Improving Protein Subcellular Location Classification by Incorporating Three-Dimensional Structure Information.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang G
PROVIDER: S-EPMC8615982 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundFluorescence microscopy is widely used to determine the subcellular location of proteins. Efforts to determine location on a proteome-wide basis create a need for automated methods to analyze the resulting images. Over the past ten years, the feasibility of using machine learning methods to recognize all major subcellular location patterns has been convincingly demonstrated, using diverse feature sets and classifiers. On a well-studied data set of 2D HeLa single-cell images, the best performance to date, 91.5%, was obtained by including a set of multiresolution features. This demonstrates the value of multiresolution approaches to this important problem.ResultsWe report here a novel approach for the classification of subcellular location patterns by classifying in multiresolution subspaces. Our system is able to work with any feature set and any classifier. It consists of multiresolution (MR) decomposition, followed by feature computation and classification in each MR subspace, yielding local decisions that are then combined into a global decision. With 26 texture features alone and a neural network classifier, we obtained an increase in accuracy on the 2D HeLa data set to 95.3%.ConclusionWe demonstrate that the space-frequency localized information in the multiresolution subspaces adds significantly to the discriminative power of the system. Moreover, we show that a vastly reduced set of features is sufficient, consisting of our novel modified Haralick texture features. Our proposed system is general, allowing for any combinations of sets of features and any combination of classifiers.
| S-EPMC1933440 | biostudies-literature
Project description:Single Nucleotide Polymorphisms (SNPs) are an important source of human genome variability. Non-synonymous SNPs occurring in coding regions result in single amino acid polymorphisms (SAPs) that may affect protein function and lead to pathology. Several methods attempt to estimate the impact of SAPs using different sources of information. Although sequence-based predictors have shown good performance, the quality of these predictions can be further improved by introducing new features derived from three-dimensional protein structures.In this paper, we present a structure-based machine learning approach for predicting disease-related SAPs. We have trained a Support Vector Machine (SVM) on a set of 3,342 disease-related mutations and 1,644 neutral polymorphisms from 784 protein chains. We use SVM input features derived from the protein's sequence, structure, and function. After dataset balancing, the structure-based method (SVM-3D) reaches an overall accuracy of 85%, a correlation coefficient of 0.70, and an area under the receiving operating characteristic curve (AUC) of 0.92. When compared with a similar sequence-based predictor, SVM-3D results in an increase of the overall accuracy and AUC by 3%, and correlation coefficient by 0.06. The robustness of this improvement has been tested on different datasets and in all the cases SVM-3D performs better than previously developed methods even when compared with PolyPhen2, which explicitly considers in input protein structure information.This work demonstrates that structural information can increase the accuracy of disease-related SAPs identification. Our results also quantify the magnitude of improvement on a large dataset. This improvement is in agreement with previously observed results, where structure information enhanced the prediction of protein stability changes upon mutation. Although the structural information contained in the Protein Data Bank is limiting the application and the performance of our structure-based method, we expect that SVM-3D will result in higher accuracy when more structural date become available.
| S-EPMC3194195 | biostudies-literature
Project description:BackgroundProtein subcellular localization prediction plays an important role in biology research. Since traditional methods are laborious and time-consuming, many machine learning-based prediction methods have been proposed. However, most of the proposed methods ignore the evolution information of proteins. In order to improve the prediction accuracy, we present a deep learning-based method to predict protein subcellular locations.ResultsOur method utilizes not only amino acid compositions sequence but also evolution matrices of proteins. Our method uses a bidirectional long short-term memory network that processes the entire protein sequence and a convolutional neural network that extracts features from protein sequences. The position specific scoring matrix is used as a supplement to protein sequences. Our method was trained and tested on two benchmark datasets. The experiment results show that our method yields accurate results on the two datasets with an average precision of 0.7901, ranking loss of 0.0758 and coverage of 1.2848.ConclusionThe experiment results show that our method outperforms five methods currently available. According to those experiments, we can see that our method is an acceptable alternative to predict protein subcellular location.
