Stem cell differentiation platform utilizing Bayesian machine learning
| Project/Area Number |
20KK0160
|
|---|
| Research Category |
Fund for the Promotion of Joint International Research (Fostering Joint International Research (B))
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 44:Biology at cellular to organismal levels, and related fields
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
安井 孝介 京都大学, 高等研究院, 特定助教 (10877640)
ABDALKADER Rodi 立命館大学, 立命館グローバル・イノベーション研究機構, 助教 (20839964)
|
|---|
| Project Period (FY) |
2020-10-27 – 2024-03-31
|
| Project Status |
Granted (Fiscal Year 2022)
|
| Budget Amount *help |
¥18,850,000 (Direct Cost: ¥14,500,000、Indirect Cost: ¥4,350,000)
Fiscal Year 2023: ¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2022: ¥7,280,000 (Direct Cost: ¥5,600,000、Indirect Cost: ¥1,680,000)
Fiscal Year 2021: ¥7,280,000 (Direct Cost: ¥5,600,000、Indirect Cost: ¥1,680,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
|
|---|
| Keywords | stem cell / cardiomyocite / machine learning / statistics / small molecule / Stem cell / Cardiomyocite / Screening / Machine learning / DFT / Data-driven / ベイズ最適化 / 材料情報 / 機械学習 / 幹細胞分化増殖 / 再生医療 |
|---|
| Outline of Research at the Start |
In order to generate tissues for clinical purposes, cells of a specific type must be created. Such cells are usually generated by adding nutrients to a stem cell culture medium. This project will develop an AI-based platform for efficient identification nutrients for inducing the target cell state.
|
| Outline of Annual Research Achievements |
During 2032, we made three steps towards achieving our goal of realising in-silico design of small molecules for inducing cardiac differentiation.
[1] We developed a new type of molecule descriptor based on van der Waals volume shapes and hydrophilicity information. By using these descriptors in neural network model, we achieved good predictive accuracy for the cardiac differentiation effect of small molecules (true positive rate = 77 %). [2] We developed a new code for in-silicon generation of small organic compounds based on a molecule fragment library. The candidate compounds generated by this code can be tested by the neural network described above. [3] We succeeded to implement a cardiac differentiation protocol in our laboratory, which can be used to test the compounds predicted above.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
- The project was initially delay due to the loss of a stem cell laboratory at our institute for generating the model training data. However, during early FY2021 we were able to obtain some alternative training data from a collaborator, and following this we could quickly develop the machine learning model within the planned time schedule.
- Moreover, a colleague at our institute kindly allowed our project researcher to work in his wet lab. Working in this lab, the project researcher was able to quickly reproduce and optimise a cardiomyocite differentiation protocol from the literature, and is now ready to test new compounds. Thanks to this outcome, the experimental part of the project is proceeding according to plan.
|
| Strategy for Future Research Activity |
For the final year of this project, we will use our molecule-generation code along with our neural network model to predict new molecules for cardiomyocite generation. These compounds will be synthesised and then tested in a wet laboratory experiment. Finally, for the successful compounds discovered by this method, we will perform various molecular biology techniques to characterise the maturity states and other properties of the produced cardiomyocites. We hope to have submitted a manuscript on this work within the next year.
|
Report
(3 results)
Research Products
(6 results)
