Please wait

Applications

Whether you are an R&D head, Medicinal Chemist, Computational Chemist or a Cheminformatician, GOSTAR is an essential resource for drug design and discovery. GOSTAR provides the deep dive and the big picture providing the right intelligence for virtual screening, hit identification and lead optimization. Standard ontologies, clean annotation and normalized data also make GOSTAR the ideal data partner for modern AI/ML driven drug discovery pipelines.

icon

Medicinal Chemist

Computational Chemist

Cheminformatician

R&D strategy

Target Profiling

Identifying and characterizing targets druggable with small molecules is a key starting point for drug design and development. GOSTAR enables a holistic exploration of the chemical space around a target of interest. For instance, GOSTAR data can be used to:

  • Understand the pathways and indications in which a given target is implicated
  • Scan through discovery stage compounds that bind to a target and understand the chemical landscape
  • Use a scaffold-centric approach to study target binding of compounds similar to a putative NCE
  • Explore similar targets to interrogate against a compound of interest
icon
icon

Virtual Screening and
Hit Identification

GOSTAR can be used as a compound library to perform Virtual screening and Hit identification in traditional structure-based drug design methodologies. The diverse qualitative and quantitative SAR data points around each compound provide the lego bricks to build complex workflows including fragment-based, ligand-based and high-throughput screening. GOSTAR has also in-built libraries for specific target families (such as GPCR, ion-channel, kinase and nuclear receptor).

Validation and Lead Optimization

The Hit to Lead process involves tuning the structure of a hit to create analogs with improved potency, reduced off-target activities, and physiochemical/metabolic properties suggestive of reasonable in vivo pharmacokinetics. GOSTAR enables this optimization by suggesting with chemical modifications chosen by employing knowledge of the structure-activity relationship (SAR) and suggests the right functional assays for secondary validation.

icon
icon

Predictive and AI/ML Modeling

A critical bottleneck in predictive modeling for drug discovery is the availability of high-quality clean annotated datasets on which to train algorithms and search for novel compounds. GOSTAR is the ideal data partner with normalized analysis ready datasets of the highest quality. Further, Excelra provides custom curation support for AI/ML modeling including secure curation on the cloud of proprietary client data. Leave the data preparation to us and let your data scientists focus on building next generation of drug discovery algorithms.

Drug Repurposing

Repurposing and repositioning drugs is an increasingly attractive strategy for rescuing shelved compounds, finding treatments for neglected diseases, and reducing the time, cost and risk of drug development. GOSTAR data can be mined to interrogate diverse targets with a compound of interest to understand the feasibility and viability for drug rescue or for label expansion. Excelra also offers Drug Repurposing as a Service driven by our proprietary Global Repurposing Integrated Platform (GRIP) which is built with GOSTAR data at its core.

icon
icon

Competitive Intelligence and Novelty Analysis

GOSTAR's extensive patent coverage can be leveraged to perform novelty analysis around a compound of interest. GOSTAR also has a clinical compound database which captures drug lifecycle information such as indication, phase of development, sponsor and recrtuitment/approval status including suspended trials along with the reason for discontinuation where available. This rich information can to used to map out the competitive landscape around a drug, target or an indication.

Have a Question?



NOTE: To access this application, please use Google Chrome, IE, Firefox or Safari as your browser. Please make sure that JavaScript and style sheets are enabled in the browser. This site is best viewed at a resolution of 1024x768.
Powered by