TY - JOUR
T1 - A comparative study of multiple instance learning methods for cancer detection using T-cell receptor sequences
AU - Xiong, Danyi
AU - Zhang, Ze
AU - Wang, Tao
AU - Wang, Xinlei
N1 - Funding Information:
This work was supported by NIH grants R01CA258584 (PIs: T. Wang and X. Wang), R15GM131390 (PI: X. Wang), and P30CA142543 (PI: T. Wang), and Cancer Prevention and Research Institute of Texas (CPRIT) grant RP190208 (PI: T. Wang).
Publisher Copyright:
© 2021 The Author(s)
PY - 2021/1
Y1 - 2021/1
N2 - As a branch of machine learning, multiple instance learning (MIL) learns from a collection of labeled bags, each containing a set of instances. The learning process is weakly supervised due to ambiguous instance labels. Since its emergence, MIL has been applied to solve various problems including content-based image retrieval, object tracking/detection, and computer-aided diagnosis. In biomedical research, the use of MIL has been focused on medical image analysis and molecule activity prediction. We review and apply 16 methods to investigate the applicability of MIL to a novel biomedical application, cancer detection using T-cell receptor (TCR) sequences. This important application can be a viable approach for large-scale cancer screening, as TCRs can be easily profiled from a subject's peripheral blood. We consider two feasible data-generating mechanisms, and for the purpose of performance evaluation, we simulate data under each mechanism, where we vary potentially important factors to mimic realistic situations. We also apply the methods to sequencing data of ten cancer types from The Cancer Genome Atlas, as an early proof of concept for distinguishing tumor patients from healthy individuals via TCR sequencing of peripheral blood. We find that given an appropriate MIL method is used, satisfactory performance with Area Under the Receiver Operating Characteristic Curve above 80% can be achieved for five in the ten cancers. Based on our numerical results, we make suggestions about selection of a proper method and avoidance of any method with poor performance. We further point out directions of future research as well as identify a pressing need of new MIL methodologies for improved performance (for some cancer types) and more explainable outcomes.
AB - As a branch of machine learning, multiple instance learning (MIL) learns from a collection of labeled bags, each containing a set of instances. The learning process is weakly supervised due to ambiguous instance labels. Since its emergence, MIL has been applied to solve various problems including content-based image retrieval, object tracking/detection, and computer-aided diagnosis. In biomedical research, the use of MIL has been focused on medical image analysis and molecule activity prediction. We review and apply 16 methods to investigate the applicability of MIL to a novel biomedical application, cancer detection using T-cell receptor (TCR) sequences. This important application can be a viable approach for large-scale cancer screening, as TCRs can be easily profiled from a subject's peripheral blood. We consider two feasible data-generating mechanisms, and for the purpose of performance evaluation, we simulate data under each mechanism, where we vary potentially important factors to mimic realistic situations. We also apply the methods to sequencing data of ten cancer types from The Cancer Genome Atlas, as an early proof of concept for distinguishing tumor patients from healthy individuals via TCR sequencing of peripheral blood. We find that given an appropriate MIL method is used, satisfactory performance with Area Under the Receiver Operating Characteristic Curve above 80% can be achieved for five in the ten cancers. Based on our numerical results, we make suggestions about selection of a proper method and avoidance of any method with poor performance. We further point out directions of future research as well as identify a pressing need of new MIL methodologies for improved performance (for some cancer types) and more explainable outcomes.
KW - Binary classification
KW - Primary instance
KW - T-cell receptor
KW - Weakly supervised learning
KW - Witness rate
UR - http://www.scopus.com/inward/record.url?scp=85108822382&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85108822382&partnerID=8YFLogxK
U2 - 10.1016/j.csbj.2021.05.038
DO - 10.1016/j.csbj.2021.05.038
M3 - Review article
C2 - 34141144
AN - SCOPUS:85108822382
SN - 2001-0370
VL - 19
SP - 3255
EP - 3268
JO - Computational and Structural Biotechnology Journal
JF - Computational and Structural Biotechnology Journal
ER -