This document gives an overview of the DNABarcodeCompatibility R package with a brief description of the set of tools that it contains. The package includes six main functions that are briefly described below with examples. These functions allow one to load a list of DNA barcodes (such as the Illumina TruSeq small RNA kits), to filter these barcodes according to distance and nucleotide content criteria, to generate sets of compatible barcode combinations out of the filtered barcode list, and finally to generate an optimized selection of barcode combinations for multiplex sequencing experiments. In particular, the package provides an optimizer function to favour the selection of compatible barcode combinations with least heterogeneity in the frequencies of DNA barcodes, and allows one to keep barcodes that are robust against substitution and insertion/deletion errors, thereby facilitating the demultiplexing step.
The DNABarcodeCompatibility package also contains:
experiment_design() allowing one to perform all steps in one go.IlluminaIndexesRaw and IlluminaIndexes for running and testing examples.The package deals with the three existing sequencing-by-synthesis chemistries from Illumina:
library("DNABarcodeCompatibility")# This function is created for the purpose of the documentation
export_dataset_to_file =
function(dataset = DNABarcodeCompatibility::IlluminaIndexesRaw) {
if ("data.frame" %in% is(dataset)) {
write.table(dataset,
textfile <- tempfile(),
row.names = FALSE, col.names = FALSE, quote=FALSE)
return(textfile)
} else print(paste("The input dataset isn't a data.frame:",
"NOT exported into file"))
}The function experiment_design() uses a Shannon-entropy
maximization approach to identify a set of compatible barcode
combinations in which the frequencies of occurrences of the various DNA
barcodes are as uniform as possible. The optimization can be performed
in the contexts of single and dual barcoding. It performs either an
exhaustive or a random search of compatible DNA-barcode combinations,
depending on the size of the DNA-barcode set used, and on the number of
samples to be multiplexed.
txtfile <- export_dataset_to_file (
dataset = DNABarcodeCompatibility::IlluminaIndexesRaw
)
experiment_design(file1=txtfile,
sample_number=12,
mplex_level=3,
platform=4)
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## sample Lane Id sequence
## 1 1 1 RPI18 GTCCGC
## 2 2 1 RPI27 ATTCCT
## 3 3 1 RPI32 CACTCA
## 4 4 2 RPI07 CAGATC
## 5 5 2 RPI17 GTAGAG
## 6 6 2 RPI39 CTATAC
## 7 7 3 RPI21 GTTTCG
## 8 8 3 RPI29 CAACTA
## 9 9 3 RPI33 CAGGCG
## 10 10 4 RPI24 GGTAGC
## 11 11 4 RPI31 CACGAT
## 12 12 4 RPI40 CTCAGAtxtfile <- export_dataset_to_file (
dataset = DNABarcodeCompatibility::IlluminaIndexesRaw
)
experiment_design(file1=txtfile,
sample_number=12,
