User login
Deep learning can be used to determine how murine hematopoietic stem and progenitor cells (HSPCs) will differentiate, according to research published in Nature Methods.
Deep learning algorithms simulate the learning processes in people using artificial neural networks.
Researchers have reported the development of software that uses deep learning to predict which type of cell murine HSPCs will differentiate into, based on microscopy images.
“A hematopoietic stem cell’s decision to become a certain cell type cannot be observed,” said study author Carsten Marr, PhD, of Helmholtz Zentrum München–German Research Center for Environmental Health in Neuherberg, Germany.
“At this time, it is only possible to verify the decision retrospectively with cell surface markers.”
Therefore, Dr Marr and his team set out to develop an algorithm that can predict the decision in advance, and deep learning was key.
“Deep neural networks play a major role in our method,” Dr Marr said. “Our algorithm classifies light microscopic images and videos of individual cells by comparing these data with past experience from the development of such cells. In this way, the algorithm ‘learns’ how certain cells behave.”
Specifically, the researchers examined murine HSPCs filmed under a microscope in the lab. Using information on the cells’ appearance and speed, the software was able to “memorize” the corresponding behavior patterns and then make its prediction.
“Compared to conventional methods, such as fluorescent antibodies against certain surface proteins, we know how the cells will decide 3 cell generations earlier,” said Felix Buggenthin, PhD, of Helmholtz Zentrum München–German Research Center for Environmental Health.
“Since we now know which cells will develop in which way, we can isolate them earlier than before and examine how they differ at a molecular level,” Dr Marr added. “We want to use this information to understand how the choices are made for particular developmental traits.” 
Deep learning can be used to determine how murine hematopoietic stem and progenitor cells (HSPCs) will differentiate, according to research published in Nature Methods.
Deep learning algorithms simulate the learning processes in people using artificial neural networks.
Researchers have reported the development of software that uses deep learning to predict which type of cell murine HSPCs will differentiate into, based on microscopy images.
“A hematopoietic stem cell’s decision to become a certain cell type cannot be observed,” said study author Carsten Marr, PhD, of Helmholtz Zentrum München–German Research Center for Environmental Health in Neuherberg, Germany.
“At this time, it is only possible to verify the decision retrospectively with cell surface markers.”
Therefore, Dr Marr and his team set out to develop an algorithm that can predict the decision in advance, and deep learning was key.
“Deep neural networks play a major role in our method,” Dr Marr said. “Our algorithm classifies light microscopic images and videos of individual cells by comparing these data with past experience from the development of such cells. In this way, the algorithm ‘learns’ how certain cells behave.”
Specifically, the researchers examined murine HSPCs filmed under a microscope in the lab. Using information on the cells’ appearance and speed, the software was able to “memorize” the corresponding behavior patterns and then make its prediction.
“Compared to conventional methods, such as fluorescent antibodies against certain surface proteins, we know how the cells will decide 3 cell generations earlier,” said Felix Buggenthin, PhD, of Helmholtz Zentrum München–German Research Center for Environmental Health.
“Since we now know which cells will develop in which way, we can isolate them earlier than before and examine how they differ at a molecular level,” Dr Marr added. “We want to use this information to understand how the choices are made for particular developmental traits.”
Deep learning can be used to determine how murine hematopoietic stem and progenitor cells (HSPCs) will differentiate, according to research published in Nature Methods.
Deep learning algorithms simulate the learning processes in people using artificial neural networks.
Researchers have reported the development of software that uses deep learning to predict which type of cell murine HSPCs will differentiate into, based on microscopy images.
“A hematopoietic stem cell’s decision to become a certain cell type cannot be observed,” said study author Carsten Marr, PhD, of Helmholtz Zentrum München–German Research Center for Environmental Health in Neuherberg, Germany.
“At this time, it is only possible to verify the decision retrospectively with cell surface markers.”
Therefore, Dr Marr and his team set out to develop an algorithm that can predict the decision in advance, and deep learning was key.
“Deep neural networks play a major role in our method,” Dr Marr said. “Our algorithm classifies light microscopic images and videos of individual cells by comparing these data with past experience from the development of such cells. In this way, the algorithm ‘learns’ how certain cells behave.”
Specifically, the researchers examined murine HSPCs filmed under a microscope in the lab. Using information on the cells’ appearance and speed, the software was able to “memorize” the corresponding behavior patterns and then make its prediction.
“Compared to conventional methods, such as fluorescent antibodies against certain surface proteins, we know how the cells will decide 3 cell generations earlier,” said Felix Buggenthin, PhD, of Helmholtz Zentrum München–German Research Center for Environmental Health.
“Since we now know which cells will develop in which way, we can isolate them earlier than before and examine how they differ at a molecular level,” Dr Marr added. “We want to use this information to understand how the choices are made for particular developmental traits.”