PEPRF: Identification of Essential Proteins by Integrating Topological Features of PPI Network and Sequence-based Features via Random Forest

2021 ◽  
Vol 16 ◽  
Author(s):  
Chuanyan Wu ◽  
Bentao Lin ◽  
Kai Shi ◽  
Qingju Zhang ◽  
Rui Gao ◽  
...  
Keyword(s):  
Random Forest ◽  
Feature Selection Method ◽  
Selection Method ◽  
Ppi Network ◽  
Efficient Tool ◽  
Essential Proteins ◽  
Protein Protein Interaction ◽  
Topological Features ◽  
Sequence Graph ◽  
Experimental Approaches

Background: Essential proteins play an important role in the process of life, which can be identified by experimental methods and computational approaches. Experimental approaches to identify essential proteins are of high accuracy but with the limitation of time and resource-consuming. Objective: Herein, we present a computational model (PEPRF) to identify essential proteins based on machine learning. Methods: Different features of proteins were extracted. Topological features of Protein-Protein Interaction (PPI) network-based were extracted. Based on the protein sequence, graph theory-based features, information-based features, composition, and physiochemical features, etc., were extracted. Finally, 282 features were constructed. In order to select the features that contributed most to the identification, the ReliefF-based feature selection method was adopted to measure the weights of these features. As a result, 212 features were curated to train random forest classifiers. Finally, PEPRF obtained an AUC of 0.71 and an accuracy of 0.742. Conclusion: Our results show that PEPRF may be applied as an efficient tool to identify essential proteins.

scholarly journals A Non-negative Matrix Factorization Based Method for Identifying Essential Proteins

2021 ◽  
Author(s):  
Zhihong Zhang ◽  
Sai Hu ◽  
Wei Yan ◽  
Bihai Zhao ◽  
Lei Wang
Keyword(s):  
Protein Interaction ◽  
Matrix Factorization ◽  
Biological Data ◽  
Protein Domain ◽  
Biological Information ◽  
Ppi Network ◽  
Essential Proteins ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Non Negative Matrix Factorization

Abstract BackgroundIdentification of essential proteins is very important for understanding the basic requirements to sustain a living organism. In recent years, various different computational methods have been proposed to identify essential proteins based on protein-protein interaction (PPI) networks. However, there has been reliable evidence that a huge amount of false negatives and false positives exist in PPI data. Therefore, it is necessary to reduce the influence of false data on accuracy of essential proteins prediction by integrating multi-source biological information with PPI networks.ResultsIn this paper, we proposed a non-negative matrix factorization and multiple biological information based model (NDM) for identifying essential proteins. The first stage in this progress was to construct a weighted PPI network by combing the information of protein domain, protein complex and the topology characteristic of the original PPI network. Then, the non-negative matrix factorization technique was used to reconstruct an optimized PPI network with whole enough weight of edges. In the final stage, the ranking score of each protein was computed by the PageRank algorithm in which the initial scores were calculated with homologous and subcellular localization information. In order to verify the effectiveness of the NDM method, we compared the NDM with other state-of-the-art essential proteins prediction methods. The comparison of the results obtained from different methods indicated that our NDM model has better performance in predicting essential proteins.ConclusionEmploying the non-negative matrix factorization and integrating multi-source biological data can effectively improve quality of the PPI network, which resulted in the led to optimization of the performance essential proteins identification. This will also provide a new perspective for other prediction based on protein-protein interaction networks.

PREDICTION OF ESSENTIAL PROTEINS BASED ON EDGE CLUSTERING COEFFICIENT AND GENE ONTOLOGY INFORMATION

2014 ◽  
Vol 22 (03) ◽  
pp. 339-351 ◽  
Author(s):  
JIAWEI LUO ◽  
NAN ZHANG
Keyword(s):  
Gene Ontology ◽  
Network Topology ◽  
Clustering Coefficient ◽  
Ppi Network ◽  
Essential Proteins ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Survival And Development ◽  
Gene Ontology Information ◽  
Better Than

Essential proteins are important for the survival and development of organisms. Lots of centrality algorithms based on network topology have been proposed to detect essential proteins and achieve good results. However, most of them only focus on the network topology, but ignore the false positive (FP) interactions in protein–protein interaction (PPI) network. In this paper, gene ontology (GO) information is proposed to measure the reliability of the edges in PPI network and we propose a novel algorithm for identifying essential proteins, named EGC algorithm. EGC algorithm integrates topology character of PPI network and GO information. To validate the performance of EGC algorithm, we use EGC and other nine methods (DC, BC, CC, SC, EC, LAC, NC, PEC and CoEWC) to identify the essential proteins in the two different yeast PPI networks: DIP and MIPS. The results show that EGC is better than the other nine methods, which means adding GO information can help in predicting essential proteins.

