Integration Of Mechanistic Immunological Knowledge Into A Machine Learning Pipeline Improves Predictions

Paper Info

Title
Integration Of Mechanistic Immunological Knowledge Into A Machine Learning Pipeline Improves Predictions

Abstract
Recent advances have increased the dimensionality and complexity of immunological data. The authors developed a machine learning approach to incorporate prior immunological knowledge and applied it on clinical examples and a simulation study. The approach may be useful for high-dimensional datasets in clinical settings where the cohort size is limited.The dense network of interconnected cellular signalling responses that are quantifiable in peripheral immune cells provides a wealth of actionable immunological insights. Although high-throughput single-cell profiling techniques, including polychromatic flow and mass cytometry, have matured to a point that enables detailed immune profiling of patients in numerous clinical settings, the limited cohort size and high dimensionality of data increase the possibility of false-positive discoveries and model overfitting. We introduce a generalizable machine learning platform, the immunological Elastic-Net (iEN), which incorporates immunological knowledge directly into the predictive models. Importantly, the algorithm maintains the exploratory nature of the high-dimensional dataset, allowing for the inclusion of immune features with strong predictive capabilities even if not consistent with prior knowledge. In three independent studies our method demonstrates improved predictions for clinically relevant outcomes from mass cytometry data generated from whole blood, as well as a large simulated dataset. The iEN is available under an open-source licence.

Year	DOI	Venue
2020	10.1038/s42256-020-00232-8	NATURE MACHINE INTELLIGENCE
DocType	Volume	Issue
Journal	2	10
ISSN	Citations	PageRank
2522-5839	0	0.34
References	Authors
0	31

Authors (31 rows)

Cited by (0 rows)

References (0 rows)

Name	Order	Citations	PageRank
Anthony Culos	1	0	1.01
Amy S Tsai	2	0	0.34
Natalie Stanley	3	0	0.68
Martin Becker	4	0	0.34
Mohammad S Ghaemi	5	0	0.34
David R McIlwain	6	0	0.34
Ramin Fallahzadeh	7	0	0.34
Athena Tanada	8	0	0.68
Huda Nassar	9	10	3.26
Camilo Espinosa	10	0	0.34
Maria Xenochristou	11	0	0.34
Edward Ganio	12	0	0.68
Laura Peterson	13	0	0.34
Xiaoyuan Han	14	0	0.68
Ina A Stelzer	15	0	0.34
Kazuo Ando	16	0	0.68
Dyani Gaudilliere	17	0	0.68
Thanaphong Phongpreecha	18	0	0.34
Ivana Marić	19	0	0.34
Alan L Chang	20	0	0.34
Gary M Shaw	21	0	0.34
David K Stevenson	22	0	0.34
Sean Bendall	23	0	0.34
Kara L Davis	24	0	0.34
Wendy Fantl	25	0	0.34
Garry P. Nolan	26	46	7.12
Trevor Hastie	27	0	0.34
Robert Tibshirani	28	0	0.34
Martin S Angst	29	0	0.34
Brice Gaudilliere	30	0	1.01
Nima Aghaeepour	31	37	4.89