| 植田 秀樹 | D, 中間発表 | 計算システムズ生物学 | 金谷 重彦, 安本 慶一, 小野 直亮, MD.ALTAF-UL-AMIN, 黄 銘 |
|
title: Inference of cleavage mechanisms of γ-secretase using machine learning
abstract: γ-Secretase is a membrane-embedded protease that cleaves amyloid precursor protein (APP) and generates amyloid beta protein (Aβ), contributing to Alzheimer’s disease. Although γ-secretase is known to cleave APP successively, most likely in every three amino acids, the underlying mechanisms of the cleavage by γ-secretase are not well understood. In this research, we built various machine learning models which predict the amount of a peptide cleaved out by γ-secretase. We selected a model by cleavage site predictions for the reported substrates. Based on the model, we inferred the number of pockets in the active site of γ-secretase, the physicochemical properties involved in cleavages by γ-secretase, and the conserved sequence of γ-secretase. language of the presentation: Japanese | |||
| 前田 雄大 | D, 中間発表 | 計算システムズ生物学 | 金谷 重彦, 安本 慶一, 小野 直亮, MD.ALTAF-UL-AMIN, 黄 銘 |
| WANG HUIJIA | D, 中間発表 | 計算システムズ生物学 | 金谷 重彦, 安本 慶一, 黄 銘, MD.ALTAF-UL-AMIN, 小野 直亮 |
|
title: Cardiotoxicity prediction by using Graph Transformer Neural Network
abstract: The presented work is to construct a new graph neural model which was performed by introducing the sub-structure aware bias to solve the cardiotoxicity prediction problem. We take into account the different types between atoms and edges of chemical molecules in the heterogeneous graphs and extract the key feature of cardiotoxicity and active cliff molecules. We used a different combination of four types to find the best performance with an Accuracy of 90.5%. At the same time, our model got the best performance than MGCNN, ECFP with SVM, and baseline models. After using domain knowledge, the proposed model improved the model performance. Lastly, we explained the model via visualization to help medical researchers understand the key feature of cardiotoxicity molecules. language of the presentation: English | |||