Project

General

Profile

First-time autoscreening setup » History » Version 3

Anchi Cheng, 03/01/2022 12:45 AM

1 1 Anchi Cheng
h1. Smart-leginon multi-grid autoscreening
2
3
Automated square and hole finders are added to leginon to use Ptolemy (https://arxiv.org/abs/2112.01534) to determine optimal targets using computer vision algorithm and Convolutional Neural Network trained on user target selections accumulated at Simons Electron Microscopy Center at New York Biology Center (SEMC@NYSBC.
4
5
This implementation requires Ptolemy which has a separate license. For this release, the communication is through command line interface and rely on shared file system.
6
7
* At SEMC@NYSBC, Ptolemy, which was tested on python 3.9, runs in anaconda environment on the same CentOS7 computer where the main leginon process is.
8
9 3 Anchi Cheng
h2. Install Ptolemy and [[Setup Ptolemy CLI shell script|setup shell script to use its cli]]
10
11 2 Anchi Cheng
h2. Square finding localization and classification using MosaicExternalScoreFinder
12 1 Anchi Cheng
13 2 Anchi Cheng
(node alias Square Finding)
14
15
h3. Upload MSI-Ptolemy application into leginon database
16
17
Follow the instruction in [[Applications|web application tools]]
18
* Note: If your system needs two Leginon client opened, each on a different pc, use MSi-Ptolemy2.xml
19
20
If you have your own application you can do the following replacement by [[Use_the_Application_Editor_to_create_Leginon_applications|editing your application]] :
21
22
Square Targeting Node : MosaicClickTargetFinder class => MosaicScoreTargetFinder
23
Exposure Targeting Node: JAHCFinder => ScoreTargetFinder
24
25
h3.  Define target area size sampling in Leginon
26
27
Do this in the settings next to "acquisition" target panel.  Enter
28
29
# Maximal number of squares to select
30
# Number of target group to sample
31
32
For example, total of 12 squares selected in 3 groups means the program divided out all blob squares with valid area range into 3 size group (small, medium,and large).  It then choose 4 blob squares in each group with highest score given by Ptolemy as the output square targets.  High score in Ptolemy result means it is more likely to be a good square.
33
34 3 Anchi Cheng
h3. Set the limits of square area range
35 2 Anchi Cheng
36
This is set in "Thresholded" settings.  However, it is easier to set by select examples once you acquire your first grid atlas in this node.
37 3 Anchi Cheng
38
h3.