• L2-3170 - Computational Toolbox for Discovery of Prognostic Biomarkers for Survival Analysis
The Client : Javna agencija za raziskovalno dejavnost RS ( L2-3170 )
Project type: Research projects ARRS
Project duration: 2021 - 2024
  • Description

In the project, we will design and develop an interactive, visualization-based exploratory analysis toolbox to assist in finding molecular prognostic biomarkers from high-throughput molecular data and survival data obtained in clinical trials. The project will devise computational and machine learning methods to search for biomarkers, encapsulate them within interactive components with a graphical user interface, and provide visual programming to stitch these components into data analysis pipelines. The constructed methods and toolbox will support collaborations between the data scientists and domain experts-physicians, biomedical or pharma researchers-to sift through the molecular cell-response data of thousands of genes to find those that correlate most with survival. The proposed tool will access existing models, ontologies, and knowledge bases to speed up the interpretation and provide semi-automatic explanations of results. This is an applied project where we are teaming up with Genialis, a data science company specializing in computational support for precision medicine.

Research activity

Engineering sciences and technologies

Range on year

1,56 FTE

Research organisations

Genialis d.o.o.

Researchers

Blaž Zupan, Jaka Kokošar, Ela Praznik, Janez Demšar, Vesna Tanko, Marko Toplak

Project phases and their realization

Setting-up of the collaborative environment. Data acquisition and organization. Development of data mining and bioinformatics for survival biomarker discovery. Design of visual interfaces for exploratory analysis of survival data and biomarker discovery. Implementation and Integration. Experimental evaluation. Dissemination of results.

Project bibliographic references

Demšar J, Zupan B (2021) Hands-on training about overfitting, PLOS Computational Biology 17(3): e1008671.

Poličar PG, Stražar M, Zupan B (2021) Embedding to reference t-SNE space addresses batch effects in single-cell classification, Machine Learning.

Stražar M, Žagar L, Kokošar J, Tanko V, Erjavec A, Poličar P, Starič A, Demšar J, Shaulsky G, Menon V, Lamire A, Parikh A, and Zupan B (2019) scOrange - A Tool for Hands-On Training of Concepts from Single Cell Data Analytics, Bioinformatics 35(14):i4-i12.

Godec P, Pančur M, Ilenič N, Čopar A, Stražar M, Erjavec A, Pretnar A, Demšar J, Starič A, Toplak M, Žagar L, Hartman J, Wang H, Bellazzi R, Petrovič U, Garagna S, Zuccotti M, Park D, Shaulsky G, Zupan B (2019) Democratized image analytics by visual programming through integration of deep models and small-scale machine learning, Nature Communications 10(1):4551.

Štajdohar M, Rosengarten RD, Kokosar J, Jeran L, Blenkus D, Shaulsky G, Zupan B (2017) dictyExpress: a web-based platform for sequence data management and analytics in Dictyostelium and beyond, BMC Bioinformatics 18(1):291.

Financed by

Slovenian Research Agency