Accuracy Of Secondary Structure Prediction Research Articles

Prediction of protein secondary structure by the improved TCN-BiLSTM-MHA model with knowledge distillation

Secondary structure prediction is a key step in understanding protein function and biological properties and is highly important in the fields of new drug development, disease treatment, bioengineering, etc. Accurately predicting the secondary structure of proteins helps to reveal how proteins are folded and how they function in cells. The application of deep learning models in protein structure prediction is particularly important because of their ability to process complex sequence information and extract meaningful patterns and features, thus significantly improving the accuracy and efficiency of prediction. In this study, a combined model integrating an improved temporal convolutional network (TCN), bidirectional long short-term memory (BiLSTM), and a multi-head attention (MHA) mechanism is proposed to enhance the accuracy of protein prediction in both eight-state and three-state structures. One-hot encoding features and word vector representations of physicochemical properties are incorporated. A significant emphasis is placed on knowledge distillation techniques utilizing the ProtT5 pretrained model, leading to performance improvements. The improved TCN, achieved through multiscale fusion and bidirectional operations, allows for better extraction of amino acid sequence features than traditional TCN models. The model demonstrated excellent prediction performance on multiple datasets. For the TS115, CB513 and PDB (2018–2020) datasets, the prediction accuracy of the eight-state structure of the six datasets in this paper reached 88.2%, 84.9%, and 95.3%, respectively, and the prediction accuracy of the three-state structure reached 91.3%, 90.3%, and 96.8%, respectively. This study not only improves the accuracy of protein secondary structure prediction but also provides an important tool for understanding protein structure and function, which is particularly applicable to resource-constrained contexts and provides a valuable tool for understanding protein structure and function.

Accurate prediction of RNA secondary structure including pseudoknots through solving minimum-cost flow with learned potentials

Pseudoknots are key structure motifs of RNA and pseudoknotted RNAs play important roles in a variety of biological processes. Here, we present KnotFold, an accurate approach to the prediction of RNA secondary structure including pseudoknots. The key elements of KnotFold include a learned potential function and a minimum-cost flow algorithm to find the secondary structure with the lowest potential. KnotFold learns the potential from the RNAs with known structures using an attention-based neural network, thus avoiding the inaccuracy of hand-crafted energy functions. The specially designed minimum-cost flow algorithm used by KnotFold considers all possible combinations of base pairs and selects from them the optimal combination. The algorithm breaks the restriction of nested base pairs required by the widely used dynamic programming algorithms, thus enabling the identification of pseudoknots. Using 1,009 pseudoknotted RNAs as representatives, we demonstrate the successful application of KnotFold in predicting RNA secondary structures including pseudoknots with accuracy higher than the state-of-the-art approaches. We anticipate that KnotFold, with its superior accuracy, will greatly facilitate the understanding of RNA structures and functionalities.

Identification and characterization of RNA binding sites for (p)ppGpp using RNA-DRaCALA.

Ligand-binding RNAs (RNA aptamers) are widespread in the three domains of life, serving as sensors of metabolites and other small molecules. When aptamers are embedded within RNA transcripts as components of riboswitches, they can regulate gene expression upon binding their ligands. Previous methods for biochemical validation of computationally predicted aptamers are not well-suited for rapid screening of large numbers of RNA aptamers. Therefore, we utilized DRaCALA (Differential Radial Capillary Action of Ligand Assay), a technique designed originally to study protein-ligand interactions, to examine RNA-ligand binding, permitting rapid screening of dozens of RNA aptamer candidates concurrently. Using this method, which we call RNA-DRaCALA, we screened 30 ykkC family subtype 2a RNA aptamers that were computationally predicted to bind (p)ppGpp. Most of the aptamers bound both ppGpp and pppGpp, but some strongly favored only ppGpp or pppGpp, and some bound neither. Expansion of the number of biochemically verified sites allowed construction of more accurate secondary structure models and prediction of key features in the aptamers that distinguish a ppGpp from a pppGpp binding site. To demonstrate that the method works with other ligands, we also used RNA DRaCALA to analyze aptamer binding by thiamine pyrophosphate.

