## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(
    collapse = TRUE,
    comment = "#>",
    fig.height = 5,
    fig.width = 5,
    fig.align = "center"
)

## -----------------------------------------------------------------------------
library(ClustIRR)
library(knitr)
library(visNetwork)

## ----eval=FALSE---------------------------------------------------------------
#  if(!require("BiocManager", quietly = TRUE)) {
#    install.packages("BiocManager")
#  }
#  BiocManager::install("ClustIRR")

## ----graphic, echo = FALSE, fig.align="left", out.width='90%'-----------------
knitr::include_graphics("../inst/extdata/logo.png")

## -----------------------------------------------------------------------------
data("CDR3ab")

## -----------------------------------------------------------------------------
# take the first 500 CDR3b sequences from the data -> s
# s <- base::data.frame(CDR3b = CDR3ab$CDR3b[1:500])
s <- base::data.frame(CDR3b = c(CDR3ab$CDR3b[1:500], "CASSSSPGDQEQFF"))

# take 5000 CDR3b sequences 501:5500 from the data -> r
r <- base::data.frame(CDR3b = CDR3ab$CDR3b[501:5500])

## -----------------------------------------------------------------------------
str(s)

## -----------------------------------------------------------------------------
str(r)

## -----------------------------------------------------------------------------
cdr3 <- "CASSTTTGTGELFF"
k <- 4
base::colnames(stringdist::qgrams(cdr3, q = k))

## -----------------------------------------------------------------------------
t <- 3
cdr3_trimmed <- base::substr(x = cdr3, start = t + 1, stop = nchar(cdr3) - t)
base::colnames(stringdist::qgrams(cdr3_trimmed, q = k))

## -----------------------------------------------------------------------------
# insert motif LEAR
base::substr(x = s$CDR3b[1:20], start = 6, stop = 9) <- "LEAR"

## -----------------------------------------------------------------------------
o <- cluster_irr(s = s,
                 r = r,
                 version = 2,
                 ks = 4,
                 cores = 1,
                 control = list(trim_flank_aa = 3))

## -----------------------------------------------------------------------------
# extract local motifs
local_motifs <- get_clustirr_clust(o)$CDR3b$local$m

# display only passed motifs
knitr::kable(local_motifs[local_motifs$pass == TRUE, ], row.names = FALSE)

## -----------------------------------------------------------------------------
# display globally similar pairs
knitr::kable(get_clustirr_clust(o)$CDR3b$global, row.names = FALSE)

## ----fig.width=5, fig.height=4, fig.align='center'----------------------------
par(mai = c(0,0,0,0))
plot_graph(clust_irr = o)

## ----fig.width=5, fig.height=4, fig.align='center'----------------------------
plot_graph(clust_irr = o, as_visnet = TRUE)

## -----------------------------------------------------------------------------
# create a clone of 10 T-cells
clone <- base::data.frame(CDR3b = rep("CATSRPDGLAQYF", times = 20))

# append the clone to the original repertoire 's'
s <- base::rbind(s, clone)

## -----------------------------------------------------------------------------
o <- cluster_irr(s = s,
                 r = r,
                 version = 2,
                 ks = 4,
                 cores = 1,
                 control = list(trim_flank_aa = 3))

## ----fig.align='center'-------------------------------------------------------
# extract local motifs
local_motifs <- get_clustirr_clust(o)$CDR3b$local$m

# display only passed motifs
knitr::kable(local_motifs[local_motifs$pass == TRUE, ], row.names = FALSE)

## -----------------------------------------------------------------------------
# plot the clust_irr object
plot_graph(clust_irr = o, as_visnet = TRUE)

## -----------------------------------------------------------------------------
data("CDR3ab")

S0 <- base::data.frame(CDR3a = CDR3ab$CDR3a[3001:4000],
                      CDR3b = CDR3ab$CDR3b[3001:4000])

S1 <- base::data.frame(CDR3a = CDR3ab$CDR3a[5001:6000],
                      CDR3b = CDR3ab$CDR3b[5001:6000])

## -----------------------------------------------------------------------------
# insert motif LEAR in CDR3b
base::substr(x = S0$CDR3b[1:10], start = 6, stop = 9) <- "LEAR"
# insert motif REAL in CDR3a
base::substr(x = S0$CDR3a[50:59], start = 6, stop = 9) <- "REAL"

## -----------------------------------------------------------------------------
# create 3 clones
clone_1 <- data.frame(CDR3a = rep(x = "CASSEGEQFF", times = 100),
                      CDR3b = rep(x = "CASSLLARAEQFF", times = 100))

clone_2 <- data.frame(CDR3a = rep(x = "CASSLESPLHF", times = 50),
                      CDR3b = rep(x = "CASSLEEEEEEPLHF", times = 50))

clone_3 <- data.frame(CDR3a = rep(x = "CASSLESPLHF", times = 10),
                      CDR3b = rep(x = "CASSLAAAAASPLHF", times = 10))

# append clones to s
S0 <- rbind(S0, clone_1, clone_2, clone_3)

## -----------------------------------------------------------------------------
base::substr(x = S1$CDR3b[1:20], start = 6, stop = 9) <- "WWWW"
S1 <- rbind(S1, clone_1)

## -----------------------------------------------------------------------------
o_S1_vs_S0 <- cluster_irr(s = S1,
                          r = S0,
                          version = 2,
                          ks = 4,
                          cores = 1,
                          control = list(trim_flank_aa = 3))


o_S0_vs_S1 <- cluster_irr(s = S0,
                          r = S1,
                          version = 2,
                          ks = 4,
                          cores = 1,
                          control = list(trim_flank_aa = 3))

## -----------------------------------------------------------------------------
# beta & alpha chain
plot_joint_graph(clust_irr_1 = o_S1_vs_S0, 
                 clust_irr_2 = o_S0_vs_S1,
                 as_visnet = TRUE)

## -----------------------------------------------------------------------------
data("CDR3ab")

# gamma/delta chain TCR data -> notice CDR3g and CDR3d columns of 's' and 'r'
s <- base::data.frame(CDR3g = CDR3ab$CDR3a[4501:5000],
                      CDR3d = CDR3ab$CDR3b[4501:5000])

r <- base::data.frame(CDR3g = CDR3ab$CDR3a[5001:10000],
                      CDR3d = CDR3ab$CDR3b[5001:10000])


## -----------------------------------------------------------------------------
data("CDR3ab")

# heavy/light chain BCR data -> notice CDR3h and CDR3l columns of 's' and 'r'
s <- base::data.frame(CDR3h = CDR3ab$CDR3a[4501:5000],
                      CDR3l = CDR3ab$CDR3b[4501:5000])

r <- base::data.frame(CDR3h = CDR3ab$CDR3a[5001:10000],
                      CDR3l = CDR3ab$CDR3b[5001:10000])


## ----session_info-------------------------------------------------------------
utils::sessionInfo()