AUTHOR=Duong Thi Kim Chi , Tran Van Lang , Nguyen The Bao , Nguyen Thi Thuy , Ho Ngoc Trung Kien , Nguyen Thanh Q. 

TITLE=Ensemble learning-based approach for automatic classification of termite mushrooms

JOURNAL=Frontiers in Genetics

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2023.1208695

DOI=10.3389/fgene.2023.1208695

ISSN=1664-8021

ABSTRACT=Termite fungi are a type of edible mushroom that holds with significant economic, nutritional, and medicinal value. Unfortunately, identifying these mushrooms based on their morphology and folk experience is not an effective approach due to their short growth period and seasonal nature. Currently, molecular genetic techniques, including the use of the ITS (Internal Transcribed Spacer) gene sequence data, have proven to be a more effective means of identifying these species. However, the limited amount of ITS sequence data published on international GenBank for each termite mushroom species is a challenge due to the decreasing number of these termite mushrooms in nature. To address this issue, this study proposes a new method that utilizes ensemble learning techniques based on ITS sequence data to classify termite mushroom species. To train the model, the paper integrated ITS sequences from the National Center for Biotechnology Information (NCBI) and The Barcode of Life Data System (BOLD) into the dataset. The proposed model achieved good results on the test dataset, with an accuracy of 0.91 and a mean AUCROC of 0.99. The paper then used eight ITS sequences collected from termite mushroom samples in An Linh commune, Phu Giao district, Binh Duong province, Vietnam, to verify the proposed model. The results of species identification were consistent with the NCBI BLAST prediction software. This machine-learning model shows promise as an automatic solution for classifying termite mushroom species. It can help researchers better understand the local growth of these termite mushrooms and develop conservation plans for this rare and valuable plant resource.