Decision Tree Based Approaches for Detecting Protein Complex in Protein Protein Interaction Network (PPI) via Link and Sequence Analysis

Sikandar, Aisha; Bajwa, Usama Ijaz; Wang, Xuan; Sikandar, Misba; Yao, Lin; Jiang, Zoe L.; Zhang, Chunkai

doi:10.1109/access.2018.2807811

Cited by 31 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We treat the protein complex as an undirected graph and compute different topological properties as a feature set. The computed topological features for the classification of protein complexes are i) average shortest path length, ii) topological coefficient, iii) neighborhood connectivity, iv) clustering coefficient, v) degree, vi) eccentricity, vii) closeness centrality, viii) radiality, ix) stress, and x) betweenness centrality [28].…”

Section: A Topological Featuresmentioning

confidence: 99%

“…These features are computed because the mutation in an amino acid sequence may lead to a certain disease and genes causing a certain disease may have similar amino acid sequence structures. This feature set consists of discrete wavelet features in addition to length and entropy, which are used in [28]. Each of these features is described in the following subsections.…”

Section: B Biological Featuresmentioning

confidence: 99%

“…It does not require global optimization due to which its time complexity is reduced and the performance becomes efficient [34]. Moreover, it is evident from the literature [11], [28] that tree based approaches are gaining popularity for making predictions. Thus, if PART-a hybrid approach that induces a rule set on the basis of decision tree, is used, it may lead to better prediction results.…”

Section: A: Partmentioning

confidence: 99%

See 2 more Smart Citations

IoMT-Based Association Rule Mining for the Prediction of Human Protein Complexes

et al. 2020

Self Cite

View full text Add to dashboard Cite

The inspiring increase in the Internet-enabling devices has influenced health industry due to the nature of these devices where they offer health related information swiftly. One of the prominent characteristics of these devices is to provide physicians with effective diagnosis of sensitive diseases. Internet of Medical Things (IoMT) is a means of connecting medical devices to computing nodes with the help of Internet for affording real-time communications between patients and clinicians to understand the interaction of human protein complexes. A secure and correct protein complex prediction plays an important job in perceiving the principal method of various cellular determinations and to elucidate the functionality of different un-annotated proteins. Different experimental schemes have been evolved to accomplish this task, however, these schemes have high error rates and are not efficient in terms of time, cost, privacy, and security. To tackle these limitations, numerous computational models have been developed that consider a protein complex as a dense sub-graph and utilize some basic topological properties such as density and degree statistics as a feature set for protein complex prediction. Different kinds of sub-graph structures, e.g., ring, star, linear, and hybrid have also been found in Protein-Protein Interaction Network (PPIN), therefore, more advance topological properties may be helpful to predict these structures. Moreover, the amino acid sequence of protein determines its formation, thus, the sequence information is important for predicting the interacting property among proteins in a secure way. In this study, we have computed basic as well as advance topological features by considering the interaction network of human protein complexes in the IoMT environment. In addition, biological features, i.e., discrete wavelet coefficients, length, and entropy from amino acid sequences of proteins have been computed. The supervised learning method based on association rules such as Partial Tree (PART) and Non-Nested Generalized Exemplars (NNGE) are trained to identify human protein complexes on the basis of integrated topological and biological properties. The 10-fold cross validation is exercised to measure the proposed methods. Experimental results show that association rule learners with integrated features outperform other complex mining algorithms, i.e., probabilistic Bayesian Network (BN), and Random Forest, in terms of accuracy and efficiency in addition to provide privacy.

show abstract

Section: A Topological Featuresmentioning

confidence: 99%

Section: B Biological Featuresmentioning

confidence: 99%

Section: A: Partmentioning

confidence: 99%

See 1 more Smart Citation

IoMT-Based Association Rule Mining for the Prediction of Human Protein Complexes

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Decision trees are potentially strong predictors and provide a clear concept description for a dataset. Decision tree learners are popular because they are fast and they produce models that perform well with a variety of features [22,23]. The root node, which is the first node of the tree, starts to ask questions for the estimation of the data and the structure of the tree, and this process continues until nodes or leaves without branches are found [24].…”

Section: Alternating Decision Treementioning

confidence: 99%

Prediction of Viscosity Values of Nanofluids at Different pH Values by Alternating Decision Tree and Multilayer Perceptron Methods

