当前位置: X-MOL 学术J. Comput. Aid. Mol. Des. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Meta-iPVP: a sequence-based meta-predictor for improving the prediction of phage virion proteins using effective feature representation.
Journal of Computer-Aided Molecular Design ( IF 3.5 ) Pub Date : 2020-06-16 , DOI: 10.1007/s10822-020-00323-z
Phasit Charoenkwan 1 , Chanin Nantasenamat 2 , Md Mehedi Hasan 3 , Watshara Shoombuatong 2
Affiliation  

Phage virion protein (PVP) perforate the host cell membrane and eventually culminates in cell rupture thereby releasing replicated phages. The accurate identification of PVP is thus a crucial step towards improving our understanding of the biological function and mechanisms of PVPs. Therefore, it is desirable to develop a computational method that is capable of fast and accurate identification of PVPs. To address this, we propose a novel sequence-based meta-predictor employing probabilistic information (referred herein as the Meta-iPVP) for the accurate identification of PVPs. Particularly, efficient feature representation approach was used to generate discriminative probabilistic features from four machine learning (ML) algorithms making use of seven feature encodings. To the best of our knowledge, the Meta-iPVP is the first meta-based approach that has been developed for PVP prediction. Independent test results indicated that the Meta-iPVP could discern important characteristics between PVPs and non-PVPs as well as achieving the best accuracy and MCC of 0.817 and 0.642, respectively, which corresponds to 6–10% and 14–21% improvements over existing PVP predictors. As such, this demonstrates that the proposed Meta-iPVP is a more efficient, robust and promising for the identification of PVPs. The predictive model is deployed as a publicly accessible Meta-iPVP webserver freely available online at http://camt.pythonanywhere.com/Meta-iPVP.



中文翻译:

Meta-iPVP:一种基于序列的元预测器,用于使用有效的特征表示改进噬菌体病毒粒子蛋白的预测。

噬菌体病毒蛋白 (PVP) 穿透宿主细胞膜并最终导致细胞破裂,从而释放复制的噬菌体。因此,准确识别 PVP 是提高我们对 PVP 生物学功能和机制理解的关键一步。因此,需要开发一种能够快速准确识别 PVP 的计算方法。为了解决这个问题,我们提出了一种新的基于序列的元预测器,它采用概率信息(本文称为 Meta-iPVP)来准确识别 PVP。特别是,使用有效的特征表示方法从使用七种特征编码的四种机器学习 (ML) 算法生成判别概率特征。据我们所知,Meta-iPVP 是第一个为 PVP 预测开发的基于元的方法。独立测试结果表明,Meta-iPVP 可以区分 PVP 和非 PVP 之间的重要特征,并分别达到 0.817 和 0.642 的最佳准确度和 MCC,与现有技术相比分别提高了 6-10% 和 14-21% PVP 预测器。因此,这表明所提出的 Meta-iPVP 是一种更有效、更稳健且更有前景的 PVP 识别方法。预测模型部署为可公开访问的 Meta-iPVP 网络服务器,可在 http://camt.pythonanywhere.com/Meta-iPVP 在线免费获得。独立测试结果表明,Meta-iPVP 可以区分 PVP 和非 PVP 之间的重要特征,并分别达到 0.817 和 0.642 的最佳准确度和 MCC,与现有技术相比分别提高了 6-10% 和 14-21% PVP 预测器。因此,这表明所提出的 Meta-iPVP 是一种更有效、更稳健且更有前景的 PVP 识别方法。预测模型部署为可公开访问的 Meta-iPVP 网络服务器,可在 http://camt.pythonanywhere.com/Meta-iPVP 在线免费获得。独立测试结果表明,Meta-iPVP 可以区分 PVP 和非 PVP 之间的重要特征,并分别实现了 0.817 和 0.642 的最佳准确度和 MCC,与现有技术相比分别提高了 6-10% 和 14-21% PVP 预测器。因此,这表明所提出的 Meta-iPVP 是一种更有效、更稳健且更有前景的 PVP 识别方法。预测模型部署为可公开访问的 Meta-iPVP 网络服务器,可在 http://camt.pythonanywhere.com/Meta-iPVP 在线免费获得。

更新日期:2020-06-16
down
wechat
bug