Load packages

library(knitr)
## Warning: package 'knitr' was built under R version 4.3.2
library(UniprotR)
## Warning: package 'UniprotR' was built under R version 4.3.2
library(Biostrings)
## Loading required package: BiocGenerics
## 
## Attaching package: 'BiocGenerics'
## The following objects are masked from 'package:stats':
## 
##     IQR, mad, sd, var, xtabs
## The following objects are masked from 'package:base':
## 
##     anyDuplicated, aperm, append, as.data.frame, basename, cbind,
##     colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
##     get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
##     match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
##     Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,
##     table, tapply, union, unique, unsplit, which.max, which.min
## Loading required package: S4Vectors
## Loading required package: stats4
## 
## Attaching package: 'S4Vectors'
## The following object is masked from 'package:utils':
## 
##     findMatches
## The following objects are masked from 'package:base':
## 
##     expand.grid, I, unname
## Loading required package: IRanges
## 
## Attaching package: 'IRanges'
## The following object is masked from 'package:grDevices':
## 
##     windows
## Loading required package: XVector
## Loading required package: GenomeInfoDb
## Warning: package 'GenomeInfoDb' was built under R version 4.3.2
## 
## Attaching package: 'Biostrings'
## The following object is masked from 'package:base':
## 
##     strsplit
library(seqinr)
## Warning: package 'seqinr' was built under R version 4.3.2
## 
## Attaching package: 'seqinr'
## The following object is masked from 'package:Biostrings':
## 
##     translate
library(ggfortify)
## Loading required package: ggplot2
library(forcats)

Function code chunk

pid_alignments <- function(accession_ids){
  
#Create a variable of the accession ids
  
ids <-(accession_ids)

#Retrieve sequences
df <- GetSequences(ids)
df

#first change the ids from being the rownames to being a column
df$accession_id <- row.names(df)
rownames(df) <- 1:nrow(df)

#Reduce uniprot_seqs dataframe to only contain the sequences and ids
df <- df[,c("accession_id", "Sequence")]

# Create a matrix of subject and query sequences
seq_mat <-cbind2(df[2:nrow(df),1:2], df[1,1:2])
seq_mat

# Create a loop that performs pairwise alignment of each combination and calculates the percentage identity of the result of each pairwise alignment.

#alignment_score <- c()
nameSeq1 <- c()
name_refSeq <- c()
alignments <- list()

for (i in 1:nrow(seq_mat)){
  aligned_seqs <- pairwiseAlignment(AAStringSet(seq_mat[i,2]), AAStringSet(seq_mat[i,4]), substitutionMatrix = "BLOSUM50", gapOpening = -2, gapExtension = -8, scoreOnly = FALSE)
  
  nameSeq1[i] <- c(as.character(seq_mat[i,1]))
  name_refSeq[i] <- c(as.character(seq_mat[i,3]))
  alignments[[i]] <- c(aligned_seqs)
  
  pid_aln <-sapply(alignments, pid, type = "PID4")
        
#I have chosen PID4 this time but there are other options for calculating the percentage identity. See options below:
#"PID1": 100*(identicalpositions)/(alignedpositions+internalgappositions) 
#"PID2": 100*(identicalpositions)/(alignedpositions) 
#"PID3": 100*(identicalpositions)/(lengthshortersequence) 
#"PID4": 100*(identicalpositions)/(averagelengthofthetwosequences)
    }

#Create dataframe of sequence name and scores 
aligned_df <- data.frame(name_refSeq, nameSeq1, pid_aln)
colnames(aligned_df) <- c("Primary_accession_id", "Query_accession_id", "Percent_Identity")

#Create Plot of PID
PID_plot <- ggplot(aligned_df, aes(x = fct_inorder(Query_accession_id), y = Percent_Identity))+
  geom_col(fill= "turquoise3", width = 0.7)+
  theme_bw()+
  theme(axis.text.x = element_text(angle = 60, hjust = 1, size = 10), plot.title = element_text(hjust = 0.5, size = 12)) +
          labs(title = "Percent Identity plot of Pairwise alignments of Query sequences against Subject sequence",
               x = "Query accession id",
               y = "Percent Identity")

return(list(aligned_df,PID_plot))
}

Test that function works

#Test function

pid_alignments(c("A0A6P3H9Z6", "A0A3Q1MJB2", "Q08879", "A0A287AL89", "P23142", "A0A0G2JY81", "G1T0Q0", "A0A452F2R0", "Q8MJJ9", "A0A0D9QZ51", "A0A2K6SW02", "A0A2K5DTU8", "A0A2K5VCS0", "A0A2K6MZ25", "A0A2K6QYG8"))
## Please wait we are processing your accessions ...
## [[1]]
##    Primary_accession_id Query_accession_id Percent_Identity
## 1            A0A6P3H9Z6         A0A3Q1MJB2         97.53623
## 2            A0A6P3H9Z6             Q08879         84.11893
## 3            A0A6P3H9Z6         A0A287AL89         84.92967
## 4            A0A6P3H9Z6             P23142         87.87219
## 5            A0A6P3H9Z6         A0A0G2JY81         80.78890
## 6            A0A6P3H9Z6             G1T0Q0         73.20955
## 7            A0A6P3H9Z6         A0A452F2R0         94.88104
## 8            A0A6P3H9Z6             Q8MJJ9         73.11321
## 9            A0A6P3H9Z6         A0A0D9QZ51         87.72694
## 10           A0A6P3H9Z6         A0A2K6SW02         75.40741
## 11           A0A6P3H9Z6         A0A2K5DTU8         86.95652
## 12           A0A6P3H9Z6         A0A2K5VCS0         73.65398
## 13           A0A6P3H9Z6         A0A2K6MZ25         74.10072
## 14           A0A6P3H9Z6         A0A2K6QYG8         74.56647
## 
## [[2]]