Research - Institute of Biochemistry - Synthetic and Systems Biology Unit - Laboratory of Microscopic Image Analysis and Machine Learning

senior research associate


Krisztina BUZÁS
research associate

Tivadar DANKA research associate
Mária KOVÁCS research associate
József MOLNÁR research associate
Gabriella DOBRA junior research associate
Edina GYUKITY-SEBESTYÉN junior research associate
Árpád BÁLIND scientific administrator
András KRISTON scientific administrator
Mária HARMATI scientific administrator
Réka HOLLANDI scientific administrator
Krisztián KOÓS scientific administrator
Csaba MOLNÁR scientific administrator
István TASNÁDI Ph.D. student
Tímea TÓTH Ph.D. student
Ádám István SZŰCS Ph.D. student
Tamás BALASSA Ph.D. student
Ábel SZKALISITY undergraduate student


Research overview

Recent technological advancements in systems biology, lab automation, and high-throughput microscopy have opened the door to systematic discovery of complex biological systems using high-throughput light microscopy. Modern equipments produce massive amounts of data which cannot be analyzed manually.

Automating the analysis process poses several challenges related to computational cell biology. Our group dedicated to finding computational solutions to biological problems. Our research focuses on the intersection of biology and computer science, and combine wet-lab and light microscopy with image analysis and machine learning methods.

I. Microscopic image segmentation and tracking

The image processing step plays a crucial role in determining the quality of a microscopic imaging scenario. It is during this stage that biologically relevant data is extracted from the image, which ultimately determines how the cells will be categorized (by phenotype, by infection rate, etc.). The image processing stage must address many different problems, such as counting the number of cells, identifying subcellular structures, segmenting cells, and extracting a variety of specific measurements (e.g. the expression level of a certain protein).

Image segmentation

The problem of automatically inferring which regions in the image correspond to biologically interesting object(s) (e.g. cell phenotypes, 3D sub-cellular structures) is a difficult problem. Like most inference problems, it can be framed in probabilistic setting. To obtain a solution, one attempts to maximize probabilities, which corresponds to minimizing their negative logarithm in an energy minimization approach (Horvath 2006, 2009). We are interested in segmentation approaches that combine shape models and classic energy minimization techniques (eg. variational methods, Markov random fields) and incorporate not only a priori shape information into image segmentation, but intensity and textural cues as well.


We are interested in developing methods for identifying and tracking cells or sub-cellular structures on live cell images. We have been developed a software the CellTracker, which corrects illumination problems, finds alignments, as well as automatically and manually tracks cells, mainly on phase contrast images. The program is available with MatLab GUI.

Download CellTracker (9.9MB) >>
Download User Manual >>

II. Microscopic image correction techniques

For quantitative measurements based on light microscopy and especially fluorescent intensities, it is essential to normalize the image data to correct for aberrations inherent in the acquisition process. One common source of error is the result of a non-ideal illumination field produced by the objective. Our novel algorithms, described in (Smith, et al. , Piccinini et al.), addresses these issues using energy minimization. The corrected field resulting from our approach is extremely flat, and we can achieve this level of quality without requiring a calibrated reference sample.

III. Machine learning methods

The multi-parametric analysis step is concerned with interpreting the variety of collected information by identifying known patterns and discovering outliers. We are interested in the application of machine learning techniques for tasks such as phenotype identification and population analysis. We are developing the Advanced Cell Classifier ( ) (Horvath et. al. 2011), provides an interface and machine learning software for large scale microscopic imaging scenarios.

