Abstract
Electron Microscopy Maps are key in the study of bio-molecular structures, ranging from borderline atomic level to the sub-cellular range. These maps describe the envelopes that cover possibly a very large number of proteins that form molecular machines within the cell. Within those envelopes, we are interested to find what regions correspond to specific proteins so that we can understand how they function, and design drugs that can enhance or suppress a process that they are involved in, along with other experimental purposes. A classic approach by which we can begin the exploration of map regions is to apply a segmentation algorithm. This yields a mask where each voxel in 3D space is assigned an identifier that maps it to a segment; an ideal segmentation would map each segment to one protein unit, which is rarely the case. In this work, we present a method that uses bio-inspired optimization, through an Evolutionary-Optimized Segmentation algorithm, to iteratively improve upon baseline segments obtained from a classical approach, called watershed segmentation. The cost function used by the evolutionary optimization is based on an ideal segmentation classifier trained as part of this development, which uses basic structural information available to scientists, such as the number of expected units, volume and topology. We show that a basic initial segmentation with the additional information allows our evolutionary method to find better segmentation results, compared to the baseline generated by the watershed.
Highlights
The biological sciences have greatly benefited from advances in microscopy over the past decade, which have enabled techniques such as cryo-electron microscopy to produce 3D images that elucidate near-atomic level features of proteins
The main objective at the onset of this work was to create a computational protocol that would allow scientists to start from an Electron Microscopy map, gather some basic information about the proteins contained in the EM and produce better segmentation results than what baseline segmentation can produce at this time
We show that we have achieved that goal by highlighting the metrics described previously, as well as comparing against segmentation results obtained in ChimeraX [39], a well known bio-molecular manipulation tool with segmentation features
Summary
The biological sciences have greatly benefited from advances in microscopy over the past decade, which have enabled techniques such as cryo-electron microscopy to produce 3D images that elucidate near-atomic level features of proteins. The highest resolution images created have approached the 1.5 Å range [1,2,3] At this resolution, it is even possible to identify atomic structures in proteins, the results depend on the map itself. While some of the structures deposited in the PDB correspond to larger molecules, the majority of them only contain a handful of protein units To complement this high-resolution data source, we can leverage a second valuable source of data: the EM Data Resource [27]. The atomic-detailed models that correspond to EM maps under study may not always be available or we may need to deal with additional complexities, in order to obtain baseline EM maps that yield lower resolution images [31]. As we will see in our results, both from a quantitative and a qualitative point of view, we are able to improve upon baseline segmentation candidates without requiring extensive parameter tuning from researchers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
