六框翻译
六框翻译-生信人必练的200个数据处理任务-生信技能树 http://www.biotrainee.com/thread-1444-1-1.html(出处: 生信技能树)
密码子是按3个碱基翻译的， 所以从第一位开始翻译会得到一个氨基酸序列， 从第二位翻译会得到一个不同的氨基酸序列 从第三位开始又会得到一个不同的序列。 从第四位开始就会和第一个开始翻译的序列一样（因为这两个都是从序列里面的起始密码子开始翻译的）， 所以相对于单链，会有3种翻译的方式， 同样的情况在互补链上也会有3种，所以就一共有六种翻译方式。读出六条序列，即6框翻译。 关于真核生物翻译的起始起始： 首先是核糖体40s小亚基以及一些真核翻译起始因子结合mRNA的5'帽结构形成复合体，之后就会向下滑动，找AUG，翻译起始还要受到AUG附近序列控制，比如Kozak序列：CCa／gCCAUGG，如果找到了AUG，而且附近的序列又比较适合起始，那么翻译就开始了。
my(%codon) = ( 'TCA' => 'S', # Serine 'TCC' => 'S', # Serine 'TCG' => 'S', # Serine 'TCT' => 'S', # Serine 'TTC' => 'F', # Phenylalanine 'TTT' => 'F', # Phenylalanine 'TTA' => 'L', # Leucine 'TTG' => 'L', # Leucine 'TAC' => 'Y', # Tyrosine 'TAT' => 'Y', # Tyrosine 'TAA' => '*', # Stop 'TAG' => '*', # Stop 'TGC' => 'C', # Cysteine 'TGT' => 'C', # Cysteine 'TGA' => '*', # Stop 'TGG' => 'W', # Tryptophan 'CTA' => 'L', # Leucine 'CTC' => 'L', # Leucine 'CTG' => 'L', # Leucine 'CTT' => 'L', # Leucine 'CCA' => 'P', # Proline 'CCC' => 'P', # Proline 'CCG' => 'P', # Proline 'CCT' => 'P', # Proline 'CAC' => 'H', # Histidine 'CAT' => 'H', # Histidine 'CAA' => 'Q', # Glutamine 'CAG' => 'Q', # Glutamine 'CGA' => 'R', # Arginine 'CGC' => 'R', # Arginine 'CGG' => 'R', # Arginine 'CGT' => 'R', # Arginine 'ATA' => 'I', # Isoleucine 'ATC' => 'I', # Isoleucine 'ATT' => 'I', # Isoleucine 'ATG' => 'M', # Methionine 'ACA' => 'T', # Threonine 'ACC' => 'T', # Threonine 'ACG' => 'T', # Threonine 'ACT' => 'T', # Threonine 'AAC' => 'N', # Asparagine 'AAT' => 'N', # Asparagine 'AAA' => 'K', # Lysine 'AAG' => 'K', # Lysine 'AGC' => 'S', # Serine 'AGT' => 'S', # Serine 'AGA' => 'R', # Arginine 'AGG' => 'R', # Arginine 'GTA' => 'V', # Valine 'GTC' => 'V', # Valine 'GTG' => 'V', # Valine 'GTT' => 'V', # Valine 'GCA' => 'A', # Alanine 'GCC' => 'A', # Alanine 'GCG' => 'A', # Alanine 'GCT' => 'A', # Alanine 'GAC' => 'D', # Aspartic Acid 'GAT' => 'D', # Aspartic Acid 'GAA' => 'E', # Glutamic Acid 'GAG' => 'E', # Glutamic Acid 'GGA' => 'G', # Glycine 'GGC' => 'G', # Glycine 'GGG' => 'G', # Glycine 'GGT' => 'G', # Glycine ); $dna=shift @ARGV; $protein=""; for(my $i=0; $i < (length($dna) - 2) ; $i += 3) {$protein.=$codon{substr($dna,$i,3)} } print "+1\t$protein\n"; $protein=""; for(my $i=1; $i < (length($dna) - 2) ; $i += 3) {$protein.=$codon{substr($dna,$i,3)} } print "+2\t$protein\n"; $protein=""; for(my $i=2; $i < (length($dna) - 2) ; $i += 3) {$protein.=$codon{substr($dna,$i,3)} } print "+3\t$protein\n"; $dna=reverse($dna); $dna=~tr/ACGTacgt/TGCAtgca/; $protein=""; for(my $i=0; $i < (length($dna) - 2) ; $i += 3) {$protein.=$codon{substr($dna,$i,3)} } print "-1\t$protein\n"; $protein=""; for(my $i=1; $i < (length($dna) - 2) ; $i += 3) {$protein.=$codon{substr($dna,$i,3)} } print "-2\t$protein\n"; $protein=""; for(my $i=2; $i < (length($dna) - 2) ; $i += 3) {$protein.=$codon{substr($dna,$i,3)} } print "-3\t$protein\n";
