Extend ranges for prime editing

Extend target ranges to span in which to look for spacer-pam seqs

extend_for_pe(
  gr,
  bsgenome,
  nrt = 16,
  spacer = strrep("N", 20),
  pam = "NGG",
  plot = FALSE
)

Arguments

gr

GRanges-class
bsgenome

BSgenome-class
nrt

number: reverse transcription length
spacer

string: spacer pattern in extended IUPAC alphabet
pam

string: pam pattern in extended IUPAC alphabet
plot

TRUE (default) or FALSE

Value

GRanges-class

Details

Extend target ranges to find nearby spacers for prime editing

Examples

require(magrittr)
bsgenome <- BSgenome.Hsapiens.UCSC.hg38::BSgenome.Hsapiens.UCSC.hg38
gr <- char_to_granges(c( PRNP = 'chr20:4699600:+',             # snp
                         HBB  = 'chr11:5227002:-',             # snp
                         HEXA = 'chr15:72346580-72346583:-',   # del
                         CFTR = 'chr7:117559593-117559595:+'), # ins
                     bsgenome = bsgenome)
find_primespacers(gr, bsgenome)
#> Find primespacers for 4 targets
#> 	Found 10 primespacers
#> 	Count offtargets with max 0 mismatches using bowtie
#> 		Count genome (mis)matches
#> 			Expand iupac ambiguities in pam
#> 			Write reads to ~/multicrisprout/spacers.fa
#> 			Map reads: ~/multicrisprout/spacers/spacers_to_BSgenome.Hsapiens.UCSC.hg38.txt
#> 			Load results
#> 				Read 53 hits with max 1 mismatch(es)
#> 				Retain 20 after removing NGG 'N' mismatches (avoid double counting expanded pams)
#> 				Retain 20 after removing NGG 'G1' mismatches(except for NGG -> NAG, which is allowed)
#> 				Retain 20 after removing NGG 'G2' mismatches
#> 				Retain 11 after removing more than 0 mismatches
#> 			Count matches
#> 		Count off-targets
#> 		       9 are off0 free
#> 	Score ontargets
#> 		Add (4-23-3) contextseqs
#> 		Score contextseqs with Doench2014
#> Find nickspacers
#> Find spacers in 10 targets
#> 	Found 32 spacers
#> 	Count offtargets with max 2 mismatches using bowtie
#> 		Count genome (mis)matches
#> 			Expand iupac ambiguities in pam
#> 			Write reads to ~/multicrisprout/spacers.fa
#> 			Map reads: ~/multicrisprout/spacers/spacers_to_BSgenome.Hsapiens.UCSC.hg38.txt
#> 			Load results
#> 				Read 91 hits with max 2 mismatch(es)
#> 				Retain 37 after removing NGG 'N' mismatches (avoid double counting expanded pams)
#> 				Retain 36 after removing NGG 'G1' mismatches(except for NGG -> NAG, which is allowed)
#> 				Retain 33 after removing NGG 'G2' mismatches
#> 				Retain 33 after removing more than 2 mismatches
#> 			Count matches
#> 		Count off-targets
#> 		       30 are off0 free
#> 		       32 are off1 free
#> 		       24 are off2 free
#> 	Filter for best offtarget counts
#> 		Retain 32 with best off0 counts per pename
#> 		Retain 32 with best off1 counts per pename
#> 		Retain 24 with best off2 counts per pename
#> 	Score ontargets
#> 		Add (4-23-3) contextseqs
#> 		Score contextseqs with Doench2014
#> Warning: Removed 34 rows containing missing values (geom_point).
#> Warning: Removed 34 rows containing missing values (geom_point).
#> GRanges object with 10 ranges and 21 metadata columns:
#>          seqnames              ranges strand |  targetname targetstart
#>             <Rle>           <IRanges>  <Rle> | <character>   <integer>
#>   CFTR_1     chr7 117559575-117559594      + |        CFTR   117559593
#>   CFTR_2     chr7 117559606-117559625      - |        CFTR   117559593
#>    HBB_1    chr11     5227003-5227022      - |         HBB     5227002
#>    HBB_2    chr11     5226984-5227003      + |         HBB     5227002
#>   HEXA_1    chr15   72346551-72346570      + |        HEXA    72346580
#>   HEXA_2    chr15   72346558-72346577      + |        HEXA    72346580
#>   PRNP_1    chr20     4699568-4699587      + |        PRNP     4699600
