Discovering cancer genes by integrating network and functional properties

Li, Li; Zhang, Kangyu; Lee, James; Cordes, Shaun; Davis, Donald M.; Tang, Zhijun

doi:10.1186/1755-8794-2-61

Cited by 39 publications

(40 citation statements)

References 43 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, using machine learning methods, a model is learned that links some of these features to disease-relatedness. In the context of predicting involvement in cancer, examples of feature-based methods include Milenkovic et al [24], Furney et al [25] and Li et al [26]. Milenkovic et al [24] characterize a protein using a "signature vector" that describes the local network structure around the node in terms of so-called graphlets, small fixed graph structures in which the node occurs.…”

Section: Introductionmentioning

confidence: 99%

“…Furney et al [25] use the Gene Ontology annotations of a protein as features, as well as a number of other properties; they use a chi-square-based selection criterion to select the likely most relevant features, then apply Naive Bayes. Li et al [26] compare three classifiers: SVM, Naive Bayes and logistic regression and they find that the SVM classifier on average performed slightly better than the Naive Bayes and logistic regression methods, and that among SVMs using different types of features individually, including GO annotations as features gives the best performance, while sequence and conservation features have relatively weak predictive power.…”

Section: Introductionmentioning

confidence: 99%

“…It is not our goal to compare different machine learning algorithms; we restrict ourselves to the Naive Bayes classifier. The performance of the method might be optimized by using another learning method, but we expect the difference to be small (see also Li et al [26]). Our main claim lies in the usefulness of the new features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Genes Involved in Human Cancer Using Network Contextual Information

Rahmani

Blockeel

Bender

2012

Journal of Integrative Bioinformatics

View full text Add to dashboard Cite

SummaryProtein-Protein Interaction (PPI) networks have been widely used for the task of predicting proteins involved in cancer. Previous research has shown that functional information about the protein for which a prediction is made, proximity to specific other proteins in the PPI network, as well as local network structure are informative features in this respect. In this work, we introduce two new types of input features, reflecting additional information: (1) Functional Context: the functions of proteins interacting with the target protein (rather than the protein itself); and (2) Structural Context: the relative position of the target protein with respect to specific other proteins selected according to a novel ANOVA (analysis of variance) based measure. We also introduce a selection strategy to pinpoint the most informative features. Results show that the proposed feature types and feature selection strategy yield informative features. A standard machine learning method (Naive Bayes) that uses the features proposed here outperforms the current state-of-the-art methods by more than 5% with respect to F-measure. In addition, manual inspection confirms the biological relevance of the top-ranked features.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Genes Involved in Human Cancer Using Network Contextual Information

Rahmani

Blockeel

Bender

2012

Journal of Integrative Bioinformatics

View full text Add to dashboard Cite

show abstract

“…For example, Furney et al [6] identified some common structural, functional and evolutionary properties of cancer genes and then used these properties to predict novel cancer genes. Ostlund et al [7] proposed a network searching method, MaxLink, to find candidate cancer gene based on their connectivity to known cancer genes, and Li et al [8] integrated network and functional properties to identify cancer genes.…”

mentioning

confidence: 99%

“…Alternatively, with the availability of genome-wide sequences, and genomics and proteomics data, bioinformatics methods have been applied to identify potential cancer genes, significantly reducing the number of candidate genes for further testing [5]. Bioinformatics methods based either on gene annotation and sequence features or on network analysis have provided powerful tools to accelerate cancer gene discovery [6][7][8][9][10]. For example, Furney et al [6] identified some common structural, functional and evolutionary properties of cancer genes and then used these properties to predict novel cancer genes.…”

mentioning

confidence: 99%

Predicting potential cancer genes by integrating network properties, sequence features and functional annotations

Liu

Xie

2013

Sci. China Life Sci.

View full text Add to dashboard Cite

The discovery of novel cancer genes is one of the main goals in cancer research. Bioinformatics methods can be used to accelerate cancer gene discovery, which may help in the understanding of cancer and the development of drug targets. In this paper, we describe a classifier to predict potential cancer genes that we have developed by integrating multiple biological evidence, including protein-protein interaction network properties, and sequence and functional features. We detected 55 features that were significantly different between cancer genes and non-cancer genes. Fourteen cancer-associated features were chosen to train the classifier. Four machine learning methods, logistic regression, support vector machines (SVMs), BayesNet and decision tree, were explored in the classifier models to distinguish cancer genes from non-cancer genes. The prediction power of the different models was evaluated by 5-fold cross-validation. The area under the receiver operating characteristic curve for logistic regression, SVM, Baysnet and J48 tree models was 0.834, 0.740, 0.800 and 0.782, respectively. Finally, the logistic regression classifier with multiple biological features was applied to the genes in the Entrez database, and 1976 cancer gene candidates were identified. We found that the integrated prediction model performed much better than the models based on the individual biological evidence, and the network and functional features had stronger powers than the sequence features in predicting cancer genes.cancer gene, logistic regression, network property, sequence feature, functional annotation

show abstract

Network‐ and attribute‐based classifiers can prioritize genes and pathways for autism spectrum disorders and intellectual disability

Kou

Betancur²,

Xu³

et al. 2012

American J of Med Genetics Pt C

View full text Add to dashboard Cite

Autism spectrum disorders (ASD) are a group of related neurodevelopmental disorders with significant combined prevalence (~1%) and high heritability. Dozens of individually rare genes and loci associated with high-risk for ASD have been identified, which overlap extensively with genes for intellectual disability (ID). However, studies indicate that there may be hundreds of genes that remain to be identified. The advent of inexpensive massively parallel nucleotide sequencing can reveal the genetic underpinnings of heritable complex diseases, including ASD and ID. However, whole exome sequencing (WES) and whole genome sequencing (WGS) provides an embarrassment of riches, where many candidate variants emerge. It has been argued that genetic variation for ASD and ID will cluster in genes involved in distinct pathways and protein complexes. For this reason, computational methods that prioritize candidate genes based on additional functional information such as protein-protein interactions or association with specific canonical or empirical pathways, or other attributes, can be useful. In this study we applied several supervised learning approaches to prioritize ASD or ID disease gene candidates based on curated lists of known ASD and ID disease genes. We implemented two network-based classifiers and one attribute-based classifier to show that we can rank and classify known, and predict new, genes for these neurodevelopmental disorders. We also show that ID and ASD share common pathways that perturb an overlapping synaptic regulatory subnetwork. We also show that features relating to neuronal phenotypes in mouse knockouts can help in classifying neurodevelopmental genes. Our methods can be applied broadly to other diseases helping in prioritizing newly identified genetic variation that emerge from disease gene discovery based on WES and WGS.

show abstract

Discovering cancer genes by integrating network and functional properties

Cited by 39 publications

References 43 publications

Predicting Genes Involved in Human Cancer Using Network Contextual Information

Predicting Genes Involved in Human Cancer Using Network Contextual Information

Predicting potential cancer genes by integrating network properties, sequence features and functional annotations

Network‐ and attribute‐based classifiers can prioritize genes and pathways for autism spectrum disorders and intellectual disability

Contact Info

Product

Resources

About