Structure-based Protein Function Prediction Research Articles

Targeted isolation of Methanobrevibacter strains from fecal samples expands the cultivated human archaeome

Archaea are vital components of the human microbiome, yet their study within the gastrointestinal tract (GIT) is limited by the scarcity of cultured representatives. Our study presents a method for the targeted enrichment and isolation of methanogenic archaea from human fecal samples. The procedure combines methane breath testing, in silico metabolic modeling, media optimization, FACS, dilution series, and genomic sequencing through Nanopore technology. Additional analyzes include the co-cultured bacteriome, comparative genomics of archaeal genomes, functional comparisons, and structure-based protein function prediction of unknown differential traits. Successful establishment of stable archaeal cultures from 14 out of 16 fecal samples yielded nine previously uncultivated strains, eight of which are absent from a recent archaeome genome catalog. Comparative genomic and functional assessments of Methanobrevibacter smithii and Candidatus Methanobrevibacter intestini strains from individual donors revealed features potentially associated with gastrointestinal diseases. Our work broadens available archaeal representatives for GIT studies, and offers insights into Candidatus Methanobrevibacter intestini genomes’ adaptability in critical microbiome contexts.

Enhancing Protein Function Prediction Performance by Utilizing AlphaFold-Predicted Protein Structures.

The structure of a protein is of great importance in determining its functionality, and this characteristic can be leveraged to train data-driven prediction models. However, the limited number of available protein structures severely limits the performance of these models. AlphaFold2 and its open-source data set of predicted protein structures have provided a promising solution to this problem, and these predicted structures are expected to benefit the model performance by increasing the number of training samples. In this work, we constructed a new data set that acted as a benchmark and implemented a state-of-the-art structure-based approach for determining whether the performance of the function prediction model can be improved by putting additional AlphaFold-predicted structures into the training set and further compared the performance differences between two models separately trained with real structures only and AlphaFold-predicted structures only. Experimental results indicated that structure-based protein function prediction models could benefit from virtual training data consisting of AlphaFold-predicted structures. First, model performances were improved in all three categories of Gene Ontology terms (GO terms) after adding predicted structures as training samples. Second, the model trained only on AlphaFold-predicted virtual samples achieved comparable performances to the model based on experimentally solved real structures, suggesting that predicted structures were almost equally effective in predicting protein functionality.

Structure-based protein function prediction using graph convolutional networks

The rapid increase in the number of proteins in sequence databases and the diversity of their functions challenge computational approaches for automated function prediction. Here, we introduce DeepFRI, a Graph Convolutional Network for predicting protein functions by leveraging sequence features extracted from a protein language model and protein structures. It outperforms current leading methods and sequence-based Convolutional Neural Networks and scales to the size of current sequence repositories. Augmenting the training set of experimental structures with homology models allows us to significantly expand the number of predictable functions. DeepFRI has significant de-noising capability, with only a minor drop in performance when experimental structures are replaced by protein models. Class activation mapping allows function predictions at an unprecedented resolution, allowing site-specific annotations at the residue-level in an automated manner. We show the utility and high performance of our method by annotating structures from the PDB and SWISS-MODEL, making several new confident function predictions. DeepFRI is available as a webserver at https://beta.deepfri.flatironinstitute.org/.

Prediction of protein function using a deep convolutional neural network ensemble

BackgroundThe availability of large databases containing high resolution three-dimensional (3D) models of proteins in conjunction with functional annotation allows the exploitation of advanced supervised machine learning techniques for automatic protein function prediction.MethodsIn this work, novel shape features are extracted representing protein structure in the form of local (per amino acid) distribution of angles and amino acid distances, respectively. Each of the multi-channel feature maps is introduced into a deep convolutional neural network (CNN) for function prediction and the outputs are fused through support vector machines or a correlation-based k-nearest neighbor classifier. Two different architectures are investigated employing either one CNN per multi-channel feature set, or one CNN per image channel.ResultsCross validation experiments on single-functional enzymes (n = 44,661) from the PDB database achieved 90.1% correct classification, demonstrating an improvement over previous results on the same dataset when sequence similarity was not considered.DiscussionThe automatic prediction of protein function can provide quick annotations on extensive datasets opening the path for relevant applications, such as pharmacological target identification. The proposed method shows promise for structure-based protein function prediction, but sufficient data may not yet be available to properly assess the method’s performance on non-homologous proteins and thus reduce the confounding factor of evolutionary relationships.

