Prediction of protein functional domains from sequences using artificial neural networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Murvai J
PROVIDER: S-EPMC311121 | biostudies-literature | 2001 Aug
REPOSITORIES: biostudies-literature
Publications
Prediction of protein functional domains from sequences using artificial neural networks.
Murvai J J Vlahovicek K K Szepesvári C C Pongor S S
Genome research 20010801 8
An artificial neural network (ANN) solution is described for the recognition of domains in protein sequences. A query sequence is first compared to a reference database of domain sequences by use of and the output data, encoded in the form of six parameters, are forwarded to feed-forward artificial neural networks with six input and six hidden units with sigmoidal transfer function. The recognition is based on the distribution of scores precomputed for the known domain groups in a database versu ...[more]
Similar Datasets
Project description:A significant amount of attention has been given to the design and synthesis of co-crystals by both industry and academia because of its potential to change a molecule's physicochemical properties. Yet, difficulties arise when searching for adequate combinations of molecules (or coformers) to form co-crystals, hampering the efficient exploration of the target's solid-state landscape. This paper reports on the application of a data-driven co-crystal prediction method based on two types of artificial neural network models and co-crystal data present in the Cambridge Structural Database. The models accept pairs of coformers and predict whether a co-crystal is likely to form. By combining the output of multiple models of both types, our approach shows to have excellent performance on the proposed co-crystal training and validation sets, and has an estimated accuracy of 80 % for molecules for which previous co-crystallization data is unavailable.
| S-EPMC7756866 | biostudies-literature
Project description:Closely connected to human carbon emissions, global climate change is affecting regional economic and social development, natural ecological environment, food security, water supply, and many other social aspects. In a word, climate change has become a vital issue of general concern in the current society. In this study, the carbon emission data of Chinese provinces in 1999-2019 are collected and analyzed, so as to identify the carbon emission of direct consumption per 10,000 residents in each province (including each municipal city and autonomous region) and the entire nation based on population data. The Arc Geographic Information Science Engine (ArcGIS Engine) and C#.NET platform are employed to call the MATLAB neural network toolbox. A model is selected and embedded in the prediction system to develop the entire system. This study demonstrates that the carbon emissions per resident in Northern China are significantly higher than those in Southern China, with the rate of carbon emissions continuing to increase over time. Compared with other models, the Elman neural network has a higher carbon emission prediction accuracy, but with more minor errors. For instance, its accuracy and prediction performance are improved by 55.93% and 19.48%, respectively, compared with the Backpropagation Neural Network (BPNN). The prediction results show that China is expected to reach its peak carbon emission in around 2025-2030. The above results are acquired based on the concept of carbon emissions and neural network model theories, supported by GIS component technology and intelligent methods. The feasibility of BPNN, Radial Basis Function (RBF) and Elman neural network models for predicting residential carbon emissions is analyzed. This study also designs a comprehensive, integrated and extensible visual intelligent platform, which is easy to implement and stable in operation. The trend and characteristics of carbon emission changes from 2027 to 2032 are explored and predicted based on the data about direct carbon emissions of Chinese provincial residents from 1999 to 2019, purposed to provide a scientific basis for the control and planning of carbon emissions.
| S-EPMC8118316 | biostudies-literature
Project description:Predicting SARS-CoV-2 mutations is difficult, but predicting recurrent mutations driven by the host, such as those caused by host deaminases, is feasible. We used machine learning to predict which positions from the SARS-CoV-2 genome will hold a recurrent mutation and which mutations will be the most recurrent. We used data from April 2021 that we separated into three sets: a training set, a validation set, and an independent test set. For the test set, we obtained a specificity value of 0.69, a sensitivity value of 0.79, and an Area Under the Curve (AUC) of 0.8, showing that the prediction of recurrent SARS-CoV-2 mutations is feasible. Subsequently, we compared our predictions with updated data from January 2022, showing that some of the false positives in our prediction model become true positives later on. The most important variables detected by the model's Shapley Additive exPlanation (SHAP) are the nucleotide that mutates and RNA reactivity. This is consistent with the SARS-CoV-2 mutational bias pattern and the preference of some host deaminases for specific sequences and RNA secondary structures. We extend our investigation by analyzing the mutations from the variants of concern Alpha, Beta, Delta, Gamma, and Omicron. Finally, we analyzed amino acid changes by looking at the predicted recurrent mutations in the M-pro and spike proteins.
