Mercurial > repos > perssond > unmicst

comparison unmicst.xml @ 0:6bec4fef6b2e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/ohsu-comp-bio/unmicst commit 73e4cae15f2d7cdc86719e77470eb00af4b6ebb7-dirty"
author perssond
date Fri, 12 Mar 2021 00:17:29 +0000
parents
children 74fe58ff55a5
comparison
equal deleted inserted replaced
-1:000000000000 0:6bec4fef6b2e
1 <tool id="unmicst" name="UnMicst" version="@VERSION@.1" profile="17.09">
2 <description>UNet Model for Identifying Cells and Segmenting Tissue</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6
7 <expand macro="requirements"/>
8 @VERSION_CMD@
9
10 <command detect_errors="exit_code"><![CDATA[
11 #set $typeCorrected = str($image.name).replace('.ome.tiff','').replace('.ome.tif','').replace('.tiff','').replace('.tif','')+'.ome.tif'
12
13 ln -s $image '$typeCorrected';
14
15 @CMD_BEGIN@ '$typeCorrected'
16
17 #if $stackoutput
18 --stackOutput
19 #end if
20
21 --outputPath `pwd`
22 --channel $channel
23 --model $model
24 --mean $mean
25 --std $stdev
26 --scalingFactor $scalingfactor;
27
28 ## Move files to different files for from_work_dir differentiation
29 #if $stackoutput
30 mv *Probabilities*.tif Probabilities.tif;
31 mv *Preview*.tif Preview.tif
32 #else
33 mv *ContoursPM*.tif ContoursPM.tif;
34 mv *NucleiPM*.tif NucleiPM.tif
35 #end if
36 ]]></command>
37
38 <inputs>
39 <param name="image" type="data" format="tiff" label="Registered TIFF"/>
40 <param name="model" type="select" label="Model">
41 <option value="nucleiDAPI">nucleiDAPI</option>
42 <option value="mousenucleiDAPI">mousenucleiDAPI</option>
43 <option value="CytoplasmIncell">CytoplasmIncell</option>
44 <option value="CytoplasmZeissNikon">CytoplasmZeissNikon</option>
45 </param>
46 <param name="mean" type="float" value="-1" label="Mean (-1 for model default)"/>
47 <param name="stdev" type="float" value="-1" label="Standard Deviation (-1 for model default)"/>
48 <param name="channel" type="integer" value="0" label="Channel to perform inference on"/>
49 <param name="stackoutput" type="boolean" label="Stack probability map outputs"/>
50 <param name="scalingfactor" type="float" value="1.0" label="Factor to scale by"/>
51 </inputs>
52
53 <outputs>
54 <data format="tiff" name="previews" from_work_dir="Preview.tif" label="${tool.name} on ${on_string}: Preview">
55 <filter>stackoutput</filter>
56 </data>
57 <data format="tiff" name="probabilities" from_work_dir="Probabilities.tif" label="${tool.name} on ${on_string}: Probabilities">
58 <filter>stackoutput</filter>
59 </data>
60 <data format="tiff" name="contours" from_work_dir="ContoursPM.tif" label="${tool.name} on ${on_string}: ContoursPM">
61 <filter>not stackoutput</filter>
62 </data>
63 <data format="tiff" name="nuclei" from_work_dir="NucleiPM.tif" label="${tool.name} on ${on_string}: NucleiPM">
64 <filter>not stackoutput</filter>
65 </data>
66 </outputs>
67 <help><![CDATA[
68 UnMicst - UNet Model for Identifying Cells and Segmenting Tissue
69 Image Preprocessing
70 Images can be preprocessed by inferring nuclei contours via a pretrained UNet model. The model is trained on 3 classes : background, nuclei contours and nuclei centers. The resulting probability maps can then be loaded into any modular segmentation pipeline that may use (but not limited to) a marker controlled watershed algorithm.
71
72 The only input file is: an .ome.tif or .tif (preferably flat field corrected, minimal saturated pixels, and in focus. The model is trained on images acquired at 20x with binning 2x2 or a pixel size of 0.65 microns/px. If your settings differ, you can upsample/downsample to some extent.
73
74 Running as a Docker container
75
76 The docker image is distributed through Dockerhub and includes UnMicst with all of its dependencies. Parallel images with and without gpu support are available.
77
78 docker pull labsyspharm/unmicst:latest
79 docker pull labsyspharm/unmicst:latest-gpu
80 Instatiate a container and mount the input directory containing your image.
81
82 docker run -it --runtime=nvidia -v /path/to/data:/data labsyspharm/unmicst:latest-gpu bash
83 When using the CPU-only image, --runtime=nvidia can be omitted:
84
85 docker run -it -v /path/to/data:/data labsyspharm/unmicst:latest bash
86 UnMicst resides in the /app directory inside the container:
87
88 root@0ea0cdc46c8f:/# python app/UnMicst.py /data/input/my.tif --outputPath /data/results
89 Running in a Conda environment
90
91 If Docker is not available on your system, you can run the tool locally by creating a Conda environment. Ensure conda is installed on your system, then clone the repo and use conda.yml to create the environment.
92
93 git clone https://github.com/HMS-IDAC/UnMicst.git
94 cd UnMicst
95 conda env create -f conda.yml
96 conda activate unmicst
97 python UnMicst.py /path/to/input.tif --outputPath /path/to/results/directory
98 References:
99 S Saka, Y Wang, J Kishi, A Zhu, Y Zeng, W Xie, K Kirli, C Yapp, M Cicconet, BJ Beliveau, SW Lapan, S Yin, M Lin, E Boyde, PS Kaeser, G Pihan, GM Church, P Yin, Highly multiplexed in situ protein imaging with signal amplification by Immuno-SABER, Nat Biotechnology (accepted)
100
101 OHSU Wrapper Repo: https://github.com/ohsu-comp-bio/UnMicst
102 ]]></help>
103 <expand macro="citations" />
104 </tool>