Protein encoder: An autoencoder-based ensemble feature selection scheme to predict protein secondary structure

Proteins play a vital role in the human body as they perform important metabolic tasks. Experimental identification of protein structure is expensive and time consuming. The prediction of protein secondary structure is significant to identify the protein tertiary structure and its folds. The feature subset selection from high dimensional protein primary sequence is a key to improve the accuracy of Protein Secondary Structure Prediction (PSSP). Therefore, it is essential to select the relevant features from high dimensional data to predict the protein secondary structure. This work presents a novel method for the PSSP problem based on a two-phase feature selection technique. The first stage utilizes an unsupervised autoencoder for feature extractions. Whereas, the second stage is an ensemble of three feature selection methods, namely, generic univariate select, recursive feature elimination, and Pearson's correlation. This phase combines multiple feature subsets using mutual information to select the optimum feature subset. For classification, different resultant subset features are used. These include random forest, decision tree, and multilayer perceptron. Two sets of experiments are performed on five datasets for the assessment of proposed work. The proposed solution is compared with three state-of-the-art methods based on Q3 accuracy, Q8 accuracy, and segment overlap score. Obtained results show that the proposed framework performs better in the majority of the cases than the past contributions. The proposed framework achieves Q8 accuracies of 82%, 80%, 79%, 73%, and 74% and Q3 accuracies of 90%, 90%, 92%, 79%, and 74% on CB6133, CB6133-filtered, CB513, CASP10, and CASP11 datasets, respectively.

Prediction of protein secondary structure based on an improved channel attention and multiscale convolution module.

Prediction of the protein secondary structure is a key issue in protein science. Protein secondary structure prediction (PSSP) aims to construct a function that can map the amino acid sequence into the secondary structure so that the protein secondary structure can be obtained according to the amino acid sequence. Driven by deep learning, the prediction accuracy of the protein secondary structure has been greatly improved in recent years. To explore a new technique of PSSP, this study introduces the concept of an adversarial game into the prediction of the secondary structure, and a conditional generative adversarial network (GAN)-based prediction model is proposed. We introduce a new multiscale convolution module and an improved channel attention (ICA) module into the generator to generate the secondary structure, and then a discriminator is designed to conflict with the generator to learn the complicated features of proteins. Then, we propose a PSSP method based on the proposed multiscale convolution module and ICA module. The experimental results indicate that the conditional GAN-based protein secondary structure prediction (CGAN-PSSP) model is workable and worthy of further study because of the strong feature-learning ability of adversarial learning.

Reaching alignment-profile-based accuracy in predicting protein secondary and tertiary structural properties without alignment

Protein language models have emerged as an alternative to multiple sequence alignment for enriching sequence information and improving downstream prediction tasks such as biophysical, structural, and functional properties. Here we show that a method called SPOT-1D-LM combines traditional one-hot encoding with the embeddings from two different language models (ProtTrans and ESM-1b) for the input and yields a leap in accuracy over single-sequence-based techniques in predicting protein 1D secondary and tertiary structural properties, including backbone torsion angles, solvent accessibility and contact numbers for all six test sets (TEST2018, TEST2020, Neff1-2020, CASP12-FM, CASP13-FM and CASP14-FM). More significantly, it has a performance comparable to profile-based methods for those proteins with homologous sequences. For example, the accuracy for three-state secondary structure (SS3) prediction for TEST2018 and TEST2020 proteins are 86.7% and 79.8% by SPOT-1D-LM, compared to 74.3% and 73.4% by the single-sequence-based method SPOT-1D-Single and 86.2% and 80.5% by the profile-based method SPOT-1D, respectively. For proteins without homologous sequences (Neff1-2020) SS3 is 80.41% by SPOT-1D-LM which is 3.8% and 8.3% higher than SPOT-1D-Single and SPOT-1D, respectively. SPOT-1D-LM is expected to be useful for genome-wide analysis given its fast performance. Moreover, high-accuracy prediction of both secondary and tertiary structural properties such as backbone angles and solvent accessibility without sequence alignment suggests that highly accurate prediction of protein structures may be made without homologous sequences, the remaining obstacle in the post AlphaFold2 era.

