1. Bioinformatics 生物信息学理论和实践 唐继军 jtang@cse.sc.edu 13928761660

2. !/usr/bin/perl -w use Bio; use strict; use warnings; my $DNA = fasta_read(); print "First ", dna2peptide($DNA), "\n"; print "Second ", dna2peptide(substr($DNA, 1)), "\n"; print "Third ", dna2peptide(substr($DNA, 2)), "\n"; $DNA = reverse $DNA; $DNA =~ tr/ACGTacgt/TGCAtgca/; print "Fourth ", dna2peptide($DNA), "\n"; print "Fifth ", dna2peptide(substr($DNA, 1)), "\n"; print "Sixth ", dna2peptide(substr($DNA, 2)), "\n";

3. my $x = 10; for (my $x = 0; $x < 5; $x++) { Scope(); print $x, "\n"; } print $x, "\n"; sub Scope { my $x = 0; }

4. my $x = 10; for (my $x = 0; $x < 5; $x++) { Scope(); print $x, "\n"; } print $x, "\n"; sub Scope { $x = 0; }

5. sub extract_sequence_from_fasta_data { my(@fasta_file_data) = @_; my $sequence = ''; foreach my $line (@fasta_file_data) { if ($line =~ /^\s*$/) { next; } elsif($line =~ /^\s*#/) { next; } elsif($line =~ /^>/) { next; } else { $sequence.= $line; } # remove non-sequence data (in this case, whitespace) from $sequence string $sequence =~ s/\s//g; return $sequence; }

6. Molecular Scissors Molecular Cell Biology, 4 th edition

8. R = G or A Y = C or T M = A or C K = G or T S = G or C W = A or T B = not A (C or G or T) D = not C (A or G or T) H = not G (A or C or T) V = not T (A or C or G) N = A or C or G or T

9. sub IUB_to_regexp { my($iub) = @_; my $regular_expression = ‘’; my %iub2character_class = ( A => 'A', C => 'C', G => 'G', T => 'T', R => '[GA]', Y => '[CT]', M => '[AC]', K => '[GT]', S => '[GC]', W => '[AT]', B => '[CGT]', D => '[AGT]', H => '[ACT]', V => '[ACG]', N => '[ACGT]', ); $iub =~ s/\^//g; for ( my $i = 0 ; $i < length($iub) ; ++$i ) { $regular_expression.= $iub2character_class{substr($iub, $i, 1)}; } return $regular_expression; }

10. Hash Initialize: my %hash = (); Add key/value pair: $hash{$key} = $value; Add more keys: %hash = ( 'key1', 'value1', 'key2', 'value2 ); %hash = ( key1 => 'value1', key2 => 'value2', ); Delete: delete $hash{$key};

11. while ( my ($key, $value) = each(%hash) ) { print "$key => $value\n"; } foreach my $key ( keys %hash ) { my $value = $hash{$key}; print "$key => $value\n"; }

12. sub parseREBASE { my($rebasefile) = @_; my @rebasefile = ( ); my %rebase_hash = ( ); my $name; my $site; my $regexp; open($rebase_filehandle, $rebasefile) or die "Cannot open file\n"; while( ) { # Discard header lines ( 1.. /Rich Roberts/ ) and next; # Discard blank lines /^\s*$/ and next; # Split the two (or three if includes parenthesized name) fields my @fields = split( " ", $_); $name = shift @fields; $site = pop @fields; # Translate the recognition sites to regular expressions $regexp = IUB_to_regexp($site); # Store the data into the hash $rebase_hash{$name} = "$site $regexp"; } # Return the hash containing the reformatted REBASE data return %rebase_hash; }

13. Range ( 1.. /Rich Roberts/ ) and next from first line till some line containing Rich Roberts If that is true, it will check the statement after "and" If that is not true, it will not check the statement after "and" open(…) or die If can open, the statement is already true, no need to check the statement after "or" If cannot open, the statement is false, need to check the statement after "or" to see if it can be true

