Selected Publications#

Publications (as of 01/12/2023)

Peter Horvath has published 128 peer-reviewed scientific articles, with an h-index of 44, the cumulative impact factor of 1346.5, and 13339 citations (Google Scholar – https://scholar.google.hu/citations?user=R4hqVckAAAAJ&hl=en). Relevant selected publications are summarized below. The asterisk indicates co-corresponding authorship.



Hirling, D., Tasnadi, E., Caicedo, J., Caroprese M.V., Sjögren R., Aubreville M., Koos, K., & Horvath, P. (2023) Segmentation metric misinterpretations in bioimage analysis, Nature Methods P:1-4, IF: 48

This paper describes how image segmentation metrics should be used, introduces a general notation system and highlights the importance of their proper use.



Hollandi, R., Moshkov, N., Paavolainen L., Tasnadi, E., Piccinini, F., Horvath, P. ; (2022) Nucleus segmentation: towards automated solutions; Trends in Cell Biology, (32) 4, IF: 19,

They reviewed the most recent deep learning single-cell segmentation methods, gave a detailed benchmark, and developed a web portal where one can interactively select the most appropriate tool.



Mund, A., Coscia, F., Hollandi, R., Kovacs, F., Kriston, A., Brunner, A-D., Bzorek, M., Naimy, S., Gjerdrum, L. M. R., Dyring-Andersen, B., Bulkescher, J., Lukas, C., Gnann, C., Lundberg, E., Horvath, P.*& Mann, M.*, (2022) Deep Visual Proteomics defines single-cell identity and heterogeneity; Nature Biotechnology 40, 1231-1240, IF: 46.9

This paper introduces the Deep Visual Proteomics concept, which combines deep learning, single cell isolation and ultrasensitive proteomics, in order to molecularly and morphologically characterize a cell that is selected in its native cellular environment.



Szkalisity, A., Piccinini, F., Beleon, A., Balassa, T., Varga, I.G., Migh, E., Molnar, Cs., Paavolainen, L., Timonen, S., Banerjee, I., Ikonen, E., Yamauchi, Y., Ando, I., Peltonen, J., Pietiäinen, V., Honti, V., Horvath, P. (2021) Regression plane concept for analysing continuous cellular processes with machine learning; Nature communications 12 (1), 1-9, IF: 14.919

A continuous manner for single cell phenotyping was presented using a multi parametric regression model that provides a new way in order to consider the ever morphological changing state of the cell.



Koos, K., Olah, G., Balassa, T., Mihut, N., Rozsa, M., Ozsvar, A., Tasnadi, E., Barzo, P., Farago, N., Puskas, L., Molnar, G., Molnar, J., Tamas, G., Horvath, P. (2021) Automatic deep learning-driven label-free image-guided patch clamp system; Nature communications 12 (1), 1-11 2,IF: 14.919

This paper presents the first fully automated patch clamp robot by combining using video microscopy, deep learning, tracking and robot control tools. The analyzed single-cell is selected and approached by the machine fully autonomously.



Hollandi, R., Szkalisity, A., Toth, T., Tasnadi, E., Molnar, Cs., Mathe, B., Grexa, I., Molnar, J., Balind A., Gorbe, M., Kovacs, M., Migh, E., Goodman, A., Balassa, T., Koos, K., Wang, W., Caicedo, J. C., Bara, N., Kovacs, F., Paavolainen, L., Danka, T., Kriston, A., Carpenter, A. E., Smith K., Horvath, P. (2020) nucleAIzer: A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer, Cell Systems 10 (5), 453-458. e6, IF: 10.304

A deep learning workflow was presented that learns from the never seen data so that it synthesizes instances from the incoming images and adopts itself onto the data. The model reached the highest score on the DSB 2018 competition.



Brasko, C., Smith, K., Molnar, Cs., Farago, N., Hegedus, L., Balind, A., Balassa, T., Szkalisity, A., Sukosd, F., Kocsis, K., Balint, B., Paavolainen, L., Enyedi, M. Z., Nagy, I., Puskas, L.G., Haracska, L., Tamas, G., Horvath P. (2018) Intelligent image-based in situ single-cell isolation. Nature communications 9 (1), 226, IF:11.878

The CAMI technique was presented here, that is a deep learning driven single-cell isolation concept. It connects two microscopes, of which one is a micromanipulator and selects cells that may be molecularly characterized. In this early work we present DNA and RNA sequencing of the selected cells.



Carragher, N., Piccinini, F., Tesei, A., Trask, J., Bickle, M., Horvath, P. (2018)

Concerns, challenges and promises of high-content analysis of 3D cellular models.

Nature Reviews Drug Discovery 17 (8), 606-606 IF: 57.618

This paper discusses the SWOT of 3 dimensional organoid screening, highlights advantages, and defines upcoming challenges of the field.



Horvath, P., Aulner, N., Bickle, M., Davies, A., Del Nery, E., Ebner, D., Montoya, M., Ostling, P., Pietiainen, V., Price, L., Shorte, S., Turcatti, G., von Schantz, C., Carragher, N. (2016) Screening out irrelevant cell-based models of disease, Nature reviews Drug discovery 15 (11), 751-769, IF:47.120

Peter Horvath initiated a new society, -the EUCAI- and with other members from Europe we reviewed and commented on problems in disease models and screening. This work had an impact in creating new topics for the H2020 program.



Smith K., Li Y., Piccinini, F., Csucs G., Balazs C., Bevilacqua A., Horvath, P. (2015) CIDRE: an illumination-correction method for optical microscopy. Nature Methods 12 (5), 404-406, IF:25.328

This paper introduces a novel image improvement technique that removes the illumination defects of microscopes by using an energy minimization technique. The method is the state of the art in microscopy image correction.