We are particularly interested in:

  • Efficient semi-supervised learning for HCS - using active learning and semi-supervised learning to speed up learning processes
  • Selecting the best learning method - It has been shown that, among existing learning methods, there is no “silver bullet” that outperforms all other methods on any given problem. We are developing a solution to this problem , which automatically selects the best learning method and optimizes its parameters for a given data set

Selected publications

Meier, R., Franceschini, A., Horvath, P., Tetard, M., Mancini, R., Mering, C. v., Helenius, A. (2014) Genome-wide siRNA screens reveal VAMP3 as a novel host factor required for Uukuniemi virus late penetration. Journal of Virology

Kiss, A., Horvath, P., Rothballer, A., Kutay, U., Csucs, G. (2014) Nuclear Motility in Glioma Cells Reveals a Cell-Line Dependent Role of Various Cytoskeletal Components. PLoS One

Smith, K., Horvath, P. (2014) Active Learning Strategies for Phenotypic Profiling of High-Content Screens. Journal of Biomolecular Screening

Indranil, B., Yamautchi, Y., Helenius, A., Horvath, P. (2013) High-content analysis of sequential events during the early phase of influenza A virus infection. PLoS One

Piccinini, F., Bevilacqua, A., Smith, K., Horvath, P. (2013) Vignetting And Photo-Bleaching Correction In Automated Fluorescence Microscopy From An Array Of Overlapping Images IEEE ISBI, San Francisco

Riess, T., Marino, J., Wandke, C., Merhof, D., Deussen, O., Csucs, G., Kutay, U., Horvath, P. (2012) Image Analysis of Nuclear Envelope Breakdown Events Using KNIME Computational Systems Biology (WCSB12)

Misselwitz, B., Barrett, N., Kreibich, S., Vonaesch, P., Andritschke, D., Rout, S., Weidner, K., Sormaz, M., Songhet, P., Horvath, P., Chabria, M., Vogel, V., Spori, D., Jenny, P., Hardt, W. (2012) Near surface swimming of Salmonella Typhimurium explains target-site selection and cooperative invasion PLoS Pathogens

Huotari, J., Meyer-Schaller, N., Katheder, N., Horvath, P., Helenius, A., Peter, M. (2012) Novel role of Cul3 in late endosome maturation Proc Natl Acad Sci USA

Lee, S., S., Horvath, P., Pelet, S., Hegemann, B., Lee, L., P., Peter, M. (2012) Quantitative and dynamic assay of single cell chemotaxis Integrative Biology

Yamauchi, Y., Boukari, H., Banerjee, I., Sbalzarini, I., F., Horvath, P., Helenius, A. (2011) Histone Deacetylase 8 is Required for Centrosome Cohesion and Influenza A Virus Entry PLoS Pathogens

Horvath, P., Wild, T., Kutay, U., Csucs, G. (2011) Machine learning improves the precision and robustness of high-content screens, using non-linear multi-parametric methods to analyze screening results J. Biomolecular Screening

Laurell, E., Beck, K., Krupina, K., Theerthagiri, G., Bodenmiller, B., Horvath, P., Abersold, R., Antonin, W., Kutay, U. (2011) Phosphorylation of Nup98 by multiple kinases is crucial for NPC disassembly during mitotic entry Cell. Volume 144, Issue 4, 18 February

Wild, T., Horvath, P., Wyler, E., Widmann, B., Badertscher, L., Zemp, I., Kozak, K., Csucs, G., Lund, E., Kutay, U. (2010) A protein inventory of human ribosome biogenesis reveals an essential function of Exportin 5 in 60S subunit export PLoS Biol 8:e1000522

Turgay, Y., Ungricht, R., Rothballer, A., Kiss, A., Csucs, G., Horvath, P., Kutay, U. (2010) A classical NLS and the SUN domain contribute to the targeting of SUN2 to the inner nuclear membrane EMBO Journal, 29, 2262 – 2275

Misselwitz, B., Strittmatter, G., Periaswamy, B., Schlumberger, M., C., Rout, S., Horvath, P., Kozak, K., Hardt, W. (2010) Enhanced CellClassifier: a multi-class classification tool for microscopy images BMC Bioinformatics 11: 30

Horvath, P., Jermyn, I., Kato, Z., Zerubia, J. (2009) A higher-order active contour model of a "gas of circles" and its application to tree crown extraction Pattern Recognition., 42(5):699-709