A New Method That Reconstructs Continuous Biological Processes

Scientists at the Helmholtz Zentrum München have created a new method that reconstructs continuous biological processes. The study was published in ‘Nature Communications.’
Today, life science is generating massive data in very short cycles. Making that data suitable and controllable for evaluation is the goal of the researchers at the Helmholtz Zentrum München’s Institute of Computational Biology. With that in mind, Dr. Alexander Wolf and his colleague are attempting to create software that handles this evaluation.
According to Wolf, the study dealt with the issues that software is unable to assign image data to continuous processes. For instance, it is possible to categorize information according to defined classifications, but in developmental biology and disease progression, the limits are rapidly reached since the processes are continuous. To take that into account, the researchers employed methods from machine learning processes. They combined pictures into processes and displayed them in a way that people understand.
To understand the capability of the method, the researchers selected two approaches. In the first experiment, the software was used to reconstruct the continuous cell cycle of leukocytes using pictures from an imaging flow cytometer. In the second example, the scientists reconstructed diabetic retinopathy progress. The software was feed with 30,000 retinas images as sparring partners. Since the software automatically compiles the data into a continuous process, it allows the researchers to predict the progression of disease on a continuous scale.


답글 남기기

아래 항목을 채우거나 오른쪽 아이콘 중 하나를 클릭하여 로그 인 하세요:

WordPress.com 로고

WordPress.com의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

Google+ photo

Google+의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

Twitter 사진

Twitter의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )

Facebook 사진

Facebook의 계정을 사용하여 댓글을 남깁니다. 로그아웃 /  변경 )


%s에 연결하는 중