Identification of average molecular weight (AMW) as a useful chemical descriptor to discriminate liver injury-inducing drugs

Yuki Shimizu, Takamitsu Sasaki, Jun-ichi Takeshita, Michiko Watanabe, Ryota Shizu, Takuomi Hosaka and Kouichi Yoshinari

PLOS ONE, 2021, vol. 16, issue 6, 1-15

Abstract: Drug-induced liver injury (DILI) is one of major causes of discontinuing drug development and withdrawing drugs from the market. In this study, we investigated chemical properties associated with DILI using in silico methods, to identify a physicochemical property useful for DILI screening at the early stages of drug development. Total of 652 drugs, including 432 DILI-positive drugs (DILI drugs) and 220 DILI-negative drugs (no-DILI drugs) were selected from Liver Toxicity Knowledge Base of US Food and Drug Administration. Decision tree models were constructed using 2,473 descriptors as explanatory variables. In the final model, the descriptor AMW, representing average molecular weight, was found to be at the first node and showed the highest importance value. With AMW alone, 276 DILI drugs (64%) and 156 no-DILI drugs (71%) were correctly classified. Discrimination with AMW was then performed using therapeutic category information. The performance of discrimination depended on the category and significantly high performance (>0.8 balanced accuracy) was obtained in some categories. Taken together, the present results suggest AMW as a novel descriptor useful for detecting drugs with DILI risk. The information presented may be valuable for the safety assessment of drug candidates at the early stage of drug development.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0253855 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 53855&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0253855

DOI: 10.1371/journal.pone.0253855

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().