Related Experiment Video
Updated: Nov 19, 2025
07:19
Bioluminescent Optogenetics 2.0: Harnessing Bioluminescence to Activate Photosensory Proteins In Vitro and In Vivo
Published on: August 4, 2021
5.0K
iBLP: An XGBoost-Based Predictor for Identifying Bioluminescent Proteins
Dan Zhang1, Hua-Dong Chen2, Hasan Zulfiqar1
1School of Life Science and Technology and Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu 610054, China.
Computational and Mathematical Methods in Medicine
|January 28, 2021
Summary
Identifying bioluminescent proteins (BLPs) is challenging due to low sequence similarity. This study introduces iBLP, a novel computational framework using XGBoost and sequence features for accurate BLP identification across diverse organisms.
Area of Science:
- Biochemistry
- Bioinformatics
- Molecular Biology
Background:
- Bioluminescent proteins (BLPs) are crucial for biological research, enabling applications in gene expression analysis, drug discovery, and cellular imaging.
- Identifying BLPs is difficult due to their low sequence similarity across different organisms.
Purpose of the Study:
- To develop a novel computational framework for accurate identification of bioluminescent proteins (BLPs).
- To address the challenge of low sequence similarity among BLPs.
Main Methods:
- Utilized eXtreme gradient boosting (XGBoost) algorithm with sequence-derived features for BLP prediction.
- Collected and analyzed BLP data from bacteria, eukaryotes, and archaea.
- Evaluated various feature extraction methods and classification algorithms to optimize prediction models.
Main Results:
- Developed iBLP, a robust predictor for identifying BLPs based on an optimal XGBoost model.
- Demonstrated iBLP's strong performance on training and independent datasets.
- Showcased iBLP's superiority compared to existing methods for BLP identification.
Conclusions:
- The proposed iBLP framework offers a powerful and accurate solution for computational BLP identification.
- iBLP provides a valuable tool for researchers in various biological and biomedical fields.
- The iBLP webserver and software package are publicly accessible for wider research application.
