| Project/Area Number |
16K07205
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Genome biology
|
|---|
| Research Institution | Nihon University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
谷口 奈央 福岡歯科大学, 口腔歯学部, 准教授 (60372885)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2017: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 口腔細菌叢 / 機械学習 / 深層学習 / 系統解析 / 口臭 / 細菌叢 / 菌叢解析 / 口腔内細菌 / サポートベクターマシン / n-グラム / メタゲノム |
|---|
| Outline of Final Research Achievements |
We demonstrated genome-wide comparisons based on n-gram (pentagram) profiles and construction of phylogenetic trees. Pentagram profiles consisting of 512 degenerated patterns of five nucleotides were calculated from 2,602 sequences of bacterial genomes. Pentanucleotide frequency analysis was used to separate species that are difficult to distinguish based on 16S rRNA gene sequences, and the results showed clear separation of Yersinia pestis from Yersinia pseudotuberculosis, Shigella from Escherichia coli. In addtion, a discrimination classifier model was constructed by profiling 16S rRNA-based operational taxonomic units (OTUs) and calculating their relative abundance in saliva samples from 90 subjects. Our deep learning model achieved a predictive accuracy of 97%, compared to the 79% obtained with a support vector machine. This approach is expected to be useful in screening the saliva for prediction of oral malodour before visits to specialist clinics.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で得られた結果から、５塩基連続配列の出現頻度に基づく系統解析は、これまでの手法では困難であった系統解析を可能にすると期待できる。この方法は特に近縁種の解析に有効だったが、遺伝子の連続配置の出現頻度に基づく方法が進化的に離れた種や属のあいだでの解析に効果を発揮する可能性がある。今まで主流だった方法は、特定の遺伝子あるいは複数の遺伝子の相同性によって解析するもので、ゲノム全体の比較によって解析を行なうものがほとんどなかったので、本研究の成果から新たな視点での系統解析が発展すると期待できる。さらに、このような手法に基づく菌叢解析の応用例も示すことができた。
|