G-LoSA for Prediction of Protein-Ligand Binding Sites and Structures.

Recent advances in high-throughput structure determination and computational protein structure prediction have significantly enriched the universe of protein structure. However, there is still a large gap between the number of available protein structures and that of proteins with annotated function in high accuracy. Computational structure-based protein function prediction has emerged to reduce this knowledge gap. The identification of a ligand binding site and its structure is critical to the determination of a protein's molecular function. We present a computational methodology for predicting small molecule ligand binding site and ligand structure using G-LoSA, our protein local structure alignment and similarity measurement tool. All the computational procedures described here can be easily implemented using G-LoSA Toolkit, a package of standalone software programs and preprocessed PDB structure libraries. G-LoSA and G-LoSA Toolkit are freely available to academic users at http://compbio.lehigh.edu/GLoSA . We also illustrate a case study to show the potential of our template-based approach harnessing G-LoSA for protein function prediction.

Automated protein motif generation in the structure-based protein function prediction tool ProMOL.

ProMOL, a plugin for the PyMOL molecular graphics system, is a structure-based protein function prediction tool. ProMOL includes a set of routines for building motif templates that are used for screening query structures for enzyme active sites. Previously, each motif template was generated manually and required supervision in the optimization of parameters for sensitivity and selectivity. We developed an algorithm and workflow for the automation of motif building and testing routines in ProMOL. The algorithm uses a set of empirically derived parameters for optimization and requires little user intervention. The automated motif generation algorithm was first tested in a performance comparison with a set of manually generated motifs based on identical active sites from the same 112 PDB entries. The two sets of motifs were equally effective in identifying alignments with homologs and in rejecting alignments with unrelated structures. A second set of 296 active site motifs were generated automatically, based on Catalytic Site Atlas entries with literature citations, as an expansion of the library of existing manually generated motif templates. The new motif templates exhibited comparable performance to the existing ones in terms of hit rates against native structures, homologs with the same EC and Pfam designations, and randomly selected unrelated structures with a different EC designation at the first EC digit, as well as in terms of RMSD values obtained from local structural alignments of motifs and query structures. This research is supported by NIH grant GM078077.

Structural Protein Function Prediction - A Comprehensive Review

The large amounts of available protein structures emerges the need for computational methods for protein function prediction. Predicting protein function is mainly based on finding similarities between proteins with unknown function with already annotated proteins. This may be achieved using different protein characteristics: sequences, interactions, localization, structure and or psychochemical. A lot of review papers mainly focus on sequence and psychochemical features- based methods. This is because sequence and psychochemical data are easy to deal with and to interpret the results, and much available compared to protein structures. However, structure-based computational methods provide additional accuracy and reliability of protein function prediction. Therefore, unlike many review papers, this paper presents an up-to-date review on the structure-based protein function prediction. The aim was to provide a recent and comprehensive review of protein structure related topics: function aspects, structural classification, databases, tools and methods.

Automated Generation of Motif Templates in Protein Function Prediction Software ProMOL

ProMOL, an extension for molecular visualization system PyMOL, is structure‐based protein function prediction software. ProMOL implements routines for building motif templates based on active sites of proteins of known structure and function and screening unassigned structures for presence of the motif templates. Presently, motif generation in ProMOL requires user intervention in optimization of parameters for sensitivity and selectivity. An algorithm was developed to automate motif building and testing routines of ProMOL. The algorithm uses a set of empirically derived parameters for optimization, requires little user intervention, and provides a possibility for extending the ProMOL library of motif templates at a much higher rate. Presently, the library contains 181 motif templates. As a result of automating motif building and testing routines, 388 motif templates were generated and tested against their native, known homologous, and non‐homologous structures. The automatically generated motif templates exhibited comparable performance to the existing manually generated motif templates in terms of the rates of true positive and true negative results. The research is supported by 2R15GM078077–02.