scholarly journals Comparing protein-protein interaction networks of SARS-CoV-2 and (H1N1) influenza using topological features

2021 ◽  
Author(s):  
Hakimeh Khojasteh ◽  
Alireza Khanteymoori ◽  
Mohammad Hossein Olyaee
Keyword(s):  
Dimensionality Reduction ◽  
Power Law ◽  
Protein Interaction ◽  
Interaction Network ◽  
H1n1 Influenza ◽  
Centrality Measures ◽  
Essential Proteins ◽  
Protein Protein Interaction ◽  
Topological Features ◽  
High Level

Background: SARS-CoV-2 pandemic first emerged in late 2019 in China. It has since infected more than 183 million individuals and caused about 4 million deaths globally. A protein-protein interaction network (PPIN) and its analysis can provide insight into the behavior of cells and lead to advance the procedure of drug discovery. The identification of essential proteins is crucial to understand for cellular survival. There are many centrality measures to detect influential nodes in complex networks. Since SARS-CoV-2 and (H1N1) influenza PPINs pose 553 common proteins. Analyzing influential proteins and comparing these networks together can be an effective step helping biologists in drug design. Results: We used 21 centrality measures on SARS-CoV-2 and (H1N1) influenza PPINs to identify essential proteins. PCA-based dimensionality reduction was applied on normalized centrality values. Some measures demonstrated a high level of contribution in comparison to others in both PPINs, like Barycenter, Decay, Diffusion degree, Closeness (Freeman), Closeness (Latora), Lin, Radiality, and Residual. Using validation measures, the appropriate clustering method was chosen for centrality measures. We also investigated some graph theory-based properties like the power law, exponential distribution, and robustness. Conclusions: Through analysis and comparison, both networks exhibited remarkable experimental results. The network diameters were equal and in terms of heterogeneity, SARS-CoV-2 PPIN tends to be more heterogeneous. Both networks under study display a typical power-law degree distribution. Dimensionality reduction and unsupervised learning methods were so effective to reveal appropriate centrality measures.

MRF-RFS: A Modified Random Forest Recursive Feature Selection Algorithm for Nasopharyngeal Carcinoma Segmentation

2020 ◽  
Vol 59 (04/05) ◽  
pp. 151-161
Author(s):  
Yuchen Fei ◽  
Fengyu Zhang ◽  
Chen Zu ◽  
Mei Hong ◽  
Xingchen Peng ◽  
...  
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Nasopharyngeal Carcinoma ◽  
Soft Tissues ◽  
Feature Selection Method ◽  
Selection Method ◽  
Feature Subset ◽  
Selection Algorithm ◽  
Feature Selection Algorithm ◽  
Tumor Margins

Abstract Background An accurate and reproducible method to delineate tumor margins is of great importance in clinical diagnosis and treatment. In nasopharyngeal carcinoma (NPC), due to limitations such as high variability, low contrast, and discontinuous boundaries in presenting soft tissues, tumor margin can be extremely difficult to identify in magnetic resonance imaging (MRI), increasing the challenge of NPC segmentation task. Objectives The purpose of this work is to develop a semiautomatic algorithm for NPC image segmentation with minimal human intervention, while it is also capable of delineating tumor margins with high accuracy and reproducibility. Methods In this paper, we propose a novel feature selection algorithm for the identification of the margin of NPC image, named as modified random forest recursive feature selection (MRF-RFS). Specifically, to obtain a more discriminative feature subset for segmentation, a modified recursive feature selection method is applied to the original handcrafted feature set. Moreover, we combine the proposed feature selection method with the classical random forest (RF) in the training stage to take full advantage of its intrinsic property (i.e., feature importance measure). Results To evaluate the segmentation performance, we verify our method on the T1-weighted MRI images of 18 NPC patients. The experimental results demonstrate that the proposed MRF-RFS method outperforms the baseline methods and deep learning methods on the task of segmenting NPC images. Conclusion The proposed method could be effective in NPC diagnosis and useful for guiding radiation therapy.

scholarly journals TulsiPIN: an interologous protein interactome ofOcimum tenuiflorum

2019 ◽  
Author(s):  
Vikram Singh ◽  
Gagandeep Singh ◽  
Vikram Singh
Keyword(s):  
Small World ◽  
Ppi Network ◽  
Modular Architecture ◽  
High Confidence ◽  
Scale Free ◽  
Protein Protein Interaction ◽  
Topological Features ◽  
Ppi Networks ◽  
A Genome ◽  
Transcription Regulators

