Structure Prediction Modeling Research Articles

Accurate protein function prediction via graph attention networks with predicted structure information.

Experimental protein function annotation does not scale with the fast-growing sequence databases. Only a tiny fraction (<0.1%) of protein sequences has experimentally determined functional annotations. Computational methods may predict protein function very quickly, but their accuracy is not very satisfactory. Based upon recent breakthroughs in protein structure prediction and protein language models, we develop GAT-GO, a graph attention network (GAT) method that may substantially improve protein function prediction by leveraging predicted structure information and protein sequence embedding. Our experimental results show that GAT-GO greatly outperforms the latest sequence- and structure-based deep learning methods. On the PDB-mmseqs testset where the train and test proteins share <15% sequence identity, our GAT-GO yields Fmax (maximum F-score) 0.508, 0.416, 0.501, and area under the precision-recall curve (AUPRC) 0.427, 0.253, 0.411 for the MFO, BPO, CCO ontology domains, respectively, much better than the homology-based method BLAST (Fmax 0.117, 0.121, 0.207 and AUPRC 0.120, 0.120, 0.163) that does not use any structure information. On the PDB-cdhit testset where the training and test proteins are more similar, although using predicted structure information, our GAT-GO obtains Fmax 0.637, 0.501, 0.542 for the MFO, BPO, CCO ontology domains, respectively, and AUPRC 0.662, 0.384, 0.481, significantly exceeding the just-published method DeepFRI that uses experimental structures, which has Fmax 0.542, 0.425, 0.424 and AUPRC only 0.313, 0.159, 0.193.

RsRNASP: A residue-separation-based statistical potential for RNA 3D structure evaluation

Knowledge-based statistical potentials have been shown to be rather effective in protein 3-dimensional (3D) structure evaluation and prediction. Recently, several statistical potentials have been developed for RNA 3D structure evaluation, while their performances are either still at a low level for the test datasets from structure prediction models or dependent on the “black-box” process through neural networks. In this work, we have developed an all-atom distance-dependent statistical potential based on residue separation for RNA 3D structure evaluation, namely rsRNASP, which is composed of short- and long-ranged potentials distinguished by residue separation. The extensive examinations against available RNA test datasets show that rsRNASP has apparently higher performance than the existing statistical potentials for the realistic test datasets with large RNAs from structure prediction models, including the newly released RNA-Puzzles dataset, and is comparable to the existing top statistical potentials for the test datasets with small RNAs or near-native decoys. In addition, rsRNASP is superior to RNA3DCNN, a recently developed scoring function through 3D convolutional neural networks. rsRNASP and the relevant databases are available to the public.

Using machine learning to study protein-protein interactions: From the uromodulin polymer to egg zona pellucida filaments.

Neural network-based models for protein structure prediction have recently reached near-experimental accuracy and are fast becoming a powerful tool in the arsenal of biologists. As suggested by initial studies using RoseTTAFold or the ColabFold implementation of AlphaFold2, a particularly interesting future development will be the optimization of these computational methods to also routinely yield high-confidence predictions of protein-protein interactions. Here I use AlphaFold2 and ColabFold to investigate the activation and polymerization of uromodulin (UMOD)/Tamm-Horsfall protein, a zona pellucida (ZP) module-containing protein whose precursor and filamentous structures have been previously determined experimentally by X-ray crystallography and cryo-EM, respectively. Despite having no knowledge of the UMOD polymer structure (coordinates for which were neither used for model training nor as template), AlphaFold2/ColabFold are able to recapitulate a crucial conformational change underlying UMOD polymerization, as well as the general organization of protein subunits within the resulting filament. This surprising result is achieved by simply deleting from the input sequence a stretch of residues that correspond to a polymerization-inhibiting C-terminal propeptide. By mimicking in silico the activating effect of propeptide dissociation triggered by site-specific proteolysis of the protein precursor, this example has implications for the assembly of egg coat proteins and the many other molecules that also contain a ZP module. Most importantly, it shows the potential of exploiting machine learning not only to accurately predict the structures of individual proteins or complexes, but also to carry out computational experiments replicating specific molecular events.

