GOSTAR TPD logo

GOSTAR TPD

Structure-activity relationship database for targeted protein degrader research, covering 45,000+ degraders across 10 modalities with 120,000+ manually curated SAR data points.

Solution by Excelra
Visit website

Overview

GOSTAR™ TPD is a structure-activity relationship (SAR) database focused exclusively on targeted protein degraders (TPDs), developed by Excelra. It is designed for researchers and professionals working in TPD drug discovery, including medicinal chemists, AI and data scientists, drug development executives, and broader drug discovery teams. The database contains detailed, standardized information on over 45,000 targeted protein degraders across multiple modalities, sourced from patents, scientific publications, regulatory submissions, and other documents.

All data in GOSTAR™ TPD is manually curated by expert chemists — no automated scraping is used — and every data point undergoes a three-tiered quality control process. The database holds QMS-ISO-9001:2015 certification, and each data point is linked to its original source to support traceability and validation.

Database Coverage and Scale

  • Over 45,000 unique targeted protein degraders
  • 120,000+ SAR data points
  • Coverage of 10+ protein degrader modalities
  • Over 1,500 biological targets
  • 250+ annotated data fields covering chemical, biological, and therapeutic properties
  • Data sourced from over 10,000 documents, including patents and publications
  • Compounds and data from 100+ companies and institutes

Data Quality and Curation

  • Fully manually curated by medicinal chemistry experts; no automated data scraping
  • Three-tiered quality control process applied to every data point
  • QMS-ISO-9001:2015 certified curation process
  • Every data point is referenced and linked to its original source for traceability
  • Focused exclusively on protein degraders, excluding irrelevant data found in broader chemistry databases

Data Structure and Informatics Readiness

  • Standardized vocabulary and units across all data to minimize post-processing requirements
  • Structured for direct use in AI/ML models with minimal additional cleaning
  • Available in multiple formats: flat files, hierarchical files, semantic format, Oracle databases, MySQL™ databases, and others
  • Bulk data access available via flat file, API, or exports

Update Frequency and Timeliness

  • Standard monthly updates to the database
  • Custom curation available for critical or urgent data needs, with updates possible within 24 hours of source publication
  • Over 10,000 patents and publications screened to capture novel degraders from the earliest stages of disclosure

Use Cases by Role

  • AI, informaticians, and data scientists: Access to over 120,000 data points on 45,000+ degraders across 10 modalities and 1,500+ protein targets; standardized, machine-friendly data formats reduce time spent on data cleaning and preparation for model building.
  • Medicinal chemists: User-friendly interface focused on SAR data for protein degraders only; supports deep exploration of chemical spaces and export of data sets of interest; data harmonized for pharmaceutical design and discovery workflows.
  • Drug development executives and strategic professionals: Curates degraders from patents and publications at the time of publication, enabling early visibility into the TPD landscape; supports landscape analysis, modality and target review, and pipeline decision-making.
  • All drug development and discovery professionals: Flexible data delivery options ranging from bulk flat files to rapid-turnaround custom curation; supports AI/ML drug discovery, exploratory research, and regulatory-grade traceability requirements.

GOSTAR™ TPD is part of Excelra's broader GOSTAR™ SAR database family and is positioned as a dedicated resource for the TPD field, distinct from general-purpose chemistry databases. Data delivery options — including flat files, APIs, database formats, and custom curation services — are designed to support a range of computational and research workflows.

Meta

Domain
Research Intelligence & Discovery
Subdomain
Chemical & Patent Intelligence
Software type(s)
Database / Knowledge Base
Deployment type(s)
Cloud / SaaS
Industry vertical(s)
Academic / ResearchBiotechCROPharma
Development stage(s)
Research & DiscoveryPreclinical / Pre-Market
Target user(s)
Research ScientistBioinformatician / Computational ScientistMedicinal Chemist