From: Michael R. Crusoe <crusoe@debian.org>
Subject: Spelling typos fixes
Forwarded: https://github.com/soedinglab/MMseqs2/pull/359
--- mmseqs2.orig/data/workflow/searchslicedtargetprofile.sh
+++ mmseqs2/data/workflow/searchslicedtargetprofile.sh
@@ -69,7 +69,7 @@
     fi
 
     # predict NUM_SEQS_THAT_SATURATE as the average number of prefilter results per profile in previous steps
-    # this allows to increase NUM_PROFS_IN_STEP
+    # this allows one to increase NUM_PROFS_IN_STEP
     if [ "${NUM_PREF_RESULTS_IN_ALL_PREV_STEPS}" -gt 0 ]; then
         # BE MORE CAUTIOUS?
         NUM_PROFS_PROCESSED="$((FIRST_INDEX_LINE-1))"
--- mmseqs2.orig/src/MMseqsBase.cpp
+++ mmseqs2/src/MMseqsBase.cpp
@@ -717,7 +717,7 @@
                                           {"DB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::allDb },
                                           {"DB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA | DbType::VARIADIC, &DbValidator::allDb }}},
         {"subtractdbs",          subtractdbs,          &par.subtractdbs,          COMMAND_SET,
-                "Remove all entries from first DB occuring in second DB by key",
+                "Remove all entries from first DB occurring in second DB by key",
                 NULL,
                 "Martin Steinegger <martin.steinegger@snu.ac.kr>",
                 "<i:resultDBLeft> <i:resultDBRight> <o:resultDB>",
--- mmseqs2.orig/src/commons/DBReader.cpp
+++ mmseqs2/src/commons/DBReader.cpp
@@ -1106,7 +1106,7 @@
                 if (idx != std::string::npos) {
                     ext = names[i].substr(idx);
                 } else {
-                    Debug(Debug::ERROR) << "File extention was not found but it is expected to be there!\n"
+                    Debug(Debug::ERROR) << "File extension was not found but it is expected to be there!\n"
                                         << "Filename: " << names[i] << ".\n";
                     EXIT(EXIT_FAILURE);
                 }
--- mmseqs2.orig/src/commons/Parameters.cpp
+++ mmseqs2/src/commons/Parameters.cpp
@@ -87,7 +87,7 @@
         PARAM_FORMAT_OUTPUT(PARAM_FORMAT_OUTPUT_ID, "--format-output", "Format alignment output", "Choose comma separated list of output columns from: query,target,evalue,gapopen,pident,fident,nident,qstart,qend,qlen\ntstart,tend,tlen,alnlen,raw,bits,cigar,qseq,tseq,qheader,theader,qaln,taln,qframe,tframe,mismatch,qcov,tcov\nqset,qsetid,tset,tsetid,taxid,taxname,taxlineage,qorfstart,qorfend,torfstart,torfend", typeid(std::string), (void *) &outfmt, ""),
         PARAM_DB_OUTPUT(PARAM_DB_OUTPUT_ID, "--db-output", "Database output", "Return a result DB instead of a text file", typeid(bool), (void *) &dbOut, "", MMseqsParameter::COMMAND_EXPERT),
         // --include-only-extendablediagonal
-        PARAM_RESCORE_MODE(PARAM_RESCORE_MODE_ID, "--rescore-mode", "Rescore mode", "Rescore diagonals with:\n0: Hamming distance\n1: local alignment (score only)\n2: local alignment\n3: global alignment\n4: longest alignment fullfilling window quality criterion", typeid(int), (void *) &rescoreMode, "^[0-4]{1}$"),
+        PARAM_RESCORE_MODE(PARAM_RESCORE_MODE_ID, "--rescore-mode", "Rescore mode", "Rescore diagonals with:\n0: Hamming distance\n1: local alignment (score only)\n2: local alignment\n3: global alignment\n4: longest alignment fulfilling window quality criterion", typeid(int), (void *) &rescoreMode, "^[0-4]{1}$"),
