Lecture: Identification of targeted proteins by Jamu formulas for different efficacies using machine ...


Lecture: Identification of targeted proteins by Jamu formulas for different efficacies using machine learning approach

[img]

March 16, 2018, 09:30 to: 10:30
Room 341 - Basic Medical Sciences Building 750 McDermot Avenue Winnipeg Manitoba
Team: Events, Training & News

CHIMb.ca
[img]

Lecture: Identification of targeted proteins by Jamu formulas for different efficacies using machine learning approach

Team: Events, Training & News

Location: Room 341 - Basic Medical Sciences Building 750 McDermot Avenue Winnipeg Manitoba

March 16, 2018, 09:30 to: 10:30

Description


Speaker: Dr. Md. Altaf-Ul-Amin, Associate Professor,  Computational Systems Biology Laboratory,  NARA Institute of Science and Technology, Japan


Dr. Md. Altaf-Ul-Amin received his BSc degree in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology , his MS from Universiti Kebangsaan Malaysia and his PhD from  Nara Institute of Science and Technology (NAIST), Japan. He has worked at universities in Bangladesh, Malaysia and Japan. Currently, he is an Associate Professor in the Computational Systems Biology Laboratory of NAIST. His research encompasses topics in network biology, systems biology, cheminformatics and biological databases.

Abstract: Popular traditional medicines from Indonesia are known as Jamu. A Jamu formula is composed of a single plant or a mixture of several plants, and the formulation of Jamu is generally developed based on the experience. In this talk, Dr. Altaf-Ul-Amin will discuss in silico prediction of the interactions between compounds of Jamu herbs and human proteins by utilizing data-intensive science and machine learning methods. Verifying the proteins that are targeted by compounds of natural herbs will be helpful to select natural herb-based drug candidates. Initially, data related to compounds, target proteins, and interactions between them were collected from open access databases. Compounds and amino acid sequences were represented by fingerprint and amino acid composition, respectively. Then, classification-prediction models that predict the interactions between compounds and target proteins through a machine learning method were constructed. A Random Forest model constructed based on MACCS fingerprint and amino acid composition obtained the highest accuracy (89%). Our previous study identified 94 important Jamu compounds related to different efficacies. Dr. Altaf-Ul-Amin used the best model to predict target proteins for aforementioned 94 compounds and assessed the results by supporting evidence from published literature and other sources.

 

Learning Objectives:

(1) To promote an understanding of the relationship between chronic and infectious diseases in humans and traditional medicines from Indonesia.

(2) To share recent metabolomics studies of Jamu medicines that can shed light on disease-metabolite relationships.

(3) To focus on identification of targeted proteins by Jamu formulas for different efficacies using machine learning approach

Map

Location: 750 McDermot Avenue, Winnipeg, Manitoba, Canada