| S-EPMC9736107 | biostudies-literature
Project description:High-throughput sequencing technologies have generated massive protein sequences, but the annotations of protein sequences highly rely on the low-throughput and expensive biological experiments. Therefore, accurate and fast computational alternatives are needed to infer functional knowledge from protein sequences. The gene ontology (GO) directed acyclic graph (DAG) contains the hierarchical relationships between GO terms but is hard to be integrated into machine learning algorithms for functional predictions. We developed a deep learning system named PANDA2 to predict protein functions, which used the cutting-edge graph neural network to model the topology of the GO DAG and integrated the features generated by transformer protein language models. Compared with the top 10 methods in CAFA3, PANDA2 ranked first in cellular component ontology (CCO), tied first in biological process ontology (BPO) but had a higher coverage rate, and second in molecular function ontology (MFO). Compared with other recently-developed cutting-edge predictors DeepGOPlus, GOLabeler, and DeepText2GO, and benchmarked on another independent dataset, PANDA2 ranked first in CCO, first in BPO, and second in MFO. PANDA2 can be freely accessed from http://dna.cs.miami.edu/PANDA2/.
| S-EPMC8808544 | biostudies-literature
Project description:Recombinant DNA technology has, in the last decades, contributed to a vast expansion of the use of protein drugs as pharmaceutical agents. However, such biological drugs can lead to the formation of anti-drug antibodies (ADAs) that may result in adverse effects, including allergic reactions and compromised therapeutic efficacy. Production of ADAs is most often associated with activation of CD4 T cell responses resulting from proteolysis of the biotherapeutic and loading of drug-specific peptides into major histocompatibility complex (MHC) class II on professional antigen-presenting cells. Recently, readouts from MHC-associated peptide proteomics (MAPPs) assays have been shown to correlate with the presence of CD4 T cell epitopes. However, the limited sensitivity of MAPPs challenges its use as an immunogenicity biomarker. In this work, MAPPs data was used to construct an artificial neural network (ANN) model for MHC class II antigen presentation. Using Infliximab and Rituximab as showcase stories, the model demonstrated an unprecedented performance for predicting MAPPs and CD4 T cell epitopes in the context of protein-drug immunogenicity, complementing results from MAPPs assays and outperforming conventional prediction models trained on binding affinity data.
| S-EPMC7325480 | biostudies-literature
Project description:BACKGROUND:Proteins, especially larger ones, are often composed of individual evolutionary units, domains, which have their own function and structural fold. Predicting domains is an important intermediate step in protein analyses, including the prediction of protein structures. RESULTS:We describe novel systems for the prediction of protein domain boundaries powered by Recursive Neural Networks. The systems rely on a combination of primary sequence and evolutionary information, predictions of structural features such as secondary structure, solvent accessibility and residue contact maps, and structural templates, both annotated for domains (from the SCOP dataset) and unannotated (from the PDB). We gauge the contribution of contact maps, and PDB and SCOP templates independently and for different ranges of template quality. We find that accurately predicted contact maps are informative for the prediction of domain boundaries, while the same is not true for contact maps predicted ab initio. We also find that gap information from PDB templates is informative, but, not surprisingly, less than SCOP annotations. We test both systems trained on templates of all qualities, and systems trained only on templates of marginal similarity to the query (less than 25% sequence identity). While the first batch of systems produces near perfect predictions in the presence of fair to good templates, the second batch outperforms or match ab initio predictors down to essentially any level of template quality.We test all systems in 5-fold cross-validation on a large non-redundant set of multi-domain and single domain proteins. The final predictors are state-of-the-art, with a template-less prediction boundary recall of 50.8% (precision 38.7%) within +/- 20 residues and a single domain recall of 80.3% (precision 78.1%). The SCOP-based predictors achieve a boundary recall of 74% (precision 77.1%) again within +/- 20 residues, and classify single domain proteins as such in over 85% of cases, when we allow a mix of bad and good quality templates. If we only allow marginal templates (max 25% sequence identity to the query) the scores remain high, with boundary recall and precision of 59% and 66.3%, and 80% of all single domain proteins predicted correctly. CONCLUSION:The systems presented here may prove useful in large-scale annotation of protein domains in proteins of unknown structure. The methods are available as public web servers at the address: http://distill.ucd.ie/shandy/ and we plan on running them on a multi-genomic scale and make the results public in the near future.
| S-EPMC2711945 | biostudies-other
Project description:The fundamental period is one of the most critical parameters for the seismic design of structures. There are several literature approaches for its estimation which often conflict with each other, making their use questionable. Furthermore, the majority of these approaches do not take into account the presence of infill walls into the structure despite the fact that infill walls increase the stiffness and mass of structure leading to significant changes in the fundamental period. In the present paper, artificial neural networks (ANNs) are used to predict the fundamental period of infilled reinforced concrete (RC) structures. For the training and the validation of the ANN, a large data set is used based on a detailed investigation of the parameters that affect the fundamental period of RC structures. The comparison of the predicted values with analytical ones indicates the potential of using ANNs for the prediction of the fundamental period of infilled RC frame structures taking into account the crucial parameters that influence its value.