注：还可以参照下面的代码
1 use strict; 2 use warnings; 3 4 5 my $dna =''; 6 my $protein =''; 7 my @file_data=( ); 8 my @filedata; 9 my $revcom=''; 10 11 12 #打开文件 13 @filedata = get_file_data(); 14 #得到序列 15 $dna = extract_sequence_from_fasta_data(@filedata); 16 17 #六框阅读翻译 18 19 print "\n---------------------Reading Frame 1-----------------\n"; 20 $protein=translate_frame($dna,1); 21 print_sequence($protein,70); 22 23 print "\n---------------------Reading Frame 2-----------------\n"; 24 $protein=translate_frame($dna,2); 25 print_sequence($protein,70); 26 27 print "\n---------------------Reading Frame 3-----------------\n"; 28 $protein=translate_frame($dna,3); 29 print_sequence($protein,70); 30 31 print "\n---------------------Reading Frame 4-----------------\n"; 32 $protein=translate_frame($dna,4); 33 print_sequence($protein,70); 34 35 print "\n---------------------Reading Frame 5-----------------\n"; 36 $protein=translate_frame($dna,5); 37 print_sequence($protein,70); 38 39 print "\n---------------------Reading Frame 6-----------------\n"; 40 $protein=translate_frame($dna,6); 41 print_sequence($protein,70); 42 43 sub get_file_data 44 { 45 # A subroutine to get data from a file given its filename 46 #读取文件的子序列 47 my $dna_filename; 48 my @filedata; 49 print "please input the Path just like this f:\\\\perl\\\\data.txt\n"; 50 chomp($dna_filename=<STDIN>); 51 open(DNAFILENAME,$dna_filename)||die("can not open the file!"); 52 @filedata = <DNAFILENAME>; 53 close DNAFILENAME; 54 return @filedata;#子函数的返回值一定要记住写 55 } 56 57 sub extract_sequence_from_fasta_data 58 { 59 #******************************************************************* 60 # A subroutine to extract FASTA sequence data from an array 61 # 得到其中的序列 62 # fasta格式介绍： 63 # 包括三个部分 64 # 1.第一行中以>开头的注释行，后面是名称和序列的来源 65 # 2.标准单字母符号的序列 66 # 3.*表示结尾 67 #******************************************************************* 68 69 my (@fasta_file_data) =@_; 70 my $sequence =' '; 71 foreach my $line (@fasta_file_data) 72 { 73 #这里忽略空白行 74 if ($line=~/^\s*$/) 75 { 76 next; 77 } 78 #忽略注释行 79 elsif($line=~/^\s*#/) 80 { 81 next; 82 } 83 #忽略fasta的第一行 84 elsif($line=~/^>/) 85 { 86 next; 87 } 88 else 89 { 90 $sequence .=$line; 91 } 92 } 93 $sequence=~s/\s//g; 94 return $sequence; 95 } 96 97 sub print_sequence 98 { 99 # A subroutine to format and print sequence data 100 my ($sequence, $length) = @_; 101 for (my $pos =0; $pos<length($sequence);$pos+=$length) 102 { 103 print substr($sequence,$pos,$length),"\n"; 104 } 105 } 106 107 108 109 sub codon2aa 110 { 111 112 #第三种方法 113 #也就是运用哈希 114 #我们将所有的密码子作为hash的key，然后将代表的氨基酸作为hash的value 115 #然后进行匹配 116 # codon2aa 117 # A