, Farhan M. Syed, Ines I. Atmosukarto, Benjamin J. C. Quah

Abstract
Clinical adoption of immune checkpoint inhibitors in cancer management has highlighted the interconnection between carcinogenesis and the immune system. Immune cells are integral to the tumour microenvironment and can influence the outcome of therapies. Better understanding of an individual’s immune landscape may play an important role in treatment personalisation.

Introduction
Carcinogenesis is a complex and multi-layered process involving various cellular and tissue networks. Although tumours can be recognised by the immune system, resulting in their growth suppression or elimination, they can also evolve to escape and/or suppress immune responses resulting in tumour growth and metastasis.

Methods:
To monitor changes to the systemic cellular and soluble immune signatures of tumour-bearing animals, a small volume of blood was obtained from the animals’ tail veins in a minimally invasive, feature-rich and high-throughput strategy for clinical translation. Multiparameter flow cytometry was used to generate cell-surface immune signatures, while soluble immune profiles were obtained from the plasma using a bead-based immunoassay established on the same basic principles as sandwich immunoassays.

Discussion
In this study we aimed to investigate the utility of a high-throughput multiparameter flow cytometry method, coupled with a machine learning (ML)-based statistical analysis, to screen blood for immune features capable of predicting cancer presence and growth, and also make inferences about underlying cancer-immune biology.

Acknowledgments: We wish to acknowledge Mick Devoy and Dr Harpreet Vohra for their expert help with flow cytometry.

Citation: Simon Davis DA, Mun S, Smith JM, Hammill D, Garrett J, Gosling K, et al. (2022) Machine learning predicts cancer subtypes and progression from blood immune signatures. PLoS ONE 17(2): e0264631. https://doi.org/10.1371/journal.pone.0264631

Editor: Afsheen Raza, Hamad Medical Corporation, QATAR

Received: November 4, 2021; Accepted: February 14, 2022; Published: February 28, 2022.

Copyright: © 2022 Simon Davis et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All relevant data are within the manuscript, its Supporting Information files and/or held in the Australian National University (ANU) DATA COMMONS repository at https://dx.doi.org/10.25911/6153a8ab5747c (which has the raw Flow Cytometry Standard (FCS) files).

Funding: This work was partially supported by the Radiation Oncology Private Practice Trust Fund, Canberra Health Services, Canberra, Australia. The funder provided support in the form of salaries and/or research materials for authors B.J.C.Q, D.A.S.D., S.M., J.S., F.M.S., I.I.A. but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Competing interests: We have read the journal’s policy and the authors of this manuscript have the following competing interests: I.I.A., J.P., and K.G. declare that they are employees of the biotechnology company Lipotek Pty Ltd. This does not alter our adherence to PLOS ONE policies on sharing data and materials. The remaining authors have declared that no competing interests exist.

Latest Issue
Get instant
access to our latest e-book
THERMOFISHER SEA SGS - ADVANCED ANALYTICS Adare Pharma Solutions - Pediatric Formulation Solutions Thermo Fisher Scientific - 60th year celebration of The Gibco brand Thermo Fisher Scientific - LC-MS biopharmaceutical applications CPC - The Future of Aseptic Connections in Cell and Gene Therapies CPHI PMEC China - Virtual Expo Connect ThermoFisher - Accekerate therapeutic development