Autodock Tutorial

Python code to download list of pdb files

#!/usr/bin/python """ This simple script can be used to download pdb files directly from internet usage: python getpdb.py <pdbids> example: python getpdb.py 3ZBQ 4HXP 4HXM 4B8F """ import urllib url = "http://www.rcsb.org/pdb/download/downloadFile.do?fileFormat=pdb&compression=NO&structureId=" from sys import argv for i in argv[1:]: pdbid = url+str(i) open( i+".pdb", "w" ).write( urllib.urlopen(pdbid).read() ) print i+".pdb"

Python class for basic operations dealing with DNA sequence

class DNA: """Class representing DNA as a string sequence.""" basecomplement = {'A': 'T', 'C': 'G', 'T': 'A', 'G': 'C'} codon2aa = {"TTT":"F","TTC":"F","TTA":"L","TTG":"L","TCT":"S","TCC":"S", "TCA":"S","TCG":"S","TAT":"Y","TAC":"Y","TAA":"*","TAG":"*", "TGT":"C","TGC":"C","TGA":"*","TGG":"W","CTT":"L","CTC":"L", "CTA":"L","CTG":"L","CCT":"P","CCC":"P","CCA":"P","CCG":"P", "CAT":"H","CAC":"H","CAA":"Q","CAG":"Q","CGT":"R","CGC":"R", "CGA":"R","CGG":"R","ATT":"I","ATC":"I","ATA":"I","ATG":"M", "ACT":"T","ACC":"T","ACA":"T","ACG":"T","AAT":"N","AAC":"N", "AAA":"K","AAG":"K","AGT":"S","AGC":"S","AGA":"R","AGG":"R", "GTT":"V","GTC":"V","GTA":"V","GTG":"V","GCT":"A","GCC":"A", "GCA":"A","GCG":"A","GAT":"D","GAC":"D","GAA":"E","GAG":"E", "GGT":"G","GGC":"G","GGA":"G","GGG":"G"} def __init__(self, s): """Create DNA instance initialized to string s.""" self.seq = s def transcribe(self): """Return as rna string.""" return self.seq.replace('T', 'U') def reverse(self): """Return dna string in reverse order.""" letters = list(self.seq) letters.reverse() return ''.join(letters) def complement(self): """Return the complementary dna string.""" letters = list(self.seq) letters = [self.basecomplement[base] for base in letters] return ''.join(letters) def reversecomplement(self): """Return the reverse of complement of the dna string.""" letters = list(self.seq) letters.reverse() letters = [self.basecomplement[base] for base in letters] return ''.join(letters) def gc(self): """Return the % of dna composed of G+C.""" s = self.seq gc = s.count('G') + s.count('C') return gc * 100.0 / len(s) def codons(self): """Return list of codons for the dna string,""" s = self.seq end = len(s) - (len(s) % 3) - 1 codons = [s[i:i+3] for i in range(0, end, 3)] return codons def translate(self): """Return amino acid sequence translating dna seq.""" s = self.seq codons = self.codons() aa = [self.codon2aa[aa] for aa in codons] return ''.join(aa) """ How to use this code... save this code in a file name as bio.py then open python terminal and use this as a module for example... >>> from bio import * >>> S = DNA('ATGTGCGTGCTC') >>> S <bio.DNA instance at 0x02A09B48> >>> S.translate() 'MCVL' >>> S.transcribe() 'AUGUGCGUGCUC' >>> S.reverse() 'CTCGTGCGTGTA' >>> S.complement() 'TACACGCACGAG' >>> S.codons() ['ATG', 'TGC', 'GTG', 'CTC'] >>> """

RNA to protein conversion (translation) using perl

# This is my first post starting with very basic code... print “Enter the RNA sequence: “; $rna = <>; chomp($rna); $rna =~s/[^acgu]//ig; my $rna = uc($rna); my(%genetic_code) = ( ‘GGA’ => ‘G’, ‘GGC’ => ‘G’, ‘GGG’ => ‘G’, ‘GGU’ => ‘G’, # Glycine ‘GCA’ => ‘A’, ‘GCC’ => ‘A’, ‘GCG’ => ‘A’, ‘GCU’ => ‘A’, # Alanine ‘GUA’ => ‘V’, ‘GUC’ => ‘V’, ‘GUG’ => ‘V’, ‘GUU’ => ‘V’, # Valine ‘CCA’ => ‘P’, ‘CCC’ => ‘P’, ‘CCG’ => ‘P’, ‘CCU’ => ‘P’, # Proline ‘UCA’ => ‘S’, ‘UCC’ => ‘S’, ‘UCG’ => ‘S’, ‘UCU’ => ‘S’, # Serine ‘CUA’ => ‘L’, ‘CUC’ => ‘L’, ‘CUG’ => ‘L’, ‘CUU’ => ‘L’, # Leucine ‘CGA’ => ‘R’, ‘CGC’ => ‘R’, ‘CGG’ => ‘R’, ‘CGU’ => ‘R’, # Arginine ‘ACA’ => ‘T’, ‘ACC’ => ‘T’, ‘ACG’ => ‘T’, ‘ACU’ => ‘T’, # Threonine ‘AUA’ => ‘I’, ‘AUC’ => ‘I’, ‘AUU’ => ‘I’, # Isoleucine ‘UAA’ => ‘_’, ‘UAG’ => ‘_’, ‘UGA’ => ‘_’, # Stop ‘AAA’ => ‘K’, ‘AAG’ => ‘K’, # Lysine ‘AGC’ => ‘S’, ‘AGU’ => ‘S’, # Serine ‘UUA’ => ‘L’, ‘UUG’ => ‘L’, # Leucine ‘AGA’ => ‘R’, ‘AGG’ => ‘R’, # Arginine ‘UAC’ => ‘Y’, ‘UAU’ => ‘Y’, # Tyrosine ‘UGC’ => ‘C’, ‘UGU’ => ‘C’, # Cysteine ‘CAA’ => ‘Q’, ‘CAG’ => ‘Q’, # Glutamine ‘AAC’ => ‘N’, ‘AAU’ => ‘N’, # Asparagine ‘UUC’ => ‘F’, ‘UUU’ => ‘F’, # Phenylalanine ‘GAC’ => ‘D’, ‘GAU’ => ‘D’, # Aspartic Acid ‘GAA’ => ‘E’, ‘GAG’ => ‘E’, # Glutamic Acid ‘UGG’ => ‘W’, # Tryptophan ‘CAC’ => ‘H’, # Histidine ‘AUG’ => ‘M’, # Methionine ‘CAU’ => ‘H’, # Histidine ); my ($protein) = “”; for(my $i=0;$i<length($rna)-2;$i+=3) { $codon = substr($rna,$i,3); $protein .= $genetic_code{$codon}; } print “Translated protein sequence is $protein”; #This program can also used for six reading frame, by changing the three #character shift in forward and reverse of the RNA sequence.