@article{MTMT:34786803, title = {SuperCUT, an unsupervised multimodal image registration with deep learning for biomedical microscopy}, url = {https://m2.mtmt.hu/api/publication/34786803}, author = {Grexa, István and Iván, Zsanett Zsófia and Migh, Ede and Kovács, Ferenc and Bolck, Hella A and Zheng, Xiang and Mund, Andreas and Moshkov, Nikita and Csapóné Miczán, Vivien and Koós, Krisztián and Horváth, Péter}, doi = {10.1093/bib/bbae029}, journal-iso = {BRIEF BIOINFORM}, journal = {BRIEFINGS IN BIOINFORMATICS}, volume = {25}, unique-id = {34786803}, issn = {1467-5463}, abstract = {Numerous imaging techniques are available for observing and interrogating biological samples, and several of them can be used consecutively to enable correlative analysis of different image modalities with varying resolutions and the inclusion of structural or molecular information. Achieving accurate registration of multimodal images is essential for the correlative analysis process, but it remains a challenging computer vision task with no widely accepted solution. Moreover, supervised registration methods require annotated data produced by experts, which is limited. To address this challenge, we propose a general unsupervised pipeline for multimodal image registration using deep learning. We provide a comprehensive evaluation of the proposed pipeline versus the current state-of-the-art image registration and style transfer methods on four types of biological problems utilizing different microscopy modalities. We found that style transfer of modality domains paired with fully unsupervised training leads to comparable image registration accuracy to supervised methods and, most importantly, does not require human intervention.}, year = {2024}, eissn = {1477-4054}, orcid-numbers = {Mund, Andreas/0000-0002-7843-5341} } @article{MTMT:34782532, title = {Learning representations for image-based profiling of perturbations}, url = {https://m2.mtmt.hu/api/publication/34782532}, author = {Moshkov, Nikita and Bornholdt, Michael and Benoit, Santiago and Smith, Matthew and Mcquin, Claire and Goodman, Allen and Senft, Rebecca A. and Han, Yu and Babadi, Mehrtash and Horváth, Péter and Cimini, Beth A. and Carpenter, Anne E. and Singh, Shantanu and Caicedo, Juan C.}, doi = {10.1038/s41467-024-45999-1}, journal-iso = {NAT COMMUN}, journal = {NATURE COMMUNICATIONS}, volume = {15}, unique-id = {34782532}, issn = {2041-1723}, abstract = {Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient. Assessing cell phenotypes in image-based assays requires solid computational methods for transforming images into quantitative data. Here, the authors present a strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation.}, year = {2024}, eissn = {2041-1723} } @article{MTMT:34395398, title = {Role of the kisspeptin-KISS1R axis in the pathogenesis of chronic kidney disease and uremic cardiomyopathy}, url = {https://m2.mtmt.hu/api/publication/34395398}, author = {Dinh, Hoa and Kovács, Zsuzsanna and Kis, Merse and Kupecz, Klaudia and Sejben, Anita and Szűcs, Gergő and Márványkövi, Fanni and Siska, Andrea and Freiwan, Marah and Pósa, Szonja Polett and Galla, Zsolt and Ibos, Katalin Eszter and Bodnár, Éva and Lauber, Gülsüm Yilmaz and Goncalves, Ana Isabel Antunes and Acar, Eylem and Kriston, András and Kovács, Ferenc and Horváth, Péter and Bozsó, Zsolt and Tóth, Gábor and Földesi, Imre and Monostori, Péter and Cserni, Gábor and Podesser, Bruno K. and Lehoczki, Andrea Marianna and Pokreisz, Peter and Kiss, Attila and Dux, László and Csabafi, Krisztina and Sárközy, Márta}, doi = {10.1007/s11357-023-01017-8}, journal-iso = {GEROSCIENCE}, journal = {GEROSCIENCE: OFFICIAL JOURNAL OF THE AMERICAN AGING ASSOCIATION (AGE)}, volume = {46}, unique-id = {34395398}, issn = {2509-2715}, abstract = {The prevalence of chronic kidney disease (CKD) is increasing globally, especially in elderly patients. Uremic cardiomyopathy is a common cardiovascular complication of CKD, characterized by