mplex_level=3,
platform=2)
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## sample Lane Id sequence
## 1 1 1 RPI05 ACAGTG
## 2 2 1 RPI08 ACTTGA
## 3 3 1 RPI27 ATTCCT
## 4 4 2 RPI03 TTAGGC
## 5 5 2 RPI22 CGTACG
## 6 6 2 RPI44 TATAAT
## 7 7 3 RPI13 AGTCAA
## 8 8 3 RPI26 ATGAGC
## 9 9 3 RPI36 CCAACA
## 10 10 4 RPI24 GGTAGC
## 11 11 4 RPI31 CACGAT
## 12 12 4 RPI48 TCGGCAtxtfile <- export_dataset_to_file (
dataset = DNABarcodeCompatibility::IlluminaIndexesRaw
)
experiment_design(file1=txtfile,
sample_number=12,
mplex_level=3,
platform=1)
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## sample Lane Id sequence
## 1 1 1 RPI01 ATCACG
## 2 2 1 RPI27 ATTCCT
## 3 3 1 RPI44 TATAAT
## 4 4 2 RPI04 TGACCA
## 5 5 2 RPI23 GAGTGG
## 6 6 2 RPI25 ACTGAT
## 7 7 3 RPI40 CTCAGA
## 8 8 3 RPI41 GACGAC
## 9 9 3 RPI42 TAATCG
## 10 10 4 RPI07 CAGATC
## 11 11 4 RPI08 ACTTGA
## 12 12 4 RPI11 GGCTACtxtfile <- export_dataset_to_file (
dataset = DNABarcodeCompatibility::IlluminaIndexesRaw
)
experiment_design(file1=txtfile,
sample_number=12,
mplex_level=3,
platform=4,
metric = "hamming",
d = 3)
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## sample Lane Id sequence
## 1 1 1 RPI05 ACAGTG
## 2 2 1 RPI20 GTGGCC
## 3 3 1 RPI26 ATGAGC
## 4 4 2 RPI16 CCGTCC
## 5 5 2 RPI17 GTAGAG
## 6 6 2 RPI18 GTCCGC
## 7 7 3 RPI24 GGTAGC
## 8 8 3 RPI39 CTATAC
## 9 9 3 RPI47 TCGAAG
## 10 10 4 RPI02 CGATGT
## 11 11 4 RPI10 TAGCTT
## 12 12 4 RPI36 CCAACA# Select the first half of barcodes from the dataset
txtfile1 <- export_dataset_to_file (
DNABarcodeCompatibility::IlluminaIndexesRaw[1:24,]
)
# Select the second half of barcodes from the dataset
txtfile2 <- export_dataset_to_file (
DNABarcodeCompatibility::IlluminaIndexesRaw[25:48,]
)
# Get compatibles combinations of least redundant barcodes
experiment_design(file1=txtfile1,
sample_number=12,
mplex_level=3,
platform=4,
file2=txtfile2)
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## Id Lane
## 1 RPI06 1
## 2 RPI14 1
## 3 RPI23 1
## 4 RPI04 2
## 5 RPI07 2
## 6 RPI21 2
## 7 RPI01 3
## 8 RPI10 3
## 9 RPI11 3
## 10 RPI05 4
## 11 RPI09 4
## 12 RPI15 4
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## Id Lane
## 1 RPI26 1
## 2 RPI34 1
## 3 RPI42 1
## 4 RPI33 2
## 5 RPI40 2
## 6 RPI43 2
## 7 RPI37 3
## 8 RPI39 3
## 9 RPI45 3
## 10 RPI27 4
## 11 RPI38 4
## 12 RPI46 4
## Id Lane sequence
## 1 RPI06 1 GCCAAT
## 2 RPI14 1 AGTTCC
## 3 RPI23 1 GAGTGG
## 4 RPI04 2 TGACCA
## 5 RPI07 2 CAGATC
## 6 RPI21 2 GTTTCG
## 7 RPI01 3 ATCACG
## 8 RPI10 3 TAGCTT
## 9 RPI11 3 GGCTAC
## 10 RPI05 4 ACAGTG
## 11 RPI09 4 GATCAG
## 12 RPI15 4 ATGTCA
## Id Lane sequence
## 1 RPI26 1 ATGAGC
## 2 RPI34 1 CATGGC
## 3 RPI42 1 TAATCG
## 4 RPI33 2 CAGGCG
## 5 RPI40 2 CTCAGA
## 6 RPI43 2 TACAGC
## 7 RPI37 3 CGGAAT
## 8 RPI39 3 CTATAC
## 9 RPI45 3 