@article{MTMT:31794636,
	title = {Neuropilin-1 is a host factor for SARS-CoV-2 infection},
	url = {https://m2.mtmt.hu/api/publication/31794636},
	author = {Daly, James L. and Simonetti, Boris and Klein, Katja and Chen, Kai-En and Williamson, Maia Kavanagh and Anton-Plagaro, Carlos and Shoemark, Deborah K. and Simon-Gracia, Lorena and Bauer, Michael and Hollandi, Réka and Greber, Urs F. and Horváth, Péter and Sessions, Richard B. and Helenius, Ari and Hiscox, Julian A. and Teesalu, Tambet and Matthews, David A. and Davidson, Andrew D. and Collins, Brett M. and Cullen, Peter J. and Yamauchi, Yohei},
	doi = {10.1126/science.abd3072},
	journal-iso = {SCIENCE},
	journal = {SCIENCE},
	volume = {370},
	unique-id = {31794636},
	issn = {0036-8075},
	abstract = {Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative agent of coronavirus disease 2019 (COVID-19), uses the viral spike (S) protein for host cell attachment and entry. The host protease furin cleaves the full-length precursor S glycoprotein into two associated polypeptides: S1 and S2. Cleavage of S generates a polybasic Arg-Arg-Ala-Arg carboxyl-terminal sequence on S1, which conforms to a C-end rule (CendR) motif that binds to cell surface neuropilin-1 (NRP1) and NRP2 receptors. We used x-ray crystallography and biochemical approaches to show that the S1 CendR motif directly bound NRP1. Blocking this interaction by RNA interference or selective inhibitors reduced SARS-CoV-2 entry and infectivity in cell culture. NRP1 thus serves as a host factor for SARS-CoV-2 infection and may potentially provide a therapeutic target for COVID-19.},
	year = {2020},
	eissn = {1095-9203},
	pages = {861-865},
	orcid-numbers = {Daly, James L./0000-0002-4551-1256; Simonetti, Boris/0000-0002-0304-6640; Matthews, David A./0000-0003-4611-8795}
}

@article{MTMT:31334623,
	title = {nucleAIzer: A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer},
	url = {https://m2.mtmt.hu/api/publication/31334623},
	author = {Hollandi, Réka and Szkalisity, Ábel and Tóth, Tímea and Tasnádi, Ervin Áron and Molnár, Csaba and Mathe, Botond and Grexa, István and Molnár, József and Bálind, Árpád and Gorbe, Mate and Kovács, Mária and Migh, Ede and Goodman, Allen and Balassa, Tamás and Koós, Krisztián and Wang, Wenyu and Caicedo, Juan Carlos and Bara, Norbert and Kovács, Ferenc and Paavolainen, Lassi and Danka, Tivadar and Kriston, András and Carpenter, Anne Elizabeth and Smith, Kevin and Horváth, Péter},
	doi = {10.1016/j.cels.2020.04.003},
	journal-iso = {CELL SYST},
	journal = {CELL SYSTEMS},
	volume = {10},
	unique-id = {31334623},
	issn = {2405-4712},
	abstract = {Single-cell segmentation is typically a crucial task of image-based cellular analysis. We present nucleAIzer, a deep-learning approach aiming toward a truly general method for localizing 2D cell nuclei across a diverse range of assays and light microscopy modalities. We outperform the 739 methods submitted to the 2018 Data Science Bowl on images representing a variety of realistic conditions, some of which were not represented in the training data. The key to our approach is that during training nucleAIzer automatically adapts its nucleus-style model to unseen and unlabeled data using image style transfer to automatically generate augmented training samples. This allows the model to recognize nuclei in new and different experiments efficiently without requiring expert annotations, making deep learning for nucleus segmentation fairly simple and labor free for most biological light microscopy experiments. It can also be used online, integrated into CellProfiler and freely downloaded at www.nucleaizer.org. A record of this paper's transparent peer review process is included in the Supplemental Information.},
	year = {2020},
	eissn = {2405-4720},
	pages = {453-458},
	orcid-numbers = {Molnár, Csaba/0000-0002-6124-1209; Molnár, József/0000-0002-9185-9376}
}