left ventricular hypertrophy (LVH), diastolic dysfunction, and fibrosis. Kisspeptins and their receptor, KISS1R, exert a pivotal influence on kidney pathophysiology and modulate age-related pathologies across various organ systems. KISS1R agonists, including kisspeptin-13 (KP-13), hold promise as novel therapeutic agents within age-related biological processes and kidney-related disorders. Our investigation aimed to elucidate the impact of KP-13 on the trajectory of CKD and uremic cardiomyopathy. Male Wistar rats (300–350 g) were randomized into four groups: (I) sham-operated, (II) 5/6 nephrectomy-induced CKD, (III) CKD subjected to a low dose of KP-13 (intraperitoneal 13 µg/day), and (IV) CKD treated with a higher KP-13 dose (intraperitoneal 26 µg/day). Treatments were administered daily from week 3 for 10 days. After 13 weeks, KP-13 increased systemic blood pressure, accentuating diastolic dysfunction’s echocardiographic indicators and intensifying CKD-associated markers such as serum urea levels, glomerular hypertrophy, and tubular dilation. Notably, KP-13 did not exacerbate circulatory uremic toxin levels, renal inflammation, or fibrosis markers. In contrast, the higher KP-13 dose correlated with reduced posterior and anterior wall thickness, coupled with diminished cardiomyocyte cross-sectional areas and concurrent elevation of inflammatory ( Il6, Tnf ), fibrosis ( Col1 ), and apoptosis markers ( Bax/Bcl2 ) relative to the CKD group. In summary, KP-13’s influence on CKD and uremic cardiomyopathy encompassed heightened blood pressure and potentially activated inflammatory and apoptotic pathways in the left ventricle.}, year = {2024}, eissn = {2509-2723}, pages = {2463-2488}, orcid-numbers = {Kovács, Zsuzsanna/0000-0002-4197-4579; Sejben, Anita/0000-0002-9434-2989; Szűcs, Gergő/0000-0003-1874-2718; Márványkövi, Fanni/0000-0002-5114-1319; Pósa, Szonja Polett/0000-0002-7535-9689; Galla, Zsolt/0000-0002-9166-1212; Ibos, Katalin Eszter/0000-0001-5243-9945; Goncalves, Ana Isabel Antunes/0009-0009-3428-3321; Acar, Eylem/0000-0002-0599-6893; Kriston, András/0000-0001-8500-4315; Bozsó, Zsolt/0000-0002-5713-3096; Tóth, Gábor/0000-0002-3604-4385; Földesi, Imre/0000-0002-3329-8136; Monostori, Péter/0000-0003-3591-6054; Cserni, Gábor/0000-0003-1344-7744; Podesser, Bruno K./0000-0002-4641-7202; Lehoczki, Andrea Marianna/0000-0002-4285-7518; Pokreisz, Peter/0000-0003-2810-9000; Kiss, Attila/0000-0003-4652-1998; Dux, László/0000-0002-1270-1678; Csabafi, Krisztina/0000-0002-2008-7604; Sárközy, Márta/0000-0002-5929-2146} } @article{MTMT:34080269, title = {Segmentation metric misinterpretations in bioimage analysis}, url = {https://m2.mtmt.hu/api/publication/34080269}, author = {Hirling, Dominik and Tasnádi, Ervin Áron and Caicedo, Juan and Caroprese, Maria V. and Sjögren, Rickard and Aubreville, Marc and Koós, Krisztián and Horváth, Péter}, doi = {10.1038/s41592-023-01942-8}, journal-iso = {NAT METHODS}, journal = {NATURE METHODS}, volume = {21}, unique-id = {34080269}, issn = {1548-7091}, abstract = {Quantitative evaluation of image segmentation algorithms is crucial in the field of bioimage analysis. The most common assessment scores, however, are often misinterpreted and multiple definitions coexist with the same name. Here we present the ambiguities of evaluation metrics for segmentation algorithms and show how these misinterpretations can alter leaderboards of influential competitions. We also propose guidelines for how the currently existing problems could be tackled.