TAFPred: Torsion Angle Fluctuations Prediction from Protein Sequences

Simple Summary This study aimed to create an intelligent computer model called TAFPred to predict how proteins move and twist by looking at their sequences. By analyzing different features of the protein sequences, the model can accurately estimate the degree of flexibility of protein structures per residue. The investigators used an advanced machine learning technique called LightGBM to make these predictions even better. Compared to existing methods, TAFPred significantly improved in accurately predicting how proteins bend and twist within the individual and collective residual degree of freedom. This study is vital because understanding protein flexibility helps us know how they function in our bodies. By improving our ability to predict protein movements, this study brings us closer to unlocking the secrets of how proteins work and the role of protein flexibility in cellular functions, which can have critical applications in medicine and biology. Protein molecules show varying degrees of flexibility throughout their three-dimensional structures. The flexibility is determined by the fluctuations in torsion angles, specifically phi (& phi;) and psi (& psi;), which define the protein backbone. These angle fluctuations are derived from variations in backbone torsion angles observed in different models. By analyzing the fluctuations in Cartesian coordinate space, we can understand the structural flexibility of proteins. Predicting torsion angle fluctuations is valuable for determining protein function and structure when these angles act as constraints. In this study, a machine learning method called TAFPred is developed to predict torsion angle fluctuations using protein sequences directly. The method incorporates various features, such as disorder probability, position-specific scoring matrix profiles, secondary structure probabilities, and more. TAFPred, employing an optimized Light Gradient Boosting Machine Regressor (LightGBM), achieved high accuracy with correlation coefficients of 0.746 and 0.737 and mean absolute errors of 0.114 and 0.123 for the & phi; and & psi; angles, respectively. Compared to the state-of-the-art method, TAFPred demonstrated significant improvements of 10.08% in MAE and 24.83% in PCC for the phi angle and 9.93% in MAE, and 22.37% in PCC for the psi angle.

Automated summary

This study developed an intelligent computer model called TAFPred to predict protein movements and torsion angle fluctuations based on their sequences. By analyzing various features of the protein sequences, the model achieved high accuracy in estimating protein flexibility. The use of the machine learning technique LightGBM further improved the predictions compared to existing methods. This study is important for understanding protein function and structure, and it has potential applications in medicine and biology.