How to do an evaluation: pitfalls and traps.

by: Paul C Hawkins, Gregory L Warren, A G Skillman, Anthony Nicholls

J Comput Aided Mol Des (23 January 2008)

View FullText article

Springer (DOI), Pubmed, Hubmed

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

thanatos, BragilMassoud, LamBras

Find related articles with these CiteULike tags

benchmarks, cheminformatics, comparison, docking, review, statistics, virtual_screening

Abstract

The recent literature is replete with papers evaluating computational tools (often those operating on 3D structures) for their performance in a certain set of tasks. Most commonly these papers compare a number of docking tools for their performance in cognate re-docking (pose prediction) and/or virtual screening. Related papers have been published on ligand-based tools: pose prediction by conformer generators and virtual screening using a variety of ligand-based approaches. The reliability of these comparisons is critically affected by a number of factors usually ignored by the authors, including bias in the datasets used in virtual screening, the metrics used to assess performance in virtual screening and pose prediction and errors in crystal structures used.

@article{citeulike:2294933, abstract = {The recent literature is replete with papers evaluating computational tools (often those operating on 3D structures) for their performance in a certain set of tasks. Most commonly these papers compare a number of docking tools for their performance in cognate re-docking (pose prediction) and/or virtual screening. Related papers have been published on ligand-based tools: pose prediction by conformer generators and virtual screening using a variety of ligand-based approaches. The reliability of these comparisons is critically affected by a number of factors usually ignored by the authors, including bias in the datasets used in virtual screening, the metrics used to assess performance in virtual screening and pose prediction and errors in crystal structures used.}, address = {OpenEye Scientific Software, 9, Bisbee Court, Suite D, Santa Fe, NM, 87508, USA, phawkins@eyesopen.com.}, author = {Hawkins, Paul C. and Warren, Gregory L. and Skillman, A G. and Nicholls, Anthony }, citeulike-article-id = {2294933}, doi = {10.1007/s10822-007-9166-3}, issn = {0920-654X}, journal = {J Comput Aided Mol Des}, keywords = {benchmarks, comparison, docking}, month = {January}, posted-at = {2008-01-27 13:49:59}, priority = {2}, title = {How to do an evaluation: pitfalls and traps.}, url = {http://dx.doi.org/10.1007/s10822-007-9166-3}, year = {2008} }

RIS record

TY - JOUR ID - citeulike:2294933 L3 - citeulike-article-id:2294933 TI - How to do an evaluation: pitfalls and traps. JF - J Comput Aided Mol Des AD - OpenEye Scientific Software, 9, Bisbee Court, Suite D, Santa Fe, NM, 87508, USA, phawkins@eyesopen.com. SN - 0920-654X N2 - The recent literature is replete with papers evaluating computational tools (often those operating on 3D structures) for their performance in a certain set of tasks. Most commonly these papers compare a number of docking tools for their performance in cognate re-docking (pose prediction) and/or virtual screening. Related papers have been published on ligand-based tools: pose prediction by conformer generators and virtual screening using a variety of ligand-based approaches. The reliability of these comparisons is critically affected by a number of factors usually ignored by the authors, including bias in the datasets used in virtual screening, the metrics used to assess performance in virtual screening and pose prediction and errors in crystal structures used. KW - benchmarks KW - comparison KW - docking AU - Hawkins, Paul AU - Warren, Gregory AU - Skillman, A AU - Nicholls, Anthony PY - 2008/01/23/ UR - http://dx.doi.org/10.1007/s10822-007-9166-3 ER -

RIS BibTeX