PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R

By Jan Grau, Ivo Grosse, Jens Keilwagen. Bioinform., 2015

370 citations recorded by the source corpus.

Summary: Precision-recall (PR) and receiver operating characteristic (ROC) curves are valuable measures of classifier performance. Here, we present the R-package PRROC, which allows for computing and visualizing both PR and ROC curves. In contrast to available R-packages, PRROC allows for computing PR and ROC curves and areas under these curves for soft-labeled data using a continuous interpolation between the points of PR curves. In addition, PRROC provides a generic plot function for generating publication-quality graphics of PR and ROC curves. Availability and implementation: PRROC is available from CRAN and is licensed under GPL 3. Contact: grau@informatik.uni-halle.de

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/62b839dcb0eee3e8487a436bfb367a283283ea7d

How researchers see this paper

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

In Artificial Intelligence

1. Stefan Posch
2. Jan Grau
3. Jens Keilwagen

Citations in the corpus

• Benchmark and integration of resources for the estimation of human transcription factor activities (2018, methodology): “3) (Grau et al. 2015) and we used the areas under the curves (AUPRC and AUROC) as performance metrics.”
• Learning from mistakes: Accurate prediction of cell type-specific transcription factor binding (2017, methodology): “For each of the TFs, we collect all position weight matrix models from the HOCOMOCO database (Kulakovskiy et al. , 2016) as well as our in-house database DBcorrDB (Grau et al. , 2015a), and Slim/LSlim models of the respective TFs from a previous publica-933 tion (Keilwagen and Grau, 2015).”