Refining intra-protein contact prediction by graph analysis.
Ontology highlight
ABSTRACT: Background
Accurate prediction of intra-protein residue contacts from sequence information will allow the prediction of protein structures. Basic predictions of such specific contacts can be further refined by jointly analyzing predicted contacts, and by adding information on the relative positions of contacts in the protein primary sequence.Results
We introduce a method for graph analysis refinement of intra-protein contacts, termed GARP. Our previously presented intra-contact prediction method by means of pair-to-pair substitution matrix (P2PConPred) was used to test the GARP method. In our approach, the top contact predictions obtained by a basic prediction method were used as edges to create a weighted graph. The edges were scored by a mutual clustering coefficient that identifies highly connected graph regions, and by the density of edges between the sequence regions of the edge nodes. A test set of 57 proteins with known structures was used to determine contacts. GARP improves the accuracy of the P2PConPred basic prediction method in whole proteins from 12% to 18%.Conclusion
Using a simple approach we increased the contact prediction accuracy of a basic method by 1.5 times. Our graph approach is simple to implement, can be used with various basic prediction methods, and can provide input for further downstream analyses.
SUBMITTER: Frenkel-Morgenstern M
PROVIDER: S-EPMC1892094 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Protein solubility is significant in producing new soluble proteins that can reduce the cost of biocatalysts or therapeutic agents. Therefore, a computational model is highly desired to accurately predict protein solubility from the amino acid sequence. Many methods have been developed, but they are mostly based on the one-dimensional embedding of amino acids that is limited to catch spatially structural information. In this study, we have developed a new structure-aware method GraphSol to predict protein solubility by attentive graph convolutional network (GCN), where the protein topology attribute graph was constructed through predicted contact maps only from the sequence. GraphSol was shown to substantially outperform other sequence-based methods. The model was proven to be stable by consistent [Formula: see text] of 0.48 in both the cross-validation and independent test of the eSOL dataset. To our best knowledge, this is the first study to utilize the GCN for sequence-based protein solubility predictions. More importantly, this architecture could be easily extended to other protein prediction tasks requiring a raw protein sequence.
| S-EPMC7869490 | biostudies-literature
Project description:Synthetic lethality (SL) has shown great promise for the discovery of novel targets in cancer. CRISPR double-knockout (CDKO) technologies can only screen several hundred genes and their combinations, but not genome-wide. Therefore, good SL prediction models are highly needed for genes and gene pairs selection in CDKO experiments. In this paper, we develop a novel multi-layer encoder for individual sample-specific SL prediction (MLEC-iSL). Unlike existing SL prediction models, MLEC-iSL is built to predict SL connectivity first. Because SL connectivity is scalable from existing genes in the training data to new genes in validation data, we hypothesize MLEC-iSL has better SL prediction performance. MLEC-iSL has three encoders, namely gene encoder, graph encoder, and transformer encoder. MLEC-iSL has high performance in K562 (AUPR, 0.73; AUC, 0.72) and Jurkat (AUPR, 0.73; AUC, 0.71) cells while no existing methods exceed 0.62 AUPR and AUC in either cell. MLEC-iSL guided CDKO experiment in 22Rv1 cells yielded a 46.8% SL ratio amongst its selected gene pairs. Six of top ten SL connectivity hub genes are validated in 22Rv1 cells. It reveals SL gene pairs and dependency between apoptosis and mitosis cell death pathways.
2024-09-13 | GSE262953 | GEO
Project description:BackgroundProtein-protein interactions (PPIs) are central to many biological processes. Considering that the experimental methods for identifying PPIs are time-consuming and expensive, it is important to develop automated computational methods to better predict PPIs. Various machine learning methods have been proposed, including a deep learning technique which is sequence-based that has achieved promising results. However, it only focuses on sequence information while ignoring the structural information of PPI networks. Structural information of PPI networks such as their degree, position, and neighboring nodes in a graph has been proved to be informative in PPI prediction.ResultsFacing the challenge of representing graph information, we introduce an improved graph representation learning method. Our model can study PPI prediction based on both sequence information and graph structure. Moreover, our study takes advantage of a representation learning model and employs a graph-based deep learning method for PPI prediction, which shows superiority over existing sequence-based methods. Statistically, Our method achieves state-of-the-art accuracy of 99.15% on Human protein reference database (HPRD) dataset and also obtains best results on Database of Interacting Protein (DIP) Human, Drosophila, Escherichia coli (E. coli), and Caenorhabditis elegans (C. elegan) datasets.ConclusionHere, we introduce signed variational graph auto-encoder (S-VGAE), an improved graph representation learning method, to automatically learn to encode graph structure into low-dimensional embeddings. Experimental results demonstrate that our method outperforms other existing sequence-based methods on several datasets. We also prove the robustness of our model for very sparse networks and the generalization for a new dataset that consists of four datasets: HPRD, E.coli, C.elegan, and Drosophila.