#>   PRNP_2    chr20     4699569-4699588      + |        PRNP     4699600
#>   PRNP_3    chr20     4699575-4699594      + |        PRNP     4699600
#>   PRNP_4    chr20     4699578-4699597      + |        PRNP     4699600
#>          targetend  crisprname         crisprspacer   crisprpam  crisprprimer
#>          <integer> <character>          <character> <character>   <character>
#>   CFTR_1 117559595      CFTR_1 ATTAAAGAAAATATCATCTT         TGG AAGAAAATATCAT
#>   CFTR_2 117559595      CFTR_2 TCTGTATCTATATTCATCAT         AGG TATCTATATTCAT
#>    HBB_1   5227002       HBB_1 CATGGTGCATCTGACTCCTG         AGG GTGCATCTGACTC
#>    HBB_2   5227002       HBB_2 GTAACGGCAGACTTCTCCTC         AGG CGGCAGACTTCTC
#>   HEXA_1  72346583      HEXA_1 TGTAGAAATCCTTCCAGTCA         GGG GAAATCCTTCCAG
#>   HEXA_2  72346583      HEXA_2 ATCCTTCCAGTCAGGGCCAT         AGG TTCCAGTCAGGGC
#>   PRNP_1   4699600      PRNP_1 AGCAGCTGGGGCAGTGGTGG         GGG GCTGGGGCAGTGG
#>   PRNP_2   4699600      PRNP_2 GCAGCTGGGGCAGTGGTGGG         GGG CTGGGGCAGTGGT
#>   PRNP_3   4699600      PRNP_3 GGGGCAGTGGTGGGGGGCCT         TGG CAGTGGTGGGGGG
#>   PRNP_4   4699600      PRNP_4 GCAGTGGTGGGGGGCCTTGG         CGG TGGTGGGGGGCCT
#>          crisprtranscript               crisprextension
#>               <character>                   <character>
#>   CFTR_1 CTTTGGTGTTTCCTAT ATAGGAAACACCAAAGATGATATTTTCTT
#>   CFTR_2 CATAGGAAACACCAAA TTTGGTGTTTCCTATGATGAATATAGATA
#>    HBB_1 CTGAGGAGAAGTCTGC GCAGACTTCTCCTCAGGAGTCAGATGCAC
#>    HBB_2 CTCAGGAGTCAGATGC GCATCTGACTCCTGAGGAGAAGTCTGCCG
#>   HEXA_1 TCAGGGCCATAGGATA TATCCTATGGCCCTGACTGGAAGGATTTC
#>   HEXA_2 CATAGGATATACGGTT AACCGTATATCCTATGGCCCTGACTGGAA
#>   PRNP_1 TGGGGGGCCTTGGCGG CCGCCAAGGCCCCCCACCACTGCCCCAGC
#>   PRNP_2 GGGGGGCCTTGGCGGC GCCGCCAAGGCCCCCCACCACTGCCCCAG
#>   PRNP_3 CCTTGGCGGCTACATG CATGTAGCCGCCAAGGCCCCCCACCACTG
#>   PRNP_4 TGGCGGCTACATGCTG CAGCATGTAGCCGCCAAGGCCCCCCACCA
#>                      crisprextrange       off      off0 Doench2014
#>                         <character> <numeric> <numeric>  <numeric>
#>   CFTR_1 chr7:117559579-117559607:-         0         0 0.03399990
#>   CFTR_2 chr7:117559593-117559621:+         0         0 0.22337056
#>    HBB_1    chr11:5226990-5227018:+         1         1 0.13111422
#>    HBB_2    chr11:5226988-5227016:-         0         0 0.41398065
#>   HEXA_1  chr15:72346555-72346583:-         0         0 0.10728361
#>   HEXA_2  chr15:72346562-72346590:-         0         0 0.03942528
#>   PRNP_1    chr20:4699572-4699600:-         0         0 0.00994899
#>   PRNP_2    chr20:4699573-4699601:-         0         0 0.04496627
#>   PRNP_3    chr20:4699579-4699607:-         0         0 0.00996254
#>   PRNP_4    chr20:4699582-4699610:-         0         0 0.20935863
#>                                                                                                        nickrange
#>                                                                                                      <character>
#>   CFTR_1                                                                              chr7:117559646-117559665:-
#>   CFTR_2                                                                              chr7:117559506-117559525:+
#>    HBB_1                                                         chr11:5226916-5226935:+;chr11:5226917-5226936:+
#>    HBB_2                                                                                                    <NA>
#>   HEXA_1 chr15:72346621-72346640:-;chr15:72346628-72346647:-;chr15:72346632-72346651:-;chr15:72346647-72346666:-
#>   HEXA_2 chr15:72346621-72346640:-;chr15:72346628-72346647:-;chr15:72346632-72346651:-;chr15:72346647-72346666:-
#>   PRNP_1                                 chr20:4699632-4699651:-;chr20:4699633-4699652:-;chr20:4699664-4699683:-
