AUTHOR=Kusuma Wisnu Ananta , Habibi Zulfahmi Ibnu , Amir Muhammad Fahmi , Fadli Aulia , Khotimah Husnul , Dewanto Vektor , Heryanto Rudi 

TITLE=Bipartite graph search optimization for type II diabetes mellitus Jamu formulation using branch and bound algorithm

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2022.978741

DOI=10.3389/fphar.2022.978741

ISSN=1663-9812

ABSTRACT=Jamu is an Indonesian traditional herbal medicine that has been practised for generations. Jamu is made from various medicinal plants. Each plant has several compounds directly related to the target protein that are directly associated with a disease. A pharmacological graph can form relationships between plants, active compounds, and target proteins. Research related to the prediction of Jamu formulas for some diseases has been carried out, but there are problems in finding combinations or compositions of Jamu formulas because of the increase in search space size. Some studies adopted the drug-target interaction (DTI) implemented using machine learning or deep learning to predict the DTI for discovering Jamu formula. However, this approach raises important issues, such as imbalanced and high dimensional, overfitting, as well as the need for more procedures to trace compounds to their plants. This study proposes an alternative approach by implementing bi-partite graph search optimization using the branch and bound algorithm to discover the combination or composition of Jamu formulas by optimizing the search on a plant-protein bipartite graph. The branch and bound technique is implemented using the search strategy of Breadth First Search (BrFS), Depth First Search (DFS), and Best First Search (BFS). In order to show the performance of the proposed method, we compared our method with a complete search algorithm, searching all nodes in the tree without pruning. In this study, we specialize in applying the proposed method to search for the Jamu formula for Type II Diabetes Mellitus (T2DM). The result shows that the bipartite graph search with the branch and bound algorithm reduces computation time up to 40 times faster than the complete search strategy to search for a composition of plants. The binary branching strategy is the best choice, while the breadth-first search strategy is the best option in this research. In addition, the proposed method can report the composition of one to four plants for the T2DM Jamu formula. For a combination of 4 plants, we obtain Angelica Sinensis, Citrus aurantium, Glycyrrhiza uralensis, Mangifera indica. This approach is expected to be an alternative way to discover the Jamu formula more accurately.