[Bio] / FigKernelScripts / svr_find_fused_genes.pl Repository:
ViewVC logotype

Diff of /FigKernelScripts/svr_find_fused_genes.pl

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 1.1, Mon Apr 18 19:02:12 2011 UTC revision 1.2, Tue Apr 19 18:57:45 2011 UTC
# Line 24  Line 24 
24  use Carp;  use Carp;
25  use Getopt::Long;  use Getopt::Long;
26    
27    =head1 svr_find_fused_genes
28    
29      svr_find_fused_genes [options] [<seqs.fa] >fusion.tbl
30    
31    Find genes that are homologous to the query genes and prints a list
32    of fusions among them.
33    
34    Examples:
35    
36      svr_find_fused_genes -peg 'fig|83333.1.peg.784'
37    
38      svr_find_fused_genes < query.fasta > fusions.table
39    
40      svr_find_fused_genes  -o hits.fasta  -r report  -t tree.html  < query.fasta  > fusion.table
41    
42    =head2 Introduction
43    
44    usage: svr_find_fused_genes [options] [<seqs.fa] >fusion.tbl
45    
46           -a   n_processor     - number of processors to use (D = 4)
47           -b   database        - database to search against: SEED (D), PSEED, PPSEED, FASTA file name, FIG genome ID
48           -i   min_ident       - minimum fraction identity (D = 0.1)
49           -u   max_q_uncov     - maximum unmatched query (D = 100)
50           -r   report_file     - output file of psiblast report
51           -o   output          - output psiblast search hits in fasta
52           -t   html_tree       - output html tree painted with fusion genes
53           -l                   - run search locally if a local database is specified
54           -peg fid             - query gene ID
55    
56    =head2 Command-Line options
57    
58    =over 4
59    
60    =item -a n_processor
61    
62    Number of processors to use (D = 4)
63    
64    =item -b database
65    
66    Database for psiblast to search against. It can be a FASTA file name,
67    a FIG genome ID, or a string, SEED, PSEED or PPSEED, to indicate one of the
68    preconfigured database of all protein sequences from complete
69    genomes. The default is SEED.
70    
71    =item -i min_ident
72    
73    Minimum fraction identity used in psi-blast search (D = 0.1).
74    
75    =item -l
76    
77    With the -l option, psiblast search is run locally. The database must
78    be a local FASTA file.
79    
80    =item -u max_q_uncov
81    
82    Maximum unmatched query, c-term or n-term (D = 100).
83    
84    =item -o output_file
85    
86    With the -o option, psiblast hits are written to a FASTA file.
87    
88    =item -r report_file
89    
90    Output file name for psiblast records produced as a 11-column table containing:
91    
92      [ subject_id, bit_score, e_value,
93        subject_length, status,
94        fraction_ident, fraction_positive,
95        query_uncov_n_term, query_uncov_c_term,
96        subject_uncov_n_term, subject_uncov_c_term ]
97    
98    =item -t html_tree
99    
100    With the -t option, a HTML tree is generated with the functional roles
101    of sequences colored and the fused genes highlighted.
102    
103    =back
104    
105    =head2 Input
106    
107    The input search profile is a FASTA file read from STDIN or a PEG ID
108    specified with the -peg option.
109    
110    =head2 Output
111    
112    The set of predicted fused genes is written to STDOUT.
113    
114      [ fused_gene_ID, subject_uncov_n_term, subject_uncov_c_term ]
115    
116    =cut
117    
118    
119  use AlignTree;  use AlignTree;
120  use ATserver;  use ATserver;
# Line 40  Line 131 
131    
132         -a   n_processor     - number of processors to use (D = 4)         -a   n_processor     - number of processors to use (D = 4)
133         -b   database        - database to search against: SEED (D), PSEED, PPSEED, FASTA file name, FIG genome ID         -b   database        - database to search against: SEED (D), PSEED, PPSEED, FASTA file name, FIG genome ID
134         -i   min_ident       - minimum fraction identity (D = 0.12)         -i   min_ident       - minimum fraction identity (D = 0.1)
135         -u   max_q_uncov     - maximum unmatched query (D = 80)         -u   max_q_uncov     - maximum unmatched query (D = 100)
136         -r   report_file     - output file of psiblast report         -r   report_file     - output file of psiblast report
137         -o   output          - output psiblast search hits in fasta         -o   output          - output psiblast search hits in fasta
138         -t   html_tree       - output html tree painted with fusion genes         -t   html_tree       - output html tree painted with fusion genes

Legend:
Removed from v.1.1  
changed lines
  Added in v.1.2

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3