OneHotEncoding and LSTM-based deep learning models for protein secondary structure prediction

Protein Secondary Structure (PSS) prediction emerges as a hot topic in the area of bioinformatics.PSS helps to predict the tertiary structure and helps to understand its structures, which in turn helps to design various drugs. The existing PSS prediction techniques are capable of achieving Q3 accuracy of nearly 80% and have no improvement till now. In this paper, we propose a novel technique that uses amino acid sequences alone as an input feature and the respected feature vector matrix is given through the deep learning model (DLM) for PSS prediction. We use OneHotEncoding and LSTM (Long Short Term Memory) technique to forecast PSS that helps to achieve more accuracy. The OneHotEncoder is used to extract the local contexts of amino-acid sequences, and LSTM captures the long-distance interdependencies among aminoacids. The overall implementation is carried in MATLAB 2020a. The performance of this model is evaluated in terms of precision, recall, F1-score, and by the percentage of accuracy of both Q3 and Q8 secondary structure predictions. The Q3 structure of the proposed scheme gained 86.54, 85.2 and 85.7%CullPDB, CASP10, and CASP11 and the accuracy of Q8 is 77.8, 72.5 and 74.9% on the benchmark datasets such as CullPDB, CASP10, and CASP11 respectively. Some of the advantages of the proposed scheme are minimize the computation time and achieves better accuracy when compared to the other baseline models in the prediction of PSS.

LinAliFold and CentroidLinAliFold: fast RNA consensus secondary structure prediction for aligned sequences using beam search methods.

RNA consensus secondary structure prediction from aligned sequences is a powerful approach for improving the secondary structure prediction accuracy. However, because the computational complexities of conventional prediction tools scale with the cube of the alignment lengths, their application to long RNA sequences, such as viral RNAs or long non-coding RNAs, requires significant computational time. In this study, we developed LinAliFold and CentroidLinAliFold, fast RNA consensus secondary structure prediction tools based on minimum free energy and maximum expected accuracy principles, respectively. We achieved software acceleration using beam search methods that were successfully used for fast secondary structure prediction from a single RNA sequence. Benchmark analyses showed that LinAliFold and CentroidLinAliFold were much faster than the existing methods while preserving the prediction accuracy. As an empirical application, we predicted the consensus secondary structure of coronaviruses with approximately 30000 nt in 5 and 79 min by LinAliFold and CentroidLinAliFold, respectively. We confirmed that the predicted consensus secondary structure of coronaviruses was consistent with the experimental results. The source codes of LinAliFold and CentroidLinAliFold are freely available at https://github.com/fukunagatsu/LinAliFold-CentroidLinAliFold. Supplementary data are available at Bioinformatics Advances online.

Prediction of Protein Secondary Structure Based on WS-BiLSTM Model

Protein secondary structure prediction is an important topic in bioinformatics. This paper proposed a novel model named WS-BiLSTM, which combined the wavelet scattering convolutional network and the long-short-term memory network for the first time to predict protein secondary structure. This model captures nonlocal interactions between amino acid sequences and remembers long-range interactions between amino acids. In our WS-BiLSTM model, the wavelet scattering convolutional network is used to extract protein features from the PSSM sliding window; the extracted features are combined with the original PSSM data as the input features of the long-short-term memory network to predict protein secondary structure. It is worth noting that the wavelet scattering convolutional network is asymmetric as a member of the continuous wavelet family. The Q3 accuracy on the test set CASP9, CASP10, CASP11, CASP12, CB513, and PDB25 reached 85.26%, 85.84%, 84.91%, 85.13%, 86.10%, and 85.52%, which were higher 2.15%, 2.16%, 3.5%, 3.19%, 4.22%, and 2.75%, respectively, than using the long-short-term memory network alone. Comparing our results with the state-of-art methods shows that our proposed model achieved better results on the CB513 and CASP12 data sets. The experimental results show that the features extracted from the wavelet scattering convolutional network can effectively improve the accuracy of protein secondary structure prediction.

Convolution-Bidirectional Temporal Convolutional Network for Protein Secondary Structure Prediction

As a basic feature extraction method, convolutional neural networks have some information loss problems when dealing with sequence problems, and a temporal convolutional network can compensate for this problem. Howerover, ordinary temporal convolutional networks can not deal well protein secondary structure prediction because of their one-way analysis. Therefore, we propose an integrated deep learning model called Convoluntional-Bidirectional Temporal Convolutional Network. for 3-state and 8-state protein secondary structure predictions based on a convolutional neural network and bidirectional temporal convolutional networks. Because the model combines the advantages of the convolutional neural network and bidirectional temporal convolution network, it can not only capture the local correlation in the amino acid sequence but also analyse the long-distance interaction in the amino acid sequence. Therefore, this model can effectively improve the accuracy of protein secondary structure predictions. The experimental results show that the combination of convolutional neural network and bidirectional temporal convolutional network is effective for predicting protein secondary structure.

Determination of RNA Structure with In Vitro SHAPE Experiments.