A robust deep structured prediction model for petroleum reservoir characterization using pressure transient test data

A robust deep learning model consisting of long short-term memory and fully connected neural networks has been proposed to automatically interpret homogeneous petroleum reservoirs having infinite, no flow, and constant pressure outer boundary conditions. The pressure change data recorded during the well test operation along with its derivative is input into the model to perform the classification for identifying the reservoir model and, further, regression to estimate output parameter. Gaussian noise was added to analytical models while generating the synthetic training data. The hyperparameters were regulated to perform model optimization, resulting in a batch size of 64, Adam optimization algorithm, learning rate of 0.01, and 80:10:10 data split ratio as the best choices of hyperparameters. The performance accuracy also increased with an increase in the number of samples during training. Suitable classification and regression metrics have been used to evaluate the performance of the models. The paper also demonstrates the prediction performance of the optimized model using simulated and actual oil well pressure drawdown test cases. The proposed model achieved minimum and maximum relative errors of 0.0019 and 0.0308, respectively, in estimating output for the simulated test cases and relative error of 0.0319 for the real test case.

Steel Structure Prediction Model for Fixed Roof Oil Tanks

AbstractThis paper will focus on fixed roof storage tanks and its sub‐category cone roof tanks. Paper presents major factors and outputs of tank design process. Theoretical analysis is done for a cone roof tank model and correlation between tank surface, shell thickness and total steel weight used. Detailed algorithm for tank design was realized using MathCAD software using Eurocode standards. Using this algorithm, 432 hypothetical tanks were designed. Data analysis of the collected output data was analysed using R statistics programming language. Using regression models and testing them led to the optimum statistical model.For the purpose of this work, data for 21 real world tanks including fixed roof and floating roof tanks were collected. The data was collected with help of MOL, INA and few other EPC contractors. Paper compares real world data with outputs of the model.Model can be used for quick estimates and control of material consumptions. Taking few input parameters and applying minimal effort can lead to a very accurate steel consumption prediction. With additional real‐world data, acceptable ranges of deviation from the mean could be set‐up. Thus, allowing for better control on Client part or EPC companies.

A novel structural adaptive discrete grey prediction model and its application in forecasting renewable energy generation

The rapidly growing renewable energy generation instigates stochastic volatility of electricity supply that may compromise the power grid's stability and increase the grid imbalance cost. Therefore, accurate mid-to-long term renewable energy generation forecasting is of great significance for integrating renewable energy systems with smart grid and energy strategic planning. For this purpose, a new structural adaptive discrete grey prediction model is proposed. Overall, the proposed model possesses three main contributions. Firstly, the introduction of nonlinear term and periodic term strengthens the ability of the traditional DGM (1,1) model to capture the nonlinear and linear development trend of time series and improves the adaptability of the grey prediction model to arbitrary periodic time series. Secondly, the emerging coefficients are determined by the particle swarm optimization algorithm and hold-out cross-validation method, and the adaptive selection of the model structure is realized. From the perspective of expert system, it reduces the need for modeling knowledge. Thirdly, the consistency of stretching, unbiasedness, and compatibility with other grey models are discussed, which further verified the feasibility and practicability of the proposed model. Besides, the performance of the proposed model is compared with those of a series of grey prediction models and non-grey prediction methods to verify the feasibility and superiority of this new approach by three real cases. The results indicate that the proposed model benefits from its adaptive structure and produces reliable predictions.

PSO Based Neuro-fuzzy Model for Secondary Structure Prediction of Protein

PSO Based Neuro-fuzzy Model for Secondary Structure Prediction of Protein

Protein structure prediction by AlphaFold2: are attention and symmetries all you need?

The functions of most proteins result from their 3D structures, but determining their structures experimentally remains a challenge, despite steady advances in crystallography, NMR and single-particle cryoEM. Computationally predicting the structure of a protein from its primary sequence has long been a grand challenge in bioinformatics, intimately connected with understanding protein chemistry and dynamics. Recent advances in deep learning, combined with the availability of genomic data for inferring co-evolutionary patterns, provide a new approach to protein structure prediction that is complementary to longstanding physics-based approaches. The outstanding performance of AlphaFold2 in the recent Critical Assessment of protein Structure Prediction (CASP14) experiment demonstrates the remarkable power of deep learning in structure prediction. In this perspective, we focus on the key features of AlphaFold2, including its use of (i) attention mechanisms and Transformers to capture long-range dependencies, (ii) symmetry principles to facilitate reasoning over protein structures in three dimensions and (iii) end-to-end differentiability as a unifying framework for learning from protein data. The rules of protein folding are ultimately encoded in the physical principles that underpin it; to conclude, the implications of having a powerful computational model for structure prediction that does not explicitly rely on those principles are discussed.

