By using GOSTAR, which comes with a parseable dataset, you can obtain the latest organized SAR information and focus on your research.
●Unmatched data quality and scale GOSTAR is one of the world's largest databases of low molecular weight compounds, curated manually by top experts. It is organized, integrated, and updated through manual curation, allowing for immediate use in analysis and AI model development. By using GOSTAR, you can free yourself from the tasks of collecting and organizing data, enabling you to focus your valuable time on the most important research activities. GOSTAR is one of the largest low molecular SAR databases in the world, containing approximately 9 million low molecular weight compounds and nearly 30 million SAR data points. The database is built from 80,000 patents filtered from about 40 million and 200,000 research articles filtered from about 10 million, with data extracted through manual work by experts and standardized and structured based on specified rules. 【Features】 ■ A centralized data source for one of the largest low molecular SAR information collections in the world ■ Automatically adjusted for display based on the type of ligand, making it easy to read ■ Sortable by any data column and color-coded based on values *For more details, please refer to the PDF materials or feel free to contact us.*
Inquire About This Product
Related Videos
basic information
Excelra's GOSTAR provides the world's largest SAR content as a centralized data source, allowing researchers to thoroughly explore the known chemical space surrounding their target of interest. This database is manually curated by our scientific team, which extracts and enriches datasets from functional assays, in vitro, and in vivo tests. Various low molecular weight activities, including SAR, physicochemical properties, metabolism, ADME, and toxicity profiles, are included in GOSTAR. GOSTAR is a large dataset representing the quantitative binding interactions of known compounds and targets obtained from in vitro and in vivo (enzyme and cell-based models) experiments. It offers high-quality data that is immediately analyzable, making it suitable as training data for AI/ML (machine learning) technologies. It enables the rapid construction of predictive models for specific target activities and ADMET properties, contributing to the acceleration of drug discovery.
Price information
【Contract Model】 ◆ Online Access With GOSTAR's online service, you can search and analyze via a web browser. Depending on the contract, you can download search results, allowing you to integrate them into your internal database or use them as training data for AI/ML predictive models. There are user-based licenses and corporate licenses with unlimited users. ◆ File Delivery We provide all data or can narrow it down to specific categories. Data formats: Oracle, PostgreSQL, MySQL, text files, EXCEL, SDF, RDF, etc.
Delivery Time
Applications/Examples of results
Ten of the top 20 pharmaceutical companies in the world utilize GOSTAR for their drug discovery programs. In today's data-driven drug discovery landscape, structured high-quality datasets that encompass structure-activity relationships (SAR), physicochemical properties, and ADMET are essential for predictive modeling and AI/ML-driven drug discovery programs. ■Main Applications■ - As training data for AI (activity prediction, property prediction) - Drug design - Virtual screening - Lead optimization - Competitor research - Patentability research - Drug repositioning
catalog（10）
Download All Catalogs
News about this product（1）
Company information
Patocoa Inc. is a specialized company in drug discovery support systems. Additionally, we focus on improving and streamlining compliance-related operations concerning regulated substances, and we have provided various solutions to pharmaceutical companies, chemical companies, universities, and government agencies. We contribute to accelerating drug discovery and reducing costs with our cutting-edge chemoinformatics systems.