3P264 FCANAL(構造を基にしたタンパク質機能御予測法)の様々なタンパク質への適用(22B.生命情報科学:機能ゲノミクス,ポスター,日本生物物理学会年会第51回(2013年度))

3P264 FCANAL(構造を基にしたタンパク質機能御予測法)の様々なタンパク質への適用(22B.生命情報科学:機能ゲノミクス,ポスター,日本生物物理学会年会第51回(2013年度))

GSAFold: A new application of GSA to protein structure prediction

The folding process defines three-dimensional protein structures from their amino acid chains. A protein's structure determines its activity and properties; thus knowing such conformation on an atomic level is essential for both basic and applied studies of protein function and dynamics. However, the acquisition of such structures by experimental methods is slow and expensive, and current computational methods mostly depend on previously known structures to determine new ones. Here we present a new software called GSAFold that applies the generalized simulated annealing (GSA) algorithm on ab initio protein structure prediction. The GSA is a stochastic search algorithm employed in energy minimization and used in global optimization problems, especially those that depend on long-range interactions, such as gravity models and conformation optimization of small molecules. This new implementation applies, for the first time in ab initio protein structure prediction, an analytical inverse for the Visitation function of GSA. It also employs the broadly used NAMD Molecular Dynamics package to carry out energy calculations, allowing the user to select different force fields and parameterizations. Moreover, the software also allows the execution of several simulations simultaneously. Applications that depend on protein structures include rational drug design and structure-based protein function prediction. Applying GSAFold in a test peptide, it was possible to predict the structure of mastoparan-X to a root mean square deviation of 3.00 Å.

Cutoff Scanning Matrix (CSM): structural classification and function prediction by protein inter-residue distance patterns

BackgroundThe unforgiving pace of growth of available biological data has increased the demand for efficient and scalable paradigms, models and methodologies for automatic annotation. In this paper, we present a novel structure-based protein function prediction and structural classification method: Cutoff Scanning Matrix (CSM). CSM generates feature vectors that represent distance patterns between protein residues. These feature vectors are then used as evidence for classification. Singular value decomposition is used as a preprocessing step to reduce dimensionality and noise. The aspect of protein function considered in the present work is enzyme activity. A series of experiments was performed on datasets based on Enzyme Commission (EC) numbers and mechanistically different enzyme superfamilies as well as other datasets derived from SCOP release 1.75.ResultsCSM was able to achieve a precision of up to 99% after SVD preprocessing for a database derived from manually curated protein superfamilies and up to 95% for a dataset of the 950 most-populated EC numbers. Moreover, we conducted experiments to verify our ability to assign SCOP class, superfamily, family and fold to protein domains. An experiment using the whole set of domains found in last SCOP version yielded high levels of precision and recall (up to 95%). Finally, we compared our structural classification results with those in the literature to place this work into context. Our method was capable of significantly improving the recall of a previous study while preserving a compatible precision level.ConclusionsWe showed that the patterns derived from CSMs could effectively be used to predict protein function and thus help with automatic function annotation. We also demonstrated that our method is effective in structural classification tasks. These facts reinforce the idea that the pattern of inter-residue distances is an important component of family structural signatures. Furthermore, singular value decomposition provided a consistent increase in precision and recall, which makes it an important preprocessing step when dealing with noisy data.

Identification of family-specific residue packing motifs and their use for structure-based protein function prediction: II. Case studies and applications

This paper describes several case studies concerning protein function inference from its structure using our novel approach described in the accompanying paper. This approach employs family-specific motifs, i.e. three-dimensional amino acid packing patterns that are statistically prevalent within a protein family. For our case studies we have selected families from the SCOP and EC classifications and analyzed the discriminating power of the motifs in depth. We have devised several benchmarks to compare motifs mined from unweighted topological graph representations of protein structures with those from distance-labeled (weighted) representations, demonstrating the superiority of the latter for function inference in most families. We have tested the robustness of our motif library by inferring the function of new members added to SCOP families, and discriminating between several families that are structurally similar but functionally divergent. Furthermore we have applied our method to predict function for several proteins characterized in structural genomics projects, including orphan structures, and we discuss several selected predictions in depth. Some of our predictions have been corroborated by other computational methods, and some have been validated by independent experimental studies, validating our approach for protein function inference from structure.