#>   PRNP_2                                 chr20:4699632-4699651:-;chr20:4699633-4699652:-;chr20:4699664-4699683:-
#>   PRNP_3                                 chr20:4699632-4699651:-;chr20:4699633-4699652:-;chr20:4699664-4699683:-
#>   PRNP_4                                 chr20:4699632-4699651:-;chr20:4699633-4699652:-;chr20:4699664-4699683:-
#>                                                                                   nickspacer
#>                                                                                  <character>
#>   CFTR_1                                                                AGTTTCTTACCTCTTCTAGT
#>   CFTR_2                                                                GAGGGTAAAATTAAGCACAG
#>    HBB_1                                           ACCTTGATACCAACCTGCCC;CCTTGATACCAACCTGCCCA
#>    HBB_2                                                                                <NA>
#>   HEXA_1 TGGTCACCAAGGCCGGCTTC;CTGGAACTGGTCACCAAGGC;GGAGCTGGAACTGGTCACCA;AGTGAACTATATGAAGGAGC
#>   HEXA_2 TGGTCACCAAGGCCGGCTTC;CTGGAACTGGTCACCAAGGC;GGAGCTGGAACTGGTCACCA;AGTGAACTATATGAAGGAGC
#>   PRNP_1                      TCACTGCCGAAATGTATGAT;GTCACTGCCGAAATGTATGA;GCATGTTTTCACGATAGTAA
#>   PRNP_2                      TCACTGCCGAAATGTATGAT;GTCACTGCCGAAATGTATGA;GCATGTTTTCACGATAGTAA
#>   PRNP_3                      TCACTGCCGAAATGTATGAT;GTCACTGCCGAAATGTATGA;GCATGTTTTCACGATAGTAA
#>   PRNP_4                      TCACTGCCGAAATGTATGAT;GTCACTGCCGAAATGTATGA;GCATGTTTTCACGATAGTAA
#>                  nickpam     nickoff    nickoff0    nickoff1    nickoff2
#>              <character> <character> <character> <character> <character>
#>   CFTR_1             TGG           0           0           0           0
#>   CFTR_2             TGG           0           0           0           0
#>    HBB_1         AGG;GGG         1;1         1;1         0;0         0;0
#>    HBB_2            <NA>        <NA>        <NA>        <NA>        <NA>
#>   HEXA_1 CGG;CGG;AGG;TGG     0;0;0;0     0;0;0;0     0;0;0;0     0;0;0;0
#>   HEXA_2 CGG;CGG;AGG;TGG     0;0;0;0     0;0;0;0     0;0;0;0     0;0;0;0
#>   PRNP_1     GGG;TGG;CGG       0;0;0       0;0;0       0;0;0       0;0;0
#>   PRNP_2     GGG;TGG;CGG       0;0;0       0;0;0       0;0;0       0;0;0
#>   PRNP_3     GGG;TGG;CGG       0;0;0       0;0;0       0;0;0       0;0;0
#>   PRNP_4     GGG;TGG;CGG       0;0;0       0;0;0       0;0;0       0;0;0
#>              nickDoench2014
#>                 <character>
#>   CFTR_1               0.38
#>   CFTR_2               0.49
#>    HBB_1          0.06;0.42
#>    HBB_2               <NA>
#>   HEXA_1 0.01;0.05;0.32;0.2
#>   HEXA_2 0.01;0.05;0.32;0.2
#>   PRNP_1     0.14;0.32;0.52
#>   PRNP_2     0.14;0.32;0.52
#>   PRNP_3     0.14;0.32;0.52
#>   PRNP_4     0.14;0.32;0.52
#>   -------
#>   seqinfo: 595 sequences (1 circular) from hg38 genome
(grext <- extend_for_pe(gr))
#> GRanges object with 8 ranges and 3 metadata columns:
#>          seqnames              ranges strand |  targetname targetstart
#>             <Rle>           <IRanges>  <Rle> | <character>   <integer>
#>   PRNP_f    chr20     4699568-4699605      + |        PRNP     4699600
#>    HBB_f    chr11     5226970-5227007      + |         HBB     5227002
#>   HEXA_f    chr15   72346551-72346585      + |        HEXA    72346580
#>   CFTR_f     chr7 117559563-117559598      + |        CFTR   117559593
#>   PRNP_r    chr20     4699595-4699632      - |        PRNP     4699600
#>    HBB_r    chr11     5226997-5227034      - |         HBB     5227002
#>   HEXA_r    chr15   72346578-72346612      - |        HEXA    72346580
#>   CFTR_r     chr7 117559590-117559625      - |        CFTR   117559593
#>          targetend
#>          <integer>
#>   PRNP_f   4699600
#>    HBB_f   5227002