}, year = {2024}, eissn = {1548-7105}, pages = {213-216}, orcid-numbers = {Aubreville, Marc/0000-0002-5294-5247} } @article{MTMT:34436978, title = {Mitochondrial and immune response dysregulation in melanoma recurrence}, url = {https://m2.mtmt.hu/api/publication/34436978}, author = {Szadai, Leticia and Guedes, Jéssica de Siqueira and Woldmar, Nicole and de Almeida, Natália Pinto and Jánosi, Ágnes Judit and Rajeh, Ahmad and Kovács, Ferenc and Kriston, András and Migh, Ede and Wan, Guihong and Nguyen, Nga and Oskolás, Henriett and Appelqvist, Roger and Nogueira, Fábio Cn and Domont, Gilberto B and Yu, Kun-Hsing and Semenov, Eugene R and Malm, Johan and Rezeli, Melinda and Wieslander, Elisabet and Fenyö, David and Kemény, Lajos and Horváth, Péter and Németh, István Balázs and Marko-Varga, György and Gil, Jeovanis}, doi = {10.1002/ctm2.1495}, journal-iso = {CLIN TRANSL MED}, journal = {CLINICAL AND TRANSLATIONAL MEDICINE}, volume = {13}, unique-id = {34436978}, issn = {2001-1326}, year = {2023}, eissn = {2001-1326}, orcid-numbers = {Kemény, Lajos/0000-0002-2119-9501} } @article{MTMT:34417027, title = {Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation - A meta-analysis.}, url = {https://m2.mtmt.hu/api/publication/34417027}, author = {Bukva, Mátyás and Dobra, Gabriella and Gyukity-Sebestyén, Edina and Böröczky, Timea and Korsós, Marietta Margaréta and David G, Meckes and Horváth, Péter and Buzás, Krisztina and Harmati, Mária}, doi = {10.1186/s12964-023-01344-5}, journal-iso = {CELL COMM SIGN}, journal = {CELL COMMUNICATION AND SIGNALING}, volume = {21}, unique-id = {34417027}, issn = {1478-811X}, abstract = {Although interest in the role of extracellular vesicles (EV) in oncology is growing, not all potential aspects have been investigated. In this meta-analysis, data regarding (i) the EV proteome and (ii) the invasion and proliferation capacity of the NCI-60 tumor cell lines (60 cell lines from nine different tumor types) were analyzed using machine learning methods.On the basis of the entire proteome or the proteins shared by all EV samples, 60 cell lines were classified into the nine tumor types using multiple logistic regression. Then, utilizing the Least Absolute Shrinkage and Selection Operator, we constructed a discriminative protein panel, upon which the samples were reclassified and pathway analyses were performed. These panels were validated using clinical data (n = 4,665) from Human Protein Atlas.Classification models based on the entire proteome, shared proteins, and discriminative protein panel were able to distinguish the nine tumor types with 49.15%, 69.10%, and 91.68% accuracy, respectively. Invasion and proliferation capacity of the 60 cell lines were predicted with R2 = 0.68 and R2 = 0.62 (p < 0.0001). The results of the Reactome pathway analysis of the discriminative protein panel suggest that the molecular content of EVs might be indicative of tumor-specific biological processes.Integrating in vitro EV proteomic data, cell physiological characteristics, and clinical data of various tumor types illuminates the diagnostic, prognostic, and therapeutic potential of EVs. Video Abstract.}, keywords = {CLASSIFICATION; PROLIFERATION; INVASION; PREDICTION; machine learning; Extracellular vesicles; NCI-60; [Meta-analysis]}, year = {2023}, eissn = {1478-811X}, orcid-numbers = {Bukva, Mátyás/0000-0002-5225-0285; Dobra, Gabriella/0000-0002-2814-7720; Gyukity-Sebestyén, Edina/0000-0003-1383-6301; Böröczky, Timea/0009-0009-3390-7809; Buzás, Krisztina/0000-0001-8933-2033; Harmati, Mária/0000-0002-4875-5723} } @article{MTMT:34334191, title = {Structure preserving adversarial generation of labeled training samples for single-cell segmentation}, url = {https://m2.mtmt.hu/api/publication/34334191}, author = {Tasnádi, Ervin Áron and Sliz-Nagy, Alex and Horváth, Péter}, doi = {10.1016/j.crmeth.2023.100592}, journal-iso = {CELL REP METH}, journal = {CELL REPORTS METHODS}, volume = {3}, unique-id = {34334191}, abstract = {We introduce a generative data augmentation strategy to improve the accuracy of instance segmentation of microscopy data for complex tissue structures. Our pipeline uses regular and conditional generative adver-sarial networks (GANs) for image-to-image translation to construct synthetic microscopy images along with their corresponding masks to simulate the distribution and shape of the objects and their appearance. The synthetic samples are then used for training an instance segmentation network (for example, StarDist or Cell -pose). We show on two single-cell-resolution tissue datasets that our method improves the accuracy of downstream instance segmentation tasks compared with traditional training strategies using either the raw data or basic augmentations. We also compare the quality of the object masks with those generated by a traditional cell population simulation method, finding that our synthesized masks are closer to the ground truth considering Fre ' chet inception distances.