#Written by Prasuna Dahal

use warnings;
use XML::Simple;
use LWP::UserAgent;
use HTTP::Request::Common;
use URI::Escape;
use Text::CSV;
use Data::Dumper;

my $i = 0;
my @keystr;
my @kwrds = {"inhibitors", "activity", "complex", "activator", "activity", "activities", "activated", "proteins", "deficiency", "levels", "functions", "reductions", "protease", "proteases"};
my $file = "proteinlist.csv";
my $ua = LWP::UserAgent->new;
my $csv = Text::CSV->new({sep_char => ','});

#Open the result in a CSV file
open (my $fh, ">", "test1.csv");
print $fh "Valid Proteins\n";

#open file containig protein_name
#open(my $data1, '<', "proteinlist.csv");

#Open the file containing the PubMed IDs
open(my $data, '<', "test.csv");
while (my $line = <$data>) {
chomp $line;

if ($csv->parse($line)) {
	#Skip 1st line
	next if ($. == 1);

	my @fields = $csv-fields();
	#Replace (-) with (,)
	$fields[0] =~ tr/-/,/;
	my $id = $fields[0];

	#Initialize http request
	my $args = "db=pubmed&id=$id&retmode=text&rettype=abstract";
	my $req = new HTTP::Request POST => 'https://eutils.ncbi.nlm.nih.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;
	
	$fields[0] =~ tr/,/-/;

	my @abstract = split (/[.]/, $content);
	for $abstract(@abstract){
		@var1 = split ((/[ ]|[,]/), $abstract);
		foreach $var1(@var1){
			open(my $data1, "<", $file);
			while (my $line1 = <$data1>) {
				chomp $line1;
				my @fields1 = split ",", $line1;
				$keystr[$i] = $fields1[0];
				$i++;
				if ($var1=~ /\b$keystr[$i]\b/i){
					foreach $kwrds(@kwrds){
						if ($var1=~ /\b$kwrds\b/i){
							my $valid_prot = $var1;
							}
						}
						print $fh "$valid_prot\n";
						print "$valid_prot\n";
						}
					}
				}
			}	
		}
	}
close($fh);