Labeled_AAV8_Capsid_Data

<b>Data &amp; File Overview</b><b>Directory of Files</b>:<b><i>All_Patches_resized.zip</i></b><b>Size</b>: (9.44GB)<b>Description</b>:<br>This is a compressed folder that contains preprocessed patches. Each patch is an image of one of the following classes:full capsidpartially full capsidempty capsidaggregationicebroken capsidbackground<b>names_labels_df.csv.zip</b><b>Size</b>: (293KB)<b>Description</b>:<br>This is a compressed .csv file that contains 94,830 patch instances each with a patch name and the associated class label.<b>Additional Notes:</b>This data was used in conjunction with the code at https://github.com/lcgutier/capsid-eyes to create the Capsidize app at https://github.com/lcgutier/Capsidize.<b>File Naming Convention</b>:<b>Annotated and Preprocessed Images</b>:The classes are defined as follows: 1=Full capsid, 2=Partially full capsid, 3=empty capsid, 4=aggregation, 5=ice, 6=broken capsid, 7=background Training and testing sets were randomly sampled from the resulting patches and each class was balanced.Images are named according to the dataset they belong to, followed by the original image ID number and lastly with the annotation ID number.<b>Data Description</b><b>names_labels_df.csv.zip</b><b>Columns</b>: patch_name, label<b>Rows</b>: 94,830 patch instances<b>Class Types</b><b>Full Capsids</b>, <b>label</b>=1, <b>Description</b>: A capsid with a dark ring and even dark infill density.<b>Partial Capsids</b>, <b>label</b>=2, <b>Description</b>: A capsid with a dark ring and a mid-range infill density.<b>Empty Capsids</b>, <b>label</b>=3, <b>Description</b>: A capsid with a dark ring and a light infill density.<b>Aggregation</b>, <b>label</b>=4, <b>Description</b>: A cluster of capsids.<b>Ice</b>, <b>label</b>=5, <b>Description</b>: Dark globular crystals that range in size.<b>Broken Capsids</b>, <b>label</b>=6, <b>Description</b>: Full, partial, or empty capsids that have broken. These are often only fragments.<b>Background</b>, <b>label</b>=7, <b>Description</b>: This class contains all background masks including those as a result of background differences seen at the carbon grid hole/grid material boundary.<b>Methodological Information</b><b>Software-specific information</b>:<b>Name</b>: Capsidize<b>Version</b>: 1.0.0<b>System Requirements</b>: Macos or Python 3.9<b>Open Source</b>: Yes<b>Developer</b>: Lilianna GutierrezProduct RepositorySource RepositoryAdditional Notes: The source code held in the capsid-eyes github repository can be run without macos, but the app was compiled on darwin-arm64.<b>Equipment-specific information</b>:<br><b>Sample Preparation</b><b>Manufacturer</b>: (Thermo Fisher Scientific [TFS], Waltham, MA, USA)<b>Model</b>: Vitrobot Mk 4<b>Use</b>: cooled in a bath of liquid nitrogen to freeze samples for imaging<b>Imaging</b><b>Manufacturer</b>: Thermo Fisher Scientific<b>Model</b>: Krios 3Gi microscope<b>Use</b>: To collect TEM images. Operating at 300 kVolts and equipped with a Selectris energy filter and Falcon 4i direct electron detecting camera operating in electron counting mode.