BC CLC-Pred: a freely available web-application for quantitative and qualitative predictions of substance cytotoxicity in relation to human breast cancer cell lines

BC CLC-Pred: a freely available web-application for quantitative and qualitative predictions of substance cytotoxicity in relation to human breast cancer cell lines

In silico prediction of cell line cytotoxicity considerably decreases time and financial costs during drug development of new antineoplastic agents. (Q)SAR models for the prediction of drug-like compound cytotoxicity in relation to nine breast cancer cell lines (T47D, ZR-75-1, MX1, Hs-578T, MCF7-DOX...

Full description

Saved in:
Bibliographic Details
Published in:SAR and QSAR in environmental research Vol. 35; no. 1; pp. 1 - 9
Main Authors: Lagunin, A.A., Sezganova, A.S., Muraviova, E.S., Rudik, A.V., Filimonov, D.A.
Format: Journal Article
Language:English
Published: England Taylor & Francis 2024
Taylor & Francis Ltd
Subjects:
Antineoplastic Agents - pharmacology
Breast cancer
Breast Neoplasms - drug therapy
Cell culture
Cell Line, Tumor
cell lines
CLC-Pred
Cytotoxicity
Drug development
Female
GUSAR
Humans
in silico prediction
Lead compounds
MCF-7 Cells
Predictions
Quantitative Structure-Activity Relationship
Software
Toxicity
Tumor cell lines
Webs
CLC-Pred
Cytotoxicity
breast cancer
in silico prediction
cell lines
GUSAR
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In silico prediction of cell line cytotoxicity considerably decreases time and financial costs during drug development of new antineoplastic agents. (Q)SAR models for the prediction of drug-like compound cytotoxicity in relation to nine breast cancer cell lines (T47D, ZR-75-1, MX1, Hs-578T, MCF7-DOX, MCF7, Bcap37, MCF7R, BT-20) were created by GUSAR software based on the data from ChEMBL database (v. 30). The separate datasets related with IC 50 and IG 50 values were used for the creation of (Q)SAR models for each cell line. Based on leave-one-out and 5F CV procedures, 24 reasonable (Q)SAR models were selected for the creation of a freely available web-application (BC CLC-Pred: https://www.way2drug.com/bc/ ) to predict substance cytotoxicity in relation to human breast cancer cell lines. The mean accuracies of prediction r 2 , RMSE, Balance Accuracy for the selected (Q)SAR models calculated by 5F CV were 0.599, 0.679 and 0.875, respectively. As a result, BC CLC-Pred provides simultaneous quantitative and qualitative predictions of IC 50 and IG 50 values for most of the nine breast cancer cell lines, which may be helpful in selecting promising compounds and optimizing lead compounds during the development of new antineoplastic agents against breast cancer.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1062-936X
1029-046X
DOI:10.1080/1062936X.2023.2289050