Identification of family-specific residue packing motifs and their use for structure-based protein function prediction: I. Method development

Protein function prediction is one of the central problems in computational biology. We present a novel automated protein structure-based function prediction method using libraries of local residue packing patterns that are common to most proteins in a known functional family. Critical to this approach is the representation of a protein structure as a graph where residue vertices (residue name used as a vertex label) are connected by geometrical proximity edges. The approach employs two steps. First, it uses a fast subgraph mining algorithm to find all occurrences of family-specific labeled subgraphs for all well characterized protein structural and functional families. Second, it queries a new structure for occurrences of a set of motifs characteristic of a known family, using a graph index to speed up Ullman's subgraph isomorphism algorithm. The confidence of function inference from structure depends on the number of family-specific motifs found in the query structure compared with their distribution in a large non-redundant database of proteins. This method can assign a new structure to a specific functional family in cases where sequence alignments, sequence patterns, structural superposition and active site templates fail to provide accurate annotation.

Local surface shape-based protein function prediction using Zernike descriptors

Structural genomics projects have been solving an increasing number of protein structures with unknown function. As the number of uncharacterized protein structures continues to grow, there is increasing need for effective computational strategies for structure-based protein function prediction. As of now, there are more than 2400 protein structures in the PDB database, which are categorized as unknown function and thus are awaiting functional characterization. Previously, we have reported a fast global protein surface shape comparison method based on 3D Zernike descriptors.

2P-242 立体構造を用いたタンパク質機能予測法FCANALのさまざまなタンパク質への応用(生命情報科学-機能ゲノミクス,第47回日本生物物理学会年会)

2P-242 立体構造を用いたタンパク質機能予測法FCANALのさまざまなタンパク質への応用(生命情報科学-機能ゲノミクス,第47回日本生物物理学会年会)

3P-297 タンパク質機能予測法FCANALのさまざまな酵素への適用(生命情報科学・機能ゲノミクス,第46回日本生物物理学会年会)

3P-297 タンパク質機能予測法FCANALのさまざまな酵素への適用(生命情報科学・機能ゲノミクス,第46回日本生物物理学会年会)

2P303 立体構造情報を利用したタンパク質機能予測法FCANAL : 酵素・結合タンパク質への応用(生命情報科学 B) 機能ゲノミクス))

2P303 立体構造情報を利用したタンパク質機能予測法FCANAL : 酵素・結合タンパク質への応用(生命情報科学 B) 機能ゲノミクス))

タンパク質立体構造情報を利用した機能予測法FCANAL：酵素・結合タンパク質への応用

Structural genomics projects are beginning to produce protein structures with unknown functions, thereby creating a need for high-throughput methods to predict functions. Although sequence-based function prediction methods have been used extensively, structure-based prediction is believed to provide higher specificity and sensitivity because functions are closely related to the three-dimensional structures of functional sites, which are more strongly conserved during evolution than sequence. We have developed FCANAL, a method to predict functions using a score matrix obtained from the distances between Cα atoms and frequencies of appearance [1]. The previous report used key residues predicted from sequence comparisons (motifs). In this report, we have expanded the method to include enzymes and binding proteins with key residues predicted on the basis of three-dimensional structures. Using FCANAL, we constructed score matrices for 31 enzymes. When we applied them to all of the structure entries deposited in the Protein Data Bank, FCANAL could detect functional sites with high accuracy. This suggests that FCANAL will help identify the functions of newly determined structures and pinpoint their functionally important regions.

3P282 立体構造情報を利用したタンパク質機能予測法FCANALの一般化(生命情報科学 B) 機能ゲノミクス)

3P282 立体構造情報を利用したタンパク質機能予測法FCANALの一般化(生命情報科学 B) 機能ゲノミクス)

タンパク質立体構造情報に基づいた機能予測法の一般化

タンパク質立体構造情報に基づいた機能予測法の一般化