PredictONCO

PredictONCO predicts the effects of somatic and missense mutations on protein sequence, structure, stability, function, and drug binding to support precision oncology decision-making.


Key Features:

  • Mutation Impact Analysis: Assesses how specific mutations affect protein sequential and structural properties, evaluating impacts on protein stability and function to infer variant pathogenicity.
  • Virtual Screening for Inhibitors: Employs virtual screening techniques to identify potential therapeutic inhibitors and to explore drug repurposing using FDA/EMA-approved drugs.
  • Binding Affinity Calculations: Calculates binding affinities of approved drugs with wild-type and mutant proteins to inform treatment selection.
  • Extensive Coverage: Covers 44 common oncological targets.
  • Validation and Reliability: Predictions were confirmed against 108 clinically validated mutations.

Scientific Applications:

  • Missense Mutation Analysis: Applied to missense mutations including K22A in cyclin-dependent kinase 4 (identified in melanoma), E1197K in anaplastic lymphoma kinase 4 (identified in lung carcinoma), and V765A in epidermal growth factor receptor (in a patient with congenital mismatch repair deficiency), increasing confidence in variant pathogenicity and suggesting effective inhibitors.

Methodology:

Integrates predictive algorithms and computational tools with data from established databases to perform protein stability and function analysis, virtual screening for inhibitors, and binding affinity calculations.

Topics

Details

Cost:
Free of charge
Tool Type:
web application
Operating Systems:
Mac, Linux, Windows
Added:
4/19/2024
Last Updated:
11/24/2024

Operations

Publications

Stourac J, Borko S, Khan RT, Pokorna P, Dobias A, Planas-Iglesias J, Mazurenko S, Pinto G, Szotkowska V, Sterba J, Slaby O, Damborsky J, Bednar D. PredictONCO: a web tool supporting decision-making in precision oncology by extending the bioinformatics predictions with advanced computing and machine learning. Briefings in Bioinformatics. 2023;25(1). doi:10.1093/bib/bbad441. PMID:38066711. PMCID:PMC10709543.

PMID: 38066711
Funding: - Czech Ministry of Education: CZECRIN LM2023049, TEAMING-CZ.02.1.01/0.0/0.0/17_043/0009632 - Technology Agency of the Czech Republic: TN02000109 - European Union: 857560 - Brno University of Technology: FIT-S-23-8209 - Czech Ministry of Health: NU20-03-00240 - National Institute for Cancer Research: LX22NPO5102

Documentation