Demirpolat

Daş

2019

Applied Sciences

View full text Add to dashboard Cite

Due to the poor thermal properties of conventional thermal fluids such as water, oil and ethylene glycol, small solid particles are added to these fluids to enhance heat transfer. Since the viscosity change determines the rheological behavior of a liquid, it is very important to examine the parameters affecting the viscosity. Since the experimental viscosity measurement is expensive and time-consuming, it is more practical to estimate this parameter. In this study, CuO (copper oxide) nanoparticles were produced and then Scanning Electron Microscope (SEM) images analyses of the produced particles were made. Nanofluids were obtained by using pure water, ethanol and ethylene glycol materials together with the produced nanoparticles and the viscosity values were calculated by experimental setups at different density and temperatures. For the viscosity values of nanofluids, predictive models were created by using different computational intelligence methods. Mean square error (MSE), root mean square error (RMSE) and mean absolute percentage error (MAPE) error analyses were used to determine the accuracy of the predictive models. The multilayer perceptron method, which has the least error value in computational methods, was chosen as the best predicting method. The multilayer perceptron method, with an average accuracy of 51%, performed better than the alternating decision tree method. As a result, the viscosity increased with the increase in the pH of the nanofluids produced by adding CuO nanoparticles and decreased with the increase in the temperature of the nanofluids. The importance of this study is to create a predictive model using computational intelligence methods for viscosity values calculated with different pH values.

show abstract

“…The protein-protein interaction (PPI) network is a common technique to analyze the mechanism of traditional Chinese medicine and disease from the molecular level 18 . The functional modules in the protein-interaction network are composed of interacting proteins, which together participate in specific biological processes 19 . Therefore, analyzing the functional modules in the network is of great significance for studying the mechanism of HQ treatment of laryngeal cancer.…”

mentioning

confidence: 99%

Mechanism of Astragalus membranaceus in the treatment of laryngeal cancer based on gene co-expression network and molecular docking

Dong

Huo

Sun

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Astragalus membranaceus (HUANG QI, HQ) is a kind of traditional Chinese medicine. Researchers have widely concerned its antitumor effect. At present, there is still a lack of research on the treatment of laryngeal cancer with HQ. In this study, we integrated data from the weighted gene co-expression network of laryngeal cancer samples and the components and targets of HQ. A new method for dividing PPI network modules is proposed. Important targets of HQ treatment for laryngeal cancer were obtained through the screening of critical modules. These nodes performed differential expression analysis and survival analysis through external data sets. GSEA enrichment analysis reveals pathways for important targets participation. Finally, molecular docking screened active ingredients in HQ that could interact with important targets. Combined with the laryngeal cancer gene co expression network and HQ PPI network, we obtained the critical module related to laryngeal cancer. Among them, MMP1, MMP3, and MMP10 were chosen as important targets. External data sets demonstrate that their expression in tumor samples is significantly higher than in normal samples. The survival time of patients with high expression group was significantly shortened, which is a negative factor for prognosis. GSEA enrichment analysis found that they are mainly involved in tumor-related pathways such as ECM receptor interaction and Small cell lung cancer. The docking results show that the components that can well bind to important targets of HQ are quercetin, rutin, and Chlorogenic acid, which may be the primary mechanism of the anti-cancer effect of HQ. These findings provide a preliminary research basis for Chinese medicine treatment of laryngeal cancer and offer ideas to related drug design. Laryngeal cancer is one of the common malignant tumors of the head and neck, most of which are squamous cell carcinoma 1. It ranks second in the incidence of head and neck cancer (HNSC). The affected population is mainly middle-aged and older men over 40 years old, with a slight trend of youth 2. The occurrence and development of laryngeal cancer are related to many factors, including smoking, drinking, HPV infection, radiation, low intake of vegetables and fruits, insufficient trace elements, and disorders of sex hormone metabolism 3-5. In the early stage of laryngeal cancer, laser treatment has less damage and less postoperative complications 6. For most patients with laryngeal cancer, open surgery is still the main treatment. Radiotherapy and chemotherapy were used as auxiliary means 7. Targeted treatment of tumor can increase drug sensitivity, improve curative effect and reduce side effects 8. However, not all patients can benefit from it 9. Clearing tumors, preserving function, controlling recurrence, and improving quality of life are the goals of treating laryngeal cancer 5 .

show abstract

Decision Tree Based Approaches for Detecting Protein Complex in Protein Protein Interaction Network (PPI) via Link and Sequence Analysis

Cited by 31 publications

References 19 publications

IoMT-Based Association Rule Mining for the Prediction of Human Protein Complexes

IoMT-Based Association Rule Mining for the Prediction of Human Protein Complexes

Prediction of Viscosity Values of Nanofluids at Different pH Values by Alternating Decision Tree and Multilayer Perceptron Methods

Mechanism of Astragalus membranaceus in the treatment of laryngeal cancer based on gene co-expression network and molecular docking

Contact Info

Product

Resources

About