ProteinUnet—An efficient alternative to SPIDER3‐single for sequence‐based prediction of protein secondary structures

Abstract

Predicting protein function and structure from sequence remains an unsolved problem in bioinformatics. The best performing methods rely heavily on evolutionary information from multiple sequence alignments, which means their accuracy deteriorates for sequences with a few homologs, and given the increasing sequence database sizes requires long computation times. Here, a single-sequence-based prediction method is presented, called ProteinUnet, leveraging an U-Net convolutional network architecture. It is compared to SPIDER3-Single model, based on long short-term memory-bidirectional recurrent neural networks architecture. Both methods achieve similar results for prediction of secondary structures (both threeand eight-state), half-sphere exposure, and contact number, but ProteinUnet has two times fewer parameters, 17 times shorter inference time, and can be trained 11 times faster. Moreover, ProteinUnet tends to be better for short sequences and residues with a low number of local contacts. Additionally, the method of loss weighting is presented as an effective way of increasing accuracy for rare secondary structures.

ProteinUnet2 for Fast Protein Secondary Structure Prediction: A Step Towards Proper Evaluation

“…ProteinUnet2 signi cantly extends and improves our previous ProteinUnet deep architecture [15]. It introduces multiple inputs with evolutionary pro les like PSSM, HHblits, and contact maps.…”

“…ProteinUnet2 architecture U-Net architectures have proven to be extremely effective in image segmentation tasks [32,33]. The U-shaped architecture of ProteinUnet2 is based on the idea from our previous ProteinUnet for secondary structure prediction [15] (for which the results are presented in Supplementary Table S1). The new architecture was adjusted to handle multiple inputs by using multiple contractive paths, one for each input (Fig.…”

“…Given the growing number of known protein sequences, and more effective neural network architectures, recent methods are able to predict the secondary structure with more than 85% accuracy like SPOT-1D [13] based on long short-term memory (LSTM) bi-directional recurrent neural networks (BRNN) or SAINT [14] based on convolutions with self-attention mechanism.. In this study, we present ProteinUnet2, a signi cantly extended and improved version of ProteinUnet, our previous deep neural network architecture for SS3 and SS8 prediction from a single sequence [15]. It is now possible to feed any number of features to the input of the network (like PSSM or HHblits).…”

Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction

“…Its successor, SPIDER3, improved the performance overall, and now the method predicts four PSAs at once, including contact number with four iterations for the prediction [ 58 ]. ProteinUnet, published in 2020, yields similar accuracy for secondary structure prediction as SPIDER3-single, but uses half parameters with an 11-fold faster training time [ 59 , 60 ]. Most servers and methods discussed now have over 84% Q 3 score in their latest versions with deeper neural networks and better algorithms.…”

SPOT-1D-LM: Reaching Alignment-profile-based Accuracy in Predicting Protein Secondary and Tertiary Structural Properties without Alignment

“…To date, only a few single-sequence-based methods have been developed for protein secondary structure prediction. Examples are PSIPRED-Single 11 , SPIDER3-Single 12 , ProteinUnet 13 , NetSurfP-2.0 4 , and SPOT-1D-Single 14 . PSIPRED-Single predicts the secondary structure only while SPIDER3-Single, ProteinUnet, and SPOT-1D-Single predicts secondary structure, Accessible Surface Area (ASA) 15 , Half-Sphere Exposure (HSE) 16 and Backbone torsion angles ( ψ, ϕ, θ , and τ ).…”