Molecular and Mechanistic Characterization of PddB, the First PLP-Independent 2,4-Diaminobutyric Acid Racemase Discovered in an Actinobacterial D-Amino Acid Homopolymer Biosynthesis.

We recently disclosed that the biosynthesis of antiviral γ-poly-D-2,4-diaminobutyric acid (poly-D-Dab) in Streptoalloteichus hindustanus involves an unprecedented cofactor independent stereoinversion of Dab catalyzed by PddB, which shows weak homology to diaminopimelate epimerase (DapF). Enzymological properties and mechanistic details of this enzyme, however, had remained to be elucidated. Here, through a series of biochemical characterizations, structural modeling, and site-directed mutageneses, we fully illustrate the first Dab-specific PLP-independent racemase PddB and further provide an insight into its evolution. The activity of the recombinant PddB was shown to be optimal around pH 8.5, and its other fundamental properties resembled those of typical PLP-independent racemases/epimerases. The enzyme catalyzed Dab specific stereoinversion with a calculated equilibrium constant of nearly unity, demonstrating that the reaction catalyzed by PddB is indeed racemization. Its activity was inhibited upon incubation with sulfhydryl reagents, and the site-directed substitution of two putative catalytic Cys residues led to the abolishment of the activity. These observations provided critical evidence that PddB employs the thiolate-thiol pair to catalyze interconversion of Dab isomers. Despite the low levels of sequence similarity, a phylogenetic analysis of PddB indicated its particular relevance to DapF among PLP-independent racemases/epimerases. Secondary structure prediction and 3D structural modeling of PddB revealed its remarkable conformational analogy to DapF, which in turn allowed us to predict amino acid residues potentially responsible for the discrimination of structural difference between diaminopimelate and its specific substrate, Dab. Further, PddB homologs which seemed to be narrowly distributed only in actinobacterial kingdom were constantly encoded adjacent to the putative poly-D-Dab synthetase gene. These observations strongly suggested that PddB could have evolved from the primary metabolic DapF in order to organize the biosynthesis pathway for the particular secondary metabolite, poly-D-Dab. The present study is on the first molecular characterization of PLP-independent Dab racemase and provides insights that could contribute to further discovery of unprecedented PLP-independent racemases.

Exploring Nucleic Acid Structure‐Function Relationships in Remote Biochemistry Instruction

The covid-19 pandemic has forced universities around the world to transition to online, remote, or hybrid instruction. This challenge is exacerbated in the laboratory sciences as the limitations on in-person instruction force instructors to conduct curriculum triage and develop new creative avenues for providing meaningful experiential learning opportunities. However, some learning objectives such as nucleic acid structure function relationships can still be pursued with the rigor necessary to train future biochemists and biophysicists using web-based RNA and DNA structural analysis programs. The decades of research in nucleic acid structure prediction algorithms and modeling programs have laid an exceptional foundation for remote teaching and learning in the biosciences. We evaluate the various nucleic acid secondary and tertiary structure prediction programs and their capabilities for remote laboratory activities and research projects. We identify the particular strengths of each program and learning objectives each one can be used to pursue. We also present a series of guided and independent inquiry activities using these prediction programs exploring nucleic acid secondary and tertiary structure suitable for introductory or advanced biochemistry courses using asynchronous or synchronous modalities. Activities include an exploration of nucleic acid secondary structures and relative stabilities, identifying non-canonical interactions within RNA folds, predicting tertiary interactions, comparing predicted structures to published experimentally-determined secondary structures, and investigating how mutations in the nucleic acid sequence can affect secondary and tertiary structure. Tools to increase engagement and discussion in synchronous virtual laboratory sessions are also presented. These activities focus on the SARS-CoV-2 viral RNA structure but can be modified for any particular RNA or DNA. Available biophysical technology resources provide an avenue for continuing high-level instruction despite the challenges of classroom and laboratory de-densification.