| S-EPMC8539821 | biostudies-literature
Project description:We have constructed a non-homologous database, termed the Integrated Sequence-Structure Database (ISSD) which comprises the coding sequences of genes, amino acid sequences of the corresponding proteins, their secondary structure and straight phi,psi angles assignments, and polypeptide backbone coordinates. Each protein entry in the database holds the alignment of nucleotide sequence, amino acid sequence and the PDB three-dimensional structure data. The nucleotide and amino acid sequences for each entry are selected on the basis of exact matches of the source organism and cell environment. The current version 1.0 of ISSD is available on the WWW at http://www.protein.bio.msu.su/issd/ and includes 107 non-homologous mammalian proteins, of which 80 are human proteins. The database has been used by us for the analysis of synonymous codon usage patterns in mRNA sequences showing their correlation with the three-dimensional structure features in the encoded proteins. Possible ISSD applications include optimisation of protein expression, improvement of the protein structure prediction accuracy, and analysis of evolutionary aspects of the nucleotide sequence-protein structure relationship.
| S-EPMC147252 | biostudies-other
Project description:The FSSP database presents a continuously updated structural classification of three-dimensional protein folds. It is derived using an automatic structure comparison program (Dali) for the all-against-all comparison of over 6000 three-dimensional coordinate sets in the Protein Data Bank (PDB). Sequence-related protein families are covered by a representative set of 813 protein chains. Hierachical clustering based on structural similarities yields a fold tree that defines 253 fold classes. For each representative protein chain, there is a database entry containing structure-structure alignments with its structural neighbours in the PDB. The database is accessible online through World Wide Web browsers and by anonymous ftp (file transfer protocol). The overview of fold space and the individual data sets provide a rich source of information for the study of both divergent and convergent aspects of molecular evolution, and define useful test sets and a standard of truth for assessing the correctness of sequence-sequence or sequence-structure alignments.
| S-EPMC146389 | biostudies-other
Project description:BackgroundCurrent peak callers for identifying RNA-binding protein (RBP) binding sites from CLIP-seq data take into account genomic read profiles, but they ignore the underlying transcript information, that is information regarding splicing events. So far, there are no studies available that closer observe this issue.ResultsHere we show that current peak callers are susceptible to false peak calling near exon borders. We quantify its extent in publicly available datasets, which turns out to be substantial. By providing a tool called CLIPcontext for automatic transcript and genomic context sequence extraction, we further demonstrate that context choice affects the performances of RBP binding site prediction tools. Moreover, we show that known motifs of exon-binding RBPs are often enriched in transcript context sites, which should enable the recovery of more authentic binding sites. Finally, we discuss possible strategies on how to integrate transcript information into future workflows.ConclusionsOur results demonstrate the importance of incorporating transcript information in CLIP-seq data analysis. Taking advantage of the underlying transcript information should therefore become an integral part of future peak calling and downstream analysis tools.
| S-EPMC7745353 | biostudies-literature
Project description:The three-dimensional (3D) structure of RNA usually plays an important role in the recognition with RNA-binding protein. Along with the discovering of RNAs, several RNA databases are developed to study the functions of RNA based on sequence, secondary structure, local 3D structural motif and global structure. Based on RNA function and structure, different RNAs are classified and stored in SCOR and DARTS, respectively. The classification of RNA structures is useful in RNA structure prediction and function annotation. However, the SCOR and DARTS are not updated any more. In this study, we present an RNA classification database RR3DD based on RNA fold with the global 3D structural similarity. The RR3DD includes 13,601 RNA chains from PDB and mmCIF format structures which are classified into 780 RNA folds. The RNA chains from PDB and mmCIF format structures are aligned and clustered into 675 and 220 RNA folds, respectively. By analysing the RNA structure in RR3DD, we find that there are 11 clusters with more than 50 members. These clusters include rRNAs, riboswitches, tRNAs and so on. By mapping RR3DD into Rfam, we found that some RNAs without annotation by Rfam can be annotated through structural alignment. For example, we analysed tRNAs and found that tRNA were successfully grouped in RR3DD for which Rfam did not classify them into one family. Finally, we provide a web interface of RR3DD offering functions of browsing RR3DD, annotating RNA 3D structure and finding templates for RNA homology modelling.
