Evaluation of enzyme activity predictions for variants of unknown significance in Arylsulfatase A.

Continued advances in variant effect prediction are necessary to demonstrate the ability of machine learning methods to accurately determine the clinical impact of variants of unknown significance (VUS). Towards this goal, the ARSA Critical Assessment of Genome Interpretation (CAGI) challenge was designed to characterize progress by utilizing 219 experimentally assayed missense VUS in the Arylsulfatase A (ARSA) gene to assess the performance of community-submitted predictions of variant functional effects. The challenge involved 15 teams, and evaluated additional predictions from established and recently released models. Notably, a model developed by participants of a genetics and coding bootcamp, trained with standard machine-learning tools in Python, demonstrated superior performance among submissions. Furthermore, the study observed that state-of-the-art deep learning methods provided small but statistically significant improvement in predictive performance compared to less elaborate techniques. These findings underscore the utility of variant effect prediction, and the potential for models trained with modest resources to accurately classify VUS in genetic and clinical research.

DescribePROT in 2023: more, higher-quality and experimental annotations and improved data download options.

The DescribePROT database of amino acid-level descriptors of protein structures and functions was substantially expanded since its release in 2020. This expansion includes substantial increase in the size, scope, and quality of the underlying data, the addition of experimental structural information, the inclusion of new data download options, and an upgraded graphical interface. DescribePROT currently covers 19 structural and functional descriptors for proteins in 273 reference proteomes generated by 11 accurate and complementary predictive tools. Users can search our resource in multiple ways, interact with the data using the graphical interface, and download data at various scales including individual proteins, entire proteomes, and whole database. The annotations in DescribePROT are useful for a broad spectrum of studies that include investigations of protein structure and function, development and validation of predictive tools, and to support efforts in understanding molecular underpinnings of diseases and development of therapeutics. DescribePROT can be freely accessed at http://biomine.cs.vcu.edu/servers/DESCRIBEPROT/.

DescribePROT: database of amino acid-level protein structure and function predictions.

We present DescribePROT, the database of predicted amino acid-level descriptors of structure and function of proteins. DescribePROT delivers a comprehensive collection of 13 complementary descriptors predicted using 10 popular and accurate algorithms for 83 complete proteomes that cover key model organisms. The current version includes 7.8 billion predictions for close to 600 million amino acids in 1.4 million proteins. The descriptors encompass sequence conservation, position specific scoring matrix, secondary structure, solvent accessibility, intrinsic disorder, disordered linkers, signal peptides, MoRFs and interactions with proteins, DNA and RNAs. Users can search DescribePROT by the amino acid sequence and the UniProt accession number and entry name. The pre-computed results are made available instantaneously. The predictions can be accesses via an interactive graphical interface that allows simultaneous analysis of multiple descriptors and can be also downloaded in structured formats at the protein, proteome and whole database scale. The putative annotations included by DescriPROT are useful for a broad range of studies, including: investigations of protein function, applied projects focusing on therapeutics and diseases, and in the development of predictors for other protein sequence descriptors. Future releases will expand the coverage of DescribePROT. DescribePROT can be accessed at http://biomine.cs.vcu.edu/servers/DESCRIBEPROT/.

A Hybrid Levenberg-Marquardt Algorithm on a Recursive Neural Network for Scoring Protein Models.

We have studied the ability of three types of neural networks to predict the closeness of a given protein model to the native structure associated with its sequence. We show that a partial combination of the Levenberg-Marquardt algorithm and the back-propagation algorithm produced the best results, giving the lowest error and largest Pearson correlation coefficient. We also find, as previous studies, that adding associative memory to a neural network improves its performance. Additionally, we find that the hybrid method we propose was the most robust in the sense that other configurations of it experienced less decline in comparison to the other methods. We find that the hybrid networks also undergo more fluctuations on the path to convergence. We propose that these fluctuations allow for better sampling. Overall we find it may be beneficial to treat different parts of a neural network with varied computational approaches during optimization.

Computational Ways to Enhance Protein Inhibitor Design.