14. Array operators push and pop (right-most element) @mylist = (1,2,3); push(@mylist,4,5,6); $oldvalue = pop(@mylist); shift and unshift (left-most element) @fred = (5,6,7); unshift(@fred,2,3,4); $x = shift(@fred); reverse: @a = (7,8,9); @b = reverse(@a); sort: @a = (7,9,9); @b = sort(@a);

15. sub match_positions { my($regexp, $sequence) = @_; use BeginPerlBioinfo; my @positions = ( ); while ( $sequence =~ /$regexp/ig ) { push ( @positions, pos($sequence) - length($&) + 1); } return @positions; }

16. use BeginPerlBioinfo; my %rebase_hash = ( ); my @file_data = ( ); my $query = ''; my $dna = ''; my $recognition_site = ''; my $regexp = ''; my @locations = ( ); @file_data = get_file_data("sample.dna"); $dna = extract_sequence_from_fasta_data(@file_data); %rebase_hash = parseREBASE('bionet'); do { print "Search for what restriction site for (or quit)?: "; $query = ; chomp $query; if ($query =~ /^\s*$/ ) { exit; } if ( exists $rebase_hash{$query} ) { ($recognition_site, $regexp) = split ( " ", $rebase_hash{$query}); @locations = match_positions($regexp, $dna); if (@locations) { print "Searching for $query $recognition_site $regexp\n"; print "Restriction site for $query at :", join(" ", @locations), "\n"; } else { print "A restriction enzyme $query is not in the DNA:\n"; } } until ( $query =~ /quit/ ); exit;

17. Print to file Open a file to print open FILE, ">filename.txt"; open (FILE, ">filename.txt“); Print to the file print FILE $str;

18. #write new file open(FILE, ">out") or die "Cannot open file to write"; print FILE "Test\n"; close FILE; exit;

19. #Append open(FILE, ">>out") or die "Cannot open file to write"; print FILE "Test\n"; close FILE; exit;

20. #!/usr/bin/perl print "My name is $0 \n"; print "First arg is: $ARGV[0] \n"; print "Second arg is: $ARGV[1] \n"; print "Third arg is: $ARGV[2] \n"; $num = $#ARGV + 1; print "How many args? $num \n"; print "The full argument string was: @ARGV \n";

21. use BeginPerlBioinfo; my %rebase_hash = ( ); my @file_data = ( ); my $query = ''; my $dna = ''; my $recognition_site = ''; my $regexp = ''; my @locations = ( ); @file_data = get_file_data($ARGV[0]); $dna = extract_sequence_from_fasta_data(@file_data); %rebase_hash = parseREBASE('bionet'); do { print "Search for what restriction site for (or quit)?: "; $query = ; chomp $query; if ($query =~ /^\s*$/ ) { exit; } if ( exists $rebase_hash{$query} ) { ($recognition_site, $regexp) = split ( " ", $rebase_hash{$query}); @locations = match_positions($regexp, $dna); if (@locations) { print "Searching for $query $recognition_site $regexp\n"; print "Restriction site for $query at :", join(" ", @locations), "\n"; } else { print "A restriction enzyme $query is not in the DNA:\n"; } } until ( $query =~ /quit/ ); exit;

22. use BeginPerlBioinfo; my %rebase_hash = ( ); my @file_data = ( ); my $query = ''; my $dna = ''; my $recognition_site = ''; my $regexp = ''; my @locations = ( ); @file_data = get_file_data($ARGV[0]); $dna = extract_sequence_from_fasta_data(@file_data); %rebase_hash = parseREBASE($ARGV[1]); do { print "Search for what restriction site for (or quit)?: "; $query = ; chomp $query; if ($query =~ /^\s*$/ ) { exit; } if ( exists $rebase_hash{$query} ) { ($recognition_site, $regexp) = split ( " ", $rebase_hash{$query}); @locations = match_positions($regexp, $dna); if (@locations) { print "Searching for $query $recognition_site $regexp\n"; print "Restriction site for $query at :", join(" ", @locations), "\n"; } else { print "A restriction enzyme $query is not in the DNA:\n"; } } until ( $query =~ /quit/ ); exit;