#>   HEXA_f  72346583
#>   CFTR_f 117559595
#>   PRNP_r   4699600
#>    HBB_r   5227002
#>   HEXA_r  72346583
#>   CFTR_r 117559595
#>   -------
#>   seqinfo: 595 sequences (1 circular) from hg38 genome
find_spacers(grext, bsgenome, complement = FALSE)
#> Find spacers in 8 targets
#> 	Found 10 spacers
#> 	Count offtargets with max 2 mismatches using bowtie
#> 		Count genome (mis)matches
#> 			Expand iupac ambiguities in pam
#> 			Write reads to ~/multicrisprout/spacers.fa
#> 			Map reads: ~/multicrisprout/spacers/spacers_to_BSgenome.Hsapiens.UCSC.hg38.txt
#> 			Load results
#> 				Read 140 hits with max 2 mismatch(es)
#> 				Retain 80 after removing NGG 'N' mismatches (avoid double counting expanded pams)
#> 				Retain 77 after removing NGG 'G1' mismatches(except for NGG -> NAG, which is allowed)
#> 				Retain 71 after removing NGG 'G2' mismatches
#> 				Retain 71 after removing more than 2 mismatches
#> 			Count matches
#> 		Count off-targets
#> 		       9 are off0 free
#> 		       9 are off1 free
#> 		       2 are off2 free
#> 	Score ontargets
#> 		Add (4-23-3) contextseqs
#> 		Score contextseqs with Doench2014
#> GRanges object with 10 ranges and 11 metadata columns:
#>            seqnames              ranges strand |  targetname targetstart
#>               <Rle>           <IRanges>  <Rle> | <character>   <integer>
#>     CFTR_f     chr7 117559575-117559594      + |        CFTR   117559593
#>     CFTR_r     chr7 117559606-117559625      - |        CFTR   117559593
#>      HBB_f    chr11     5226984-5227003      + |         HBB     5227002
#>      HBB_r    chr11     5227003-5227022      - |         HBB     5227002
#>   HEXA_f_1    chr15   72346551-72346570      + |        HEXA    72346580
#>   HEXA_f_2    chr15   72346558-72346577      + |        HEXA    72346580
#>   PRNP_f_1    chr20     4699568-4699587      + |        PRNP     4699600
#>   PRNP_f_2    chr20     4699569-4699588      + |        PRNP     4699600
#>   PRNP_f_3    chr20     4699575-4699594      + |        PRNP     4699600
#>   PRNP_f_4    chr20     4699578-4699597      + |        PRNP     4699600
#>            targetend  crisprname         crisprspacer   crisprpam       off
#>            <integer> <character>          <character> <character> <numeric>
#>     CFTR_f 117559595      CFTR_f ATTAAAGAAAATATCATCTT         TGG         2
#>     CFTR_r 117559595      CFTR_r TCTGTATCTATATTCATCAT         AGG         1
#>      HBB_f   5227002       HBB_f GTAACGGCAGACTTCTCCTC         AGG         0
#>      HBB_r   5227002       HBB_r CATGGTGCATCTGACTCCTG         AGG         4
#>   HEXA_f_1  72346583    HEXA_f_1 TGTAGAAATCCTTCCAGTCA         GGG         1
#>   HEXA_f_2  72346583    HEXA_f_2 ATCCTTCCAGTCAGGGCCAT         AGG         0
#>   PRNP_f_1   4699600    PRNP_f_1 AGCAGCTGGGGCAGTGGTGG         GGG        11
#>   PRNP_f_2   4699600    PRNP_f_2 GCAGCTGGGGCAGTGGTGGG         GGG        27
#>   PRNP_f_3   4699600    PRNP_f_3 GGGGCAGTGGTGGGGGGCCT         TGG        11
#>   PRNP_f_4   4699600    PRNP_f_4 GCAGTGGTGGGGGGCCTTGG         CGG         4
#>                 off0      off1      off2 Doench2014
#>            <numeric> <numeric> <numeric>  <numeric>
#>     CFTR_f         0         0         2 0.03399990
#>     CFTR_r         0         0         1 0.22337056
#>      HBB_f         0         0         0 0.41398065
#>      HBB_r         1         0         3 0.13111422
#>   HEXA_f_1         0         0         1 0.10728361
#>   HEXA_f_2         0         0         0 0.03942528
#>   PRNP_f_1         0         0        11 0.00994899
#>   PRNP_f_2         0         9        18 0.04496627
#>   PRNP_f_3         0         0        11 0.00996254
#>   PRNP_f_4         0         0         4 0.20935863
#>   -------
#>   seqinfo: 595 sequences (1 circular) from hg38 genome