Isadora Leitzke Guidotti, Lucas Mocellin Goulart, Gabriel Liston de Menek, Eduardo Grutzmann Furtado, Daniela Peres Martinez, Frederico Schmitt Kremer
{"title":"Caramel: A web-based QSAR tool for melanoma drug discovery","authors":"Isadora Leitzke Guidotti, Lucas Mocellin Goulart, Gabriel Liston de Menek, Eduardo Grutzmann Furtado, Daniela Peres Martinez, Frederico Schmitt Kremer","doi":"10.1016/j.simpa.2024.100623","DOIUrl":null,"url":null,"abstract":"<div><p>Melanoma is one of the most aggressive and prevalent types of cancer and the development of novel drugs for its treatment is an ongoing effort. Virtual screening methods may accelerate the discovery of drug candidates by reducing the number of molecules to be tested <em>in vitro</em> and <em>in vivo</em>, using techniques based on properties of the ligand (eg: QSAR, pharmacophore, Lipinski rules) and the receptor/complex (eg: molecular docking, molecular dynamics). QSAR (Quantitative Structure Activity Relationship) allows the estimation of molecule properties and potential activities based on its structure, usually described based on numerical features, using statistical and machine learning methods. Here we describe Caramel, a web-based QSAR tool that provides predictive models for the growth inhibition of different melanoma cell lines, providing a fast and efficient way to select potentially active molecules <em>in silico</em>.</p></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2665963824000113/pdfft?md5=1a71937b4fe002cda3fceae9e3638b63&pid=1-s2.0-S2665963824000113-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Software Impacts","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2665963824000113","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
Melanoma is one of the most aggressive and prevalent types of cancer and the development of novel drugs for its treatment is an ongoing effort. Virtual screening methods may accelerate the discovery of drug candidates by reducing the number of molecules to be tested in vitro and in vivo, using techniques based on properties of the ligand (eg: QSAR, pharmacophore, Lipinski rules) and the receptor/complex (eg: molecular docking, molecular dynamics). QSAR (Quantitative Structure Activity Relationship) allows the estimation of molecule properties and potential activities based on its structure, usually described based on numerical features, using statistical and machine learning methods. Here we describe Caramel, a web-based QSAR tool that provides predictive models for the growth inhibition of different melanoma cell lines, providing a fast and efficient way to select potentially active molecules in silico.