23. Regular Expression ^ beginning of string $ end of string. any character except newline * match 0 or more times + match 1 or more times ? match 0 or 1 times; | alternative ( ) grouping; “storing” [ ] set of characters { } repetition modifier \ quote or special

24. Repeats a*zero or more a’s a+one or more a’s a?zero or one a’s (i.e., optional a) a{m}exactly m a’s a{m,}at least m a’s a{m,n}at least m but at most n a’s

25. \

26. []

29. Perl tr/// function tr means transliterate – replaces a character with another character $dna =~ tr/a/c/ replaces all “a” with “c” in in $dna It also works on a range: $dna =~ tr/a-z/A-Z/ replaces all lower case letters with upper case tr also counts $count = ($string =~ tr/A//) (you might think this also deletes all “A” from the string, but it doesn’t)

30. Wildcards Perl has a set of wildcard characters for Reg. Exps. that are completely different than the ones used by Unix the dot (. ) matches any character \d matches any digit (a number from 0-9) \w matches any text character (a letter or number, not punctuation or space) \s matches white space (any amount) ^ matches the beginning of a line $ matches the end of a line (Yes, this is very confusing!)

31. Repeat for a count Use curly brackets to show that a character repeats a specific number (or range) of times: find an EcoRI fragment of 100-500 bp length (two EcoRI sites with any other sequence between): if $ecofrag =~ /GAATTC[GATC]{100,500}GAATTC/ The + sign is used to indicate an unlimited number of repeats (occurs 1 or more times)

32. my $mystring; $mystring = "Hello world!"; if($mystring =~ m/World/) { print "Yes"; } if($mystring =~ m/World/i) { print "Yes"; }

33. Grabbing parts of a string Regular expressions can do more than just ask ‘ if ” questions They can be used to extract parts of a line of text into variables; Check this out: /^>(\w+)\s(. +)$/; Complete gibberish, right? It means: -look for the > sign at the beginning of a FASTA formatted sequence file -dump the first word (\w+) into variable $1 ( the sequence ID ) -after a space, dump the rest of the line (.+), until you reach the end of line $, into variable $2 ( the description )

34. $mystring = "[2004/04/13] The date of this article."; if($mystring =~ m/(\d)/) { print "The first digit is $1."; } if($mystring =~ m/(\d+)/) { print "The first number is $1."; } if($mystring =~ m/(\d+)\/(\d+)\/(\d+)/) { print "The date is $1-$2-$3"; } while($mystring =~ m/(\d+)/g) { print "Found number $1."; } @myarray = ($mystring =~ m/(\d+)/g); print join(",", @myarray);

35. Working with Single DNA Sequences

36. Learning Objectives Discover how to manipulate your DNA sequence on a computer, analyze its composition, predict its restriction map, and amplify it with PCR Find out about gene-prediction methods, their potential, and their limitations Understand how genomes and sequences and assembled

37. Outline 1.Cleaning your DNA of contaminants 2.Digesting your DNA in the computer 3.Finding protein-coding genes in your DNA sequence 4.Assembling a genome

38. Cleaning DNA Sequences In order to sequence genomes, DNA sequences are often cloned in a vector (plasmid, YAC, or cosmide) Sequences of the vector can be mixed with your DNA sequence Before working with your DNA sequence, you should always clean it with VecScreen

39. VecScreen http://www.ncbi.nlm.nih.gov/VecScreen /VecScreen.html Runs a special version of Blast A system for quickly identifying segments of a nucleic acid sequence that may be of vector origin

44. What to do if hits found If hits are in the extremity, can just remove them If in the middle, or vectors are not what you are using, the safest thing is to throw the sequence away

