Department of Computational and Data Sciences, Indian Institute of Science, Bangalore 560012, India; Structural Biology and Bio-Computing Laboratory, Department of Bioinformatics, Alagappa University, Karaikudi 630004, India.
Department of Computational and Data Sciences, Indian Institute of Science, Bangalore 560012, India.
Comput Biol Chem. 2024 Oct;112:108158. doi: 10.1016/j.compbiolchem.2024.108158. Epub 2024 Jul 23.
Studying the relationship between sequences and their corresponding three-dimensional structure assists structural biologists in solving the protein-folding problem. Despite several experimental and in-silico approaches, still understanding or decoding the three-dimensional structures from the sequence remains a mystery. In such cases, the accuracy of the structure prediction plays an indispensable role. To address this issue, an updated web server (CSSP-2.0) has been created to improve the accuracy of our previous version of CSSP by deploying the existing algorithms. It uses input as probabilities and predicts the consensus for the secondary structure as a highly accurate three-state Q3 (helix, strand, and coil). This prediction is achieved using six recent top-performing methods: MUFOLD-SS, RaptorX, PSSpred v4, PSIPRED, JPred v4, and Porter 5.0. CSSP-2.0 validation includes datasets involving various protein classes from the PDB, CullPDB, and AlphaFold databases. Our results indicate a significant improvement in the accuracy of the consensus Q3 prediction. Using CSSP-2.0, crystallographers can sort out the stable regular secondary structures from the entire complex structure, which would aid in inferring the functional annotation of hypothetical proteins. The web server is freely available at https://bioserver3.physics.iisc.ac.in/cgi-bin/cssp-2/.
研究序列与其相应的三维结构之间的关系有助于结构生物学家解决蛋白质折叠问题。尽管有几种实验和计算方法，但仍然难以从序列中理解或解码三维结构。在这种情况下，结构预测的准确性起着不可或缺的作用。为了解决这个问题，我们创建了一个更新的网络服务器 (CSSP-2.0)，通过部署现有的算法来提高我们之前版本 CSSP 的准确性。它将输入作为概率，并预测二级结构的共识为高度准确的三态 Q3（螺旋、链和线圈）。这一预测是使用六种最新的表现出色的方法实现的：MUFOLD-SS、RaptorX、PSSpred v4、PSIPRED、JPred v4 和 Porter 5.0。CSSP-2.0 的验证包括涉及来自 PDB、CullPDB 和 AlphaFold 数据库的各种蛋白质类别的数据集。我们的结果表明，共识 Q3 预测的准确性有了显著提高。使用 CSSP-2.0，晶体学家可以从整个复杂结构中整理出稳定的规则二级结构，这有助于推断假设蛋白质的功能注释。该网络服务器可在 https://bioserver3.physics.iisc.ac.in/cgi-bin/cssp-2/ 免费获得。
