2021年度 人工知能学会全国大会(第35回)

講演情報

国際セッション

国際セッション(Regular) » ER-2 Machine learning

[2N3-IS-2b] Machine learning (2/5)

2021年6月9日(水) 13:20 〜 15:00 N会場 (IS会場)

Chair: Eri Sato-Shimokawara (Tokyo Metropolitan University)

13:20 〜 13:40

[2N3-IS-2b-01] The identification of molecular networks on therapeutic responsiveness in AI

〇Shihori Tanabe1,Ryuichi Ono1, Horacio Cabral2, Sabina Quader3, Ed Perkins4, Akihiko Hirose1, Mitsunobu Kano5, Shinpei Ijichi6, Kohei Kessoku7, Hiroshi Yokozaki8, Hiroki Sasaki9 (1, Natl. Inst. of Health Sciences, 2. Univ. of Tokyo, 3. iCONM, 4. USACE ERDC, 5. Okayama Univ., 6. DataRobot Inc., 7. TECNOS Data Science Engineering Inc., 8. Kobe Univ., 9. Natl. Cancer Ctr. Res. Inst.)

キーワード:Molecular Network, AI, therapeutics

Molecular networks affect the responsiveness of diseases to therapeutics. (1) The objective of the study is to identify the molecular networks related to therapeutic responsiveness in diseases. Epithelial-mesenchymal transition (EMT) and cancer stem cells (CSCs) are involved in drug resistance in cancer, and share some molecular characteristics. To reveal the molecular networks responsible for cancer malignancy, gene expression and molecular networks in diffuse-type gastric cancer (GC), which is resistant to anti-cancer drugs, and intestinal-type GC were analyzed. Since the involvement of RNA viral network was identified in GC, the molecules and causal networks in RNA viral networks, as well as in diffuse- and intestinal-type GC were explored. CSC-related networks included glioblastoma multiforme signaling pathway. (2) Outline of the conclusions of the results: Using AI methods, we generated the candidate models including Elastic-Net Classifier (L2 / Binomial Deviance) (Cross Validation score LogLoss 0.3839, AUC 0.9037) and eXtreme Gradient Boosted Trees Classifier (Cross Validation score LogLoss 0.2647, AUC 0.9565) that can distinguish the differences between diffuse- and intestinal-type GC using molecular network data. The alteration in molecular networks may affect the therapeutic responsiveness.

講演PDFパスワード認証
論文PDFの閲覧にはログインが必要です。参加登録者の方は「参加者用ログイン」画面からログインしてください。あるいは論文PDF閲覧用のパスワードを以下にご入力ください。

パスワード