In recent years, Deep Learning techniques have achieved some success in bioinformatics tasks, including protein conformation prediction. In this work, we propose a Bidirectional Long Short-Term Memory (BLSTM) network system, called Human Proteins Angles Prediction (HPAP), in order to improve the prediction of dihedral angles of proteins. We have introduced a discrete subdivision in classes of 5° for protein torsion angles and four new features related to accessible surface area and volume. In total there are 73 classes (72 classes include the angles between -180° and 180°, a further class is used to code the free angles at the beginning of the sequence) with a maximum expected error of ± 2.5°. We have tested three model variants in several parameter combinations. With our model, we have obtained a decrease of the mean absolute error of about 2° for the ψ angle. Although our dataset is reduced in size, the accuracy of φ and ψ angles is comparable to the existing methods. Predicting angles accurately is useful for accurately reconstructing the three-dimensional structure of a protein. In this context, the prediction is limited to the φ and ψ angles and we will visualize what happens locally when a prediction is correct. In case the prediction is far from true angles, even a small error can deconstruct the backbone.
Reconstruction and Visualization of Protein Structures by exploiting Bidirectional Neural Networks and Discrete Classes
Auriemma Citarella A.
;Porcelli Lorenzo.;Di Biasi L;Risi M.;Tortora G.
2021
Abstract
In recent years, Deep Learning techniques have achieved some success in bioinformatics tasks, including protein conformation prediction. In this work, we propose a Bidirectional Long Short-Term Memory (BLSTM) network system, called Human Proteins Angles Prediction (HPAP), in order to improve the prediction of dihedral angles of proteins. We have introduced a discrete subdivision in classes of 5° for protein torsion angles and four new features related to accessible surface area and volume. In total there are 73 classes (72 classes include the angles between -180° and 180°, a further class is used to code the free angles at the beginning of the sequence) with a maximum expected error of ± 2.5°. We have tested three model variants in several parameter combinations. With our model, we have obtained a decrease of the mean absolute error of about 2° for the ψ angle. Although our dataset is reduced in size, the accuracy of φ and ψ angles is comparable to the existing methods. Predicting angles accurately is useful for accurately reconstructing the three-dimensional structure of a protein. In this context, the prediction is limited to the φ and ψ angles and we will visualize what happens locally when a prediction is correct. In case the prediction is far from true angles, even a small error can deconstruct the backbone.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.