Realization of precision medicine for cancer chemotherapy

• Project/Area Number: 18K08617
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 55020:Digestive surgery-related
• Research Institution: Osaka University
• Principal Investigator: SAKAI Daisuke 大阪大学, 医学部附属病院, 特任講師(常勤) (10621071)
• Co-Investigator(Kenkyū-buntansha): 石井 秀始 大阪大学, 医学系研究科, 特任教授(常勤) (10280736) ; 今野 雅允 大阪大学, 医学系研究科, 寄附講座講師 (80618207)
• Project Period (FY): 2018-04-01 – 2021-03-31
• Project Status: Completed (Fiscal Year 2020)
• Budget Amount: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000); Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000); Fiscal Year 2019: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2018: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: 化学療法 / 消化器がん / 人工知能

Outline of Final Research Achievements

If a sequence of cancer cells removed by surgery can be performed and the combination of effective anticancer drugs can be determined based on the data, the effect of postoperative chemotherapeutic treatment will increase dramatically. As a result, it is thought that this will lead to improved prognosis. However, at present, it takes a considerable amount of time and effort for humans to analyze sequence data obtained from cancer cells and determine effective anticancer agents, and it is difficult to derive the optimal combination of anticancer agents for individual patients. It's impossible. Therefore, in this study, deep learning was performed using artificial intelligence (AI) from sequence data of about 200 types of cancer cells and susceptibility data of each cell to 265 types of anticancer drugs, and the optimum resistance was obtained from the sequence data. We aimed to build a treatment support system that derives a combination of drugs.

Academic Significance and Societal Importance of the Research Achievements

実装した畳み込みニューラルネットワーク(Convolutional Neural Network :CNN)を用いて最適な抗がん剤の組み合わせの決定を行うことにより、同臨床検体を用いてマウス移植モデル(patient-derived xenograft: PDXモデル)を作成し、人工知能により導き出された効果的抗がん剤の組み合わせで精密医療を目指した基盤を構築することができた。

Research Products

• [Journal Article] A phase II trial of dose-reduced nab-paclitaxel for patients with previously treated, advanced or recurrent gastric cancer (OGSG 1302) (2020)
  • Author(s): Tamura Shigeyuki、Taniguchi Hirokazu、Nishikawa Kazuhiro、Imamura Hiroshi、Fujita Junya、Takeno Atsushi、Matsuyama Jin、Kimura Yutaka、Kawada Junji、Hirao Motohiro、Hirota Masashi、Fujitani Kazumasa、Kurokawa Yukinori、Sakai Daisuke、Kawakami Hisato、Shimokawa Toshio、Satoh Taroh
  • Journal Title: International Journal of Clinical Oncology Volume: 25 Issue: 12 Pages: 2035-2043
  • DOI: 10.1007/s10147-020-01768-w
  • Peer Reviewed / Open Access
• [Journal Article] Comparison of S-1?cisplatin every 5?weeks with capecitabine-cisplatin every 3?weeks for HER2-negative gastric cancer (recurrent after S-1 adjuvant therapy or chemotherapy-na?ve advanced): pooled analysis of HERBIS-2 (OGSG 1103) and HERBIS-4A (OGSG 1105) trials (2020)
  • Author(s): Kawakami Hisato、for the Osaka Gastrointestinal Cancer Chemotherapy Study Group (OGSG)、Fujitani Kazumasa、Matsuyama Jin、Akamaru Yusuke、Tamura Shigeyuki、Endo Shunji、Kimura Yutaka、Makari Youichi、Tamura Takao、Sugimoto Naotoshi、Sakai Daisuke et al
  • Journal Title: International Journal of Clinical Oncology Volume: 25 Issue: 9 Pages: 1635-1643
  • DOI: 10.1007/s10147-020-01711-z
  • Peer Reviewed / Open Access
• [Journal Article] Evaluation of FOLFOX or CAPOX reintroduction with or without bevacizumab in relapsed colorectal cancer patients treated with oxaliplatin as adjuvant chemotherapy (REACT study) (2020)
  • Author(s): Kotaka Masahito、Iwamoto Shigeyoshi、Satake Hironaga、Sakai Daisuke、Kudo Toshihiro、Fukunaga Mutsumi、Konishi Ken、Ide Yoshihito、Ikumoto Taro、Tsuji Akihito、Sano Yasushi、Kato Takeshi、Sugimoto Naotoshi、Satoh Taroh、Kanazawa Akiyoshi、Kurata Takayasu、Yamanaka Takeharu、Tomita Naohiro
  • Journal Title: International Journal of Clinical Oncology Volume: 25 Issue: 8 Pages: 1515-1522
  • DOI: 10.1007/s10147-020-01701-1
  • Peer Reviewed / Open Access
• [Journal Article] Distinct methylation levels of mature microRNAs in gastrointestinal cancers (2019)
  • Author(s): Konno Masamitsu、Koseki Jun、Asai Ayumu、Yamagata Akira、Shimamura Teppei、Motooka Daisuke、Okuzaki Daisuke、Kawamoto Koichi、Mizushima Tsunekazu、Eguchi Hidetoshi、Takiguchi Shuji、Satoh Taroh、Mimori Koshi、Ochiya Takahiro、Doki Yuichiro、Ofusa Ken、Mori Masaki、Ishii Hideshi
  • Journal Title: Nature Communications Volume: 10 Issue: 1 Pages: 3888-3888
  • DOI: 10.1038/s41467-019-11826-1
  • Peer Reviewed / Open Access
• [Journal Article] Application of C. elegans cancer screening test for the detection of pancreatic tumor in genetically engineered mice (2019)
  • Author(s): Ueda Yuji、Kawamoto Koichi、Konno Masamitsu、Noguchi Kozo、Kaifuchi Satoru、Satoh Taroh、Eguchi Hidetoshi、Doki Yuichiro、Hirotsu Takaaki、Mori Masaki、Ishii Hideshi
  • Journal Title: Oncotarget Volume: 10 Issue: 52 Pages: 5412-5418
  • DOI: 10.18632/oncotarget.27124
  • Peer Reviewed / Open Access
• [Journal Article] A Convolutional Neural Network Uses Microscopic Images to Differentiate between Mouse and Human Cell Lines and Their Radioresistant Clones (2018)
  • Author(s): Toratani Masayasu、Konno Masamitsu、Asai Ayumu、Koseki Jun、Kawamoto Koichi、Tamari Keisuke、Li Zhihao、Sakai Daisuke、Kudo Toshihiro、Satoh Taroh、Sato Katsutoshi、Motooka Daisuke、Okuzaki Daisuke、Doki Yuichiro、Mori Masaki、Ogawa Kazuhiko、Ishii Hideshi
  • Journal Title: Cancer Research Volume: 78 Issue: 23 Pages: 6703-6707
  • DOI: 10.1158/0008-5472.can-18-0653
  • Peer Reviewed / Open Access
• [Journal Article] Cell?free culture conditioned medium elicits pancreatic β cell lineage?specific epigenetic reprogramming in mice (2018)
  • Author(s): Kawamoto Koichi、Ohashi Tomofumi、Konno Masamitsu、Nishida Naohiro、Koseki Jun、Matsui Hidetoshi、Sakai Daisuke、Kudo Toshihiro、Eguchi Hidetoshi、Satoh Taroh、Doki Yuichiro、Mori Masaki、Ishii Hideshi
  • Journal Title: Oncology Letters Volume: 16 Pages: 3255-3259
  • DOI: 10.3892/ol.2018.9008
  • Peer Reviewed / Open Access