#Reference Francis #use warnings; use XML::Simple; use LWP::UserAgent; use HTTP::Request::Common; use URI::Escape; use Data::Dumper; use Text::CSV; use List::Util qw( min max ); my @protein_keywords = ("inhibitors", "inhibitor", "activity", "activi +tor", "activities", "activated", "proteins", "deficiency", "levels", +"functions", "reductions", "protease", "proteases", "complex concentr +ate"); my $ua = LWP::UserAgent->new; my $csv = Text::CSV->new({ sep_char => ',' }); my $ab_csv = Text::CSV->new({ sep_char => ',' }); #Open result CSV file. open(my $fh, ">", "output1.csv"); print $fh "Pubmed ID, Drug Name, Position of keywords, Valid Proteins, + Position of proteins, Minimum separation, Scoring\n"; #open abnormal condition csv file my $i = 0; my @protein_list; open(my $abnorm, '<', "Protein.csv"); while (my $ab_line = <$abnorm>) { chomp $ab_line; if ($ab_csv->parse($ab_line)) { #skip first line next if ($. == 1); my @ab_fields = $ab_csv->fields(); $protein_list[$i] = $ab_fields[0].$ab_fields[1]; $i++; } } #Open specified CSV file open(my $data, '<', "finalidlist.csv"); while (my $line = <$data>) { chomp $line; if ($csv->parse($line)) { #Skip first line next if ($. == 1); } my @fields = $csv->fields(); my $valid_proteins = ""; push my @id , $fields[1]; foreach my $id(@id){ if ($id ne "no"){ #Initialize http request my $args = "db=pubmed&id=$id&retmode=text&rettype=abstract"; my $req = new HTTP::Request POST => 'https://eutils.ncbi.nlm.n +ih.gov/entrez/eutils/efetch.fcgi'; $req->content_type('application/x-www-form-urlencoded'); $req->content($args); #Get response my $response = $ua->request($req); my $content = $response->content; #$content = lc($content); my @abstract = split /[.]/, $content; my $keyword_position = ""; foreach my $protein_keywords(@protein_keywords) { my $i = 0; foreach my $abstract (@abstract){ if($abstract =~ /\b$protein_keywords\b/i) { $keyword_position = $keyword_position . "+" . $i; $i++; } else { $i++; } }} foreach my $protein_list(@protein_list) { my @each_protein_list = split/[+]/, $protein_list; my $i = 0; my $protein_position = ""; foreach my $abstract(@abstract){ my @tempt = split /[,]/, $abstract; foreach my $each_protein(@each_protein_list) { if ($each_protein eq "\U$each_protein"){ $each_protein = uc $each_protein; } foreach my $tempt(@tempt){ #yo tempt + wala loop chai , wala kura separate garnalai ho hai but problem solv +e vako xaina if($tempt =~ /\b$each_protein\b/i) #main modify + garne thau yo ho ..match navayara tanaab diyako xa { $valid_proteins = $each_protein; #print $tempt; #print "\n"; #print $each_protein; #print "\n"; $protein_position = $protein_position . "+" . +$i; }} } $i++; } if($protein_position ne "") { my $field2 = $keyword_position; my $field3 = $protein_position; my @keywords = split /[+]/, $keyword_position; splice (@keywords, 0, 1); my @proteins = split /[+]/, $protein_position; splice (@proteins, 0, 1); sub uniq { my %seen; grep !$seen{$_}++, @_; } @proteins = uniq(@proteins); my @temp; my $f = 0; foreach my $proteins(@proteins){ my $k = 0; my @difference; foreach my $keywords(@keywords) { my $diff = ($proteins - $keywords); $difference[$k] = abs $diff; $k++; } $temp[$f] = min @difference; $f++; } my $min = min @temp; if($min == 0) { print "$valid_proteins\n"; $scoring = 1; print $fh "$fields[1], $fields[0], $field2, $valid +_proteins, $field3, $min, $scoring\n"; print "$fields[1], $fields[0], $field2, $valid_pro +teins, $field3, $min, $scoring\n"; } elsif($min == 1) { print "not matched\n"; $scoring = 0.5; print $fh "$fields[0], $fields[0], $field2, Unmatc +hed proteins, $field3, $min, $scoring\n"; print "$fields[0], $fields[0], $field2, Unmatched +proteins, $field3, $min, $scoring\n"; } else { print "not matched\n"; $scoring = 0.2; print $fh "$fields[1], $fields[0] $field2, Unmatch +ed proteins, $field3, $min, $scoring\n"; print "$fields[1], $fields[0] $field2, Unmatched p +roteins, $field3, $min, $scoring\n"; } #print $fh "$fields[0], $field2, $protein_list, $field +3, $min, $scoring\n"; } } } else { print "not matched\n"; $scoring = 0; print $fh "Undef, $fields[0] $field2, Unmatched proteins, $fie +ld3, $min, $scoring\n"; print "Undef, $fields[0] $field2, Unmatched proteins, $field3, + $min, $scoring\n"; } } } close($fh);
This is the code I am using to extract the protein names from the PubMed abstracts. But many lines in of the file "finalidlist" that consists of PubMed IDs is skipped. Can anyone help me whats the problem?
In reply to Few lines in CSV file are skipped by pdahal
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |