Use of Receiver Operating Characteristic (ROC) Analysis to Evaluate Sequence Matching

By Michael Gribskov, Nina L. Robinson. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches (2014, methodology): “We also compared UniRef50- and UniProtKB-based searches using ROC50 score (Gribskov and Robinson, 1996), which is the area under the receiver operating characteristic (ROC) curve up to the first 50 false positives.”
Evaluation of machine learning classifiers for mobile malware detection (2014, unknown): “ROC analysis has found ramiﬁcations into sequence matching comparisons (Gribskov and Robinson 1996), comparing the best average conﬁguration in experiments (Shabtai et al. 2012), visualizing and analyzing the behaviour of diagnostic systems (Lamiaa Ibrahim et al. 2013) and evaluating classiﬁer…”
Extensions of marginalized graph kernels (2004, methodology): “As for the MUTAG dataset, the computation time of the kernel signican tly decreases with each iteration of the Morgan index (gure 3). Performance, measured by the normalized area under the ROC curve plotting the number true positives as a function of false positives ( Gribskov & Robinson, 1996 ), is”
Adaptive computation and machine learning (1998, methodology): “In addition to the ROC score, we compute the ROC50 score, which is the ROC score computed only up to the first 50 false positives (Gribskov and Robinson, 1996).”
Diet and dioxins: the need to cut back. (2004, methodology): “Instead we evaluate our results by computing the ROC and ROC-50 scores [42].”
Domain enhanced lookup time accelerated BLAST (2012, methodology): “popular measure of retrieval accuracy, the Receiver Operating Characteristic (ROC) [33].”
Finding weak similarities between proteins by sequence profile comparison. (2003, methodology): “To compare the search sensitivity of different methods, another measure, the truncated receiver operating characteristic (ROC), has been used as well (29,30).”
A statistical framework for genomic data fusion (2004, background): “We report the receiver operating characteristic (ROC) score, which is the area under a curve that plots true positive rate as a function of false positive rate for differing classification thresholds (Hanley and McNeil, 1982; Gribskov and Robinson, 1996).”
Homology Detection via Family Pairwise Search (1998, unknown): “Figure 2(a) shows the average ROC50 scores for each homology detection method on all 73 protein families in the study.”
Improved pairwise alignment of genomic dna (2007, methodology): “Gusfield (1997) applies a suffix tree to the problem of finding exact substring matches between two strings.”
Soft Ngram Representation and Modeling for Protein Remote Homology Detection (2017, methodology): “Detection accuracies are measured: i) using the receiver operating characteristic (ROC) score [27], which represents the area under the ROC curve (the larger the”
Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework (2010, background): “In practical applications, it is rare to obtain the detailed pharmacological information about all compounds to be tested, so the result suggests that the predicted pharmacological information is useful for identification of unknown drug–target i250 [11:44 12/5/2010 Bioinformatics-btq176.tex] Page: ”