Abstract
Drug development is a long, expensive and multistage process geared to achieving safe drugs with high efficacy. A crucial prerequisite for completing the medication regimen for oral drugs, particularly for pediatric and geriatric populations, is achieving taste that does not hinder compliance. Currently, the aversive taste of drugs is tested in late stages of clinical trials. This can result in the need to reformulate, potentially resulting in the use of more animals for additional toxicity trials, increased financial costs and a delay in release to the market. Here we present BitterIntense, a machine learning tool that classifies molecules into “very bitter” or “not very bitter”, based on their chemical structure. The model, trained on chemically diverse compounds, has above 80% accuracy on several test sets. Our results suggest that about 25% of drugs are predicted to be very bitter, with even higher prevalence (~40%) in COVID19 drug candidates and in microbial natural products. Only ~10% of toxic molecules are predicted to be intensely bitter, and it is also suggested that intense bitterness does not correlate with hepatotoxicity of drugs. However, very bitter compounds may be more cardiotoxic than not very bitter compounds, possessing significantly lower QPlogHERG values. BitterIntense allows quick and easy prediction of strong bitterness of compounds of interest for food, pharma and biotechnology industries. We estimate that implementation of BitterIntense or similar tools early in drug discovery process may lead to reduction in delays, in animal use and in overall financial burden.
| Original language | American English |
|---|---|
| Pages (from-to) | 568-576 |
| Number of pages | 9 |
| Journal | Computational and Structural Biotechnology Journal |
| Volume | 19 |
| DOIs | |
| State | Published - Jan 2021 |
Bibliographical note
Funding Information:MYN is grateful to the late Professor Amirav Gordon for his invaluable advice, encouragement and support. The authors thank Yuli Slavutsky and Dr. Yuval Benjamini for helpful discussions on machine learning methods. The core data science scholarship to EM from the Center for Interdisciplinary Data Science Research (CIDR) is gratefully acknowledged. MYN and EM participate in Mu.Ta.Lig (CA15135) and ERNEST (CA18133) COST actions. MYN is supported by the Israel Science Foundation grants ISF 494/16 and ISF-NSFC2463/16.
Funding Information:
MYN is grateful to the late Professor Amirav Gordon for his invaluable advice, encouragement and support. The authors thank Yuli Slavutsky and Dr. Yuval Benjamini for helpful discussions on machine learning methods. The core data science scholarship to EM from the Center for Interdisciplinary Data Science Research (CIDR) is gratefully acknowledged. MYN and EM participate in Mu.Ta.Lig (CA15135) and ERNEST (CA18133) COST actions. MYN is supported by the Israel Science Foundation grants ISF 494/16 and ISF-NSFC2463/16. MYN conceived the project, MYN, EM and ADW designed the computational analysis, EM wrote the codes, trained the model and performed all computational analyses, ADW provided data on compounds for the positive and negatives sets and data for toxicity and in-vitro activities, KS provided data and critical discussions, RI and SJ obtained the in-vivo data, EM and MYN have written the manuscript, all authors have read and approved the manuscript.
Publisher Copyright:
© 2021 The Authors
Keywords
- Bitter
- Drug discovery
- Drugs
- Machine learning
- Taste
- Toxicity