rdkit.ML.Scoring.Scoring module

$Id$

Scoring - Calculate rank statistics

Created by Sereina Riniker, October 2012 after a file from Peter Gedeck, Greg Landrum

param scores: ordered list with descending similarity containing

active/inactive information

param col: column index in scores where active/inactive information is stored param fractions: list of fractions at which the value shall be calculated param alpha: exponential weight

rdkit.ML.Scoring.Scoring.CalcAUC(scores, col)

Determines the area under the ROC curve

rdkit.ML.Scoring.Scoring.CalcBEDROC(scores, col, alpha)

BEDROC original defined here: Truchon, J. & Bayly, C.I. Evaluating Virtual Screening Methods: Good and Bad Metric for the “Early Recognition” Problem. J. Chem. Inf. Model. 47, 488-508 (2007).

rdkit.ML.Scoring.Scoring.CalcEnrichment(scores, col, fractions)

Determines the enrichment factor for a set of fractions

rdkit.ML.Scoring.Scoring.CalcRIE(scores, col, alpha)

RIE original definded here: Sheridan, R.P., Singh, S.B., Fluder, E.M. & Kearsley, S.K. Protocols for Bridging the Peptide to Nonpeptide Gap in Topological Similarity Searches. J. Chem. Inf. Comp. Sci. 41, 1395-1406 (2001).

rdkit.ML.Scoring.Scoring.CalcROC(scores, col)

Determines a ROC curve