Two new computational approaches are described to aid in the design of new peptide-based drugs by evaluating ensembles of protein structures from their dynamics and through the assessing of structures using empirical contact potential. These approaches build on the concept that conformational variability can aid in the binding process and, for disordered proteins, can even facilitate the binding of more diverse ligands. This latter consideration indicates that such a design process should be less restrictive so that multiple inhibitors might be effective. The example chosen here focuses on proteins/peptides that bind to hemagglutinin (HA) to block the large-scale conformational change for activation. Variability in the conformations is considered from sets of experimental structures, or as an alternative, from their simple computed dynamics; the set of designe peptides/small proteins from the David Baker lab designed to bind to hemagglutinin, is the large set considered and is assessed with the new empirical contact potentials.

Many-to-one binding by intrinsically disordered protein regions.

Disordered binding regions (DBRs), which are embedded within intrinsically disordered proteins or regions (IDPs or IDRs), enable IDPs or IDRs to mediate multiple protein-protein interactions. DBR-protein complexes were collected from the Protein Data Bank for which two or more DBRs having different amino acid sequences bind to the same (100% sequence identical) globular protein partner, a type of interaction herein called many-to-one binding. Two distinct binding profiles were identified: independent and overlapping. For the overlapping binding profiles, the distinct DBRs interact by means of almost identical binding sites (herein called "similar"), or the binding sites contain both common and divergent interaction residues (herein called "intersecting"). Further analysis of the sequence and structural differences among these three groups indicate how IDP flexibility allows different segments to adjust to similar, intersecting, and independent binding pockets.

Entropy, Fluctuations, and Disordered Proteins.

Entropy should directly reflect the extent of disorder in proteins. By clustering structurally related proteins and studying the multiple-sequence-alignment of the sequences of these clusters, we were able to link between sequence, structure, and disorder information. We introduced several parameters as measures of fluctuations at a given MSA site and used these as representative of the sequence and structure entropy at that site. In general, we found a tendency for negative correlations between disorder and structure, and significant positive correlations between disorder and the fluctuations in the system. We also found evidence for residue-type conservation for those residues proximate to potentially disordered sites. Mutation at the disorder site itself appear to be allowed. In addition, we found positive correlation for disorder and accessible surface area, validating that disordered residues occur in exposed regions of proteins. Finally, we also found that fluctuations in the dihedral angles at the original mutated residue and disorder are positively correlated while dihedral angle fluctuations in spatially proximal residues are negatively correlated with disorder. Our results seem to indicate permissible variability in the disordered site, but greater rigidity in the parts of the protein with which the disordered site interacts. This is another indication that disordered residues are involved in protein function.

Reoptimized UNRES Potential for Protein Model Quality Assessment.

Ranking protein structure models is an elusive problem in bioinformatics. These models are evaluated on both the degree of similarity to the native structure and the folding pathway. Here, we simulated the use of the coarse-grained UNited RESidue (UNRES) force field as a tool to choose the best protein structure models for a given protein sequence among a pool of candidate models, using server data from the CASP11 experiment. Because the original UNRES was optimized for Molecular Dynamics simulations, we reoptimized UNRES using a deep feed-forward neural network, and we show that introducing additional descriptive features can produce better results. Overall, we found that the reoptimized UNRES performs better in selecting the best structures and tracking protein unwinding from its native state. We also found a relatively poor correlation between UNRES values and the model's Template Modeling Score (TMS). This is remedied by reoptimization. We discuss some cases where our reoptimization procedure is useful. The reoptimized version of UNRES (OUNRES) is available at http://mamiris.com and http://www.unres.pl.

An analysis and evaluation of the WeFold collaborative for protein structure prediction and its pipelines in CASP11 and CASP12.

Every two years groups worldwide participate in the Critical Assessment of Protein Structure Prediction (CASP) experiment to blindly test the strengths and weaknesses of their computational methods. CASP has significantly advanced the field but many hurdles still remain, which may require new ideas and collaborations. In 2012 a web-based effort called WeFold, was initiated to promote collaboration within the CASP community and attract researchers from other fields to contribute new ideas to CASP. Members of the WeFold coopetition (cooperation and competition) participated in CASP as individual teams, but also shared components of their methods to create hybrid pipelines and actively contributed to this effort. We assert that the scale and diversity of integrative prediction pipelines could not have been achieved by any individual lab or even by any collaboration among a few partners. The models contributed by the participating groups and generated by the pipelines are publicly available at the WeFold website providing a wealth of data that remains to be tapped. Here, we analyze the results of the 2014 and 2016 pipelines showing improvements according to the CASP assessment as well as areas that require further adjustments and research.

