Identification of Novel Antifibrotic Drug by Data-Driven Research Using AI

• Project/Area Number: 20K15422
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 37030:Chemical biology-related
• Research Institution: Osaka University
• Principal Investigator: Nojima Yosui 大阪大学, 数理・データ科学教育研究センター, 特任講師(常勤) (30815717)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Project Status: Completed (Fiscal Year 2022)
• Budget Amount: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000); Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000); Fiscal Year 2021: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000); Fiscal Year 2020: ¥390,000 (Direct Cost: ¥300,000、Indirect Cost: ¥90,000)
• Keywords: 人工知能 / AI / 機械学習 / IPF / ドラッグリポジショニング / 計算生物学 / 創薬探索 / マルチオミクス / ビッグデータ / 特発性肺線維症 / マルチオミックス

Outline of Research at the Start

特発性肺線維症(IPF)は遺伝的要因および環境的要因によって発症する呼吸器疾患であり、有効な治療薬が社会的に求められている。IPFは肺がんと密接に関連しており、発症メカニズムに多くの類似点がある。そこで本研究では、大規模な公共癌細胞株データと人工知能を活用し、データ駆動的な研究を展開する。具体的には細胞のマルチオミックスデータと化合物情報を用いて、化合物添加による細胞生存率を予測する人工知能を開発する。開発した人工知能にIPF患者肺のマルチオミックスデータと化合物情報を入力し、IPF治療に有効な候補化合物を提案する。最終的には、実験的検証により化合物の薬理効果を確認する。

Outline of Final Research Achievements

In the first year, I aimed to develop an AI for predicting cell survival rates through compound addition. The evaluation was conducted using two types of cross-validation methods. In the following year, I inputted multiomics data and compound information from IPF (Idiopathic Pulmonary Fibrosis) patients into the model constructed in the previous year to predict cell survival rates for each compound. Originally, our plan was to purchase IPF patient samples and collect multiomics data, but due to the impact of the COVID-19 pandemic, it became difficult to obtain the samples. Therefore, I partially collected multiomics data from IPF patient lungs through public databases. As a result, it was found that integrating multiple omics data, such as genes, proteins, and metabolites, is essential for improving accuracy, as it fell below the accuracy obtained in the first year.

Academic Significance and Societal Importance of the Research Achievements

IPFなどの難病はデータ量が少なく、IPF単独のデータでは人工知能による解析は不向きである。そこで本研究では、IPFと同じく細胞増殖によって発症し、情報が豊富にある癌のデータに着目した。単一の疾患では人工知能の入力データ量として不十分であっても、類似性のある疾患のデータを用いてカバーすることができれば、希少難病などの領域にも人工知能による解析アプローチが適用できると考えられる。

