Research and Information Systems, LLC, Indianapolis, IN, USA.
Department of Physics, Indiana University, Indianapolis, IN, USA.
Methods Mol Biol. 2025;2867:141-152. doi: 10.1007/978-1-0716-4196-5_8.
We analyzed four cases from the CASP15 experiment with low prediction accuracy and compared AlphaFold2, SPINE-X, and Seder on these cases. We find that overall, AlphaFold2 performs better than SPINE-X in predicting secondary structure (SS) and solvent accessible surface area (ASA). For some cases, SPINE-X better predicts sheet and coil regions. We also find that AlphaFold2 is better than Seder in selecting the best matching tertiary structure model for one case and is worse in another case. For two cases Alphafold2 and Seder selected the same models. From the cases presented here, it appears that AlphaFold2 predicts more compact structures than the native one. We find that while, as widely reported, AlphaFold2 significantly improved protein tertiary structure prediction, there are cases, such as the four presented here, for which the tertiary structure prediction could still be significantly enhanced. The source code, license, and documentation for SPINE-X and Seder are available from Research and Information Systems, LLC at http://mamiris.com .
我们分析了 CASP15 实验中预测准确率较低的四个案例，并在这些案例上比较了 AlphaFold2、SPINE-X 和 Seder。我们发现，总体而言，AlphaFold2 在预测二级结构（SS）和溶剂可及表面积（ASA）方面优于 SPINE-X。对于某些案例，SPINE-X 可以更好地预测片层和卷曲区域。我们还发现，在一个案例中，AlphaFold2 优于 Seder 选择最佳匹配的三级结构模型，而在另一个案例中则表现不佳。对于两个案例，AlphaFold2 和 Seder 选择了相同的模型。从这里呈现的案例来看，AlphaFold2 似乎预测出比天然结构更紧凑的结构。我们发现，尽管如广泛报道的那样，AlphaFold2 极大地改进了蛋白质三级结构预测，但仍有一些案例，如这里呈现的四个案例，其三级结构预测仍可以显著增强。SPINE-X 和 Seder 的源代码、许可证和文档可从 Research and Information Systems, LLC 获得，网址为 http://mamiris.com。