subroutine to translate a DNA 3-character codon to an amino acid 118 # Version 3, using hash lookup 119 my($codon) = @_; 120 121 $codon = uc $codon;#uc=uppercase;lc=lowercase 122 #也就是大小写转换，uc表示将所有的小写 转换为大写 123 #lc将所有的大写转换为小写 124 125 my(%genetic_code) = ( 126 127 'TCA' => 'S', # Serine 128 'TCC' => 'S', # Serine 129 'TCG' => 'S', # Serine 130 'TCT' => 'S', # Serine 131 'TTC' => 'F', # Phenylalanine 132 'TTT' => 'F', # Phenylalanine 133 'TTA' => 'L', # Leucine 134 'TTG' => 'L', # Leucine 135 'TAC' => 'Y', # Tyrosine 136 'TAT' => 'Y', # Tyrosine 137 'TAA' => '_', # Stop 138 'TAG' => '_', # Stop 139 'TGC' => 'C', # Cysteine 140 'TGT' => 'C', # Cysteine 141 'TGA' => '_', # Stop 142 'TGG' => 'W', # Tryptophan 143 'CTA' => 'L', # Leucine 144 'CTC' => 'L', # Leucine 145 'CTG' => 'L', # Leucine 146 'CTT' => 'L', # Leucine 147 'CCA' => 'P', # Proline 148 'CCC' => 'P', # Proline 149 'CCG' => 'P', # Proline 150 'CCT' => 'P', # Proline 151 'CAC' => 'H', # Histidine 152 'CAT' => 'H', # Histidine 153 'CAA' => 'Q', # Glutamine 154 'CAG' => 'Q', # Glutamine 155 'CGA' => 'R', # Arginine 156 'CGC' => 'R', # Arginine 157 'CGG' => 'R', # Arginine 158 'CGT' => 'R', # Arginine 159 'ATA' => 'I', # Isoleucine 160 'ATC' => 'I', # Isoleucine 161 'ATT' => 'I', # Isoleucine 162 'ATG' => 'M', # Methionine 163 'ACA' => 'T', # Threonine 164 'ACC' => 'T', # Threonine 165 'ACG' => 'T', # Threonine 166 'ACT' => 'T', # Threonine 167 'AAC' => 'N', # Asparagine 168 'AAT' => 'N', # Asparagine 169 'AAA' => 'K', # Lysine 170 'AAG' => 'K', # Lysine 171 'AGC' => 'S', # Serine 172 'AGT' => 'S', # Serine 173 'AGA' => 'R', # Arginine 174 'AGG' => 'R', # Arginine 175 'GTA' => 'V', # Valine 176 'GTC' => 'V', # Valine 177 'GTG' => 'V', # Valine 178 'GTT' => 'V', # Valine 179 'GCA' => 'A', # Alanine 180 'GCC' => 'A', # Alanine 181 'GCG' => 'A', # Alanine 182 'GCT' => 'A', # Alanine 183 'GAC' => 'D', # Aspartic Acid 184 'GAT' => 'D', # Aspartic Acid 185 'GAA' => 'E', # Glutamic Acid 186 'GAG' => 'E', # Glutamic Acid 187 'GGA' => 'G', # Glycine 188 'GGC' => 'G', # Glycine 189 'GGG' => 'G', # Glycine 190 'GGT' => 'G', # Glycine 191 ); 192 193 if(exists $genetic_code{$codon}) 194 { 195 return $genetic_code{$codon}; 196 } 197 else 198 { 199 200 print STDERR "Bad codon \"$codon\"!!\n"; 201 exit; 202 } 203 } 204 205 sub dna2peptide 206 { 207 my ($dna)=@_; 208 my $protein =''; 209 for (my $i=0; $i<(length($dna)-2);$i+=3) 210 { 211 $protein .=codon2aa(substr($dna,$i,3)); 212 } 213 return $protein;#这个词错误找了一晚上，没有返回值，所以结果总是没有内容，以后要引以为戒，子程序一定要有返回值 214 } 215 216 sub translate_frame 217 { 218 my ($seq,$start,$end)=@_; 219 my $protein; 220 221 unless($end) 222 { 223 $end=length($seq); 224 } 225 return dna2peptide(substr($seq,$start-1,$end-$start+1)); 226 }