Comparing NMR and X-ray protein structure: Lindemann-like parameters and NMR disorder.

Disordered protein chains and segments are fast becoming a major pathway for our understanding of biological function, especially in more evolved species. However, the standard definition of disordered residues: the inability to constrain them in X-ray derived structures, is not easily applied to NMR derived structures. We carry out a statistical comparison between proteins whose structure was resolved using NMR and using X-ray protocols. We start by establishing a connection between these two protocols for obtaining protein structure. We find a close statistical correspondence between NMR and X-ray structures if fluctuations inherent to the NMR protocol are taken into account. Intuitively this tends to lend support to the validity of both NMR and X-ray protocols in deriving biomolecular models that correspond to in vivo conditions. We then establish Lindemann-like parameters for NMR derived structures and examine what order/disorder cutoffs for these parameters are most consistent with X-ray data and how consistent are they. Finally, we find critical value of [Formula: see text] for the best correspondence between X-ray and NMR derived order/disorder assignment, judged by maximizing the Matthews correlation, and a critical value [Formula: see text] if a balance between false positive and false negative prediction is sought. We examine a few non-conforming cases, and examine the origin of the structure derived in X-ray. This study could help in assigning meaningful disorder from NMR experiments.

The GOR Method of Protein Secondary Structure Prediction and Its Application as a Protein Aggregation Prediction Tool.

The GOR method of protein secondary structure prediction is described. The original method was published by Garnier, Osguthorpe, and Robson in 1978 and was one of the first successful methods to predict protein secondary structure from amino acid sequence. The method is based on information theory, and an assumption that information function of a protein chain can be approximated by a sum of information from single residues and pairs of residues. The analysis of frequencies of occurrence of secondary structure for singlets and doublets of residues in a protein database enables prediction of secondary structure for new amino acid sequences. Because of these simple physical assumptions the GOR method has a conceptual advantage over other later developed methods such as PHD, PSIPRED, and others that are based on Machine Learning methods (like Neural Networks), give slightly better predictions, but have a "black box" nature. The GOR method has been continuously improved and modified for 30 years with the last GOR V version published in 2002, and the GOR V server developed in 2005. We discuss here the original GOR method and the GOR V program and the web server. Additionally we discuss new highly interesting and important applications of the GOR method to chameleon sequences in protein folding simulations, and for prediction of protein aggregation propensities. Our preliminary studies show that the GOR method is a promising and efficient alternative to other protein aggregation predicting tools. This shows that the GOR method despite being almost 40 years old is still important and has significant potential in application to new scientific problems.

Accurate Prediction of One-Dimensional Protein Structure Features Using SPINE-X.

Accurate prediction of protein secondary structure and other one-dimensional structure features is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. SPINE-X is a software package to predict secondary structure as well as accessible surface area and dihedral angles ϕ and ψ. For secondary structure SPINE-X achieves an accuracy of between 81 and 84 % depending on the dataset and choice of tests. The Pearson correlation coefficient for accessible surface area prediction is 0.75 and the mean absolute error from the ϕ and ψ dihedral angles are 20∘ and 33∘, respectively. The source code and a Linux executables for SPINE-X are available from Research and Information Systems at http://mamiris.com .

Fast and Accurate Accessible Surface Area Prediction Without a Sequence Profile.

A fast accessible surface area (ASA) predictor is presented. In this new approach no residue mutation profiles generated by multiple sequence alignments are used as inputs. Instead, we use only single sequence information and global features such as single-residue and two-residue compositions of the chain. The resulting predictor is both highly more efficient than sequence alignment based predictors and of comparable accuracy to them. Introduction of the global inputs significantly helps achieve this comparable accuracy. The predictor, termed ASAquick, is found to perform similarly well for so-called easy and hard cases indicating generalizability and possible usability for de-novo protein structure prediction. The source code and a Linux executables for ASAquick are available from Research and Information Systems at http://mamiris.com and from the Battelle Center for Mathematical Medicine at http://mathmed.org .

Intrinsic Disorder and Semi-disorder Prediction by SPINE-D.

