diff --git a/README.md b/README.md index fa504a6..d528187 100644 --- a/README.md +++ b/README.md @@ -187,27 +187,28 @@ MindTheGap is composed of two main modules : breakpoint detection (`find` module * `-nb-cores`: number of cores to be used for computation [default '0', ie. all available cores will be used]. * `-max-memory`: max RAM memory for the graph creation (in MBytes) [default '2000']. Increasing the memory will speed up the graph creation phase. - * `-max-disk`: max usable disk space for the graph creation (in MBytes) [default '0', ie. automatically set]. Kmers are counted by writting temporary files on the disk, to speed up the counting you can increase the usable disk space. + * `-max-disk`: max usable disk space for the graph creation (in MBytes) [default '0', ie. automatically set]. Kmers are counted by writing temporary files on the disk, to speed up the counting you can increase the usable disk space. 4. **MindTheGap Output** All the output files are prefixed either by a default name: "MindTheGap_Expe-[date:YY:MM:DD-HH:mm]" or by a user defined prefix (option `-out` of MindTheGap). Both MindTheGap modules generate the graph file if reads were given as input: - * a graph file (`.h5`). This is a binary file, to obtain information stored in it, you can use the utility program `dbginfo` located in your bin directory or in ext/gatb-core/bin/. - + +* a graph file (`.h5`). This is a binary file, to obtain information stored in it, you can use the utility program `dbginfo` located in your bin directory or in ext/gatb-core/bin/. + `MindTheGap find` generates the following output files: * a breakpoint file (`.breakpoints`) in fasta format. - * a variant file (`.othervariants.vcf`) in vcf format. It contains SNPs and deletion events. - +* a variant file (`.othervariants.vcf`) in vcf format. It contains SNPs and deletion events. + `MindTheGap fill` generates the following output files: - * a sequence file (`.insertions.fasta`) in fasta format. It contains the inserted sequences or contig gap-fills that were successfully assembled. - - * an insertion variant file (`.insertions.vcf`) in vcf format, in the case of insertion variant detection. - - * an assembly graph file (`.gfa`) in GFA format, in the case of contig gap-filling. It contains the original contigs and the obtained gap-fill sequences (nodes of the graph), together with their overlapping relationships (arcs of the graph). - - * a log file (`.info.txt`), a tabular file with some information about the filling process for each breakpoint/grap-fill. - +* a sequence file (`.insertions.fasta`) in fasta format. It contains the inserted sequences or contig gap-fills that were successfully assembled. + +* an insertion variant file (`.insertions.vcf`) in vcf format, in the case of insertion variant detection. + +* an assembly graph file (`.gfa`) in GFA format, in the case of contig gap-filling. It contains the original contigs and the obtained gap-fill sequences (nodes of the graph), together with their overlapping relationships (arcs of the graph). + +* a log file (`.info.txt`), a tabular file with some information about the filling process for each breakpoint/grap-fill. + Other optional parameters and details on input and output file formats are given in [doc/MindTheGap_insertion_caller.md](doc/MindTheGap_insertion_caller.md) and [doc/MindTheGap_assembly.md](doc/MindTheGap_assembly.md), depending on the usage. diff --git a/src/Filler.cpp b/src/Filler.cpp index a7adaa2..a68ee58 100644 --- a/src/Filler.cpp +++ b/src/Filler.cpp @@ -227,14 +227,14 @@ void Filler::execute () _insert_file_name = getInput()->getStr(STR_URI_OUTPUT)+".insertions.fasta"; _insert_file = fopen(_insert_file_name.c_str(), "w"); if(_insert_file == NULL){ - string message = "Cannot open file "+ _insert_file_name + " for writting"; + string message = "Cannot open file "+ _insert_file_name + " for writing"; throw Exception(message.c_str()); } _insert_info_file_name = getInput()->getStr(STR_URI_OUTPUT)+".info.txt"; _insert_info_file = fopen(_insert_info_file_name.c_str(), "w"); if(_insert_info_file == NULL){ - string message = "Cannot open file "+ _insert_info_file_name + " for writting"; + string message = "Cannot open file "+ _insert_info_file_name + " for writing"; throw Exception(message.c_str()); } @@ -245,8 +245,8 @@ void Filler::execute () _vcf_file_name = getInput()->getStr(STR_URI_OUTPUT)+".insertions.vcf"; _vcf_file = fopen(_vcf_file_name.c_str(), "w"); if(_vcf_file == NULL){ - //cerr <<" Cannot open file "<< _output_file <<" for writting" << endl; - string message = "Cannot open file "+ _vcf_file_name + " for writting"; + //cerr <<" Cannot open file "<< _output_file <<" for writing" << endl; + string message = "Cannot open file "+ _vcf_file_name + " for writing"; throw Exception(message.c_str()); } writeVcfHeader(); @@ -259,7 +259,7 @@ void Filler::execute () _gfa_file_name = getInput()->getStr(STR_URI_OUTPUT)+".gfa"; _gfa_file = fopen(_gfa_file_name.c_str(),"w"); if(_gfa_file == NULL){ - string message = "Cannot open file "+ _gfa_file_name + " for writting"; + string message = "Cannot open file "+ _gfa_file_name + " for writing"; throw Exception(message.c_str()); } } @@ -1004,7 +1004,7 @@ void Filler::writeFilledBreakpoint(std::vector& filledSequen osolu_i << "solution " << it->solution_rank << "/" << it->solution_count ; string solu_i = it->solution_count >1 ? osolu_i.str() : "" ; - //Writting sequence header + //writing sequence header if(_breakpointMode) //-bkpt mode, to keep the same header name as before { fprintf(_insert_file,">%s_len_%d_qual_%i_avg_cov_%.2f_median_cov_%.2f %s\n", @@ -1022,7 +1022,7 @@ void Filler::writeFilledBreakpoint(std::vector& filledSequen fprintf(_insert_file,"%s",insertionName.c_str()); } - //Writting DNA sequence + //writing DNA sequence fprintf(_insert_file,"%.*s\n",(int)llen,insertion.c_str() ); // if(it->solution_count >1) diff --git a/src/Finder.cpp b/src/Finder.cpp index 2f42d1f..0cc804e 100644 --- a/src/Finder.cpp +++ b/src/Finder.cpp @@ -281,16 +281,16 @@ void Finder::execute () _breakpoint_file_name = getInput()->getStr(STR_URI_OUTPUT)+".breakpoints"; _breakpoint_file = fopen(_breakpoint_file_name.c_str(), "w"); if(_breakpoint_file == NULL){ - //cerr <<" Cannot open file "<< _output_file <<" for writting" << endl; - string message = "Cannot open file "+ _breakpoint_file_name + " for writting"; + //cerr <<" Cannot open file "<< _output_file <<" for writing" << endl; + string message = "Cannot open file "+ _breakpoint_file_name + " for writing"; throw Exception(message.c_str()); } _vcf_file_name = getInput()->getStr(STR_URI_OUTPUT)+".othervariants.vcf"; _vcf_file = fopen(_vcf_file_name.c_str(), "w"); if(_vcf_file == NULL){ - //cerr <<" Cannot open file "<< _output_file <<" for writting" << endl; - string message = "Cannot open file "+ _vcf_file_name + " for writting"; + //cerr <<" Cannot open file "<< _output_file <<" for writing" << endl; + string message = "Cannot open file "+ _vcf_file_name + " for writing"; throw Exception(message.c_str()); } writeVcfHeader();