Prediction of tissue-of-origin of early stage cancers using serum miRNomes
Juntaro Matsuzaki, Ken Kato, Kenta Oono, Naoto Tsuchiya, Kazuki Sudo, Akihiko Shimomura, Kenji Tamura, Sho Shiino, Takayuki Kinoshita, Hiroyuki Daiko, Takeyuki Wada, Hitoshi Katai, Hiroki Ochiai, Yukihide Kanemitsu, Hiroyuki Takamaru, Seiichiro Abe, Yutaka Saitō, Narikazu Boku, Shunsuke Kondo, Hideki Ueno, Takuji Okusaka, Kazuaki Shimada, Yuichiro Ohe, Keisuke Asakura, Yukihiro Yoshida, Shun‐ichi Watanabe, Naofumi Asano, Akira Kawai, Makoto Ohno, Yoshitaka Narita, Mitsuya Ishikawa, Tomoyasu Kato, Hiroyuki Fujimoto, Shumpei Niida, Hiromi Sakamoto, Satoko Takizawa, Takuya Akiba, Daisuke Okanohara, Kouya Shiraishi, Takashi Kohno, Fumitaka Takeshita, Hitoshi Nakagama, Nobuyuki Ota, Takahiro Ochiya, Project Team for Development and Diagnostic Technology for Detection of miRNA in Body Fluids, Tomomitsu Hotta, Hitoshi Nakagama, Takahiro Ochiya, Koh Furuta, Ken Kato, Atsushi Ochiai, Shuichi Mitsunaga, Shumpei Niida, Koshi Mimori, Izuho Hatada, Masahiko Kuroda, Takanori Yokota, Masaki Mori, Hideshi Ishii, Yoshiki Murakami, Hidetoshi Tahara, Yoshinobu Baba, Akio Kobori, Satoko Takizawa, Koji Hashimoto, Mitsuharu Hirai, Masahiko Kobayashi, Hitoshi Fujimiya, Daisuke Okanohara, Hiroki Nakae, Hideaki Takashima
Abstract
BACKGROUND: Noninvasive detection of early stage cancers with accurate prediction of tumor tissue-of-origin could improve patient prognosis. Because miRNA profiles differ between organs, circulating miRNomics represent a promising method for early detection of cancers, but this has not been shown conclusively. METHODS: A serum miRNA profile (miRNomes)-based classifier was evaluated for its ability to discriminate cancer types using advanced machine learning. The training set comprised 7931 serum samples from patients with 13 types of solid cancers and 5013 noncancer samples. The validation set consisted of 1990 cancer and 1256 noncancer samples. The contribution of each miRNA to the cancer-type classification was evaluated, and those with a high contribution were identified. RESULTS: Cancer type was predicted with an accuracy of 0.88 (95% confidence interval [CI] = 0.87 to 0.90) in all stages and an accuracy of 0.90 (95% CI = 0.88 to 0.91) in resectable stages (stages 0-II). The F1 score for the discrimination of the 13 cancer types was 0.93. Optimal classification performance was achieved with at least 100 miRNAs that contributed the strongest to accurate prediction of cancer type. Assessment of tissue expression patterns of these miRNAs suggested that miRNAs secreted from the tumor environment could be used to establish cancer type-specific serum miRNomes. CONCLUSIONS: This study demonstrates that large-scale serum miRNomics in combination with machine learning could lead to the development of a blood-based cancer classification system. Further investigations of the regulating mechanisms of the miRNAs that contributed strongly to accurate prediction of cancer type could pave the way for the clinical use of circulating miRNA diagnostics.