| S-EPMC7372763 | biostudies-literature
Project description:The study of protein-protein interaction and the determination of protein functions are important parts of proteomics. Computational methods are used to study the similarity between proteins based on Gene Ontology (GO) to explore their functions and possible interactions. GO is a series of standardized terms that describe gene products from molecular functions, biological processes, and cell components. Previous studies on assessing the similarity of GO terms were primarily based on Information Content (IC) between GO terms to measure the similarity of proteins. However, these methods tend to ignore the structural information between GO terms. Therefore, considering the structural information of GO terms, we systematically analyze the performance of the GO graph and GO Annotation (GOA) graph in calculating the similarity of proteins using different graph embedding methods. When applied to the actual Human and Yeast datasets, the feature vectors of GO terms and proteins are learned based on different graph embedding methods. To measure the similarity of the proteins annotated by different GO numbers, we used Dynamic Time Warping (DTW) and cosine to calculate protein similarity in GO graph and GOA graph, respectively. Link prediction experiments were then performed to evaluate the reliability of protein similarity networks constructed by different methods. It is shown that graph embedding methods have obvious advantages over the traditional IC-based methods. We found that random walk graph embedding methods, in particular, showed excellent performance in calculating the similarity of proteins. By comparing link prediction experiment results from GO(DTW) and GOA(cosine) methods, it is shown that GO(DTW) features provide highly effective information for analyzing the similarity among proteins.
| S-EPMC8493040 | biostudies-literature
Project description:SpecP is an open-source Python module that performs Spectral Partitioning on Protein Contact Graphs. Protein Contact Graphs are graph theory based representation of the protein structure, where each amino acid forms a 'vertex' and spatial contact of any two amino acids is an 'edge' between them. Spectral partitioning is carried out in SpecP based on the second smallest spectral value (eigen value) of the Protein Contact Graph. The eigen vector corresponding to the second smallest spectral value are partitioned into two clusters based on the sign of the corresponding vector entry. Spectral Partitioning algorithm is repeatedly carried out until the desired numbers of partitions are obtained. SpecP visualizes the spectrally partitioned clusters of protein structure along with the Protein Contact Map and Protein Contact Graph which can be saved for later use. It also possesses an interactive mode whereby the user has the ability to zoom, pan, resize and save these raster images in various image formats (.eps, .jpg, .png) manually. SpecP is a stand-alone extensible tool useful for structural analysis of proteins.
| S-EPMC3705632 | biostudies-literature
Project description:Musculoskeletal models represent a powerful tool to gain knowledge on the internal forces acting at the joint level in a non-invasive way. However, these models can present some errors associated with the level of detail in their geometrical representation. For this reason, a thorough validation is necessary to prove the reliability of their predictions. This study documents the development of a generic musculoskeletal model and proposes a working logic and simulation techniques for identifying specific model features in need of refinement; as well as providing a quantitative validation for the prediction of hip contact forces (HCF). The model, implemented in the AnyBody Modeling System and based on the cadaveric dataset TLEM 2.0, was scaled to match the anthropometry of a patient fitted with an instrumented hip implant and to reproduce gait kinematics based on motion capture data. The relative contribution of individual muscle elements to the HCF and joint moments was analyzed to identify critical geometries, which were then compared to muscle magnetic resonance imaging (MRI) scans and, in case of inconsistencies, were modified to better match the volumetric scans. The predicted HCF showed good agreement with the overall trend and timing of the measured HCF from the instrumented prosthesis. The average root mean square error (RMSE), calculated for the total HCF was found to be 0.298*BW. Refining the geometries of the muscles thus identified reduced RMSE on HCF magnitudes by 17% (from 0.359*BW to 0.298*BW) over the whole gait cycle. The detailed study of individual muscle contributions to the HCF succeeded in identifying muscles with incorrect anatomy, which would have been difficult to intuitively identify otherwise. Despite a certain residual over-prediction of the final hip contact forces in the stance phase, a satisfactory level of geometrical accuracy of muscle paths has been achieved with the refinement of this model.