45. Computing a Restriction Map It is possible to cut DNA sequences using restriction enzymes Each type of restriction enzyme recognizes and cuts a different sequence: EcoR1: GAATTC BamH1: GGATCC There are more than 900 different restriction enzymes, each with a different specificity The restriction map is the list of all potential cleavage sites in a DNA molecule You can compile a restriction map with www.firstmarket.com/cutter

46. Cannot get it work!

47. http://biotools.umassmed.edu/tacg4

49. Making PCR with a Computer Polymerase Chain Reaction (PCR) is a method for amplifying DNA PCR is used for many applications, including Gene cloning Forensic analysis Paternity tests PCR amplifies the DNA between two anchors These anchors are called the PCR primer

50. Designing PCR Primers PCR primes are typically 20 nucleotides long The primers must hybridize well with the DNA On biotools.umassmed.edu, find the best location for the primers: Most stable Longest extension

54. Analyzing DNA Composition DNA composition varies a lot Stability of a DNA sequence depends on its G+C content (total guanine and cytosine) High G+C makes very stable DNA molecules Online resources are available to measure the GC content of your DNA sequence Also for counting words and internal repeats

55. http://helixweb.nih.gov/emboss/html/

56. Counting words ATGGCTGACT A, T, G, G, C, T, G, A, C, T AT, TG, GG, GC, CT, TG, GA, AC, CT ATG, TGG, GGC, GCT, CTG, TGA, GAC, ACT

57. www.genomatix.de/cgi-bin/tools/tools.pl

58. EMBOSS servers European Molecular Biology Open Software Suite http://pro.genomics.purdue.edu/emboss/

62. ORF EMBOSS NCBI

65. ncbi.nlm.nih.gov/gorf/gorf.html

67. Internal repeats A word repeated in the sequence, long enough to not occur by chance Can be imperfect (regular expression) Dot plot is the best way to spot it

68. arbl.cvmbs.colostate.edu/molkit

70. Predicting Genes The most important analysis carried out on DNA sequences is gene prediction Gene prediction requires different methods for eukaryotes and prokaryotes Most gene-prediction methods use hidden Markov Models

71. Predicting Genes in Prokaryotic Genome In prokaryotes, protein-coding genes are uninterrupted No introns Predicting protein-coding genes in prokaryotes is considered a solved problem You can expect 99% accuracy

72. Finding Prokaryotic Genes with GeneMark GeneMark is the state of the art for microbial genomes GeneMark can Find short proteins Resolve overlapping genes Identify the best start codon Use exon.gatech.edu/GeneMark Click the “heutistic models”

73. Predicting Eukaryotic Genes Eukaryotic genes (human, for example) are very hard to predict Precise and accurate eukaryotic gene prediction is still an open problem ENSEMBL contains 21,662 genes for the human genome There may well be more genes than that in the genome, as yet unpredicted You can expect 70% accuracy on the human genome with automatic methods Experimental information is still needed to predict eukaryotic genes

74. Finding Eukaryotic Genes with GenomeScan GenomeScan is the state of the art for eukaryotic genes GenomeScan works best with Long exons Genes with a low GC content It can incorporate experimental information Use genes.mit.edu/genomescan

75. Producing Genomic Data Until recently, sequencing an entire genome was very expensive and difficult Only major institutes could do it Today, scientists estimate that in 10 years, it will cost about $1000 to sequence a human genome With sequencing so cheap, assembling your own genomes is becoming an option How could you do it?

76. Sequencing and Assembling a Genome (I) To sequence a genome, the first task is to cut it into many small, overlapping pieces Then clone each piece

77. Sequencing and Assembling a Genome (II) Each piece must be sequenced Sequencing machines cannot do an entire sequence at once They can only produce short sequences smaller than 1 Kb These pieces are called reads It is necessary to assemble the reads into contigs

78. Sequencing and Assembling a Genome (III) The most popular program for assembling reads is PHRAP Available at www.phrap.org Other programs exist for joining smaller datasets For example, try CAP3 at pbil.univ-lyon1.fr/cap3.php