Research Products

• [Journal Article] Integration of pharmacoproteomic and computational approaches reveals the cellular signal transduction pathways affected by apatinib in gastric cancer cell lines (2023)
  • Author(s): Nojima Y, Aoki M, Re S, Hirano H, Abe Y, Narumi R, Muraoka S, Shoji H, Honda K, Tomonaga T, Mizuguchi K, Boku N, Adachi J.
  • Journal Title: Comput Struct Biotechnol J. Volume: Mar 15;21 Pages: 2172-2187
  • DOI: 10.1016/j.csbj.2023.03.006
  • Peer Reviewed / Open Access
• [Journal Article] CD14 and lipopolysaccharide-binding protein as novel biomarkers for sarcoidosis by proteomics of serum extracellular vesicles. (2022)
  • Author(s): Futami Y, Takeda Y, KobaT, Narumi R, Nojima Y, Ito M, Nakayama M, Ishida M,Yoshimura H, Naito Y, Fukushima K, Takimoto T, Edahiro R, Matsuki T, Nojima S, Hirata H, Koyama S, Iwahori K, Nagatomo I, Shirai Y, Suga Y, Satoh S, Futami S, Miyake K, Shiroyama T, Inoue Y, Adachi J, Tomonaga T, Ueda K, Kumanogoh A.
  • Journal Title: International immunology Volume: - Issue: 6 Pages: 1-1
  • DOI: 10.1093/intimm/dxac009
  • Peer Reviewed / Open Access
• [Journal Article] Temporal dynamics from phosphoproteomics using endoscopic biopsy specimens provides new therapeutic targets in stage IV gastric cancer (2022)
  • Author(s): Hirano H, Abe Y, Nojima Y, Aoki M, Shoji H, Isoyama J, Honda K, Boku N, Mizuguchi K, Tomonaga T, Adachi J.
  • Journal Title: Sci Rep. Volume: 12(1) Issue: 1 Pages: 4419-4419
  • DOI: 10.1038/s41598-022-08430-7
  • Peer Reviewed / Open Access
• [Journal Article] Data-driven patient stratification and drug target discovery by using medical information and serum proteome data of idiopathic pulmonary fibrosis patients (2022)
  • Author(s): Natsume-Kitatani Yayoi., et al
  • Journal Title: Research Square Volume: preprint
  • DOI: 10.21203/rs.3.rs-405195/v2
  • Open Access
• [Journal Article] Omics Data Analysis Tools for Biomarker Discovery and the Tutorial (2021)
  • Author(s): Nojima Yosui、Takeda Yoshito
  • Journal Title: Springer Proceedings in Mathematics & Statistics Volume: volume 370 Pages: 266-273
  • DOI: 10.1007/978-981-16-4866-3_19
  • ISBN: 9789811648656, 9789811648663
  • Peer Reviewed
• [Journal Article] Expression of Cancer Stem Cell Markers EpCAM and CD90 Is Correlated with Anti- and Pro-Oncogenic EphA2 Signaling in Hepatocellular Carcinoma (2021)
  • Author(s): Asakura Nobuhiko、Nakamura Naotoshi、Muroi Atsushi、Nojima Yosui、Yamashita Taro、Kaneko Shuichi、Ikeda Kazuki、Koshikawa Naohiko、Suzuki Takashi
  • Journal Title: International Journal of Molecular Sciences Volume: 22 Issue: 16 Pages: 8652-8652
  • DOI: 10.3390/ijms22168652
  • Peer Reviewed / Open Access
• [Journal Article] Proteomics of serum extracellular vesicles identifies a novel COPD biomarker, fibulin-3 from elastic fibres. (2021)
  • Author(s): Koba, Takeda, Narumi, Shiromizu, Nojima, Ito, Kuroyama, Futami, Takimoto, Matsuki, Edahiro, Nojima, Hayama, Fukushima, Hirata, Koyama, Iwahori, Nagatomo, Suzuki, Shirai, Murakami, Nakanishi, Nakatani, Suga, Miyake, Shiroyama, Kida, Sasaki, Ueda, Mizuguchi, Adachi, Tomonaga, Kumanogoh
  • Journal Title: ERJ open research. Volume: 7(1) Issue: 1 Pages: 00658-2020
  • DOI: 10.1183/23120541.00658-2020
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Estimation of relationships between chemical substructures and antibiotic resistance-related gene expression in bacteria: Adapting a canonical correlation analysis for small sample data of gathered features using consensus clustering (2020)
  • Author(s): Esaki, T., Horinouchi, T., Natsume-Kitatani, Y., Nojima, Y., and Matsui, H.
  • Journal Title: Chem-Bio Informatics Journal Volume: 20 Issue: 0 Pages: 58-61
  • DOI: 10.1273/cbij.20.58
  • NAID: 130007921242
  • ISSN: 1347-0442, 1347-6297
  • Year and Date: 2020-09-30
  • Peer Reviewed / Open Access
• [Journal Article] Metabolomic analysis of fibrotic mice combined with public RNA‐Seq human lung data reveal potential diagnostic biomarker candidates for lung fibrosis (2020)
  • Author(s): Nojima Yosui、Takeda Yoshito、Maeda Yohei、Bamba Takeshi、Fukusaki Eiichiro、Itoh Mari N.、Mizuguchi Kenji、Kumanogoh Atsushi
  • Journal Title: FEBS Open Bio Volume: 10 Issue: 11 Pages: 2427-2436
  • DOI: 10.1002/2211-5463.12982
  • Peer Reviewed / Open Access
• [Journal Article] Panomicon: A web-based environment for interactive, visual analysis of multi-omics data (2020)
  • Author(s): Allendes Osorio Rodolfo S.、Johan Nystrom-Persson、Nojima Yosui、Kosugi Yuji、Mizuguchi Kenji、Natsume-Kitatani Yayoi
  • Journal Title: Heliyon Volume: 6 Issue: 8 Pages: e04618-e04618
  • DOI: 10.1016/j.heliyon.2020.e04618
  • Peer Reviewed / Open Access
• [Presentation] シングルセルRNA-Seq解析による家族性大腸腺腫症悪性化メカニズムの解明 (2022)
  • Author(s): 今井 綾, 野島 陽水, 八尾 良司, 鈴木 貴
  • Organizer: 応用数理学会 第18回研究部会連合発表会
• [Presentation] オミクスデータを活用した肺線維症バイオマーカー探索に関する研究 (2021)
  • Author(s): 野島 陽水
  • Organizer: 第17回 研究部会連合発表会
• [Remarks] 大阪大学 研究者総覧
  • URL: https://rd.iai.osaka-u.ac.jp/ja/738018fe46601a49.html