Search

Your search keyword '"Migh E"' showing total 2 results
Start Over Author "Migh E" Topic biological phenomena
2 results on '"Migh E"'

1. Regression plane concept for analysing continuous cellular processes with machine learning.

Author

Szkalisity A, Piccinini F, Beleon A, Balassa T, Varga IG, Migh E, Molnar C, Paavolainen L, Timonen S, Banerjee I, Ikonen E, Yamauchi Y, Ando I, Peltonen J, Pietiäinen V, Honti V, and Horvath P

Subjects
Animals, Carcinoma, Hepatocellular, Cell Cycle, Cell Differentiation, Cell Line, Tumor, Drosophila melanogaster, Humans, Membrane Proteins, Supervised Machine Learning, Biological Phenomena, Cell Physiological Phenomena, Machine Learning
Abstract

Biological processes are inherently continuous, and the chance of phenotypic discovery is significantly restricted by discretising them. Using multi-parametric active regression we introduce the Regression Plane (RP), a user-friendly discovery tool enabling class-free phenotypic supervised machine learning, to describe and explore biological data in a continuous manner. First, we compare traditional classification with regression in a simulated experimental setup. Second, we use our framework to identify genes involved in regulating triglyceride levels in human cells. Subsequently, we analyse a time-lapse dataset on mitosis to demonstrate that the proposed methodology is capable of modelling complex processes at infinite resolution. Finally, we show that hemocyte differentiation in Drosophila melanogaster has continuous characteristics.

Published
2021
Full Text
View/download PDF

2. Regression plane concept for analysing continuous cellular processes with machine learning

Author

Csaba Molnar, Attila Beleon, Vilja Pietiäinen, Lassi Paavolainen, Tamas Balassa, Jaakko Peltonen, Istvan Gergely Varga, Elina Ikonen, Indranil Banerjee, Sanna Timonen, Ede Migh, Yohei Yamauchi, Filippo Piccinini, Abel Szkalisity, Peter Horvath, István Andó, Viktor Honti, STEMM - Stem Cells and Metabolism Research Program, Research Programs Unit, Faculty of Medicine, University of Helsinki, Institute for Molecular Medicine Finland, Helsinki Institute of Life Science HiLIFE, TRIMM - Translational Immunology Research Program, Computational Systems Medicine, Department of Anatomy, Lipid Trafficking Lab, Precision Systems Medicine, Szkalisity A., Piccinini F., Beleon A., Balassa T., Varga I.G., Migh E., Molnar C., Paavolainen L., Timonen S., Banerjee I., Ikonen E., Yamauchi Y., Ando I., Peltonen J., Pietiainen V., Honti V., Horvath P., Hungarian Academy of Sciences, IRCCS Istituto scientifico romagnolo per lo studio e la cura dei tumori - Meldola (FC), Indian Institute of Science Education and Research Mohali, University of Bristol, Probabilistic Machine Learning, Department of Computer Science, Aalto-yliopisto, Aalto University, Tampere University, and Computing Sciences

Subjects
0301 basic medicine, BLOOD, Computer science, Hemocyte differentiation, General Physics and Astronomy, SOFTWARE, computer.software_genre, Machine Learning, 0302 clinical medicine, Software, HEMOCYTE LINEAGES, ENCAPSULATION, Membrane Protein, Biological Phenomena, Data processing, Biological data, Multidisciplinary, Cell Cycle, Cell Differentiation, Regression, DROSOPHILA, Drosophila melanogaster, Supervised Machine Learning, Human, Carcinoma, Hepatocellular, STRATEGIES, Science, Image processing, IMMUNITY, Machine learning, General Biochemistry, Genetics and Molecular Biology, Article, MECHANISMS, Cell Physiological Phenomena, 03 medical and health sciences, Cell Line, Tumor, Classifier (linguistics), COMPARTMENTS, Animals, Humans, Animal, Plane (geometry), business.industry, Membrane Proteins, General Chemistry, 113 Computer and information sciences, FRAMEWORK, 030104 developmental biology, ComputingMethodologies_PATTERNRECOGNITION, Artificial intelligence, 3111 Biomedicine, business, computer, 030217 neurology & neurosurgery
Abstract

Biological processes are inherently continuous, and the chance of phenotypic discovery is significantly restricted by discretising them. Using multi-parametric active regression we introduce the Regression Plane (RP), a user-friendly discovery tool enabling class-free phenotypic supervised machine learning, to describe and explore biological data in a continuous manner. First, we compare traditional classification with regression in a simulated experimental setup. Second, we use our framework to identify genes involved in regulating triglyceride levels in human cells. Subsequently, we analyse a time-lapse dataset on mitosis to demonstrate that the proposed methodology is capable of modelling complex processes at infinite resolution. Finally, we show that hemocyte differentiation in Drosophila melanogaster has continuous characteristics., High-content screening prompted the development of software enabling discrete phenotypic analysis of single cells. Here, the authors show that supervised continuous machine learning can drive novel discoveries in diverse imaging experiments and present the Regression Plane module of Advanced Cell Classifier.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results