| Project/Area Number |
18K18156
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 62010:Life, health and medical informatics-related
|
|---|
| Research Institution | Institute of Physical and Chemical Research |
|---|
Principal Investigator |
Lysenko Artem 国立研究開発法人理化学研究所, 生命医科学研究センター, 研究員 (80753805)
|
|---|
| Project Period (FY) |
2018-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2019: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2018: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
|
|---|
| Keywords | Deep Learning / Precision Medicine / Cancer / Multiomics / cancer / meta-learning / multiomics / Subtype Discovery / Artificial Intelligence |
|---|
| Outline of Final Research Achievements |
Hepatocellular carcinoma (HCC) is a third most prominent cancer world-wide and is characterized by very high tumor heterogeneity making development of effective treatments particularly challenging. The problem of HCC treatment naturally fits into precision medicine paradigm, where different sub-types of the disease are identified by computational analysis and treatments are customized using this prior knowledge to achieve optimal outcomes.
The aim of this project is to facilitate better understanding of this type of cancer and development of more effective treatments by leveraging recent advances in Artificial Intelligence. This goal was achieved by developing a new type of deep learning architecture for predicting cancer outcome from high-dimensional cancer ‘omics profiling data, which was then applied in conjunction with other computational methods to comprehensively explore whole range of factors affecting patient outcomes.
|
| Academic Significance and Societal Importance of the Research Achievements |
The main contribution of this project is in making advances in computational analysis methods for large biomedical cancer datasets. These innovations will potentially lead to new discoveries necessary for better cancer diagnosis and treatment strategies.
|