Swarm optimization-based neural network model for secondary structure prediction of proteins

Proteins form the basis of all major life processes that sustain life. The functionality of a protein is a direct consequence of its underlying structure. Protein structure prediction thus serves to ascertain the function of similar or dissimilar proteins, accordingly. Secondary structure prediction paves way for 3D structures that eventually decides protein properties. It also aims to facilitate probable structures for proteins whose structures remain undiscovered. Although experimental approaches have been quite efficient in extracting protein secondary structure from its amino acid sequence, yet it is often cumbersome and time intensive to achieve it in vitro. Hence, computational approaches are required to predict secondary structures for the diverse amino acids constituting these proteins. However, the available computational models fail to register good prediction accuracy due to inadequate modelling of sequence-structure relationship. Also, the dearth of global exploration-based methods further makes them ineffective in catering to the evolving proteomic data. Accordingly, PSO (Particle swarm optimization) has been explored to propose a neural network model for protein secondary structure prediction (PSSP). Six standard datasets namely- PSS504, RS126, EVA6, CB396, Manesh and CB513 have been utilized for the training and testing of the neural network. The proposed model is evaluated on the basis of its Q3 accuracy, precision, and recall. The 10, 20, 30 and 40 fold cross validation in combination with sensitivity analysis and has been carried out for verification of results. The proposed model is found to outperform most of the existing models by demonstrating a better average Q3 accuracy lying above 81% for PSSP.

Structural Prediction Model Satisfaction and Buying Decision of Muslim Consumers Towards Fast Food by Halal Labeling

This exploration means to comprehend what impacts Muslims in Bandung in creation choices on purchasing inexpensive food. The objects of this exploration are Muslim cheap food customers in Bandung. Information was gathered through an overview utilizing polls as a helping instrument. There were 180 respondents as tests. The information examination was led utilizing Structural Equation Modeling – Partial Least Square (SEM–PLS) approach. The exploration results show that the halal logo has a positive and critical impact on purchasing choices and that the clients' fulfillment likewise has a positive and huge effect on purchasing choices. Moreover, buyers' fulfillment can intervene in the impact of the halal logo on purchasing choices. This examination result is relied upon to urge eatery supervisors to be more mindful of the significance of the halal logo on their items.

Molecular phylogeny and morphology of Cephaleuros (Trentepohliales, Chlorophyta) from southern China

ABSTRACT Cephaleuros is a subaerial green alga widely distributed in tropical and subtropical regions. In this study, we investigated the taxonomy of Cephaleuros in southern China. Eight morphospecies (C. virescens, C. karstenii, C. expansus, C. drouetii, C. diffusus, C. tumidae-setae, C. lagerheimii and C. parasiticus) were identified according to previous descriptions, among which C. karstenii was the most frequently recorded. Subsequently, molecular phylogeny of Cephaleuros was inferred from 18S rDNA, ITS rDNA, 28S rDNA and rbcL sequences. Cephaleuros was subdivided into nine clades based on ITS analysis, which were recovered in phylogenies of two concatenated datasets (18S+ITS+28S and 18S+ITS+28S+rbcL). Molecular analyses revealed that Cephaleuros was composed of two main lineages, with one lineage comprising mostly samples of C. karstenii and C. virescens and the other comprising other species. The molecular phylogenies were not congruent with conventional morphological classifications, although some clades were distinguished by one or more diagnostic features. While the morphological features used to distinguish Cephaleuros spp were not reliable, the rbcL gene proved to be a good marker for identification of Cephaleuros. The ITS2 secondary structure prediction model showed that Cephaleuros spp have one ring structure with four helices, with Helix III being the longest without a branch in clades 3, 5 and 8. The present study represents the most detailed taxonomic assessment of Cephaleuros available to date. Further taxonomic research incorporating samples from the type locality is necessary for the reassessment of C. virescens.

Structural fatigue investigation of thermite welded rail joints considering weld-induced residual stress and stress relaxation by cyclic load

This study developed a structural fatigue life prediction model of thermite welded rail joints taking account of the weld-induced residual stress and stress relaxation by external cyclic load. A three-dimensional finite element model including the sequentially coupled thermal–mechanical simulation and cyclic plasticity constitutive simulation was developed to investigate the welding process induced residual stress and the redistribution of the residual stresses due to cyclic bend fatigue loading, respectively. The numerical results of the finite element model were compared with experimental residual stress data to confirm the accuracy of the model developed. The fatigue crack propagation life prediction taking into account the as-welded residual stress and the stress redistribution was performed. The predicted life of weld-toe cracks at web-to-base location will be overestimated by at least 50% if residual stress and relaxation is not considered.

Improved protein structure refinement guided by deep learning based accuracy estimation

We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules.

OCLSTM: Optimized convolutional and long short-term memory neural network model for protein secondary structure prediction.