Over the past decade, it has become evident that a large proportion of proteins contain intrinsically disordered regions, which play important roles in pivotal cellular functions. Many computational tools have been developed with the aim of identifying the level and location of disorder within a protein. In this chapter, we describe a neural network based technique called SPINE-D that employs a unique three-state design and can accurately capture disordered residues in both short and long disordered regions. SPINE-D was trained on a large database of 4229 non-redundant proteins, and yielded an AUC of 0.86 on a cross-validation test and 0.89 on an independent test. SPINE-D can also detect a semi-disordered state that is associated with induced folders and aggregation-prone regions in disordered proteins and weakly stable or locally unfolded regions in structured proteins. We implement an online web service and an offline stand-alone program for SPINE-D, they are freely available at http://sparks-lab.org/SPINE-D/ . We then walk you through how to use the online and offline SPINE-D in making disorder predictions, and examine the disorder and semi-disorder prediction in a case study on the p53 protein.

GENN: a GEneral Neural Network for learning tabulated data with examples from protein structure prediction.

We present a GEneral Neural Network (GENN) for learning trends from existing data and making predictions of unknown information. The main novelty of GENN is in its generality, simplicity of use, and its specific handling of windowed input/output. Its main strength is its efficient handling of the input data, enabling learning from large datasets. GENN is built on a two-layered neural network and has the option to use separate inputs-output pairs or window-based data using data structures to efficiently represent input-output pairs. The program was tested on predicting the accessible surface area of globular proteins, scoring proteins according to similarity to native, predicting protein disorder, and has performed remarkably well. In this paper we describe the program and its use. Specifically, we give as an example the construction of a similarity to native protein scoring function that was constructed using GENN. The source code and Linux executables for GENN are available from Research and Information Systems at http://mamiris.com and from the Battelle Center for Mathematical Medicine at http://mathmed.org. Bugs and problems with the GENN program should be reported to EF.

Accurate single-sequence prediction of solvent accessible surface area using local and global features.

We present a new approach for predicting the Accessible Surface Area (ASA) using a General Neural Network (GENN). The novelty of the new approach lies in not using residue mutation profiles generated by multiple sequence alignments as descriptive inputs. Instead we use solely sequential window information and global features such as single-residue and two-residue compositions of the chain. The resulting predictor is both highly more efficient than sequence alignment-based predictors and of comparable accuracy to them. Introduction of the global inputs significantly helps achieve this comparable accuracy. The predictor, termed ASAquick, is tested on predicting the ASA of globular proteins and found to perform similarly well for so-called easy and hard cases indicating generalizability and possible usability for de-novo protein structure prediction. The source code and a Linux executables for GENN and ASAquick are available from Research and Information Systems at http://mamiris.com, from the SPARKS Lab at http://sparks-lab.org, and from the Battelle Center for Mathematical Medicine at http://mathmed.org.

Direct prediction of profiles of sequences compatible with a protein structure by neural networks with fragment-based local and energy-based nonlocal profiles.

Locating sequences compatible with a protein structural fold is the well-known inverse protein-folding problem. While significant progress has been made, the success rate of protein design remains low. As a result, a library of designed sequences or profile of sequences is currently employed for guiding experimental screening or directed evolution. Sequence profiles can be computationally predicted by iterative mutations of a random sequence to produce energy-optimized sequences, or by combining sequences of structurally similar fragments in a template library. The latter approach is computationally more efficient but yields less accurate profiles than the former because of lacking tertiary structural information. Here we present a method called SPIN that predicts Sequence Profiles by Integrated Neural network based on fragment-derived sequence profiles and structure-derived energy profiles. SPIN improves over the fragment-derived profile by 6.7% (from 23.6 to 30.3%) in sequence identity between predicted and wild-type sequences. The method also reduces the number of residues in low complex regions by 15.7% and has a significantly better balance of hydrophilic and hydrophobic residues at protein surface. The accuracy of sequence profiles obtained is comparable to those generated from the protein design program RosettaDesign 3.5. This highly efficient method for predicting sequence profiles from structures will be useful as a single-body scoring term for improving scoring functions used in protein design and fold recognition. It also complements protein design programs in guiding experimental design of the sequence library for screening and directed evolution of designed sequences. The SPIN server is available at http://sparks-lab.org.

A global machine learning based scoring function for protein structure prediction.