}, keywords = {Biochemical Research Methods; Nucleus segmentation}, year = {2023}, eissn = {2667-2375} } @article{MTMT:34123594, title = {The kisspeptin-1 receptor antagonist peptide-234 aggravates uremic cardiomyopathy in a rat model}, url = {https://m2.mtmt.hu/api/publication/34123594}, author = {Dinh, Hoa and Kovács, Zsuzsanna and Márványkövi, Fanni and Kis, Merse and Kupecz, Klaudia and Szűcs, Gergő and Freiwan, Marah and Lauber, Gülsüm Yilmaz and Acar, Eylem and Siska, Andrea and Ibos, Katalin Eszter and Bodnár, Éva and Kriston, András and Kovács, Ferenc and Horváth, Péter and Földesi, Imre and Cserni, Gábor and Podesser, Bruno K. and Pokreisz, Peter and Kiss, Attila and Dux, László and Csabafi, Krisztina and Sárközy, Márta}, doi = {10.1038/s41598-023-41037-0}, journal-iso = {SCI REP}, journal = {SCIENTIFIC REPORTS}, volume = {13}, unique-id = {34123594}, issn = {2045-2322}, abstract = {Uremic cardiomyopathy is characterized by diastolic dysfunction, left ventricular hypertrophy (LVH), and fibrosis. Dysregulation of the kisspeptin receptor (KISS1R)-mediated pathways are associated with the development of fibrosis in cancerous diseases. Here, we investigated the effects of the KISS1R antagonist peptide-234 (P234) on the development of uremic cardiomyopathy. Male Wistar rats (300–350 g) were randomized into four groups: (i) Sham, (ii) chronic kidney disease (CKD) induced by 5/6 nephrectomy, (iii) CKD treated with a lower dose of P234 ( ip. 13 µg/day), (iv) CKD treated with a higher dose of P234 ( ip. 26 µg/day). Treatments were administered daily from week 3 for 10 days. At week 13, the P234 administration did not influence the creatinine clearance and urinary protein excretion. However, the higher dose of P234 led to reduced anterior and posterior wall thicknesses, more severe interstitial fibrosis, and overexpression of genes associated with left ventricular remodeling ( Ctgf, Tgfb, Col3a1, Mmp9 ), stretch ( Nppa ), and apoptosis ( Bax, Bcl2, Casp7 ) compared to the CKD group. In contrast, no significant differences were found in the expressions of apoptosis-associated proteins between the groups. Our results suggest that the higher dose of P234 hastens the development and pathophysiology of uremic cardiomyopathy by activating the fibrotic TGF-β-mediated pathways.}, year = {2023}, eissn = {2045-2322}, orcid-numbers = {Kovács, Zsuzsanna/0000-0002-4197-4579; Márványkövi, Fanni/0000-0002-5114-1319; Szűcs, Gergő/0000-0003-1874-2718; Ibos, Katalin Eszter/0000-0001-5243-9945; Földesi, Imre/0000-0002-3329-8136; Cserni, Gábor/0000-0003-1344-7744; Dux, László/0000-0002-1270-1678; Csabafi, Krisztina/0000-0002-2008-7604; Sárközy, Márta/0000-0002-5929-2146} } @article{MTMT:34107493, title = {Image-based and machine learning-guided multiplexed serology test for SARS-CoV-2}, url = {https://m2.mtmt.hu/api/publication/34107493}, author = {Pietiäinen, Vilja and Polso, Minttu and Migh, Ede and Guckelsberger, Christian and Harmati, Mária and Diósdi, Ákos and Turunen, Laura and Hassinen, Antti and Potdar, Swapnil and Koponen, Annika and Gyukity-Sebestyén, Edina and Kovács, Ferenc and Kriston, András and Hollandi, Réka and Burián, Katalin and Terhes, Gabriella and Visnyovszki, Ádám and Fodor, Eszter and Lacza, Zsombor and Kantele, Anu and Kolehmainen, Pekka and Kakkola, Laura and Strandin, Tomas and Levanov, Lev and Kallioniemi, Olli and Kemény, Lajos and Julkunen, Ilkka and Vapalahti, Olli and