Please use this identifier to cite or link to this item:
http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/10003| Title: | Rectified Classifier Chains for Prediction of Antibiotic Resistance from Multi-Labelled Data with Missing Labels |
| Authors: | Mukunthan, T. Brian, G. Roberto La, R. Anil, F. |
| Keywords: | Multi-label classification;Classifier chain,;Multi-drug AMR;Missing labels;Semi-supervised model;Feature selection |
| Issue Date: | 2023 |
| Publisher: | IEEE |
| Abstract: | PredictingAntimicrobialResistance(AMR)fromgenomicdatahasimportantimplicationsforhumanandanimalhealthcare, andespeciallygivenitspotentialformorerapiddiagnosticsandinformedtreatmentchoices.Withtherecentadvancesinsequencing technologies,applyingmachinelearningtechniquesforAMRpredictionhaveindicatedpromisingresults.Despitethis,thereare shortcomingsintheliteratureconcerningmethodologiessuitableformulti-drugAMRpredictionandespeciallywheresampleswith missinglabelsexist.Toaddressthisshortcoming,weintroduceaRectifiedClassifierChain(RCC)methodforpredictingmulti-drug resistance.ThisRCCmethodwastestedusingannotatedfeaturesofgenomicssequencesandcomparedwithsimilarmulti-label classificationmethodologies.WefoundthatapplyingtheeXtremeGradientBoosting(XGBoost)basemodeltoourRCCmodel outperformedthesecond-bestmodel,XGBoostbasedbinaryrelevancemodel,by3.3%inHammingaccuracyand7.8%inF1-score. Additionally,wenotethatintheliteraturemachinelearningmodelsappliedtoAMRpredictiontypicallyareunsuitableforidentifying biomarkersinformativeoftheirdecisions;inthisstudy,weshowthatbiomarkerscontributingtoAMRpredictioncanalsobeidentified usingtheproposedRCCmethod.Weexpectthiscanfacilitategenomeannotationandpavethepathtowardsidentifyingnew biomarkersindicativeofAMR. |
| URI: | http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/10003 |
| Appears in Collections: | Electrical & Electronic Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Rectified_Classifier_Chains_for_Prediction_of_Antibiotic_Resistance_From_Multi-Labelled_Data_With_Missing_Labels.pdf | 1.47 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.