ALMERIA：利用可扩展方法提高成对分子对比度

IF 3.3 4区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

Informatica Pub Date : 2024-05-14 DOI:10.15388/24-infor558

Rafael Mena-Yedra, Juana López Redondo, Horacio Pérez-Sánchez, Pilar Martinez Ortigosa

{"title":"ALMERIA：利用可扩展方法提高成对分子对比度","authors":"Rafael Mena-Yedra, Juana López Redondo, Horacio Pérez-Sánchez, Pilar Martinez Ortigosa","doi":"10.15388/24-infor558","DOIUrl":null,"url":null,"abstract":"This work introduces ALMERIA, a decision-support tool for drug discovery. It estimates compound similarities and predicts activity, considering conformation variability. The methodology spans from data preparation to model selection and optimization. Implemented using scalable software, it handles large data volumes swiftly. Experiments were conducted on a distributed computer cluster using the DUD-E database. Models were evaluated on different data partitions to assess generalization ability with new compounds. The tool demonstrates excellent performance in molecular activity prediction (ROC AUC: 0.99, 0.96, 0.87), indicating good generalization properties of the chosen data representation and modelling. Molecular conformation sensitivity is also evaluated.\nPDF  XML","PeriodicalId":56292,"journal":{"name":"Informatica","volume":"304 1","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"ALMERIA: Boosting Pairwise Molecular Contrasts with Scalable Methods\",\"authors\":\"Rafael Mena-Yedra, Juana López Redondo, Horacio Pérez-Sánchez, Pilar Martinez Ortigosa\",\"doi\":\"10.15388/24-infor558\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work introduces ALMERIA, a decision-support tool for drug discovery. It estimates compound similarities and predicts activity, considering conformation variability. The methodology spans from data preparation to model selection and optimization. Implemented using scalable software, it handles large data volumes swiftly. Experiments were conducted on a distributed computer cluster using the DUD-E database. Models were evaluated on different data partitions to assess generalization ability with new compounds. The tool demonstrates excellent performance in molecular activity prediction (ROC AUC: 0.99, 0.96, 0.87), indicating good generalization properties of the chosen data representation and modelling. Molecular conformation sensitivity is also evaluated.\\nPDF  XML\",\"PeriodicalId\":56292,\"journal\":{\"name\":\"Informatica\",\"volume\":\"304 1\",\"pages\":\"\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Informatica\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.15388/24-infor558\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informatica","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.15388/24-infor558","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

这项工作介绍了 ALMERIA，一种用于药物发现的决策支持工具。它可以估计化合物的相似性并预测活性，同时考虑构象的可变性。该方法从数据准备到模型选择和优化。该方法使用可扩展软件实现，能迅速处理大量数据。实验在使用 DUD-E 数据库的分布式计算机集群上进行。在不同的数据分区上对模型进行了评估，以评估新化合物的通用能力。该工具在分子活性预测方面表现出色（ROC AUC：0.99、0.96、0.87），表明所选数据表示和建模具有良好的泛化特性。还对分子构象敏感性进行了评估。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

ALMERIA: Boosting Pairwise Molecular Contrasts with Scalable Methods

This work introduces ALMERIA, a decision-support tool for drug discovery. It estimates compound similarities and predicts activity, considering conformation variability. The methodology spans from data preparation to model selection and optimization. Implemented using scalable software, it handles large data volumes swiftly. Experiments were conducted on a distributed computer cluster using the DUD-E database. Models were evaluated on different data partitions to assess generalization ability with new compounds. The tool demonstrates excellent performance in molecular activity prediction (ROC AUC: 0.99, 0.96, 0.87), indicating good generalization properties of the chosen data representation and modelling. Molecular conformation sensitivity is also evaluated. PDF XML

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Informatica 工程技术-计算机：信息系统

CiteScore

5.90

自引率

6.90%

发文量

审稿时长

12 months

期刊介绍： The quarterly journal Informatica provides an international forum for high-quality original research and publishes papers on mathematical simulation and optimization, recognition and control, programming theory and systems, automation systems and elements. Informatica provides a multidisciplinary forum for scientists and engineers involved in research and design including experts who implement and manage information systems applications.