@article{MTMT:3247398,
	title = {Advanced Cell Classifier: User-Friendly Machine-Learning-Based Software for Discovering Phenotypes in High-Content Imaging Data},
	url = {https://m2.mtmt.hu/api/publication/3247398},
	author = {Piccinini, F and Balassa, Tamás and Szkalisity, Ábel and Molnár, Csaba and Paavolainen, L and Kujala, K and Buzás, Krisztina and Sarazova, M and Pietiainen, V and Kutay, U and Smith, K and Horváth, Péter},
	doi = {10.1016/j.cels.2017.05.012},
	journal-iso = {CELL SYST},
	journal = {CELL SYSTEMS},
	volume = {4},
	unique-id = {3247398},
	issn = {2405-4712},
	abstract = {High-content, imaging-based screens now routinely generate data on a scale that precludes manual verification and interrogation. Software applying machine learning has become an essential tool to automate analysis, but these methods require annotated examples to learn from. Efficiently exploring large datasets to find relevant examples remains a challenging bottleneck. Here, we present Advanced Cell Classifier (ACC), a graphical software package for phenotypic analysis that addresses these difficulties. ACC applies machine-learning and image-analysis methods to high-content data generated by large-scale, cell-based experiments. It features methods to mine microscopic image data, discover new phenotypes, and improve recognition performance. We demonstrate that these features substantially expedite the training process, successfully uncover rare phenotypes, and improve the accuracy of the analysis. ACC is extensively documented, designed to be user-friendly for researchers without machine-learning expertise, and distributed as a free open-source tool at www.cellclassifier.org.},
	year = {2017},
	eissn = {2405-4720},
	pages = {651-655},
	orcid-numbers = {Molnár, Csaba/0000-0002-6124-1209; Buzás, Krisztina/0000-0001-8933-2033}
}

@article{MTMT:2896546,
	title = {CIDRE: an illumination-correction method for optical microscopy},
	url = {https://m2.mtmt.hu/api/publication/2896546},
	author = {Smith, K and Li, YP and Piccinini, F and Csucs, G and Balazs, C and Bevilacqua, A and Horváth, Péter},
	doi = {10.1038/NMETH.3323},
	journal-iso = {NAT METHODS},
	journal = {NATURE METHODS},
	volume = {12},
	unique-id = {2896546},
	issn = {1548-7091},
	abstract = {Uneven illumination affects every image acquired by a microscope. It is often overlooked, but it can introduce considerable bias to image measurements. The most reliable correction methods require special reference images, and retrospective alternatives do not fully model the correction process. Our approach overcomes these issues for most optical microscopy applications without the need for reference images.},
	year = {2015},
	eissn = {1548-7105},
	pages = {404-406}
}

@article{MTMT:2724011,
	title = {Active Learning Strategies for Phenotypic Profiling of High-Content Screens},
	url = {https://m2.mtmt.hu/api/publication/2724011},
	author = {Smith, K and Horváth, Péter},
	doi = {10.1177/1087057114527313},
	journal-iso = {J BIOMOL SCREEN},
	journal = {JOURNAL OF BIOMOLECULAR SCREENING},
	volume = {19},
	unique-id = {2724011},
	issn = {1087-0571},
	abstract = {High-content screening is a powerful method to discover new drugs and carry out basic biological research. Increasingly, high-content screens have come to rely on supervised machine learning (SML) to perform automatic phenotypic classification as an essential step of the analysis. However, this comes at a cost, namely, the labeled examples required to train the predictive model. Classification performance increases with the number of labeled examples, and because labeling examples demands time from an expert, the training process represents a significant time investment. Active learning strategies attempt to overcome this bottleneck by presenting the most relevant examples to the annotator, thereby achieving high accuracy while minimizing the cost of obtaining labeled data. In this article, we investigate the impact of active learning on single-cell-based phenotype recognition, using data from three large-scale RNA interference high-content screens representing diverse phenotypic profiling problems. We consider several combinations of active learning strategies and popular SML methods. Our results show that active learning significantly reduces the time cost and can be used to reveal the same phenotypic targets identified using SML. We also identify combinations of active learning strategies and SML methods which perform better than others on the phenotypic profiling problems we studied.},
	year = {2014},
	eissn = {1552-454X},
	pages = {685-695}
}