Using GO-WAR for mining cross-ontology weighted association rules

Agapito, Giuseppe; Cannataro, Mario; Guzzi, Pietro Hiram; Milano, Marianna

doi:10.1016/j.cmpb.2015.03.007

Cited by 18 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rules generated using this approach were validated using gene ontologies. Another study on association rule mining in gene expression data was conducted by Agapito et al [44] where they electronically inferred annotations of the association rules by assigning different weights to different types of annotation.…”

Section: Discretization and Association Rule Miningmentioning

confidence: 99%

Graph Based Feature Selection for Reduction of Dimensionality in Next-Generation RNA Sequencing Datasets

2022

View full text Add to dashboard Cite

Analysis of high-dimensional data, with more features () than observations () (), places significant demand in cost and memory computational usage attributes. Feature selection can be used to reduce the dimensionality of the data. We used a graph-based approach, principal component analysis (PCA) and recursive feature elimination to select features for classification from RNAseq datasets from two lung cancer datasets. The selected features were discretized for association rule mining where support and lift were used to generate informative rules. Our results show that the graph-based feature selection improved the performance of sequential minimal optimization (SMO) and multilayer perceptron classifiers (MLP) in both datasets. In association rule mining, features selected using the graph-based approach outperformed the other two feature-selection techniques at a support of 0.5 and lift of 2. The non-redundant rules reflect the inherent relationships between features. Biological features are usually related to functions in living systems, a relationship that cannot be deduced by feature selection and classification alone. Therefore, the graph-based feature-selection approach combined with rule mining is a suitable way of selecting and finding associations between features in high-dimensional RNAseq data.

show abstract

Section: Discretization and Association Rule Miningmentioning

confidence: 99%

Graph Based Feature Selection for Reduction of Dimensionality in Next-Generation RNA Sequencing Datasets

2022

View full text Add to dashboard Cite

show abstract

“…A large proportion of GO annotations are generated electronically and deemed to be of lower quality as compared to those verified manually. Association rules have been used in the past to explore the impact of including electronically inferred annotations on the quality of mined association rules by assigning weights to different types of annotations (GO‐WAR) (Agapito, Cannataro, Guzzi, & Milano, ; Agapito, Milano, Guzzi, & Cannataro, ; Guzzi, Milano, & Cannataro, ). Association rule mining has also been used for curation of GO data with the goal of identifying consistency in annotations (VICD) (Shui & Cho, ).…”

Section: Association Rule Mining On Go Datamentioning

confidence: 99%

Data mining powered by the gene ontology

Manda

2020

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The gene ontology (GO) is a widely used resource for describing molecular functions, biological processes, and cellular components of gene products.Since its inception in 2006, the GO has been used to describe millions of gene products resulting in a massive data store of over 6 million annotations. The staggering amount of data that has resulted from annotating gene products with GO terms has led the way and opened new avenues for a wide variety of large-scale computational analyses. Specifically, a variety of data mining techniques such as association rule mining, clustering etc. have been applied successfully to a range of biological applications.

show abstract

“…Their ability to produce a massive amount of data has spurred the development of several pipelines for data analysis [ 1 – 4 ]. Several annotation software tools use Gene Ontology (GO) to link HT data analysis results with the affected biological mechanisms [ 5 , 6 ]. Although these software tools can effectively analyze these vast amounts of available data, the produced results are still not connected to the biological mechanisms they may influence.…”

Section: Introductionmentioning

confidence: 99%

Using BioPAX-Parser (BiP) to enrich lists of genes or proteins with pathway data

Agapito

Cannataro

2021

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

Background Pathway enrichment analysis (PEA) is a well-established methodology for interpreting a list of genes and proteins of interest related to a condition under investigation. This paper aims to extend our previous work in which we introduced a preliminary comparative analysis of pathway enrichment analysis tools. We extended the earlier work by providing more case studies, comparing BiP enrichment performance with other well-known PEA software tools. Methods PEA uses pathway information to discover connections between a list of genes and proteins as well as biological mechanisms, helping researchers to overcome the problem of explaining biological entity lists of interest disconnected from the biological context. Results We compared the results of BiP with some existing pathway enrichment analysis tools comprising Centrality-based Pathway Enrichment, pathDIP, and Signaling Pathway Impact Analysis, considering three cancer types (colorectal, endometrial, and thyroid), for a total of six datasets (that is, two datasets per cancer type) obtained from the The Cancer Genome Atlas and Gene Expression Omnibus databases. We measured the similarities between the overlap of the enrichment results obtained using each couple of cancer datasets related to the same cancer. Conclusion As a result, BiP identified some well-known pathways related to the investigated cancer type, validated by the available literature. We also used the Jaccard and meet-min indices to evaluate the stability and the similarity between the enrichment results obtained from each couple of cancer datasets. The obtained results show that BiP provides more stable enrichment results than other tools.

show abstract

Using GO-WAR for mining cross-ontology weighted association rules

Cited by 18 publications

References 31 publications

Graph Based Feature Selection for Reduction of Dimensionality in Next-Generation RNA Sequencing Datasets

Graph Based Feature Selection for Reduction of Dimensionality in Next-Generation RNA Sequencing Datasets

Data mining powered by the gene ontology

Using BioPAX-Parser (BiP) to enrich lists of genes or proteins with pathway data

Contact Info

Product

Resources

About