Classification Systems for Bacterial Protein-Protein Interaction Document Retrieval

2010 ◽  
Vol 1 (1) ◽  
pp. 34-44
Author(s):  
Hongfang Liu ◽  
Manabu Torii ◽  
Guixian Xu ◽  
Johannes Goll
Keyword(s):  
High Throughput ◽  
Protein Interaction ◽  
Document Retrieval ◽  
Classification Systems ◽  
Machine Learning Algorithms ◽  
Small Scale ◽  
Protein Protein Interaction ◽  
Manual Curation ◽  
Ppi Networks ◽  
Genomics And Proteomics

Protein-protein interaction (PPI) networks are essential to understand the fundamental processes governing cell biology. Recently, studying PPI networks becomes possible due to advances in experimental high-throughput genomics and proteomics technologies. Many interactions from such high-throughput studies and most interactions from small-scale studies are reported only in the scientific literature and thus are not accessible in a readily analyzable format. This has led to the birth of manual curation initiatives such as the International Molecular Exchange Consortium (IMEx). The manual curation of PPI knowledge can be accelerated by text mining systems to retrieve PPI-relevant articles (article retrieval) and extract PPI-relevant knowledge (information extraction). In this article, the authors focus on article retrieval and define the task as binary classification where PPI-relevant articles are positives and the others are negatives. In order to build such classifier, an annotated corpus is needed. It is very expensive to obtain an annotated corpus manually but a noisy and imbalanced annotated corpus can be obtained automatically, where a collection of positive documents can be retrieved from existing PPI knowledge bases and a large number of unlabeled documents (most of them are negatives) can be retrieved from PubMed. They compared the performance of several machine learning algorithms by varying the ratio of the number of positives to the number of unlabeled documents and the number of features used.

Classification Systems for Bacterial Protein-Protein Interaction Document Retrieval

2012 ◽  
pp. 33-43
Author(s):  
Hongfang Liu ◽  
Manabu Torii ◽  
Guixian Xu ◽  
Johannes Goll
Keyword(s):  
High Throughput ◽  
Protein Interaction ◽  
Cell Biology ◽  
Binary Classification ◽  
Document Retrieval ◽  
Knowledge Bases ◽  
Machine Learning Algorithms ◽  
Protein Protein Interaction ◽  
Manual Curation ◽  
Ppi Networks

Protein-protein interaction (PPI) networks are essential to understand the fundamental processes governing cell biology. Recently, studying PPI networks becomes possible due to advances in experimental high-throughput genomics and proteomics technologies. Many interactions from such high-throughput studies and most interactions from small-scale studies are reported only in the scientific literature and thus are not accessible in a readily analyzable format. This has led to the birth of manual curation initiatives such as the International Molecular Exchange Consortium (IMEx). The manual curation of PPI knowledge can be accelerated by text mining systems to retrieve PPI-relevant articles (article retrieval) and extract PPI-relevant knowledge (information extraction). In this article, the authors focus on article retrieval and define the task as binary classification where PPI-relevant articles are positives and the others are negatives. In order to build such classifier, an annotated corpus is needed. It is very expensive to obtain an annotated corpus manually but a noisy and imbalanced annotated corpus can be obtained automatically, where a collection of positive documents can be retrieved from existing PPI knowledge bases and a large number of unlabeled documents (most of them are negatives) can be retrieved from PubMed. They compared the performance of several machine learning algorithms by varying the ratio of the number of positives to the number of unlabeled documents and the number of features used.

scholarly journals Proteinarium: Multi-Sample Protein-Protein Interaction Analysis and Visualization Tool

2019 ◽  
Author(s):  
David Armanious ◽  
Jessica Schuster ◽  
George F. Tollefson ◽  
Anthony Agudelo ◽  
Andrew T. DeWan ◽  
...  
Keyword(s):  
High Throughput ◽  
Protein Interaction ◽  
Protein Interactions ◽  
High Throughput Screening ◽  
Interaction Analysis ◽  
Interaction Network ◽  
Visualization Tool ◽  
Sequencing Data ◽  
Protein Protein Interaction ◽  
Ppi Networks

AbstractBackgroundData analysis has become crucial in the post genomic era where the accumulation of genomic information is mounting exponentially. Analyzing protein-protein interactions in the context of the interactome is a powerful approach to understanding disease phenotypes.ResultsWe describe Proteinarium, a multi-sample protein-protein interaction network analysis and visualization tool. Proteinarium can be used to analyze data for samples with dichotomous phenotypes, multiple samples from a single phenotype or a single sample. Then, by similarity clustering, the network-based relations of samples are identified and clusters of related samples are presented as a dendrogram. Each branch of the dendrogram is built based on network similarities of the samples. The protein-protein interaction networks can be analyzed and visualized on any branch of the dendrogram. Proteinarium’s input can be derived from transcriptome analysis, whole exome sequencing data or any high-throughput screening approach. Its strength lies in use of gene lists for each sample as a distinct input which are further analyzed through protein interaction analyses. Proteinarium output includes the gene lists of visualized networks and PPI interaction files where users can analyze the network(s) on other platforms such as Cytoscape. In addition, since the dendrogram is written in Newick tree format, users can visualize it in other software platforms like Dendroscope, ITOL.ConclusionsProteinarium, through the analysis and visualization of PPI networks, allows researchers to make important observations on high throughput data for a variety of research questions. Proteinarium identifies significant clusters of patients based on their shared network similarity for the disease of interest and the associated genes. Proteinarium is a command-line tool written in Java with no external dependencies and it is freely available at https://github.com/Armanious/Proteinarium.