The structure of an RNA molecule is often critical for its correct functioning, post-transcriptional regulation, and/or translation. Predicting RNA secondary structures with in silico tools is relatively straightforward with the large array of software and webservers available. However, for long RNAs and RNA at high temperatures, in silico predictions are less accurate and require experimental validation. To this end, a variety of structural probing reagents are commonly used, both for in vitro and in vivo mapping of RNA structure. Selective 2'-hydroxyl acylation analyzed by primer extension (SHAPE) experiments make use of a nonbase-specific modifying reagent, acylating all conformationally flexible (mainly single-stranded or unpaired) nucleotides and have been employed both for in vitro and in vivo modification of RNA. Here, we describe a protocol for an in vitro SHAPE experiment, starting from in vitro transcribed RNA using a T7 polymerase system. This RNA is folded and subsequently modified in vitro with the SHAPE-reagent N-methyl isatoic anhydride (NMIA). Primer extension employing a radioactive 32P-labeled primer that binds the RNA downstream of the structure of interest will generate cDNA until the reverse transcriptase enzyme is halted by the introduced SHAPE modifications. Denaturing acrylamide gel electrophoresis of the pool of 32P-labeled cDNAs and the corresponding sequencing ladders, followed by autoradiography, will expose these stops in reverse transcription (RT) and will therefore enable to identify single-stranded nucleotides in the RNA of interest. These RT stops and NMIA-modification efficiencies can be quantified with ImageJ software and can be used to validate or increase the accuracy of RNA secondary structure predictions.

A Deep Learning Approach for Prediction of Protein Secondary Structure

The secondary structure of a protein is critical for establishing a link between the protein primary and tertiary structures. For this reason, it is important to design methods for accurate protein secondary structure prediction. Most of the existing computational techniques for protein structural and functional prediction are based on machine learning with shallow frameworks. Different deep learning architectures have already been applied to tackle protein secondary structure prediction problem. In this study, deep learning based models, i.e., convolutional neural network and long short-term memory for protein secondary structure prediction were proposed. The input to proposed models is amino acid sequences which were derived from CulledPDB dataset. Hyperparameter tuning with cross validation was employed to attain best parameters for the proposed models. The proposed models enables effective processing of amino acids and attain approximately 87.05% and 87.47% Q3 accuracy of protein secondary structure prediction for convolutional neural network and long short-term memory models, respectively.

A secondary structure-based position-specific scoring matrix applied to the improvement in protein secondary structure prediction.

Protein secondary structure prediction (SSP) has a variety of applications; however, there has been relatively limited improvement in accuracy for years. With a vision of moving forward all related fields, we aimed to make a fundamental advance in SSP. There have been many admirable efforts made to improve the machine learning algorithm for SSP. This work thus took a step back by manipulating the input features. A secondary structure element-based position-specific scoring matrix (SSE-PSSM) is proposed, based on which a new set of machine learning features can be established. The feasibility of this new PSSM was evaluated by rigid independent tests with training and testing datasets sharing <25% sequence identities. In all experiments, the proposed PSSM outperformed the traditional amino acid PSSM. This new PSSM can be easily combined with the amino acid PSSM, and the improvement in accuracy was remarkable. Preliminary tests made by combining the SSE-PSSM and well-known SSP methods showed 2.0% and 5.2% average improvements in three- and eight-state SSP accuracies, respectively. If this PSSM can be integrated into state-of-the-art SSP methods, the overall accuracy of SSP may break the current restriction and eventually bring benefit to all research and applications where secondary structure prediction plays a vital role during development. To facilitate the application and integration of the SSE-PSSM with modern SSP methods, we have established a web server and standalone programs for generating SSE-PSSM available at http://10.life.nctu.edu.tw/SSE-PSSM.

The influence of dataset homology and a rigorous evaluation strategy on protein secondary structure prediction.

