A Bayesian Framework for Combining Protein and Network Topology Information for Predicting Protein-Protein Interactions

Birlutiu, Adriana; d’Alché‐Buc, Florence; Heskes, Tom

doi:10.1109/tcbb.2014.2359441

Cited by 14 publications

(7 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Network alignment is the process of globally comparing two networks, identifying regions of similarity and to detect subnetworks that are conserved across species. Analyzing PPI networks, has been very effective in tackling many problems such as understanding the genetic factors that impact various diseases [5], drug discovery [6], predicting protein functions [7,8,9,10], identifying functional modules [11], and understanding the phylogeny from these data.…”

Section: Introductionmentioning

confidence: 99%

A Novel Computational Approach for Global Alignment for Multiple Biological Networks

Djeddi

Yahia

Nguifo

2018

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Due to the rapid progress of biological networks for modeling biological systems, a lot of biomolecular networks have been producing more and more protein-protein interaction (PPI) data. Analyzing protein-protein interaction (PPI) networks aims to find regions of topological and functional (dis)similarities between molecular networks of different species. The study of PPI networks has the potential to teach us as much about life process and diseases at the molecular level. Although few methods have been developed for multiple PPI network alignment and thus, new network alignment methods are of a compelling need. In this paper, we propose a novel algorithm for a global alignment of multiple protein-protein interaction (PPI) networks called MAPPIN. The latter relies on information available for the proteins in the networks, such as sequence, function and network topology. Our algorithm is perfectly designed to exploit current multi-core CPU architectures, and has been extensively tested on a real data (eight species). Our experimental results show that MAPPIN significantly outperforms NetCoffee in terms of coverage. Nevertheless, MAPPIN is handicapped by the time required to load the gene annotation file. An extensive comparison versus the pioneering PPI methods also show that MAPPIN is often efficient in terms of coverage, mean entropy or mean normalized.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Computational Approach for Global Alignment for Multiple Biological Networks

Djeddi

Yahia

Nguifo

2018

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

show abstract

“…For the final stage of classification, recent approaches like to use feed-forward neural network (FNN) or support vector machine (SVM), which are becoming popular in the fields of classification and detection [10]. However, SVM has the limitation that its hyperplanes should be parallel.…”

mentioning

confidence: 99%

Pathological Brain Detection by a Novel Image Feature—Fractional Fourier Entropy

Wang

Zhang

Yang

et al. 2015

Entropy

View full text Add to dashboard Cite

Aim: To detect pathological brain conditions early is a core procedure for patients so as to have enough time for treatment. Traditional manual detection is either cumbersome, or expensive, or time-consuming. We aim to offer a system that can automatically identify pathological brain images in this paper. Method: We propose a novel image feature, viz., Fractional Fourier Entropy (FRFE), which is based on the combination of Fractional Fourier Transform (FRFT) and Shannon entropy. Afterwards, the Welch's t-test (WTT) and Mahalanobis distance (MD) were harnessed to select distinguishing features. Finally, we introduced an advanced classifier: twin support vector machine (TSVM). Results: A 10ˆK-fold stratified cross validation test showed that this proposed "FRFE + WTT + TSVM" yielded an accuracy of 100.00%, 100.00%, and 99.57% on datasets that contained 66, 160, and 255 brain images, respectively. Conclusions: The proposed "FRFE + WTT + TSVM" method is superior to 20 state-of-the-art methods.

show abstract

“…Birlutiu et al presented a Bayesian framework [50] that combines information related to proteins and the interactions between them along with information on the network topology. In this work the naïve Bayes classifier was used to express the likelihood of interaction based on the features for a given protein pair.…”

Section: Machine Learning Techniques For Structure-based Methodsmentioning

confidence: 99%

Data Science Research to Support Stem Cell Therapy for Muscular Dystrophy

Salas¹,

Nathaly²

View full text Add to dashboard Cite

This thesis project focused on using a sequence-based, high-performance computational tool to design synthetic proteins and is part of current collaborative research on Duchenne Muscular Dystrophy (DMD). A possible treatment for DMD consists of injecting patients with healthy muscle satellite cells grown in tissue culture. However, such cells cannot currently be produced in quantity because they convert to muscle cells (differentiate) prematurely. Using InSiPS, the In-Silico Protein Synthesizer, protein sequences were designed to interact with target proteins and inhibit the protein-protein interaction proposed to regulate the premature differentiation. The resulting sequences were predicted to interact with the target proteins with high specificity (99.98%). Complementary biochemistry experiments indicated interactions with the intended target for two out of ten synthetic proteins. These results are being studied as part of the ongoing research seeking to develop a treatment for DMD. I would like to acknowledge and give my sincerest appreciation to the person who made possible my participation in this research project, Dr. Frank Dehne. I will always be grateful for having such a recognized investigator as my thesis supervisor, who was always happy to help and give advice with his contagious passion for research that motivated me to improve myself. An enormous thank you to Dr. Andrew Schoenrock, for his infinite patience in helping me at every step of the project, and whose expertise and knowledge of PIPE and InSiPS were crucial for my progress. Also, a big thank to Daniel Burnside for kindly helping me to understand and to explain biochemistry concepts. I also thank Dr. Ashkan Golshani and everyone in the Carleton Bioinformatics group. I was very lucky to be among dedicated investigators who were always happy to provide ideas to improve the present work. Special thanks go to Dr. Alexandre Blais, who developed the initial research proposal, who designed the biochemical experimental validation and who led the group that performed it-all with great commitment and a high sense of collaboration. My infinite appreciation goes also to Carole Love, and all the hard-work she put into proofreading and helping me with suggestions that make me feel proud of my thesis writing. I want to express my deepest gratitude to the Mexican National Council for Science and Technology (CONACyT) for sponsoring my graduate studies on behalf of my country-México-and for helping me to pursue this major milestone in my life. I am very fortunate to have in my life a special colleague who happens to be my husband and love of my life. Thank you, Pablo for your unending support and for sharing with me this adventure.

show abstract

A Bayesian Framework for Combining Protein and Network Topology Information for Predicting Protein-Protein Interactions

Cited by 14 publications

References 62 publications

A Novel Computational Approach for Global Alignment for Multiple Biological Networks

A Novel Computational Approach for Global Alignment for Multiple Biological Networks

Pathological Brain Detection by a Novel Image Feature—Fractional Fourier Entropy

Data Science Research to Support Stem Cell Therapy for Muscular Dystrophy

Contact Info

Product

Resources

About