scholarly journals Development of a Novel High-Throughput Screen and Identification of Small-Molecule Inhibitors of the Gα–RGS17 Protein–Protein Interaction Using AlphaScreen

2011 ◽  
Vol 16 (8) ◽  
pp. 869-877 ◽  
Author(s):  
Duncan I. Mackie ◽  
David L. Roman
Keyword(s):  
Small Molecule ◽  
High Throughput ◽  
Protein Interaction ◽  
High Throughput Screening ◽  
Drug Targets ◽  
Screening Method ◽  
Fold Increase ◽  
Rgs Proteins ◽  
High Throughput Screen ◽  
Protein Protein Interaction

In this study, the authors used AlphaScreen technology to develop a high-throughput screening method for interrogating small-molecule libraries for inhibitors of the Gαo–RGS17 interaction. RGS17 is implicated in the growth, proliferation, metastasis, and the migration of prostate and lung cancers. RGS17 is upregulated in lung and prostate tumors up to a 13-fold increase over patient-matched normal tissues. Studies show RGS17 knockdown inhibits colony formation and decreases tumorigenesis in nude mice. The screen in this study uses a measurement of the Gαo–RGS17 protein–protein interaction, with an excellent Z score exceeding 0.73, a signal-to-noise ratio >70, and a screening time of 1100 compounds per hour. The authors screened the NCI Diversity Set II and determined 35 initial hits, of which 16 were confirmed after screening against controls. The 16 compounds exhibited IC50 <10 µM in dose–response experiments. Four exhibited IC50 values <6 µM while inhibiting the Gαo–RGS17 interaction >50% when compared to a biotinylated glutathione-S-transferase control. This report describes the first high-throughput screen for RGS17 inhibitors, as well as a novel paradigm adaptable to many other RGS proteins, which are emerging as attractive drug targets for modulating G-protein-coupled receptor signaling.

DISTANCE-WISE PATHWAY DISCOVERY FROM PROTEIN–PROTEIN INTERACTION NETWORKS WEIGHTED BY SEMANTIC SIMILARITY

2014 ◽  
Vol 12 (01) ◽  
pp. 1450004 ◽  
Author(s):  
SLAVKA JAROMERSKA ◽  
PETR PRAUS ◽  
YOUNG-RAE CHO
Keyword(s):  
Signaling Pathways ◽  
Semantic Similarity ◽  
Protein Interaction ◽  
Protein Pair ◽  
Semantic Analysis ◽  
Topological Analysis ◽  
Cellular Mechanisms ◽  
Semantic Similarity Measure ◽  
Protein Protein Interaction ◽  
Ppi Networks

Reconstruction of signaling pathways is crucial for understanding cellular mechanisms. A pathway is represented as a path of a signaling cascade involving a series of proteins to perform a particular function. Since a protein pair involved in signaling and response have a strong interaction, putative pathways can be detected from protein–protein interaction (PPI) networks. However, predicting directed pathways from the undirected genome-wide PPI networks has been challenging. We present a novel computational algorithm to efficiently predict signaling pathways from PPI networks given a starting protein and an ending protein. Our approach integrates topological analysis of PPI networks and semantic analysis of PPIs using Gene Ontology data. An advanced semantic similarity measure is used for weighting each interacting protein pair. Our distance-wise algorithm iteratively selects an adjacent protein from a PPI network to build a pathway based on a distance condition. On each iteration, the strength of a hypothetical path passing through a candidate edge is estimated by a local heuristic. We evaluate the performance by comparing the resultant paths to known signaling pathways on yeast. The results show that our approach has higher accuracy and efficiency than previous methods.

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.

scholarly journals PPInfer: a Bioconductor package for inferring functionally related proteins using protein interaction networks

F1000Research ◽  
2017 ◽  
Vol 6 ◽  
pp. 1969
Author(s):  
Dongmin Jung ◽  
Xijin Ge
Keyword(s):  
Protein Interaction ◽  
Protein Interaction Networks ◽  
Interaction Networks ◽  
Biological Processes ◽  
Bioconductor Package ◽  
Biological Functions ◽  
Ppi Network ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Related Proteins

Interactions between proteins occur in many, if not most, biological processes. This fact has motivated the development of a variety of experimental methods for the identification of protein-protein interaction (PPI) networks. Leveraging PPI data available STRING database, we use network-based statistical learning methods to infer the putative functions of proteins from the known functions of neighboring proteins on a PPI network. This package identifies such proteins often involved in the same or similar biological functions. The package is freely available at the Bioconductor web site (http://bioconductor.org/packages/PPInfer/).

scholarly journals PPInfer: a Bioconductor package for inferring functionally related proteins using protein interaction networks

F1000Research ◽  
2018 ◽  
Vol 6 ◽  
pp. 1969 ◽  
Author(s):  
Dongmin Jung ◽  
Xijin Ge
Keyword(s):  
Protein Interaction ◽  
Protein Interaction Networks ◽  
Interaction Networks ◽  
Biological Processes ◽  
Bioconductor Package ◽  
Biological Functions ◽  
Ppi Network ◽  
Protein Protein Interaction ◽  
Ppi Networks ◽  
Related Proteins

Interactions between proteins occur in many, if not most, biological processes. This fact has motivated the development of a variety of experimental methods for the identification of protein-protein interaction (PPI) networks. Leveraging PPI data available in the STRING database, we use a network-based statistical learning methods to infer the putative functions of proteins from the known functions of neighboring proteins on a PPI network. This package identifies such proteins often involved in the same or similar biological functions. The package is freely available at the Bioconductor web site (http://bioconductor.org/packages/PPInfer/).

Sign in / Sign up

Export Citation Format

Share Document