We present a knowledge-based function to score protein decoys based on their similarity to native structure. A set of features is constructed to describe the structure and sequence of the entire protein chain. Furthermore, a qualitative relationship is established between the calculated features and the underlying electromagnetic interaction that dominates this scale. The features we use are associated with residue-residue distances, residue-solvent distances, pairwise knowledge-based potentials and a four-body potential. In addition, we introduce a new target to be predicted, the fitness score, which measures the similarity of a model to the native structure. This new approach enables us to obtain information both from decoys and from native structures. It is also devoid of previous problems associated with knowledge-based potentials. These features were obtained for a large set of native and decoy structures and a back-propagating neural network was trained to predict the fitness score. Overall this new scoring potential proved to be superior to the knowledge-based scoring functions used as its inputs. In particular, in the latest CASP (CASP10) experiment our method was ranked third for all targets, and second for freely modeled hard targets among about 200 groups for top model prediction. Ours was the only method ranked in the top three for all targets and for hard targets. This shows that initial results from the novel approach are able to capture details that were missed by a broad spectrum of protein structure prediction approaches. Source codes and executable from this work are freely available at http://mathmed.org/#Software and http://mamiris.com/.

Intrinsically semi-disordered state and its role in induced folding and protein aggregation.

Intrinsically disordered proteins (IDPs) refer to those proteins without fixed three-dimensional structures under physiological conditions. Although experiments suggest that the conformations of IDPs can vary from random coils, semi-compact globules, to compact globules with different contents of secondary structures, computational efforts to separate IDPs into different states are not yet successful. Recently, we developed a neural-network-based disorder prediction technique SPINE-D that was ranked as one of the top performing techniques for disorder prediction in the biannual meeting of critical assessment of structure prediction techniques (CASP 9, 2010). Here, we further analyze the results from SPINE-D prediction by defining a semi-disordered state that has about 50% predicted probability to be disordered or ordered. This semi-disordered state is partially collapsed with intermediate levels of predicted solvent accessibility and secondary structure content. The relative difference in compositions between semi-disordered and fully disordered regions is highly correlated with amyloid aggregation propensity (a correlation coefficient of 0.86 if excluding four charged residues and proline, 0.73 if not). In addition, we observed that some semi-disordered regions participate in induced folding, and others play key roles in protein aggregation. More specifically, a semi-disordered region is amyloidogenic in fully unstructured proteins (such as alpha-synuclein and Sup35) but prone to local unfolding that exposes the hydrophobic core to aggregation in structured globular proteins (such as SOD1 and lysozyme). A transition from full disorder to semi-disorder at about 30-40 Qs is observed in the poly-Q (poly-glutamine) tract of huntingtin. The accuracy of using semi-disorder to predict binding-induced folding and aggregation is compared with several methods trained for the purpose. These results indicate the usefulness of three-state classification (order, semi-disorder, and full-disorder) in distinguishing nonfolding from induced-folding and aggregation-resistant from aggregation-prone IDPs and in locating weakly stable, locally unfolding, and potentially aggregation regions in structured proteins. A comparison with five representative disorder-prediction methods showed that SPINE-D is the only method with a clear separation of semi-disorder from ordered and fully disordered states.

BEST: improved prediction of B-cell epitopes from antigen sequences.

Accurate identification of immunogenic regions in a given antigen chain is a difficult and actively pursued problem. Although accurate predictors for T-cell epitopes are already in place, the prediction of the B-cell epitopes requires further research. We overview the available approaches for the prediction of B-cell epitopes and propose a novel and accurate sequence-based solution. Our BEST (B-cell Epitope prediction using Support vector machine Tool) method predicts epitopes from antigen sequences, in contrast to some method that predict only from short sequence fragments, using a new architecture based on averaging selected scores generated from sliding 20-mers by a Support Vector Machine (SVM). The SVM predictor utilizes a comprehensive and custom designed set of inputs generated by combining information derived from the chain, sequence conservation, similarity to known (training) epitopes, and predicted secondary structure and relative solvent accessibility. Empirical evaluation on benchmark datasets demonstrates that BEST outperforms several modern sequence-based B-cell epitope predictors including ABCPred, method by Chen et al. (2007), BCPred, COBEpro, BayesB, and CBTOPE, when considering the predictions from antigen chains and from the chain fragments. Our method obtains a cross-validated area under the receiver operating characteristic curve (AUC) for the fragment-based prediction at 0.81 and 0.85, depending on the dataset. The AUCs of BEST on the benchmark sets of full antigen chains equal 0.57 and 0.6, which is significantly and slightly better than the next best method we tested. We also present case studies to contrast the propensity profiles generated by BEST and several other methods.