| S-EPMC4809391 | biostudies-literature
Project description:The aim of this work was to investigate effects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w ibuprofen. It was observed that with higher water content longer exposure time was required for successful printing. For understanding the effects of excipients and printing parameters on drug dissolution rate in DLP printlets two different neural networks were developed with using two commercially available softwares. After comparison of experimental and predicted values of in vitro dissolution at the corresponding time points for optimized formulation, the R2 experimental vs. predicted value was 0.9811 (neural network 1) and 0.9960 (neural network 2). According to difference f1 and similarity factor f2 (f1 = 14.30 and f2 = 52.15) neural network 1 with supervised multilayer perceptron, backpropagation algorithm, and linear activation function gave a similar dissolution profile to obtained experimental results, indicating that adequate ANN is able to set out an input-output relationship in DLP printing of pharmaceutics.
| S-EPMC6835658 | biostudies-literature
Project description:The ability to estimate the age of the donor from recovered biological material at a crime scene can be of substantial value in forensic investigations. Aging can be complex and is associated with various molecular modifications in cells that accumulate over a person's lifetime including epigenetic patterns. The aim of this study was to use age-specific DNA methylation patterns to generate an accurate model for the prediction of chronological age using data from whole blood. In total, 45 age-associated CpG sites were selected based on their reported age coefficients in a previous extensive study and investigated using publicly available methylation data obtained from 1156 whole blood samples (aged 2-90 years) analysed with Illumina's genome-wide methylation platforms (27K/450K). Applying stepwise regression for variable selection, 23 of these CpG sites were identified that could significantly contribute to age prediction modelling and multiple regression analysis carried out with these markers provided an accurate prediction of age (R2=0.92, mean absolute error (MAE)=4.6 years). However, applying machine learning, and more specifically a generalised regression neural network model, the age prediction significantly improved (R2=0.96) with a MAE=3.3 years for the training set and 4.4 years for a blind test set of 231 cases. The machine learning approach used 16 CpG sites, located in 16 different genomic regions, with the top 3 predictors of age belonged to the genes NHLRC1, SCGN and CSNK1D. The proposed model was further tested using independent cohorts of 53 monozygotic twins (MAE=7.1 years) and a cohort of 1011 disease state individuals (MAE=7.2 years). Furthermore, we highlighted the age markers' potential applicability in samples other than blood by predicting age with similar accuracy in 265 saliva samples (R2=0.96) with a MAE=3.2 years (training set) and 4.0 years (blind test). In an attempt to create a sensitive and accurate age prediction test, a next generation sequencing (NGS)-based method able to quantify the methylation status of the selected 16 CpG sites was developed using the Illumina MiSeq® platform. The method was validated using DNA standards of known methylation levels and the age prediction accuracy has been initially assessed in a set of 46 whole blood samples. Although the resulted prediction accuracy using the NGS data was lower compared to the original model (MAE=7.5years), it is expected that future optimization of our strategy to account for technical variation as well as increasing the sample size will improve both the prediction accuracy and reproducibility.
| S-EPMC5392537 | biostudies-literature
Project description:BackgroundsDespite continuing progress in X-ray crystallography and high-field NMR spectroscopy for determination of three-dimensional protein structures, the number of unsolved and newly discovered sequences grows much faster than that of determined structures. Protein modeling methods can possibly bridge this huge sequence-structure gap with the development of computational science. A grand challenging problem is to predict three-dimensional protein structure from its primary structure (residues sequence) alone. However, predicting residue contact maps is a crucial and promising intermediate step towards final three-dimensional structure prediction. Better predictions of local and non-local contacts between residues can transform protein sequence alignment to structure alignment, which can finally improve template based three-dimensional protein structure predictors greatly.MethodsCNNcon, an improved multiple neural networks based contact map predictor using six sub-networks and one final cascade-network, was developed in this paper. Both the sub-networks and the final cascade-network were trained and tested with their corresponding data sets. While for testing, the target protein was first coded and then input to its corresponding sub-networks for prediction. After that, the intermediate results were input to the cascade-network to finish the final prediction.ResultsThe CNNcon can accurately predict 58.86% in average of contacts at a distance cutoff of 8 Å for proteins with lengths ranging from 51 to 450. The comparison results show that the present method performs better than the compared state-of-the-art predictors. Particularly, the prediction accuracy keeps steady with the increase of protein sequence length. It indicates that the CNNcon overcomes the thin density problem, with which other current predictors have trouble. This advantage makes the method valuable to the prediction of long length proteins. As a result, the effective prediction of long length proteins could be possible by the CNNcon.
| S-EPMC3634008 | biostudies-literature