TCATTC
## 10 RPI27 4 ATTCCT
## 11 RPI38 4 CTAGCT
## 12 RPI46 4 TCCCGA
## sample Lane Id1 sequence1 Id2 sequence2
## 1 1 1 RPI06 GCCAAT RPI26 ATGAGC
## 2 2 1 RPI14 AGTTCC RPI34 CATGGC
## 3 3 1 RPI23 GAGTGG RPI42 TAATCG
## 4 4 2 RPI04 TGACCA RPI33 CAGGCG
## 5 5 2 RPI07 CAGATC RPI40 CTCAGA
## 6 6 2 RPI21 GTTTCG RPI43 TACAGC
## 7 7 3 RPI01 ATCACG RPI37 CGGAAT
## 8 8 3 RPI10 TAGCTT RPI39 CTATAC
## 9 9 3 RPI11 GGCTAC RPI45 TCATTC
## 10 10 4 RPI05 ACAGTG RPI27 ATTCCT
## 11 11 4 RPI09 GATCAG RPI38 CTAGCT
## 12 12 4 RPI15 ATGTCA RPI46 TCCCGA# Select the first half of barcodes from the dataset
txtfile1 <- export_dataset_to_file (
DNABarcodeCompatibility::IlluminaIndexesRaw[1:24,]
)
# Select the second half of barcodes from the dataset
txtfile2 <- export_dataset_to_file (
DNABarcodeCompatibility::IlluminaIndexesRaw[25:48,]
)
# Get compatibles combinations of least redundant barcodes
experiment_design(file1=txtfile1, sample_number=12, mplex_level=3, platform=4,
file2=txtfile2, metric="hamming", d=3)
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## Id Lane
## 1 RPI02 1
## 2 RPI06 1
## 3 RPI13 1
## 4 RPI03 2
## 5 RPI09 2
## 6 RPI12 2
## 7 RPI10 3
## 8 RPI11 3
## 9 RPI16 3
## 10 RPI04 4
## 11 RPI15 4
## 12 RPI23 4
## [1] "Theoretical max entropy: 2.48491"
## [1] "Entropy of the optimized set: 2.48491"
## Id Lane
## 1 RPI27 1
## 2 RPI41 1
## 3 RPI43 1
## 4 RPI26 2
## 5 RPI30 2
## 6 RPI48 2
## 7 RPI34 3
## 8 RPI40 3
## 9 RPI44 3
## 10 RPI37 4
## 11 RPI42 4
## 12 RPI45 4
## Id Lane sequence
## 1 RPI02 1 CGATGT
## 2 RPI06 1 GCCAAT
## 3 RPI13 1 AGTCAA
## 4 RPI03 2 TTAGGC
## 5 RPI09 2 GATCAG
## 6 RPI12 2 CTTGTA
## 7 RPI10 3 TAGCTT
## 8 RPI11 3 GGCTAC
## 9 RPI16 3 CCGTCC
## 10 RPI04 4 TGACCA
## 11 RPI15 4 ATGTCA
## 12 RPI23 4 GAGTGG
## Id Lane sequence
## 1 RPI27 1 ATTCCT
## 2 RPI41 1 GACGAC
## 3 RPI43 1 TACAGC
## 4 RPI26 2 ATGAGC
## 5 RPI30 2 CACCGG
## 6 RPI48 2 TCGGCA
## 7 RPI34 3 CATGGC
## 8 RPI40 3 CTCAGA
## 9 RPI44 3 TATAAT
## 10 RPI37 4 CGGAAT
## 11 RPI42 4 TAATCG
## 12 RPI45 4 TCATTC
## sample Lane Id1 sequence1 Id2 sequence2
## 1 1 1 RPI02 CGATGT RPI27 ATTCCT
## 2 2 1 RPI06 GCCAAT RPI41 GACGAC
## 3 3 1 RPI13 AGTCAA RPI43 TACAGC
## 4 4 2 RPI03 TTAGGC RPI26 ATGAGC
## 5 5 2 RPI09 GATCAG RPI30 CACCGG
## 6 6 2 RPI12 CTTGTA RPI48 TCGGCA
## 7 7 3 RPI10 TAGCTT RPI34 CATGGC
## 8 8 3 RPI11 GGCTAC RPI40 CTCAGA
## 9 9 3 RPI16 CCGTCC RPI44 TATAAT
## 10 10 4 RPI04 TGACCA RPI37 CGGAAT
## 11 11 4 RPI15 ATGTCA RPI42 TAATCG
## 12 12 4 RPI23 GAGTGG RPI45 TCATTCThis section guides you through the detailed API of the package with
the aim to help you build your own workflow. The package is designed to
be flexible and should be easily adaptable to most experimental
contexts, using the experiment_design() function as a template, or building your own workflow from scratch.