Protein secondary structure prediction is extremely important for determining the spatial structure and function of proteins. In this paper, we apply an optimized convolutional neural network and long short-term memory neural network models to protein secondary structure prediction, which is called OCLSTM. We use an optimized convolutional neural network to extract local features between amino acid residues. Then use the bidirectional long short-term memory neural network to extract the remote interactions between the internal residues of the protein sequence to predict the protein structure. Experiments are performed on CASP10, CASP11, CASP12, CB513, and 25PDB datasets, and the good performance of 84.68%, 82.36%, 82.91%, 84.21% and 85.08% is achieved respectively. Experimental results show that the model can achieve better results.

The Effect of Point Mutations on Structure and Dynamics of SARS-CoV-2 Main Protease Mutants

The SARS-CoV-2 main protease (Mpro) is a serine-type protease with catalytic residues His-41 and Cys-145. These residues cleave highly specific protein sequences, making Mpro a vital part of the viral replication process and an attractive target for inhibitor design. As the virus spreads across the globe, sequence mutations occur, creating an additional challenge for robust inhibitor design. In previous work we have reported results from sequence analysis, structure prediction, and molecular modeling of the first seventy-nine Mpro variants, which revealed patterns in residue substitutions and a distribution of cohesion and constraint in the active site due to mutations.

Recognition of small molecule-RNA binding sites using RNA sequence and structure.

MotivationRNA molecules become attractive small molecule drug targets to treat disease in recent years. Computer-aided drug design can be facilitated by detecting the RNA sites that bind small molecules. However, very limited progress has been reported for the prediction of small molecule–RNA binding sites.ResultsWe developed a novel method RNAsite to predict small molecule–RNA binding sites using sequence profile- and structure-based descriptors. RNAsite was shown to be competitive with the state-of-the-art methods on the experimental structures of two independent test sets. When predicted structure models were used, RNAsite outperforms other methods by a large margin. The possibility of improving RNAsite by geometry-based binding pocket detection was investigated. The influence of RNA structure’s flexibility and the conformational changes caused by ligand binding on RNAsite were also discussed. RNAsite is anticipated to be a useful tool for the design of RNA-targeting small molecule drugs.Availability and implementation http://yanglab.nankai.edu.cn/RNAsite.Supplementary information Supplementary data are available at Bioinformatics online.

Dual-Factor Approach to Consumer Acceptance of Mobile Banking

This study builds on relationship marketing literature and extends existing continuance intention theories by applying dual-factor model to understand the complex behaviors of Japanese consumers and continuance intention of using mobile financial applications, such as mobile banking and/or mobile wallet. The research model, originally developed by Amoroso and Chen, has been adopted and data collected with a sample of 513 Japanese mobile banking app consumers. A predictive structural equation model was derived from the covariance matrix and was produced to analyze the path coefficients. The results show a general support for continuance intention to use mobile banking technologies among Japanese consumers. The results show Japanese consumer satisfaction is found to be a strong predictor of loyalty and continuance intention, directly affected by perceived value, perceived enjoyment, and inertia/habit. While loyalty is found to be a key construct to directly affect continuance intention, a very strong predictor of continuance intention among Japanese mobile banking apps users.

A Deep Learning Prediction Model for Structural Deformation Based on Temporal Convolutional Networks.

The structural engineering is subject to various subjective and objective factors, the deformation is usually inevitable, the deformation monitoring data usually are nonstationary and nonlinear, and the deformation prediction is a difficult problem in the field of structural monitoring. Aiming at the problems of the traditional structural deformation prediction methods, a structural deformation prediction model is proposed based on temporal convolutional networks (TCNs) in this study. The proposed model uses a one-dimensional dilated causal convolution to reduce the model parameters, expand the receptive field, and prevent future information leakage. By obtaining the long-term memory of time series, the internal time characteristics of structural deformation data can be effectively mined. The network hyperparameters of the TCN model are optimized by the orthogonal experiment, which determines the optimal combination of model parameters. The experimental results show that the predicted values of the proposed model are highly consistent with the actual monitored values. The average RMSE, MAPE, and MAE with the optimized model parameters reduce 44.15%, 82.03%, and 66.48%, respectively, and the average running time is reduced by 45.41% compared with the results without optimization parameters. The average RMSE, MAE, and MAPE reduce by 26.88%, 62.16%, and 40.83%, respectively, compared with WNN, DBN-SVR, GRU, and LSTM models.