期刊
FRONTIERS IN IMMUNOLOGY
卷 11, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fimmu.2020.00071
关键词
pattern recognition receptors; prediction; innate immunity; machine learning; BLAST; toll-like receptors
类别
资金
- J.C. Bose Fellowship [SRP076]
- Department of Science and Technology, India
This study describes a method developed for predicting pattern recognition receptors (PRRs), which are an integral part of the immune system. The models developed here were trained and evaluated on the largest possible non-redundant PRRs, obtained from PRRDB 2.0, and non-pattern recognition receptors (Non-PRRs), obtained from Swiss-Prot. Firstly, a similarity-based approach using BLAST was used to predict PRRs and got limited success due to a large number of no-hits. Secondly, machine learning-based models were developed using sequence composition and achieved a maximum MCC of 0.63. In addition to this, models were developed using evolutionary information in the form of PSSM composition and achieved maximum MCC value of 0.66. Finally, we developed hybrid models that combined a similarity-based approach using BLAST and machine learning-based models. Our best model, which combined BLAST and PSSM based model, achieved a maximum MCC value of 0.82 with an AUROC value of 0.95, utilizing the potential of both similarity-based search and machine learning techniques. In order to facilitate the scientific community, we also developed a web server PRRpred based on the best model developed in this study (http://webs.iiitd.edu.in/ raghava/prrpred/).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据