The secondary structure prediction (SSP) of proteins has long been an essential structural biology technique with various applications. Despite its vital role in many research and industrial fields, in recent years, as the accuracy of state-of-the-art secondary structure predictors approaches the theoretical upper limit, SSP has been considered no longer challenging or too challenging to make advances. With the belief that the substantial improvement of SSP will move forward many fields depending on it, we conducted this study, which focused on three issues that have not been noticed or thoroughly examined yet but may have affected the reliability of the evaluation of previous SSP algorithms. These issues are all about the sequence homology between or within the developmental and evaluation datasets. We thus designed many different homology layouts of datasets to train and evaluate SSP prediction models. Multiple repeats were performed in each experiment by random sampling. The conclusions obtained with small experimental datasets were verified with large-scale datasets using state-of-the-art SSP algorithms. Very different from the long-established assumption, we discover that the sequence homology between query datasets for training, testing, and independent tests exerts little influence on SSP accuracy. Besides, the sequence homology redundancy between or within most datasets would make the accuracy of an SSP algorithm overestimated, while the redundancy within the reference dataset for extracting predictive features would make the accuracy underestimated. Since the overestimating effects are more significant than the underestimating effect, the accuracy of some SSP methods might have been overestimated. Based on the discoveries, we propose a rigorous procedure for developing SSP algorithms and making reliable evaluations, hoping to bring substantial improvements to future SSP methods and benefit all research and application fields relying on accurate prediction of protein secondary structures.

RNAcmap: a fully automatic pipeline for predicting contact maps of RNAs by evolutionary coupling analysis.

The accuracy of RNA secondary and tertiary structure prediction can be significantly improved by using structural restraints derived from evolutionary coupling or direct coupling analysis. Currently, these coupling analyses relied on manually curated multiple sequence alignments collected in the Rfam database, which contains 3016 families. By comparison, millions of non-coding RNA sequences are known. Here, we established RNAcmap, a fully automatic pipeline that enables evolutionary coupling analysis for any RNA sequences. The homology search was based on the covariance model built by INFERNAL according to two secondary structure predictors: a folding-based algorithm RNAfold and the latest deep-learning method SPOT-RNA. We showed that the performance of RNAcmap is less dependent on the specific evolutionary coupling tool but is more dependent on the accuracy of secondary structure predictor with the best performance given by RNAcmap (SPOT-RNA). The performance of RNAcmap (SPOT-RNA) is comparable to that based on Rfam-supplied alignment and consistent for those sequences that are not in Rfam collections. Further improvement can be made with a simple meta predictor RNAcmap (SPOT-RNA/RNAfold) depending on which secondary structure predictor can find more homologous sequences. Reliable base-pairing information generated from RNAcmap, for RNAs with high effective homologous sequences, in particular, will be useful for aiding RNA structure prediction. RNAcmap is available as a web server at https://sparks-lab.org/server/rnacmap/ and as a standalone application along with the datasets at https://github.com/sparks-lab-org/RNAcmap_standalone. A platform independent and fully configured docker image of RNAcmap is also provided at https://hub.docker.com/r/jaswindersingh2/rnacmap. Supplementary data are available at Bioinformatics online.

TMPSS: A Deep Learning-Based Predictor for Secondary Structure and Topology Structure Prediction of Alpha-Helical Transmembrane Proteins.

Alpha transmembrane proteins (αTMPs) profoundly affect many critical biological processes and are major drug targets due to their pivotal protein functions. At present, even though the non-transmembrane secondary structures are highly relevant to the biological functions of αTMPs along with their transmembrane structures, they have not been unified to be studied yet. In this study, we present a novel computational method, TMPSS, to predict the secondary structures in non-transmembrane parts and the topology structures in transmembrane parts of αTMPs. TMPSS applied a Convolutional Neural Network (CNN), combined with an attention-enhanced Bidirectional Long Short-Term Memory (BiLSTM) network, to extract the local contexts and long-distance interdependencies from primary sequences. In addition, a multi-task learning strategy was used to predict the secondary structures and the transmembrane helixes. TMPSS was thoroughly trained and tested against a non-redundant independent dataset, where the Q3 secondary structure prediction accuracy achieved 78% in the non-transmembrane region, and the accuracy of the transmembrane region prediction achieved 90%. In sum, our method showcased a unified model for predicting the secondary structure and topology structure of αTMPs by only utilizing features generated from primary sequences and provided a steady and fast prediction, which promisingly improves the structural studies on αTMPs.

RNA Secondary Structures with Limited Base Pair Span: Exact Backtracking and an Application.

The accuracy of RNA secondary structure prediction decreases with the span of a base pair, i.e., the number of nucleotides that it encloses. The dynamic programming algorithms for RNA folding can be easily specialized in order to consider only base pairs with a limited span L, reducing the memory requirements to , and further to by interleaving backtracking. However, the latter is an approximation that precludes the retrieval of the globally optimal structure. So far, the ViennaRNA package therefore does not provide a tool for computing optimal, span-restricted minimum energy structure. Here, we report on an efficient backtracking algorithm that reconstructs the globally optimal structure from the locally optimal fragments that are produced by the interleaved backtracking implemented in RNALfold. An implementation is integrated into the ViennaRNA package. The forward and the backtracking recursions of RNALfold are both easily constrained to structural components with a sufficiently negative z-scores. This provides a convenient method in order to identify hyper-stable structural elements. A screen of the C. elegans genome shows that such features are more abundant in real genomic sequences when compared to a di-nucleotide shuffled background model.

