annotate README.txt @ 3:302332b914ef draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 58587e05f604590c70550e13fc51b7425e916ed4
author iuc
date Sat, 14 Jan 2023 21:08:33 +0000
parents 457fd8fd681a
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
1 # VirHunter
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
2
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
3 VirHunter is a deep learning method that uses Convolutional Neural Networks (CNNs) and a Random Forest Classifier to identify viruses in sequening datasets. More precisely, VirHunter classifies previously assembled contigs as viral, host and bacterial (contamination).
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
4
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
5 ## System Requirements
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
6 VirHunter installation requires a Unix environment with [python 3.8](http://www.python.org/).
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
7 It was tested on Linux and macOS operating systems.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
8 For now, VirHunter is still not fully compatible with M1 chip MacBook.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
9
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
10 In order to run VirHunter you need to have git and conda already installed.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
11 If you are installing conda for the first time, we suggest you to use
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
12 a lightweight [miniconda](https://docs.conda.io/en/latest/miniconda.html).
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
13 Otherwise, you can use pip for the dependencies' installation.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
14
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
15 ## Installation
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
16
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
17 To install VirHunter, you need to download it from github and then to install the dependancies.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
18
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
19 First, clone the repository from [github](https://github.com/cbib/virhunter)
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
20
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
21 git clone https://github.com/cbib/virhunter.git
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
22
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
23 Go to the VirHunter root folder
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
24
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
25 cd virhunter/
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
26
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
27 ### Installing dependencies with Conda
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
28
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
29 First, you have to create the environment from the envs/environment.yml file.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
30 The installation may take around 500 Mb of drive space.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
31
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
32 conda env create -f envs/environment.yml
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
33
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
34 Second, activate the environment:
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
35
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
36 conda activate virhunter
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
37
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
38 ### Installing dependencies with pip
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
39
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
40 If you don't have Conda installed in your system, you can install python dependencies via pip program:
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
41
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
42 pip install -r envs/requirements.txt
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
43
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
44 Then if you have macOS you will need to install wget library to run some scripts (Conda installation already has it). You can do this with brew package manager.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
45
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
46 brew install wget
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
47
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
48 ### Testing your installation of VirHunter
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
49
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
50 You can test that VirHunter was successfully installed on the toy dataset we provide.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
51 IMPORTANT: the toy dataset is intended only to test that VirHunter has been well installed and all the scripts can be executed.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
52 These modules should not be used for prediction on your owd datasets!
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
53
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
54 First, you have to download the toy dataset
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
55
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
56 bash scripts/download_test_installation.sh
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
57
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
58 Then run the bash script that calls the testing, training and prediction python scripts of VirHunter.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
59 Attention, the training process may take some time (up to an hour).
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
60
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
61 bash scripts/test_installation.sh
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
62
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
63
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
64 ## Using VirHunter for prediction
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
65
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
66 To run VirHunter you can use the already pre-trained models or train VirHunter yourself (described in the next section).
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
67 Pre-trained model weights are already available for the multiple host plants.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
68 You can download them using the download_weights.sh script.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
69
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
70 bash scripts/download_weights.sh
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
71
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
72 Once the config file is ready, you can start the prediction:
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
73
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
74 python virhunter/predict.py --test_ds /path/to/test_ds_1
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
75
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
76 After prediction VirHunter produces two csv files and one optional fasta file:
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
77
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
78 1. The first file ends with _predicted_fragments.csv
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
79 It is an intermediate result containing predictions of the three CNN networks (probabilities of belonging to each of the virus/plant/bacteria class) and of the RF classifier for each fragment of every contig.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
80
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
81 2. The second file ends with _predicted.csv.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
82 This file contains final predictions for contigs calculated from the previous file.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
83 - id - fasta header of a contig.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
84 - length - length of the contig.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
85 - # viral fragments, # plant fragments and # bacterial fragments - the number of fragments of the contig that received corresponding class prediction by the RF classifier.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
86 - decision - class given by the VirHunter to the contig.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
87 - # viral / # total - number of viral fragments divided by the total number of fragments of the contig.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
88 - # viral / # total * length - number of viral fragments divided by the total number of fragments of the contig multiplied by contig length. It is used to display the most relevant contigs first.
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
89
457fd8fd681a planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/VirHunter commit 628688c1302dbf972e48806d2a5bafe27847bdcc
iuc
parents:
diff changeset
90 3. The fasta file ends with _viral.fasta. It contains contigs that were predicted as viral by VirHunter.