An Automated Model for Target Protein prediction in PPI

2020 ◽  
Vol 15 ◽  
Author(s):  
G. Naveen Sundar ◽  
D. Narmadha
Keyword(s):  
Protein Identification ◽  
Research Work ◽  
Target Protein ◽  
Centrality Measures ◽  
Essential Proteins ◽  
Machine Learning Model ◽  
Computer Based ◽  
Living Organisms ◽  
Protein Essentiality ◽  
Sensitivity Specificity

Background: Essential proteins play a crucial role in most of the living organisms. The computer-based task of predicting essential proteins is important for target protein identification, disease treatment and suitable drug development. Objective: Traditionally many experimental and centrality measures have been proposed by researchers to predict protein essentiality. Methods: The prediction accuracy, sensitivity, specificity identified by the traditional methods is very low. Results and Discussion: In this research work, a novel computational based approach such NC-KNN model has been proposed to identify the most essential proteins. The proposed work uses a combination of network topology measure and machine learning model to predict the essential proteins. Conclusion: The proposed work shows a remarkable improvement than seven traditional centrality based measures such as DC, BC, CC, EC, NC, ECC and SC in terms of the metrics such as accuracy(A1), precision(P1), recall(R1), sensitivity(SE) and specificity(SP).

Identification of Essential Proteins by Detecting Topological and Functional Clusters in Protein Interaction Network of Saccharomyces Cerevisiae

2019 ◽  
Vol 8 (1) ◽  
pp. 31-51
Author(s):  
Kaustav Sengupta ◽  
Sovan Saha ◽  
Piyali Chatterjee ◽  
Mahantapas Kundu ◽  
Mita Nasipuri ◽  
...  
Keyword(s):  
Saccharomyces Cerevisiae ◽  
Functional Annotation ◽  
Drug Targets ◽  
Protein Identification ◽  
State Of The Art ◽  
Interaction Network ◽  
Centrality Measures ◽  
Essential Proteins ◽  
Go Terms ◽  
Hub Proteins

Essential protein identification is an important factor to inspect the mechanisms of disease progression and to identify drug targets. With the advancement of high throughput genome sequencing projects, a bulk of protein data is available where the analysis of interaction pattern, functional annotation and characterization are necessary for detecting proteins' essentiality in network level. A set of centrality measure has been used to identify the highly connected proteins or hubs. From recent studies, it is observed that the majority of hubs are considered to be essential proteins. In this article, a method EPIN_Pred is proposed where a combination of several centrality measures is used to find the hub and non-hub proteins. Using the cohesiveness property, overlapping topological clusters are found. Using gene ontology (GO) terms, these topological clusters are again combined, if required. The performance of EPIN_Pred is also found to be superior when compared to other state-of-the-art methods.

IDENTIFICATION OF ESSENTIAL PROTEINS FROM WEIGHTED PROTEIN–PROTEIN INTERACTION NETWORKS

2013 ◽  
Vol 11 (03) ◽  
pp. 1341002 ◽  
Author(s):  
MIN LI ◽  
JIAN-XIN WANG ◽  
HUAN WANG ◽  
YI PAN
Keyword(s):  
Protein Interaction ◽  
Network Topology ◽  
Protein Interactions ◽  
Interaction Network ◽  
False Positives ◽  
Centrality Measures ◽  
Protein Protein Interactions ◽  
Weighting Method ◽  
Essential Proteins ◽  
Protein Essentiality

Identifying essential proteins is very important for understanding the minimal requirements of cellular survival and development. Fast growth in the amount of available protein–protein interactions has produced unprecedented opportunities for detecting protein essentiality on network level. A series of centrality measures have been proposed to discover essential proteins based on network topology. Unfortunately, the protein–protein interactions produced by high-throughput experiments generally have high false positives. Moreover, most of centrality measures based on network topology are sensitive to false positives. We therefore propose a new method for evaluating the confidence of each interaction based on the combination of logistic regression-based model and function similarity. Nine standard centrality measures in weighted network were redefined in this paper. The experimental results on a yeast protein interaction network shows that the weighting method improved the performance of centrality measures considerably. More essential proteins were discovered by the weighted centrality measures than by the original centrality measures used in the unweighted network. Even about 20% improvements were obtained from closeness centrality and subgraph centrality.