The file_loading_and_checking() function loads the file
containing the DNA barcodes set and analyzes its content. In particular,
it checks that each barcode in the set is unique and uniquely
identified (removing any repetition that occurs). It also checks the
homogeneity of size of the barcodes, calculates their GC content and
detects the presence of homopolymers of length >= 3.
file_loading_and_checking(
file = export_dataset_to_file(
dataset = DNABarcodeCompatibility::IlluminaIndexesRaw
)
)
## Id sequence GC_content homopolymer
## 1 RPI01 ATCACG 50.00 FALSE
## 2 RPI02 CGATGT 50.00 FALSE
## 3 RPI03 TTAGGC 50.00 FALSE
## 4 RPI04 TGACCA 50.00 FALSE
## 5 RPI05 ACAGTG 50.00 FALSE
## 6 RPI06 GCCAAT 50.00 FALSE
## 7 RPI07 CAGATC 50.00 FALSE
## 8 RPI08 ACTTGA 33.33 FALSE
## 9 RPI09 GATCAG 50.00 FALSE
## 10 RPI10 TAGCTT 33.33 FALSE
## 11 RPI11 GGCTAC 66.67 FALSE
## 12 RPI12 CTTGTA 33.33 FALSE
## 13 RPI13 AGTCAA 33.33 FALSE
## 14 RPI14 AGTTCC 50.00 FALSE
## 15 RPI15 ATGTCA 33.33 FALSE
## 16 RPI16 CCGTCC 83.33 FALSE
## 17 RPI17 GTAGAG 50.00 FALSE
## 18 RPI18 GTCCGC 83.33 FALSE
## 19 RPI19 GTGAAA 33.33 TRUE
## 20 RPI20 GTGGCC 83.33 FALSE
## 21 RPI21 GTTTCG 50.00 TRUE
## 22 RPI22 CGTACG 66.67 FALSE
## 23 RPI23 GAGTGG 66.67 FALSE
## 24 RPI24 GGTAGC 66.67 FALSE
## 25 RPI25 ACTGAT 33.33 FALSE
## 26 RPI26 ATGAGC 50.00 FALSE
## 27 RPI27 ATTCCT 33.33 FALSE
## 28 RPI28 CAAAAG 33.33 TRUE
## 29 RPI29 CAACTA 33.33 FALSE
## 30 RPI30 CACCGG 83.33 FALSE
## 31 RPI31 CACGAT 50.00 FALSE
## 32 RPI32 CACTCA 50.00 FALSE
## 33 RPI33 CAGGCG 83.33 FALSE
## 34 RPI34 CATGGC 66.67 FALSE
## 35 RPI35 CATTTT 16.67 TRUE
## 36 RPI36 CCAACA 50.00 FALSE
## 37 RPI37 CGGAAT 50.00 FALSE
## 38 RPI38 CTAGCT 50.00 FALSE
## 39 RPI39 CTATAC 33.33 FALSE
## 40 RPI40 CTCAGA 50.00 FALSE
## 41 RPI41 GACGAC 66.67 FALSE
## 42 RPI42 TAATCG 33.33 FALSE
## 43 RPI43 TACAGC 50.00 FALSE
## 44 RPI44 TATAAT 0.00 FALSE
## 45 RPI45 TCATTC 33.33 FALSE
## 46 RPI46 TCCCGA 66.67 TRUE
## 47 RPI47 TCGAAG 50.00 FALSE
## 48 RPI48 TCGGCA 66.67 FALSEThe total number of combinations depends on the number of available
barcodes and of the multiplex level. For 48 barcodes and a multiplex
level of 3, the total number of combinations (compatible or not) can be
calculated using choose(48,3), which gives 17296
combinations. In many cases the total number of combinations can become
much larger (even gigantic), and one cannot perform an exhaustive search
(see get_random_combinations() below).