Buzás, Krisztina and Paavolainen, Lassi and Horváth, Péter and Hepojoki, Jussi}, doi = {10.1016/j.crmeth.2023.100565}, journal-iso = {CELL REP METH}, journal = {CELL REPORTS METHODS}, volume = {3}, unique-id = {34107493}, year = {2023}, eissn = {2667-2375}, orcid-numbers = {Harmati, Mária/0000-0002-4875-5723; Gyukity-Sebestyén, Edina/0000-0003-1383-6301; Burián, Katalin/0000-0003-1300-2374; Terhes, Gabriella/0000-0002-7301-9672; Kemény, Lajos/0000-0002-2119-9501; Buzás, Krisztina/0000-0001-8933-2033} } @article{MTMT:34024053, title = {An integrated cell atlas of the lung in health and disease}, url = {https://m2.mtmt.hu/api/publication/34024053}, author = {Sikkema, L. and Ramírez-Suástegui, C. and Strobl, D.C. and Gillett, T.E. and Zappia, L. and Madissoon, E. and Markov, N.S. and Zaragosi, L.-E. and Ji, Y. and Ansari, M. and Arguel, M.-J. and Apperloo, L. and Banchero, M. and Bécavin, C. and Berg, M. and Chichelnitskiy, E. and Chung, M.-I. and Collin, A. and Gay, A.C.A. and Gote-Schniering, J. and Hooshiar, Kashani B. and Inecik, K. and Jain, M. and Kapellos, T.S. and Kole, T.M. and Leroy, S. and Mayr, C.H. and Oliver, A.J. and von, Papen M. and Peter, L. and Taylor, C.J. and Walzthoeni, T. and Xu, C. and Bui, L.T. and De, Donno C. and Dony, L. and Faiz, A. and Guo, M. and Gutierrez, A.J. and Heumos, L. and Huang, N. and Ibarra, I.L. and Jackson, N.D. and Kadur, Lakshminarasimha Murthy P. and Lotfollahi, M. and Tabib, T. and Talavera-López, C. and Travaglini, K.J. and Wilbrey-Clark, A. and Worlock, K.B. and Yoshida, M. and Chen, Y. and Hagood, J.S. and Agami, A. and Horváth, Péter and Lundeberg, J. and Marquette, C.-H. and Pryhuber, G. and Samakovlis, C. and Sun, X. and Ware, L.B. and Zhang, K. and van, den Berge M. and Bossé, Y. and Desai, T.J. and Eickelberg, O. and Kaminski, N. and Krasnow, M.A. and Lafyatis, R. and Nikolic, M.Z. and Powell, J.E. and Rajagopal, J. and Rojas, M. and Rozenblatt-Rosen, O. and Seibold, M.A. and Sheppard, D. and Shepherd, D.P. and Sin, D.D. and Timens, W. and Tsankov, A.M. and Whitsett, J. and Xu, Y. and Banovich, N.E. and Barbry, P. and Duong, T.E. and Falk, C.S. and Meyer, K.B. and Kropski, J.A. and Pe’er, D. and Schiller, H.B. and Tata, P.R. and Schultze, J.L. and Teichmann, S.A. and Misharin, A.V. and Nawijn, M.C. and Luecken, M.D. and Theis, F.J. and Lung, Biological Network Consortium}, doi = {10.1038/s41591-023-02327-2}, journal-iso = {NAT MED}, journal = {NATURE MEDICINE}, volume = {29}, unique-id = {34024053}, issn = {1078-8956}, abstract = {Single-cell technologies have transformed our understanding of human tissues. Yet, studies typically capture only a limited number of donors and disagree on cell type definitions. Integrating many single-cell datasets can address these limitations of individual studies and capture the variability present in the population. Here we present the integrated Human Lung Cell Atlas (HLCA), combining 49 datasets of the human respiratory system into a single atlas spanning over 2.4 million cells from 486 individuals. The HLCA presents a consensus cell type re-annotation with matching marker genes, including annotations of rare and previously undescribed cell types. Leveraging the number and diversity of individuals in the HLCA, we identify gene modules that are associated with demographic covariates such as age, sex and body mass index, as well as gene modules changing expression along the proximal-to-distal axis of the bronchial tree. Mapping new data to the HLCA enables rapid data annotation and interpretation. Using the HLCA as a reference for the study of disease, we identify shared cell states across multiple lung diseases, including SPP1 + profibrotic monocyte-derived macrophages in COVID-19, pulmonary fibrosis and lung carcinoma. Overall, the HLCA serves as an example for the development and use of large-scale, cross-dataset organ atlases within the Human Cell Atlas. © 2023, The Author(s).}, year = {2023}, eissn = {1546-170X}, pages = {1563-1577} }