Intelligent Systems for Complex Data Research Group

We find patterns in data and mine information from complexity

Research & Research Areas

We are a team of researchers at Masaryk University in Brno, Czech Republic, specializing in complex data analysis. As part of the DISA laboratory and in close collaboration with the CERIT-SC centre, we aim to discover patterns within vast amounts of complex data.

We tackle unique challenges ranging from exploring patterns in images to the intricate analysis of complex biological structures such as proteins. Our ambition is to redefine the boundaries of effective and efficient processing of large datasets by leveraging our proficiency in machine learning, data mining, and clustering techniques.

Join us!

We are constantly looking for new members, postdocs, students for bachelor's and master's theses and more!

We've introduced a Learned Metric Index – an index for complex, unstructured or high-dimensional data built as a structure of machine-learning models.

We develop our own application for searching in proteins by their structural similarity called AlphaFind.

Adhering to the Open Science principles, we publish our work without restrictions, and the Learned Metric Index Framework is available online on GitHub.

News

Interview with Matej

Matej gave an interview to Vědavýzkum.cz about how Czech science has a great opportunity to advance rapidly by improving access to research data management.

Scaling Learned Metric Index to 100M Datasets

We have scaled the Learned Metric Index to over 100 million objects. This achievement paves the way for indexing billions of complex objects in the near future.

AlphaFind: discover structure similarity across the proteome in AlphaFold DB

We have published AlphaFind – a search engine for protein structure similarity indexing the whole AlphaFold DB (214M proteins). The accompanying paper is live in the Nucleic Acids Research journal.

Workshop: Future of similarity searching in the machine learning era (May 28-29, Malta)

Big Questions in Similarity Searching in ML, Learned Indexing in Similarity Searching, Research at the University of Malta and Applications to Similarity Search, Community Impact

FAIR-IMPACT: Assessment and improvement of Research Software

We're happy to announce that Terezia's application to the FAIR-IMPACT's call was accepted. In this short project, we will strive to improve the transparency, reproducibility, and reusability of our protein search tool AlphaFind.

Interview with Terézia

Terézia provided an interview for the EOSC CZ initiative about the experience during her Ph.D. studies, Open Science and Open Source, and most importantly about research reproducibility in light of our LMI reproducibility publication.

Best Student Paper at SISAP

Miriama Jánošová and David Procházka received a "Best Student Paper" award at the Similarity Search and Applications 2021 conference for their work on Organizing Similarity Spaces using Metric Hulls.

Previous Following

Our Collaborations and Outreach

In our team, we strive to develop cooperation with other research teams from both Czechia and abroad. Our most prominent partners are:

Information Systems and Data Mining Research Group, CAU University of Keil, Germany. Together with Prof. Dr. Peer Kruger and his group, we investigate modern techniques for indexing, searching and solving (reverse) kNN data retrieval techniques.

Biological Data Management and Analysis Core Facility of the Central European Institute of Technology. Together, we work on the application of learned indexing to searching in protein structures produced by Alphafold.

Engineers from e-INFRA CZ (specifically centre CERIT-SC) help us with fine-tuning our algorithms and running our experiments, often requiering non-trivial know-how and computing power.

Loading map…

Selected Publications

2021

Organizing Similarity Spaces using Metric Hulls

JÁNOŠOVÁ Miriama PROCHÁZKA David DOHNAL Vlastislav

Article in Proceedings

14th International Conference on Similarity Search and Applications (SISAP 2021), year: 2021

Interested in Our Research? Join Us!

We are searching for new colleagues for various positions who would work with us on exciting projects, develop unique software and solve unconventional problems. In case of interest, contact is at dohnal(at)fi.muni.cz or antol(at)muni.cz.