Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design

Lipinski’s Rule of Five and Ghose filter are empirical guidelines for evaluating the drug-likeness of a compound, suggesting that orally active drugs typically fall within specific ranges for molecular descriptors such as hydrogen bond donors and acceptors, weight, and lipophilicity. We revisit thes...

Full description

Saved in:
Bibliographic Details
Main Authors: Grzegorz Miebs, Adam Mielniczuk, Miłosz Kadziński, Rafał A. Bachorz
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/21/9966
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846173512325136384
author Grzegorz Miebs
Adam Mielniczuk
Miłosz Kadziński
Rafał A. Bachorz
author_facet Grzegorz Miebs
Adam Mielniczuk
Miłosz Kadziński
Rafał A. Bachorz
author_sort Grzegorz Miebs
collection DOAJ
description Lipinski’s Rule of Five and Ghose filter are empirical guidelines for evaluating the drug-likeness of a compound, suggesting that orally active drugs typically fall within specific ranges for molecular descriptors such as hydrogen bond donors and acceptors, weight, and lipophilicity. We revisit these practices and offer a more analytical perspective using the Dominance-based Rough Set Approach (DRSA). By analyzing representative samples of drug and non-drug molecules and focusing on the same molecular descriptors, we derived decision rules capable of distinguishing between these two classes systematically and reproducibly. This way, we reduced human bias and enabled efficient knowledge extraction from available data. The performance of the DRSA model was rigorously validated against traditional rules and available machine learning (ML) approaches, showing a significant improvement over empirical rules while achieving comparable predictive accuracy to more complex ML methods. Our rules remain simple and interpretable while being characterized by high sensitivity and specificity.
format Article
id doaj-art-2c42f7067e624391a8895b3b00e010f6
institution Kabale University
issn 2076-3417
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2c42f7067e624391a8895b3b00e010f62024-11-08T14:33:58ZengMDPI AGApplied Sciences2076-34172024-10-011421996610.3390/app14219966Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug DesignGrzegorz Miebs0Adam Mielniczuk1Miłosz Kadziński2Rafał A. Bachorz3Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznań, PolandInstitute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznań, PolandInstitute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznań, PolandInstitute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznań, PolandLipinski’s Rule of Five and Ghose filter are empirical guidelines for evaluating the drug-likeness of a compound, suggesting that orally active drugs typically fall within specific ranges for molecular descriptors such as hydrogen bond donors and acceptors, weight, and lipophilicity. We revisit these practices and offer a more analytical perspective using the Dominance-based Rough Set Approach (DRSA). By analyzing representative samples of drug and non-drug molecules and focusing on the same molecular descriptors, we derived decision rules capable of distinguishing between these two classes systematically and reproducibly. This way, we reduced human bias and enabled efficient knowledge extraction from available data. The performance of the DRSA model was rigorously validated against traditional rules and available machine learning (ML) approaches, showing a significant improvement over empirical rules while achieving comparable predictive accuracy to more complex ML methods. Our rules remain simple and interpretable while being characterized by high sensitivity and specificity.https://www.mdpi.com/2076-3417/14/21/9966drug-likenessmultiple criteria decision analysisdrug designbiological activitydominance-based rough set approachdecision rules
spellingShingle Grzegorz Miebs
Adam Mielniczuk
Miłosz Kadziński
Rafał A. Bachorz
Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design
Applied Sciences
drug-likeness
multiple criteria decision analysis
drug design
biological activity
dominance-based rough set approach
decision rules
title Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design
title_full Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design
title_fullStr Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design
title_full_unstemmed Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design
title_short Beyond the Arbitrariness of Drug-Likeness Rules: Rough Set Theory and Decision Rules in the Service of Drug Design
title_sort beyond the arbitrariness of drug likeness rules rough set theory and decision rules in the service of drug design
topic drug-likeness
multiple criteria decision analysis
drug design
biological activity
dominance-based rough set approach
decision rules
url https://www.mdpi.com/2076-3417/14/21/9966
work_keys_str_mv AT grzegorzmiebs beyondthearbitrarinessofdruglikenessrulesroughsettheoryanddecisionrulesintheserviceofdrugdesign
AT adammielniczuk beyondthearbitrarinessofdruglikenessrulesroughsettheoryanddecisionrulesintheserviceofdrugdesign
AT miłoszkadzinski beyondthearbitrarinessofdruglikenessrulesroughsettheoryanddecisionrulesintheserviceofdrugdesign
AT rafałabachorz beyondthearbitrarinessofdruglikenessrulesroughsettheoryanddecisionrulesintheserviceofdrugdesign