| S-EPMC8782172 | biostudies-literature
Project description:The molecular subtypes of pancreatic cancer (PC), either classical/progenitor-like or basal/squamous-like, are currently a major topic of research because of their direct association with clinical outcomes. Some transcription factors (TFs) have been reported to be associated with these subtypes. However, the mechanisms by which these molecular signatures of PCs are established remain unknown. Epigenetic regulatory processes, supported by dynamic changes in the chromatin structure, are essential for transcriptional profiles. Previously, we reported the importance of open chromatin profiles in the biological features and transcriptional status of PCs. Here, we aimed to analyze the relationships between three-dimensional (3D) genome structures and the molecular subtypes of human PCs using Hi-C analysis. We observed a correlation of the specific elements of 3D genome modules, including compartments, topologically associating domains, and enhancer-promoter loops, with the expression of related genes. We focused on HNF1B, a TF that is implicated in the progenitor subtype. Forced expression of HNF1B in squamous-type PC organoids induced the upregulation and downregulation of genes associated with progenitor and squamous subtypes, respectively. Long-range genomic interactions induced by HNF1B were accompanied by compartment modulation and H3K27ac redistribution. We also found that these HNF1B-induced changes in subtype-related gene expression required an intrinsically disordered region, suggesting a possible involvement of phase separation in compartment modulation. Thus, mapping of 3D structural changes induced by TFs, such as HNF1B, may become a useful resource for further understanding the molecular features of PCs.
| S-EPMC10067390 | biostudies-literature
Project description:BackgroundMany biological processes are mediated by dynamic interactions between and among proteins. In order to interact, two proteins must co-occur spatially and temporally. As protein-protein interactions (PPIs) and subcellular location (SCL) are discovered via separate empirical approaches, PPI and SCL annotations are independent and might complement each other in helping us to understand the role of individual proteins in cellular networks. We expect reliable PPI annotations to show that proteins interacting in vivo are co-located in the same cellular compartment. Our goal here is to evaluate the potential of using PPI annotation in determining SCL of proteins in human, mouse, fly and yeast, and to identify and quantify the factors that contribute to this complementarity.ResultsUsing publicly available data, we evaluate the hypothesis that interacting proteins must be co-located within the same subcellular compartment. Based on a large, manually curated PPI dataset, we demonstrate that a substantial proportion of interacting proteins are in fact co-located. We develop an approach to predict the SCL of a protein based on the SCL of its interaction partners, given sufficient confidence in the interaction itself. The frequency of false positive PPIs can be reduced by use of six lines of supporting evidence, three based on type of recorded evidence (empirical approach, multiplicity of databases, and multiplicity of literature citations) and three based on type of biological evidence (inferred biological process, domain-domain interactions, and orthology relationships), with biological evidence more-effective than recorded evidence. Our approach performs better than four existing prediction methods in identifying the SCL of membrane proteins, and as well as or better for soluble proteins.ConclusionUnderstanding cellular systems requires knowledge of the SCL of interacting proteins. We show how PPI data can be used more effectively to yield reliable SCL predictions for both soluble and membrane proteins. Scope exists for further improvement in our understanding of cellular function through consideration of the biological context of molecular interactions.
| S-EPMC2663780 | biostudies-literature
Project description:Proteins display a hierarchy of structural features at primary, secondary, tertiary, and higher-order levels, an organization that guides our current understanding of their biological properties and evolutionary origins. Here, we reveal a structural organization distinct from this traditional hierarchy by statistical analysis of correlated evolution between amino acids. Applied to the S1A serine proteases, the analysis indicates a decomposition of the protein into three quasi-independent groups of correlated amino acids that we term "protein sectors." Each sector is physically connected in the tertiary structure, has a distinct functional role, and constitutes an independent mode of sequence divergence in the protein family. Functionally relevant sectors are evident in other protein families as well, suggesting that they may be general features of proteins. We propose that sectors represent a structural organization of proteins that reflects their evolutionary histories.
| S-EPMC3210731 | biostudies-literature