Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions

Anthony Culos, Amy Tsai, Natalie Stanley, Martin Becker, Mohammad Sajjad Ghaemi, David Mcilwain, Ramin Fallahzadeh, Athena Tanada, Huda Nassar, Camilo Espinosa, Maria Xenochristou, Edward Ganio, Laura Peterson, Xiaoyuan Han, Ina A. Stelzer, Kazuo Ando, Dyani Gaudilliere, Thanaphong Phongpreecha, Ivana Maric, Alan L. Chang et al. (11 additional authors not shown)

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.