DNSS2: Improved ab initio protein secondary structure prediction using advanced deep learning architectures

Accurate prediction of protein secondary structure (alpha-helix, beta-strand and coil) is a crucial step for protein inter-residue contact prediction and ab initio tertiary structure prediction. In a previous study, we developed a deep belief network-based protein secondary structure method (DNSS1) and successfully advanced the prediction accuracy beyond 80%. In this work, we developed multiple advanced deep learning architectures (DNSS2) to further improve secondary structure prediction. The major improvements over the DNSS1 method include (a) designing and integrating six advanced one-dimensional deep convolutional/recurrent/residual/memory/fractal/inception networks to predict 3-state and 8-state secondary structure, and (b) using more sensitive profile features inferred from Hidden Markov model (HMM) and multiple sequence alignment (MSA). Most of the deep learning architectures are novel for protein secondary structure prediction. DNSS2 was systematically benchmarked on independent test data sets with eight state-of-art tools and consistently ranked as one of the best methods. Particularly, DNSS2 was tested on the protein targets of 2018 CASP13 experiment and achieved the Q3 score of 81.62%, SOV score of 72.19%, and Q8 score of 73.28%. DNSS2 is freely available at: https://github.com/multicom-toolbox/DNSS2.

Boosting the accuracy of protein secondary structure prediction through nearest neighbor search and method hybridization

Motivation Protein secondary structure prediction is a fundamental precursor to many bioinformatics tasks. Nearly all state-of-the-art tools when computing their secondary structure prediction do not explicitly leverage the vast number of proteins whose structure is known. Leveraging this additional information in a so-called template-based method has the potential to significantly boost prediction accuracy. Method We present a new hybrid approach to secondary structure prediction that gains the advantages of both template- and non-template-based methods. Our core template-based method is an algorithmic approach that uses metric-space nearest neighbor search over a template database of fixed-length amino acid words to determine estimated class-membership probabilities for each residue in the protein. These probabilities are then input to a dynamic programming algorithm that finds a physically valid maximum-likelihood prediction for the entire protein. Our hybrid approach exploits a novel accuracy estimator for our core method, which estimates the unknown true accuracy of its prediction, to discern when to switch between template- and non-template-based methods. Results On challenging CASP benchmarks, the resulting hybrid approach boosts the state-of-the-art Q8 accuracy by more than 2-10%, and Q3 accuracy by more than 1-3%, yielding the most accurate method currently available for both 3- and 8-state secondary structure prediction. Availability and implementation A preliminary implementation in a new tool we call Nnessy is available free for non-commercial use at http://nnessy.cs.arizona.edu.

Boosting the accuracy of protein secondary structure prediction through nearest neighbor search and method hybridization.

MotivationProtein secondary structure prediction is a fundamental precursor to many bioinformatics tasks. Nearly all state-of-the-art tools when computing their secondary structure prediction do not explicitly leverage the vast number of proteins whose structure is known. Leveraging this additional information in a so-called template-based method has the potential to significantly boost prediction accuracy.MethodWe present a new hybrid approach to secondary structure prediction that gains the advantages of both template- and non-template-based methods. Our core template-based method is an algorithmic approach that uses metric-space nearest neighbor search over a template database of fixed-length amino acid words to determine estimated class-membership probabilities for each residue in the protein. These probabilities are then input to a dynamic programming algorithm that finds a physically valid maximum-likelihood prediction for the entire protein. Our hybrid approach exploits a novel accuracy estimator for our core method, which estimates the unknown true accuracy of its prediction, to discern when to switch between template- and non-template-based methods.ResultsOn challenging CASP benchmarks, the resulting hybrid approach boosts the state-of-the-art Q8 accuracy by more than 2–10%, and Q3 accuracy by more than 1–3%, yielding the most accurate method currently available for both 3- and 8-state secondary structure prediction.Availability and implementationA preliminary implementation in a new tool we call Nnessy is available free for non-commercial use at http://nnessy.cs.arizona.edu.