Species identification using high resolution melting (HRM) analysis with random forest classification. Issue 1 (2nd January 2019)

• Record Type: Journal Article
• Authors: Bowman, Sorelle; McNevin, Dennis; Venables, Samantha J.; Roffey, Paul; Richardson, Alice; Gahan, Michelle E.
• Is Part Of: Australian journal of forensic sciences. Volume 51:Issue 1(2019)
• Page Start: 57
• Page End: 72
• Publication Date: 2019-01-02
• Subjects: Forensic science -- rapid screening -- high resolution melt analysis -- predictive modelling -- random forest; Law -- Australia -- Periodicals; Forensic sciences -- Periodicals; Forensic Medicine -- Periodicals; 363.2505
• DOI: 10.1080/00450618.2017.1315835
• Languages: English
• ISSNs: 0045-0618

Abstract

Abstract: Species identification is an important facet of forensic investigation. In this study, human and non-human species (cow, chicken, pig, sheep, cat, dog, rabbit, fox, kangaroo and wombat) were assayed on the ViiA 7 Real-Time PCR System (Thermo Fisher Scientific) to rapidly screen for their species of origin using the high resolution melt (HRM) analysis targeting the 16S rRNA gene. Classification of HRM difference profiles using the onboard ViiA 7 software resulted in a classification accuracy of <20%. Derivative profiles (temperature versus negative first derivative of fluorescence, –d F /d T ) were classified using random forest algorithms supplemented by bagging and boosting, with either a randomly partitioned test set or a variety of folds of cross-classification, in addition to a range of trees and variables. Random forest classification with bagging conditions (constructed over 500 trees) was found to considerably outperform the ViiA 7 software for species differentiation with 100% classification accuracy for biological material from humans, domestic pets (cat and dog) and consumable meats (chicken and sheep) with an average classification accuracy of 70% across all species.