合并文件中的字段

Question 1

一种“awk”方法，

awk '
  $1!="exon" {                       # If the first died is unequal to "exon"
    if(previous)print previous       # If there is a previous line then print it
    print                            # Print the current line
    previous=start=end=exon_seq=""   # Set all variable to an empty string
    next                             # Move on to the next line in the input file
  }
  {
    if(exon_seq) {                   # if there is a sequence of lines with "exon in field 1
      if(start<=$2 && end>=$3)       # if the start value (field 2) of the previous line 
                                     # is less or equal to the current line and the end
                                     # value of the previous line is greater than or
                                     # equal to field 3 of the current line
        next                         # then do nothing and read the next line
      else                           # if there is no overlap,
        print previous               # then print the previous line
    }
    else {                           # if we are not already in the a sequence of 
                                     # "exon" lines, then this is the first one
      exon_seq=1                     # so exon_seq should become 1
    }
    previous=$0; start=$2; end=$3    # `start` become field2, `end` becomes field 3 and
                                     # `previous` becomes the current record (line)
  }
  END{                               # After all lines are processed
    if(previous) print previous      # If there still is a previous line, then print it
  }
' file

Answer

一种“awk”方法，

awk '
  $1!="exon" {                       # If the first died is unequal to "exon"
    if(previous)print previous       # If there is a previous line then print it
    print                            # Print the current line
    previous=start=end=exon_seq=""   # Set all variable to an empty string
    next                             # Move on to the next line in the input file
  }
  {
    if(exon_seq) {                   # if there is a sequence of lines with "exon in field 1
      if(start<=$2 && end>=$3)       # if the start value (field 2) of the previous line 
                                     # is less or equal to the current line and the end
                                     # value of the previous line is greater than or
                                     # equal to field 3 of the current line
        next                         # then do nothing and read the next line
      else                           # if there is no overlap,
        print previous               # then print the previous line
    }
    else {                           # if we are not already in the a sequence of 
                                     # "exon" lines, then this is the first one
      exon_seq=1                     # so exon_seq should become 1
    }
    previous=$0; start=$2; end=$3    # `start` become field2, `end` becomes field 3 and
                                     # `previous` becomes the current record (line)
  }
  END{                               # After all lines are processed
    if(previous) print previous      # If there still is a previous line, then print it
  }
' file

Question 2

我会使用 Perl 来解决如此复杂的任务。这是部分解决方案，您可能需要对其进行调整以更好地适合您：

#!/usr/bin/perl
use warnings;
use strict;
use List::Util qw{ max };

sub output {
    my $previous = shift;
    print join ' ', 'exon',
               @{$previous}{qw(start end score strand frame attribute)};
}

$\ = "\n";
my %previous;
while (<>) {
    chomp;
    my ($region, $start, $end, $score, $strand, $frame, $attribute)
        = split ' ', $_, 7;

    if ($. == 1) {
        print;

    } elsif ('exon' eq $region) {
        if (keys %previous
            and $start < $previous{end}                # Overlap.
           ) {

            if ($end > $previous{end}) {               # Not contained.
                $previous{attribute} =~ s/; Name .*//;
                $previous{attribute} .= '; ' 
                                     . ($attribute =~ /(Transcript ".*?")/)[0];
                $previous{end} = $end;
            }

        } else {
            if (keys %previous) {
                output(\%previous);
            }

            %previous = ( start     => $start,
                          end       => $end,
                          score     => $score,
                          strand    => $strand,
                          frame     => $frame,
                          attribute => $attribute,
                        );
        }

    } else {
        output(\%previous) if keys %previous;
        %previous = ();
    }
}

output(\%previous) if keys %previous;

Answer

我会使用 Perl 来解决如此复杂的任务。这是部分解决方案，您可能需要对其进行调整以更好地适合您：

#!/usr/bin/perl
use warnings;
use strict;
use List::Util qw{ max };

sub output {
    my $previous = shift;
    print join ' ', 'exon',
               @{$previous}{qw(start end score strand frame attribute)};
}

$\ = "\n";
my %previous;
while (<>) {
    chomp;
    my ($region, $start, $end, $score, $strand, $frame, $attribute)
        = split ' ', $_, 7;

    if ($. == 1) {
        print;

    } elsif ('exon' eq $region) {
        if (keys %previous
            and $start < $previous{end}                # Overlap.
           ) {

            if ($end > $previous{end}) {               # Not contained.
                $previous{attribute} =~ s/; Name .*//;
                $previous{attribute} .= '; ' 
                                     . ($attribute =~ /(Transcript ".*?")/)[0];
                $previous{end} = $end;
            }

        } else {
            if (keys %previous) {
                output(\%previous);
            }

            %previous = ( start     => $start,
                          end       => $end,
                          score     => $score,
                          strand    => $strand,
                          frame     => $frame,
                          attribute => $attribute,
                        );
        }

    } else {
        output(\%previous) if keys %previous;
        %previous = ();
    }
}

output(\%previous) if keys %previous;

合并文件中的字段

答案1

答案2

相关内容