| CPC G16B 20/00 (2019.02) [G01N 33/57484 (2013.01); G01N 33/587 (2013.01); G01N 33/6848 (2013.01); G01N 33/92 (2013.01); G16B 25/10 (2019.02); G16B 30/00 (2019.02); G16B 40/20 (2019.02); G16B 40/30 (2019.02); G16H 20/40 (2018.01); G16H 50/20 (2018.01); G01N 2570/00 (2013.01)] | 31 Claims |
|
1. A multi-omic method, comprising:
sequencing nucleic acids obtained from a biofluid sample from a subject to obtain nucleic acid sequence information;
quantifying the nucleic acids to obtain nucleic acid quantification information;
processing proteins from the biofluid sample from the subject to obtain proteomic data;
generating a combined dataset comprising at least a portion of the proteomic data, at least a portion of the nucleic acid quantification information, and at least a portion of the nucleic acid sequence information; and
determining a presence or an absence of cancer at least in part by inputting the combined dataset into a trained machine learning classifier, wherein the trained machine learning classifier has
a performance characteristic comprising an area under the curve (AUC) of a receiver operating characteristic (ROC) curve of at least 0.83, and wherein the trained machine learning classifier is trained on cancer samples and non-cancer samples.
|