# Total number of combinations
choose(48,2)
## [1] 1128
# Load barcodes
barcodes <- DNABarcodeCompatibility::IlluminaIndexes
# Time for an exhaustive search
system.time(m <- get_all_combinations(index_df = barcodes,
mplex_level = 2,
platform = 4))
## user system elapsed
## 0.407 0.006 0.416
# Each line represents a compatible combination of barcodes
head(m)
## [,1] [,2]
## [1,] "RPI04" "RPI35"
## [2,] "RPI05" "RPI19"
## [3,] "RPI06" "RPI12"
## [4,] "RPI07" "RPI17"
## [5,] "RPI10" "RPI39"
## [6,] "RPI18" "RPI25"# Total number of combinations
choose(48,3)
## [1] 17296
# Load barcodes
barcodes <- DNABarcodeCompatibility::IlluminaIndexes
# Time for an exhaustive search
system.time(m <- get_all_combinations(index_df = barcodes,
mplex_level = 3,
platform = 4))
## user system elapsed
## 6.514 0.053 6.649
# Each line represents a compatible combination of barcodes
head(m)
## [,1] [,2] [,3]
## [1,] "RPI01" "RPI02" "RPI48"
## [2,] "RPI01" "RPI03" "RPI07"
## [3,] "RPI01" "RPI03" "RPI08"
## [4,] "RPI01" "RPI03" "RPI09"
## [5,] "RPI01" "RPI03" "RPI10"
## [6,] "RPI01" "RPI03" "RPI16"When the total number of combinations is too high, it is recommended to pick combinations at random and then select those that are compatible.
# Total number of combinations
choose(48,3)
## [1] 17296
# Load barcodes
barcodes <- DNABarcodeCompatibility::IlluminaIndexes
# Time for a random search
system.time(m <- get_random_combinations(index_df = barcodes,
mplex_level = 2,
platform = 4))
## user system elapsed
## 0.202 0.001 0.206
# Each line represents a compatible combination of barcodes
head(m)
## [,1] [,2]
## [1,] "RPI04" "RPI35"
## [2,] "RPI06" "RPI12"
## [3,] "RPI10" "RPI39"
## [4,] "RPI18" "RPI25"
## [5,] "RPI26" "RPI42"
## [6,] "RPI27" "RPI45"# Total number of combinations
choose(48,4)
## [1] 194580
# Load barcodes
barcodes <- DNABarcodeCompatibility::IlluminaIndexes
# Time for a random search
system.time(m <- get_random_combinations(index_df = barcodes,
mplex_level = 4,
platform = 4))
## user system elapsed
## 0.572 0.005 0.585
# Each line represents a compatible combination of barcodes
head(m)
## [,1] [,2] [,3] [,4]
## [1,] "RPI01" "RPI14" "RPI22" "RPI23"
## [2,] "RPI01" "RPI06" "RPI12" "RPI17"
## [3,] "RPI01" "RPI03" "RPI04" "RPI33"
## [4,] "RPI01" "RPI35" "RPI39" "RPI42"
## [5,] "RPI01" "RPI14" "RPI24" "RPI41"
## [6,] "RPI01" "RPI03" "RPI04" "RPI10"# Total number of combinations
choose(48,6)
## [1] 12271512
# Load barcodes
barcodes <- DNABarcodeCompatibility::IlluminaIndexes
# Time for a random search
system.time(m <- get_random_combinations(index_df = barcodes,
mplex_level = 6,
platform = 4))
## user system elapsed
## 0.827 0.009 0.844
# Each line represents a compatible combination of barcodes
head(m)
