From 7a2815467c74fa982421f460e835539ed9ef1bde Mon Sep 17 00:00:00 2001
From: gioamendola <81375211+gioamendola@users.noreply.github.com>
Date: Tue, 30 Nov 2021 13:23:59 +0100
Subject: [PATCH] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f51ae32..2595ea4 100644
--- a/README.md
+++ b/README.md
@@ -63,7 +63,7 @@ Poor performance may be the result of several factors, which include:
 
 The above cases and others are discussed in the [JCIM article](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.1c00653). Importantly, adjusting the epsilon cutoff values may readily improve poor performance, especially with regards to TPR, FPR, Precision, and F-Score, as they impact the classification thresholds. The default cutoff values for both the active training set and the inactive training set is 0.95, so that 95% of the training set will be considered in the model building step. This allows to account for some tolerance to the presence/absence of chemical motifs. Higher values (e.g. closer to 1) for the active training cutoff generally result in more true positives and false positives alike. Instead, a higher cutoff for the inactive set fitting should mainly decrease the false positive rate with some effect on the TPR. 
 
-We suggest benchmarking using the possible combinations of **the following epsilon cutoff values: 0.84–0.95–0.98 for epsilon_active and 0.7–0.84–0.95–0.98 for epsilon_cutoff_inactive** and identify the combination with the best TPR/FPR tradeoff. Further information about the epsilon cutoff values are available in the [JCIM article](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.1c00653) and in its Supporting Information PDF. 
+As a possible starting point, we suggest benchmarking using the possible combinations of **the following epsilon cutoff values: 0.84–0.95–0.98 for epsilon_active and 0.7–0.84–0.95–0.98 for epsilon_cutoff_inactive** and identify the combination with the best TPR/FPR tradeoff. Further information about the epsilon cutoff values are available in the [JCIM article](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.1c00653) and in its Supporting Information PDF. 
 
 # RMD Algorithm
 PyRMD implements the Random Matrix Discriminant (RMD) algorithm devised by [Lee et al.](https://www.pnas.org/content/116/9/3373) to identify small molecules endowed with biological activity. Parts of the RMD algorithm code were adapted from the [MATLAB version of the RMD](https://github.com/alphaleegroup/RandomMatrixDiscriminant) and a [Python implementation proposed by Laksh Aithani](https://towardsdatascience.com/random-matrix-theory-the-best-classifier-for-prediction-of-drug-binding-f82613fb48ed) of the [Random Matrix Theory](https://www.pnas.org/content/113/48/13564).