A Computer-based Clinical Information System

1987 ◽  
Vol 26 (04) ◽  
pp. 189-194
Author(s):  
S. S. El-Gamal
Keyword(s):  
Information System ◽  
Hospital Information System ◽  
Clinical Information System ◽  
Research Work ◽  
Clinical Information ◽  
Hospital Staff ◽  
Vital Role ◽  
Daily Routine ◽  
Specialized Hospital ◽  
Computer Based

SummaryModern information technology offers new opportunities for the storage and manipulation of hospital information. A computer-based hospital information system, dedicated to urology and nephrology, was designed and developed in our center. It involves in principle the employment of a program that allows the analysis of non-restricted, non-codified texts for the retrieval and processing of clinical data and its operation by non-computer-specialized hospital staff.This Hospital Information System now plays a vital role in the efficient provision of a good quality service and is used in daily routine and research work in this hospital. This paper describes this specialized Hospital Information System.

scholarly journals An Effective Statistical Integrative Algorithm (Aeiapp) for Protein Prediction

2019 ◽  
Vol 8 (11) ◽  
pp. 132-137 ◽  
Keyword(s):  
Protein Interaction ◽  
Biological Networks ◽  
Protein Interaction Network ◽  
Protein Identification ◽  
Research Work ◽  
Interaction Network ◽  
Integrative Approach ◽  
Target Proteins ◽  
Protein Protein Interaction ◽  
Protein Protein Interaction Network

The task of predicting target proteins for new drug discovery is typically difficult. Target proteins are biologically most important to control a keen functional process. The recent research of experimental and computational -based approaches has been widely used to predict target proteins using biological networks analysis techniques. Perhaps with available methods and statistical algorithm needs to be modified and should be clearer to tag the main target. Meanwhile identifying wrong protein leads to unwanted molecular interaction and pharmacological activity. In this research work, a novel method to identify essential target proteins using integrative graph coloring algorithm has been proposed. The proposed integrative approach helps to extract essential proteins in protein-protein interaction network (PPI) by analyzing neighborhood of the active target protein. Experimental results reviewed based on protein-protein interaction network for homosapiens showed that AEIAPP based approach shows an improvement in the essential protein identification by assuming the source protein as biologically proven protein. The AEIAPP statistical model has been compared with other state of art approaches on human PPI for various diseases to produce good accurate outcome in faster manner with little memory consumption.

scholarly journals Automated Retraining of Machine Learning Models

2019 ◽  
Vol 8 (12) ◽  
pp. 445-452
Keyword(s):  
Machine Learning ◽  
Input Data ◽  
Research Work ◽  
Learning Models ◽  
Machine Learning Methods ◽  
Machine Learning Model ◽  
Crucial Component ◽  
Conventional Machine ◽  
Over Time ◽  
Machine Learning Models

Data is the most crucial component of a successful ML system. Once a machine learning model is developed, it gets obsolete over time due to presence of new input data being generated every second. In order to keep our predictions accurate we need to find a way to keep our models up to date. Our research work involves finding a mechanism which can retrain the model with new data automatically. This research also involves exploring the possibilities of automating machine learning processes. We started this project by training and testing our model using conventional machine learning methods. The outcome was then compared with the outcome of those experiments conducted using the AutoML methods like TPOT. This helped us in finding an efficient technique to retrain our models. These techniques can be used in areas where people do not deal with the actual working of a ML model but only require the outputs of ML processes

Identification of Important Proteins in Protein Interaction Network Based on SVM

2014 ◽  
Vol 644-650 ◽  
pp. 5202-5206
Author(s):  
Yan Li Zha ◽  
Wan Cheng Luo
Keyword(s):  
Protein Interaction ◽  
Interaction Network ◽  
Biological Information ◽  
Yeast Protein ◽  
Essential Proteins ◽  
Svm Model ◽  
Network Topologies ◽  
Living Organisms ◽  
Yeast Protein Interaction ◽  
Relevant Experiment

