Read FastQC Data

Read FastQC data into R.

qc_read(file, modules = "all", verbose = TRUE)

Arguments

file	Path to the file to be imported. Can be the path to either : the fastqc zipped file (e.g.: 'path/to/samplename_fastqc.zip'). No need to unzip, or the unzipped folder name (e.g.: 'path/to/samplename_fastqc'), or the sample name (e.g.: 'path/to/samplename' ) or the fastqc_data.txt file,
modules	Character vector containing the names of FastQC modules for which you want to import/inspect the data. Default is all. Allowed values include one or the combination of: "Summary", "Basic Statistics", "Per base sequence quality", "Per tile sequence quality", "Per sequence quality scores", "Per base sequence content", "Per sequence GC content", "Per base N content", "Sequence Length Distribution", "Sequence Duplication Levels", "Overrepresented sequences", "Adapter Content", "Kmer Content" Partial match of module names allowed. For example, you can use modules = "GC content", instead of the full names modules = "Per sequence GC content".
verbose	logical value. If TRUE, print filename when reading.

Value

Returns a list of tibbles containing the data for specified modules.

Examples

# Demo file
qc.file <- system.file("fastqc_results", "S1_fastqc.zip",  package = "fastqcr")
qc.file
#> [1] "/Users/kassambara/Documents/R/MyPackages/fastqcr/inst/fastqc_results/S1_fastqc.zip"
# Read all modules
qc_read(qc.file)
#> Reading: /Users/kassambara/Documents/R/MyPackages/fastqcr/inst/fastqc_results/S1_fastqc.zip
#> $summary
#> # A tibble: 12 x 3
#>    status module                       sample  
#>    <chr>  <chr>                        <chr>   
#>  1 PASS   Basic Statistics             S1.fastq
#>  2 PASS   Per base sequence quality    S1.fastq
#>  3 PASS   Per tile sequence quality    S1.fastq
#>  4 PASS   Per sequence quality scores  S1.fastq
#>  5 FAIL   Per base sequence content    S1.fastq
#>  6 WARN   Per sequence GC content      S1.fastq
#>  7 PASS   Per base N content           S1.fastq
#>  8 WARN   Sequence Length Distribution S1.fastq
#>  9 PASS   Sequence Duplication Levels  S1.fastq
#> 10 PASS   Overrepresented sequences    S1.fastq
#> 11 PASS   Adapter Content              S1.fastq
#> 12 PASS   Kmer Content                 S1.fastq
#> 
#> $basic_statistics
#> # A tibble: 8 x 2
#>   `Basic Statistics`                pass                   
#>   <chr>                             <chr>                  
#> 1 Measure                           Value                  
#> 2 Filename                          S1.fastq               
#> 3 File type                         Conventional base calls
#> 4 Encoding                          Sanger / Illumina 1.9  
#> 5 Total Sequences                   50299587               
#> 6 Sequences flagged as poor quality 0                      
#> 7 Sequence length                   35-76                  
#> 8 %GC                               48                     
#> 
#> $per_base_sequence_quality
#> # A tibble: 43 x 7
#>    Base   Mean Median `Lower Quartile` `Upper Quartile` `10th Percentil…
#>    <chr> <dbl>  <dbl>            <dbl>            <dbl>            <dbl>
#>  1 1      31.2     32               32               32               32
#>  2 2      31.5     32               32               32               32
#>  3 3      31.7     32               32               32               32
#>  4 4      31.7     32               32               32               32
#>  5 5      31.7     32               32               32               32
#>  6 6      35.3     36               36               36               36
#>  7 7      35.3     36               36               36               36
#>  8 8      35.3     36               36               36               36
#>  9 9      35.3     36               36               36               36
#> 10 10-11  35.3     36               36               36               36
#> # ... with 33 more rows, and 1 more variable: `90th Percentile` <dbl>
#> 
#> $per_tile_sequence_quality
#> # A tibble: 18,576 x 3
#>     Tile Base    Mean
#>    <dbl> <chr>  <dbl>
#>  1 11101 1     0.175 
#>  2 11101 2     0.0478
#>  3 11101 3     0.0668
#>  4 11101 4     0.0558
#>  5 11101 5     0.0485
#>  6 11101 6     0.0194
#>  7 11101 7     0.104 
#>  8 11101 8     0.0629
#>  9 11101 9     0.103 
#> 10 11101 10-11 0.0580
#> # ... with 18,566 more rows
#> 
#> $per_sequence_quality_scores
#> # A tibble: 34 x 2
#>    Quality Count
#>      <dbl> <dbl>
#>  1       2    75
#>  2       3     0
#>  3       4     0
#>  4       5     0
#>  5       6     0
#>  6       7     0
#>  7       8     0
#>  8       9     0
#>  9      10     0
#> 10      11     0
#> # ... with 24 more rows
#> 
#> $per_base_sequence_content
#> # A tibble: 43 x 5
#>    Base      G     A     T     C
#>    <chr> <dbl> <dbl> <dbl> <dbl>
#>  1 1      24.1  27.4  24.5  24.0
#>  2 2      23.5  27.2  25.5  23.8
#>  3 3      23.2  25.8  26.3  24.7
#>  4 4      23.5  25.9  26.2  24.3
#>  5 5      23.7  26.3  26.1  23.9
#>  6 6      24.3  25.4  25.6  24.7
#>  7 7      24.1  25.7  26.1  24.1
#>  8 8      23.5  25.8  26.2  24.5