## [,1] [,2] [,3] [,4] [,5] [,6]
## [1,] "RPI01" "RPI06" "RPI26" "RPI29" "RPI38" "RPI47"
## [2,] "RPI01" "RPI03" "RPI17" "RPI18" "RPI27" "RPI35"
## [3,] "RPI01" "RPI03" "RPI08" "RPI15" "RPI22" "RPI31"
## [4,] "RPI01" "RPI05" "RPI09" "RPI12" "RPI45" "RPI48"
## [5,] "RPI01" "RPI06" "RPI14" "RPI23" "RPI30" "RPI45"
## [6,] "RPI01" "RPI16" "RPI19" "RPI21" "RPI35" "RPI45"# Load barcodes
barcodes <- DNABarcodeCompatibility::IlluminaIndexes
# Perform a random search of compatible combinations
m <- get_random_combinations(index_df = barcodes,
mplex_level = 3,
platform = 4)
# Keep barcodes that are robust against one substitution error
filtered_m <- distance_filter(index_df = barcodes,
combinations_m = m,
metric = "hamming",
d = 3)
# Each line represents a compatible combination of barcodes
head(filtered_m)
## V1 V2 V3
## [1,] "RPI01" "RPI05" "RPI48"
## [2,] "RPI01" "RPI24" "RPI45"
## [3,] "RPI01" "RPI26" "RPI45"
## [4,] "RPI01" "RPI23" "RPI41"
## [5,] "RPI01" "RPI06" "RPI08"
## [6,] "RPI01" "RPI26" "RPI48"# Keep set of compatible barcodes that are robust against one substitution
# error
filtered_m <- distance_filter(
index_df = DNABarcodeCompatibility::IlluminaIndexes,
combinations_m = get_random_combinations(index_df = barcodes,
mplex_level = 3,
platform = 4),
metric = "hamming", d = 3)
# Use a Shannon-entropy maximization approach to reduce barcode redundancy
df <- optimize_combinations(combination_m = filtered_m,
nb_lane = 12,
index_number = 48)
## [1] "Theoretical max entropy: 3.58352"
## [1] "Entropy of the optimized set: 3.58352"
# Each line represents a compatible combination of barcodes and each row a lane
# of the flow cell
df
## V1 V2 V3
## [1,] "RPI06" "RPI12" "RPI21"
## [2,] "RPI05" "RPI10" "RPI39"
## [3,] "RPI03" "RPI13" "RPI47"
## [4,] "RPI18" "RPI27" "RPI32"
## [5,] "RPI20" "RPI30" "RPI41"
## [6,] "RPI24" "RPI28" "RPI45"
## [7,] "RPI08" "RPI40" "RPI44"
## [8,] "RPI01" "RPI02" "RPI48"
## [9,] "RPI19" "RPI35" "RPI42"
## [10,] "RPI04" "RPI33" "RPI46"
## [11,] "RPI11" "RPI22" "RPI29"
## [12,] "RPI07" "RPI14" "RPI17"# Keep set of compatible barcodes that are robust against multiple substitution
# and insertion/deletion errors
filtered_m <- distance_filter(
index_df = DNABarcodeCompatibility::IlluminaIndexes,
combinations_m = get_random_combinations(index_df = barcodes,
mplex_level = 3,
platform = 4),
metric = "seqlev", d = 4)
# Use a Shannon-entropy maximization approach to reduce barcode redundancy
df <- optimize_combinations(combination_m = filtered_m,
nb_lane = 12,
index_number = 48)
## [1] "Theoretical max entropy: 3.58352"
## [1] "Entropy of the optimized set: 2.71161"
# Each line represents a compatible combination of barcodes and each row a
# lane of the flow cell
df
## V1 V2 V3
## [1,] "RPI15" "RPI28" "RPI46"
## [2,] "RPI17" "RPI27" "RPI29"
## [3,] "RPI20" "RPI30" "RPI35"
## [4,] "RPI12" "RPI20" "RPI30"
## [5,] "RPI03" "RPI37" "RPI41"
## [6,] "RPI12" "RPI20" "RPI30"
## [7,] "RPI17" "RPI27" "RPI29"
## [8,] "RPI04" "RPI28" "RPI35"
## [9,] "RPI15" "RPI28" "RPI46"
## [10,] "RPI03" "RPI37" "RPI41"
## [11,] "RPI37" "RPI41" "RPI45"
## [12,] "RPI23" "RPI27" "RPI29"