Importance of proteins are different to perform functions of cells in living organisms according to the relevant experiment results, and more essential proteins is the most important kind of proteins. There are recently many computational approaches proposed to predict essential proteins in network level through network topologies combined with biological information of proteins. However it is still hard to identify them because of limitations of topological centralities and bioinformatic sources. And more it is the challenge is to perform better with less resources. Therefore in this paper, we first examine the correlation between common topological centralities and essential proteins and choose a few particular centralities, and then to build a SVM model, names as TC-SVM, for predicting the essential proteins. The new method has been applied to a yeast protein interaction networks, which are obtained from the BioGRID database. The ten folds experimental results show that the performance of predicting essential proteins by TC-SVM is excellent.

scholarly journals Multiple Stressor Effects of Radon and Phthalates in Children: Background Information and Future Research

2020 ◽  
Vol 17 (8) ◽  
pp. 2898
Author(s):  
W. S. Kwan ◽  
D. Nikezic ◽  
Vellaisamy A. L. Roy ◽  
K. N. Yu
Keyword(s):  
Pediatric Population ◽  
Research Work ◽  
Consumer Products ◽  
Background Information ◽  
Future Research ◽  
Future Directions ◽  
Lung Cancers ◽  
Multiple Stressor ◽  
Biological Studies ◽  
Living Organisms

The present paper reviews available background information for studying multiple stressor effects of radon (222Rn) and phthalates in children and provides insights on future directions. In realistic situations, living organisms are collectively subjected to many environmental stressors, with the resultant effects being referred to as multiple stressor effects. Radon is a naturally occurring radioactive gas that can lead to lung cancers. On the other hand, phthalates are semi-volatile organic compounds widely applied as plasticizers to provide flexibility to plastic in consumer products. Links of phthalates to various health effects have been reported, including allergy and asthma. In the present review, the focus on indoor contaminants was due to their higher concentrations and to the higher indoor occupancy factor, while the focus on the pediatric population was due to their inherent sensitivity and their spending more time close to the floor. Two main future directions in studying multiple stressor effects of radon and phthalates in children were proposed. The first one was on computational modeling and micro-dosimetric studies, and the second one was on biological studies. In particular, dose-response relationship and effect-specific models for combined exposures to radon and phthalates would be necessary. The ideas and methodology behind such proposed research work are also applicable to studies on multiple stressor effects of collective exposures to other significant airborne contaminants, and to population groups other than children.

Assessment in a Computer-Based Nursing Documentation

2009 ◽  
pp. 16-25
Author(s):  
Elfriede Fritz ◽  
Daniela Deufert ◽  
Johannes Hilbe
Keyword(s):  
Quality Criteria ◽  
Assessment Instruments ◽  
Nursing Documentation ◽  
Nursing Assessment ◽  
Documentation Quality ◽  
Needs For Care ◽  
Nursing Diagnosis ◽  
Process Documentation ◽  
Computer Based ◽  
Sensitivity Specificity

Experience in nursing practice shows that, in Austria, there are still problems with assessment in computer-based nursing documentation. Nursing documentation includes the various steps of the nursingprocess and the nursing diagnosis. In addition, an assessment instrument, which captures the needs for care, must also be integrated into it. This chapter describes different Nursing Assessment Instruments and the advantages of Computer-Based Nursing Process Documentation. Quality criteria for assessment instruments are validity, sensitivity, specificity, reliability, practicability, and the appropriateness of the instrument. Quality criteria for computer-based systems are basically software ergonomic aspects, which are not part of this study. Each country should choose for itself those specific assessment instruments that capture the needs for care of their clients. These data enable comparison of facilities and reliable cost estimates in connection with nursing.

Sign in / Sign up

Export Citation Format

Share Document