| S-EPMC6141086 | biostudies-literature
Project description:Protein-protein interactions (PPIs) are essential for most biological processes. However, current PPI networks present high levels of noise, sparseness and incompleteness, which limits our ability to understand the cell at the system level from the PPI network. Predicting novel (missing) links in noisy PPI networks is an essential computational method for automatically expanding the human interactome and for identifying biologically legitimate but undetected interactions for experimental determination of PPIs, which is both expensive and time-consuming. Recently, graph convolutional networks (GCN) have shown their effectiveness in modeling graph-structured data, which employ a 1-hop neighborhood aggregation procedure and have emerged as a powerful architecture for node or graph representations. In this paper, we propose a novel node (protein) embedding method by combining GCN and PageRank as the latter can significantly improve the GCN's aggregation scheme, which has difficulty in extending and exploring topological information of networks across higher-order neighborhoods of each node. Building on this novel node embedding model, we develop a higher-order GCN variational auto-encoder (HO-VGAE) architecture, which can learn a joint node representation of higher-order local and global PPI network topology for novel protein interaction prediction. It is worth noting that our method is based exclusively on network topology, with no protein attributes or extra biological features used. Extensive computational validations on PPI prediction task demonstrate our method without leveraging any additional biological information shows competitive performance-outperforms all existing graph embedding-based link prediction methods in both accuracy and robustness.
| S-EPMC7514053 | 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:MotivationPrediction of protein-protein interaction has become an important part of systems biology in reverse engineering the biological networks for better understanding the molecular biology of the cell. Although significant progress has been made in terms of prediction accuracy, most computational methods only predict whether two proteins interact but not their interacting residues-the information that can be very valuable for understanding the interaction mechanisms and designing modulation of the interaction. In this work, we developed a computational method to predict the interacting residue pairs-contact matrix for interacting protein domains, whose rows and columns correspond to the residues in the two interacting domains respectively and whose values (1 or 0) indicate whether the corresponding residues (do or do not) interact.ResultsOur method is based on supervised learning using support vector machines. For each domain involved in a given domain-domain interaction (DDI), an interaction profile hidden Markov model (ipHMM) is first built for the domain family, and then each residue position for a member domain sequence is represented as a 20-dimension vector of Fisher scores, characterizing how similar it is as compared with the family profile at that position. Each element of the contact matrix for a sequence pair is now represented by a feature vector from concatenating the vectors of the two corresponding residues, and the task is to predict the element value (1 or 0) from the feature vector. A support vector machine is trained for a given DDI, using either a consensus contact matrix or contact matrices for individual sequence pairs, and is tested by leave-one-out cross validation. The performance averaged over a set of 115 DDIs collected from the 3 DID database shows significant improvement (sensitivity up to 85%, and specificity up to 85%), as compared with a multiple sequence alignment-based method (sensitivity 57%, and specificity 78%) previously reported in the literature.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC3624801 | biostudies-literature
Project description:MotivationOver 300 000 protein-protein interaction (PPI) pairs have been identified in the human proteome and targeting these is fast becoming the next frontier in drug design. Predicting PPI sites, however, is a challenging task that traditionally requires computationally expensive and time-consuming docking simulations. A major weakness of modern protein docking algorithms is the inability to account for protein flexibility, which ultimately leads to relatively poor results.ResultsHere, we propose DockNet, an efficient Siamese graph-based neural network method which predicts contact residues between two interacting proteins. Unlike other methods that only utilize a protein's surface or treat the protein structure as a rigid body, DockNet incorporates the entire protein structure and places no limits on protein flexibility during an interaction. Predictions are modeled at the residue level, based on a diverse set of input node features including residue type, surface accessibility, residue depth, secondary structure, pharmacophore and torsional angles. DockNet is comparable to current state-of-the-art methods, achieving an area under the curve (AUC) value of up to 0.84 on an independent test set (DB5), can be applied to a variety of different protein structures and can be utilized in situations where accurate unbound protein structures cannot be obtained.Availability and implementationDockNet is available at https://github.com/npwilliams09/docknet and an easy-to-use webserver at https://biosig.lab.uq.edu.au/docknet. All other data underlying this article are available in the article and in its online supplementary material.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC9825772 | biostudies-literature