### Assigning sequences in R

Source: https://github.com/kvanderwaal/prrsv2_classification/blob/main/README.md

Uses a pre-trained random forest model to classify sequences from a FASTA file. Requires the adegenet, caret, and randomForest packages.

```r
#instal required packages
#install.packages("adegenet","caret","randomForest")

#load functions for making the predictions.
source(url("https://github.com/kvanderwaal/prrsv2_classification/raw/main/rf10v.predict.fun.R"))
#load the model
load(url("https://github.com/kvanderwaal/prrsv2_classification/raw/main/model.Rdata"))

#note, if you would like to predict lineages/sub-lineages instead of variants, you can load this model instead.
#lineages/sub-lineages reflect Paploski et al. 2021 (Vaccines: https://dx.doi.org/10.3201/eid2208.160496) and Yim-im et al. 2023 (Microbiology Spectrum: https://dx.doi.org/10.1128/spectrum.02916-23)
#load(url("https://github.com/kvanderwaal/prrsv2_classification/raw/main/model.rf10v.new.lin.11.2023.Rdata"))


#load alignment file (should be in your working directory). 
align.ex <- read.alignment("sequences.example.fasta",format="fasta")  #An example sequence file is available for download from Github, and should be placed in your working directory.  This should be replaced with your own .fasta file

#make the assigments
out <- make.predict(al.new=align.ex)


#write the assigments to a file.  This file will appear in your working directory
write.csv(out,file="out.csv")

#view the assignments
head(out)
#>     SequenceName    assign.final      assign.top prob.top        assign.2
#> ex1          ex1 1A-unclassified           1A.19    0.404 1A-unclassified
#> ex2          ex2           1A.14           1A.14    0.998           1A.38
#> ex3          ex3 1A-unclassified 1A-unclassified    0.942           1A.32
#> ex4          ex4            5A.1            5A.1    0.982 5B-unclassified
#> ex5          ex5            1A.5            1A.5    1.000            <NA>
#> ex6          ex6            1H.4            1H.4    0.986           1H.17
#>     prob.2 num.gaps.amb
#> ex1  0.316            0
#> ex2  0.002            0
#> ex3  0.046            0
#> ex4  0.006            0
#> ex5  0.000            0
#> ex6  0.004            0
```

--------------------------------

### Assigning sequences in Python

Source: https://github.com/kvanderwaal/prrsv2_classification/blob/main/README.md

Executes the classification script via terminal. Requires Python 3 and specific libraries including Pandas, Numpy, Biopython, SKOPS, and Requests.

```bash
usage: python3 finalPRRSVclass.py [-h] -s SEQALI -o OUT

options:
  -h, --help    Show this help message and exit
  -s, --seqali  PRRSV-2 multiple sequence alignment with length of 603 nt in FASTA format
  -o, --out     Name or full path of classification report in .csv format
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.