TargetMiner: microRNA target prediction with systematic identification of tissue-specific negative examples

Bandyopadhyay, Sanghamitra; Mitra, Ramkrishna

doi:10.1093/bioinformatics/btp503

Cited by 209 publications

(181 citation statements)

References 26 publications

Supporting

Mentioning

179

Contrasting

Unclassified

Order By: Relevance

“…Here, we computed the F-score [35] of each feature as follows: for a set of training vectors x k , k=1, 2,---, m, if the number of positive and negative instances are n + and n -, respectively, then the F-score of the i th feature is defined as: negative samples respectively. To our knowledge, these statistical tests were not employed previously in literature to choose a subset of physicochemical properties of amino acids for the prediction of amyloid fibril segments.…”

Section: Filter Based Pre-selection Methodsmentioning

confidence: 99%

An Evaluation of Feature Selection Approaches in Finding Amyloidogenic Regions in Protein Sequences

Nair¹,

Reddy²,

Hareesha³

2010

IJCA

View full text Add to dashboard Cite

Amyloidogenic regions in polypeptide chains are associated with a number of diseases. Experimental evidence is compelling in favor of the hypothesis that small segments of proteins are responsible for its amyloidogenic behavior. Thus, identifying these short peptides is critical for understanding diseases associated with protein misfolding and developing sequencetargeted anti-aggregation drugs. The in silico approaches using phenomenological models based on bio-physio-chemical properties of amino acids suffer from "curse of dimensionality". Therefore, before adopting standard classification algorithms to predict such fibril motifs, the "curse of dimensionality" needs to be solved. The present study evaluates the performance of feature selection algorithms namely filter, wrapper and embedded models in conjunction with Support Vector Machine classifier. We also propose a novel integrated feature selection strategy based on Genetic Algorithm and Support Vector Machine to get an optimal number of features in predicting the amyloid fibril-forming short stretches of peptides. In addition, we investigated the performances of feature selection models that resulted in new and complementary set of properties and concludes that the proposed integrated dimensionality reduction technique outperforms all other methods and achieves the highest sensitivity and specificity of 86% and 82% respectively.

show abstract

Section: Filter Based Pre-selection Methodsmentioning

confidence: 99%

An Evaluation of Feature Selection Approaches in Finding Amyloidogenic Regions in Protein Sequences

Nair¹,

Reddy²,

Hareesha³

2010

IJCA

View full text Add to dashboard Cite

show abstract

“…The higher rate of false positives in target prediction is due to the close resemblance of real targets with the non-targets. Bandyopadhyay et al suggested a method for systematic identification of negative samples [23]. We have adopted Bandyopadhyay's model with a modification for negative sample preparation.…”

Section: Data Collectionmentioning

confidence: 99%

“…TargetMiner is a classifier for target prediction trained with negative samples prepared by systematic identification from the false positive targets. They compared their results with predicted targets of 10 different algorithms in terms of specificity, sensitivity and accuracy and reports that accuracy of target prediction tools is still around 70% [23].…”

Section: Introductionmentioning

confidence: 99%

HTar: Hidden Markov Model Based MicroRNA Binding Site Prediction

Salim¹,

SS²

2017

J Proteomics Bioinform

View full text Add to dashboard Cite

“…Certain databases have been created using computational predictions and experimental results, for example miRBase (18), miRNAMap2.0 (19), miRGen (20), miRGator v2.0 (21) and miRecords (22). Other databases, such as TargetScan (2), PicTar (23) and TargetMiner (24), are based on algorithms designed to predict microRNA targets according to the complementary pairing with the target. Another database, TarBase (25), uses validated microRNA targets, while RNAhybrid (26) is based on hybridization between miRNA and mRNA.…”

Section: Web-based Tools For Micrornas Involved In Human Cancer (Review)mentioning

confidence: 99%

Web-based tools for microRNAs involved in human cancer

2016

View full text Add to dashboard Cite

Abstract. MicroRNAs (miRNAs/miRs) are a family of small, endogenous and evolutionarily-conserved non-coding RNAs that are involved in the regulation of several cellular and functional processes. miRNAs can act as oncogenes or tumor suppressors in all types of cancer, and could be used as prognostic and diagnostic biomarkers. Databases and computational algorithms are behind the majority of the research performed on miRNAs. These tools assemble and curate the relevant information on miRNAs and present it in a user-friendly manner. The current review presents 14 online databases that address every aspect of miRNA cancer research. Certain databases focus on miRNAs and a particular type of cancer, while others analyze the behavior of miRNAs in different malignancies at the same time. Additional databases allow researchers to search for mutations in miRNAs or their targets, and to review the naming history of a particular miRNA. All these databases are open-access, and are a valuable tool for those researchers working with these molecules, particularly those who lack access to an advanced computational infrastructure.

show abstract

TargetMiner: microRNA target prediction with systematic identification of tissue-specific negative examples

Abstract: TargetMiner is now available as an online tool at www.isical.ac.in/ approximately bioinfo_miu

Cited by 209 publications

References 26 publications

An Evaluation of Feature Selection Approaches in Finding Amyloidogenic Regions in Protein Sequences

An Evaluation of Feature Selection Approaches in Finding Amyloidogenic Regions in Protein Sequences

HTar: Hidden Markov Model Based MicroRNA Binding Site Prediction

Web-based tools for microRNAs involved in human cancer

Contact Info

Product

Resources

About