Mercurial > repos > erinija > dnp_binary_strings
annotate dnp-select-range.sh @ 0:611156829647 draft default tip
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
| author | erinija |
|---|---|
| date | Fri, 01 May 2020 12:07:46 +0000 |
| parents | |
| children |
| rev | line source |
|---|---|
|
0
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
1 #!/bin/sh |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
2 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
3 if test "$#" -ne 5; then |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
4 echo "" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
5 echo " CALL " |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
6 echo " sh dnp-select-range.sh select-range-input.tabular start length dinucleotides select-range-output.tabular" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
7 echo "" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
8 echo " INPUT " |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
9 echo " select-range-input.tabular - full length dinucleotide frequency profiles" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
10 echo " start - start position of selection - identified start position of nucleosome's sequence" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
11 echo " length - length of selection; default =146 nucleosome's length in base pairs" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
12 echo " dinucleotides - any subset of dinucleotides enclosed by quotes 'AA AC AG AT CA CC ...'" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
13 echo "" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
14 echo " OUTPUT " |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
15 echo " select-range-output.tabular - rows of input file selected at a given position spanning a length" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
16 echo "" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
17 echo " DESCRIPTION" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
18 echo " Selects rows from input table within a given range and adds a column with a position number." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
19 echo "" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
20 echo " Example of an input table" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
21 echo " AA.f AA.r AC.f AC.r AG.f AG.r AT.f AT.r ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
22 echo " 0.0763 0.067920 0.057800 0.078120 0.081600 0.061960 0.055600 0.044080 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
23 echo " 0.077160 0.073760 0.056000 0.072160 0.079400 0.060720 0.055960 0.047040 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
24 echo " 0.083320 0.071200 0.053840 0.080760 0.084560 0.064880 0.050440 0.048720 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
25 echo " 0.077960 0.068200 0.056040 0.075520 0.080120 0.061680 0.053160 0.047400 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
26 echo " 0.078200 0.069120 0.056880 0.074000 0.084360 0.060840 0.053520 0.046280 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
27 echo " ... " |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
28 echo "" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
29 echo " Example of an output table where start=20" |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
30 echo " pos AA.f AC.f AG.f AT.f CA.f CC.f CG.f CT.f ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
31 echo " 20 0.100200 0.084720 0.077200 0.072480 0.066160 0.044160 0.004560 0.060720 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
32 echo " 21 0.172440 0.024800 0.002080 0.101240 0.131840 0.007200 0.000320 0.095920 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
33 echo " 22 0.077160 0.096240 0.314320 0.047360 0.012040 0.028560 0.011840 0.013680 ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
34 echo " ..." |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
35 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
36 exit 1 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
37 fi |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
38 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
39 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
40 # input file name |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
41 name=$1 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
42 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
43 # start position |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
44 startpos=$2 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
45 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
46 # length of selection (146bp) |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
47 length=$3 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
48 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
49 # list of dinucleotides |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
50 dinucleotides=$4 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
51 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
52 # output file |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
53 out=$5 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
54 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
55 # compute length of the file |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
56 len=`wc ${name} |awk '{print $1}'` |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
57 #echo $len |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
58 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
59 len=$((len-1)) |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
60 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
61 # endpos |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
62 endpos=$((startpos+length)) |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
63 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
64 cnum=1 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
65 # TO DO:should scheck if endpos is within the range |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
66 for di in ${dinucleotides} |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
67 do |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
68 # column number for forward and complementary profile |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
69 i1=`awk -v name=$di'.f' '{ for (i=1; i<=NF; i++) if($i==name) print i; exit}' ${name}` |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
70 i2=`awk -v name=$di'.r' '{ for (i=1; i<=NF; i++) if($i==name) print i; exit}' ${name}` |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
71 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
72 echo "$di.f" > forward.${di} |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
73 awk -v k=${i1} '{print $k}' $name | sed -n "${startpos},${endpos}p" >> forward.${di} |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
74 echo "$di.r"> complement.${di} |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
75 awk -v k=${i2} '{print $k}' $name | sed -n "${startpos},${endpos}p" >> complement.${di} |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
76 cnum=$((cnum+1)) |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
77 done |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
78 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
79 # sequence positions within range |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
80 echo "pos" > seq.pos |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
81 seq ${startpos} 1 ${endpos} >> seq.pos |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
82 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
83 # paste forward |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
84 paste seq.pos forward.* > forward |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
85 paste complement.* > complement |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
86 |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
87 # create output |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
88 paste forward complement > ${out} |
|
611156829647
"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff
changeset
|
89 rm seq.pos forward* complement* |