#>  9 9      23.5  25.6  26.4  24.5
#> 10 10-11  23.6  25.9  26.4  24.1
#> # ... with 33 more rows
#> 
#> $per_sequence_gc_content
#> # A tibble: 101 x 2
#>    `GC Content` Count
#>           <dbl> <dbl>
#>  1            0  81  
#>  2            1  44  
#>  3            2  14  
#>  4            3  39.5
#>  5            4  58  
#>  6            5  78.5
#>  7            6 143  
#>  8            7 264. 
#>  9            8 342. 
#> 10            9 428. 
#> # ... with 91 more rows
#> 
#> $per_base_n_content
#> # A tibble: 43 x 2
#>    Base  `N-Count`
#>    <chr>     <dbl>
#>  1 1      0.0634  
#>  2 2      0.000310
#>  3 3      0.000270
#>  4 4      0.000153
#>  5 5      0.000149
#>  6 6      0.00938 
#>  7 7      0.00256 
#>  8 8      0.000260
#>  9 9      0.000282
#> 10 10-11  0.000604
#> # ... with 33 more rows
#> 
#> $sequence_length_distribution
#> # A tibble: 42 x 2
#>    Length Count
#>     <dbl> <dbl>
#>  1     35  1282
#>  2     36   144
#>  3     37   160
#>  4     38   172
#>  5     39   177
#>  6     40   164
#>  7     41   174
#>  8     42   183
#>  9     43   167
#> 10     44   198
#> # ... with 32 more rows
#> 
#> $sequence_duplication_levels
#> # A tibble: 16 x 3
#>    `Duplication Level` `Percentage of deduplicated` `Percentage of total`
#>    <chr>                                      <dbl>                 <dbl>
#>  1 1                                    83.8                     69.4    
#>  2 2                                    12.7                     21.1    
#>  3 3                                     2.63                     6.53   
#>  4 4                                     0.591                    1.96   
#>  5 5                                     0.152                    0.629  
#>  6 6                                     0.0400                   0.199  
#>  7 7                                     0.0128                   0.0744 
#>  8 8                                     0.00532                  0.0352 
#>  9 9                                     0.00243                  0.0181 
#> 10 >10                                   0.00393                  0.0415 
#> 11 >50                                   0.0000298                0.00218
#> 12 >100                                  0.0000247                0.00524
#> 13 >500                                  0.00000300               0.00202
#> 14 >1k                                   0.00000266               0.00260
#> 15 >5k                                   0                        0      
#> 16 >10k+                                 0.00000241               0.0565 
#> 
#> $overrepresented_sequences
#> # A tibble: 0 x 0
#> 
#> $adapter_content
#> # A tibble: 64 x 5
#>    Position `Illumina Unive… `Illumina Small… `Nextera Transp… `SOLID Small RN…
#>       <dbl>            <dbl>            <dbl>            <dbl>            <dbl>
#>  1        1       0.00000994       0.00000199        0.0000139       0         
#>  2        2       0.0000119        0.00000199        0.0000258       0.00000199
#>  3        3       0.0000179        0.00000398        0.0000358       0.00000596
#>  4        4       0.0000258        0.00000398        0.0000437       0.00000596
#>  5        5       0.0000338        0.00000398        0.0000497       0.00000596
#>  6        6       0.0000378        0.00000398        0.0000596       0.00000795
#>  7        7       0.0000437        0.00000398        0.0000676       0.00000795
#>  8        8       0.0000537        0.00000398        0.0000736       0.00000994
#>  9        9       0.0000557        0.00000398        0.0000835       0.00000994
#> 10       10       0.0000557        0.00000398        0.0000954       0.00000994
#> # ... with 54 more rows
#> 
#> $kmer_content
#> # A tibble: 0 x 0
#> 
#> $total_deduplicated_percentage
#> [1] 82.76
#> 
#> attr(,"class")
#> [1] "list"    "qc_read"

# Read a specified module
qc_read(qc.file,"Per base sequence quality")
#> Reading: /Users/kassambara/Documents/R/MyPackages/fastqcr/inst/fastqc_results/S1_fastqc.zip
#> $per_base_sequence_quality
#> # A tibble: 43 x 7
#>    Base   Mean Median `Lower Quartile` `Upper Quartile` `10th Percentil…
#>    <chr> <dbl>  <dbl>            <dbl>            <dbl>            <dbl>
#>  1 1      31.2     32               32               32               32
#>  2 2      31.5     32               32               32               32
#>  3 3      31.7     32               32               32               32
#>  4 4      31.7     32               32               32               32
#>  5 5      31.7     32               32               32               32
#>  6 6      35.3     36               36               36               36
#>  7 7      35.3     36               36               36               36
#>  8 8      35.3     36               36               36               36
#>  9 9      35.3     36               36               36               36
#> 10 10-11  35.3     36               36               36               36
#> # ... with 33 more rows, and 1 more variable: `90th Percentile` <dbl>
#> 
#> attr(,"class")
#> [1] "list"    "qc_read"