AbstractOcimum tenuiflorum, commonly known as holy basil or tulsi, is globally recognized for its multitude of medicinal properties. However, a comprehensive study revealing the complex interplay among its constituent proteins at subcellular level is still lacking. To bridge this gap, a genome scale interologous protein-protein interaction (PPI) network, TulsiPIN, is developed using 49 template plants. The reported network consists of 13, 660 nodes and 327, 409 binary interactions. A high confidence PPI network consisting of 7, 719 nodes having 95, 532 interactions was inferred using domain-domain interaction information along with interolog based statistics, and its reliability was further assessed using functional homogeneity and protein colocalization. 1, 625 vital proteins are predicted by statistically evaluating this high confidence TulsiPIN with two ensembles of corresponding random networks, each consisting of 10, 000 realizations of Erdős-Rényi and Barabási-Albert models. Topological features of TulsiPIN including small-world, scale-free and modular architecture are inspected and found to resemble with other plant PPI networks. Finally, numerous regulatory proteins like transcription factors, transcription regulators and protein kinases are profiled in TulsiPIN and a sub-network of proteins participating in 10 secondary metabolite biosynthetic pathways is studied. We believe, the methodology developed and insights imparted would be useful in understanding regulatory mechanisms in various plant species.

scholarly journals TEHRAN AIR POLLUTANTS PREDICTION BASED ON RANDOM FOREST FEATURE SELECTION METHOD

2017 ◽  
Vol XLII-4/W4 ◽  
pp. 483-488 ◽  
Author(s):  
A. Shamsoddini ◽  
M. R. Aboodi ◽  
J. Karami
Keyword(s):  
Neural Networks ◽  
Air Pollution ◽  
Feature Selection ◽  
Artificial Neural Networks ◽  
Random Forest ◽  
Sulfur Dioxide ◽  
Nitrogen Dioxide ◽  
Feature Selection Method ◽  
Selection Method ◽  
The Other

Air pollution as one of the most serious forms of environmental pollutions poses huge threat to human life. Air pollution leads to environmental instability, and has harmful and undesirable effects on the environment. Modern prediction methods of the pollutant concentration are able to improve decision making and provide appropriate solutions. This study examines the performance of the Random Forest feature selection in combination with multiple-linear regression and Multilayer Perceptron Artificial Neural Networks methods, in order to achieve an efficient model to estimate carbon monoxide and nitrogen dioxide, sulfur dioxide and PM2.5 contents in the air. The results indicated that Artificial Neural Networks fed by the attributes selected by Random Forest feature selection method performed more accurate than other models for the modeling of all pollutants. The estimation accuracy of sulfur dioxide emissions was lower than the other air contaminants whereas the nitrogen dioxide was predicted more accurate than the other pollutants.

scholarly journals Modify Random Forest Algorithm Using Hybrid Feature Selection Method

2018 ◽  
Vol 4 (2) ◽  
pp. 1-6
Author(s):  
Ahmed T. Sadiq‎ ◽  
Karrar Shareef Musawi
Keyword(s):  
Feature Selection ◽  
Random Forest ◽  
Gini Index ◽  
Feature Selection Method ◽  
Selection Method ◽  
Random Selection ◽  
Experimental Results ◽  
Random Forest Algorithm ◽  
Selection For

The Importance of Random Forrest(RF) is one of the most powerful ‎methods ‎of ‎machine learning in ‎Decision Tree.‎ The Proposed hybrid feature selection for Random Forest depend on ‎two ‎measure ‎‎Information Gain and Gini Index in varying percentages ‎based on ‎weight.‎ In this paper, we tend to ‎propose a modify Random Forrest‏ ‏‎algorithm named ‎Random Forest algorithm using hybrid ‎feature ‎‎selection ‎that uses hybrid feature ‎selection instead of ‎using ‎one feature selection. The ‎main plan is to ‎computation the ‎‎ Information ‎Gain for all random selection ‎feature then search for ‎the best split ‎‎point in ‎the node that gives the best ‎value for a hybrid ‎equation with ‎Gini Index. ‎The experimental results on the ‎dataset ‎showed that the proposed ‎modification is ‎better than the classic Random ‎Forest compared to ‎the standard static Random ‎Forest the hybrid feature ‎‎selection Random Forrest shows significant ‎improvement ‎in accuracy measure.‎

Sign in / Sign up

Export Citation Format

Share Document