         PARAM_WRAPPED_SCORING(PARAM_WRAPPED_SCORING_ID, "--wrapped-scoring", "Allow wrapped scoring", "Double the (nucleotide) query sequence during the scoring process to allow wrapped diagonal scoring around end and start", typeid(bool), (void *) &wrappedScoring, "", MMseqsParameter::COMMAND_ALIGN | MMseqsParameter::COMMAND_EXPERT),
         PARAM_FILTER_HITS(PARAM_FILTER_HITS_ID, "--filter-hits", "Remove hits by seq. id. and coverage", "Filter hits by seq.id. and coverage", typeid(bool), (void *) &filterHits, "", MMseqsParameter::COMMAND_EXPERT),
         PARAM_SORT_RESULTS(PARAM_SORT_RESULTS_ID, "--sort-results", "Sort results", "Sort results: 0: no sorting, 1: sort by E-value (Alignment) or seq.id. (Hamming)", typeid(int), (void *) &sortResults, "^[0-1]{1}$", MMseqsParameter::COMMAND_EXPERT),
@@ -130,8 +130,8 @@
         PARAM_KMER_PER_SEQ(PARAM_KMER_PER_SEQ_ID, "--kmer-per-seq", "k-mers per sequence", "k-mers per sequence", typeid(int), (void *) &kmersPerSequence, "^[1-9]{1}[0-9]*$", MMseqsParameter::COMMAND_CLUSTLINEAR),
         PARAM_KMER_PER_SEQ_SCALE(PARAM_KMER_PER_SEQ_SCALE_ID, "--kmer-per-seq-scale", "Scale k-mers per sequence", "Scale k-mer per sequence based on sequence length as kmer-per-seq val + scale x seqlen", typeid(MultiParam<float>), (void *) &kmersPerSequenceScale, "^0(\\.[0-9]+)?|1(\\.0+)?$", MMseqsParameter::COMMAND_CLUSTLINEAR),
         PARAM_INCLUDE_ONLY_EXTENDABLE(PARAM_INCLUDE_ONLY_EXTENDABLE_ID, "--include-only-extendable", "Include only extendable", "Include only extendable", typeid(bool), (void *) &includeOnlyExtendable, "", MMseqsParameter::COMMAND_CLUSTLINEAR),
-        PARAM_IGNORE_MULTI_KMER(PARAM_IGNORE_MULTI_KMER_ID, "--ignore-multi-kmer", "Skip repeating k-mers", "Skip k-mers occuring multiple times (>=2)", typeid(bool), (void *) &ignoreMultiKmer, "", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
-        PARAM_HASH_SHIFT(PARAM_HASH_SHIFT_ID, "--hash-shift", "Shift hash", "Shift k-mer hash initilization", typeid(int), (void *) &hashShift, "^[1-9]{1}[0-9]*$", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
+        PARAM_IGNORE_MULTI_KMER(PARAM_IGNORE_MULTI_KMER_ID, "--ignore-multi-kmer", "Skip repeating k-mers", "Skip k-mers occurring multiple times (>=2)", typeid(bool), (void *) &ignoreMultiKmer, "", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
+        PARAM_HASH_SHIFT(PARAM_HASH_SHIFT_ID, "--hash-shift", "Shift hash", "Shift k-mer hash initialization", typeid(int), (void *) &hashShift, "^[1-9]{1}[0-9]*$", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
         PARAM_PICK_N_SIMILAR(PARAM_PICK_N_SIMILAR_ID, "--pick-n-sim-kmer", "Add N similar to search", "Add N similar k-mers to search", typeid(int), (void *) &pickNbest, "^[1-9]{1}[0-9]*$", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
         PARAM_ADJUST_KMER_LEN(PARAM_ADJUST_KMER_LEN_ID, "--adjust-kmer-len", "Adjust k-mer length", "Adjust k-mer length based on specificity (only for nucleotides)", typeid(bool), (void *) &adjustKmerLength, "", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
         PARAM_RESULT_DIRECTION(PARAM_RESULT_DIRECTION_ID, "--result-direction", "Result direction", "result is 0: query, 1: target centric", typeid(int), (void *) &resultDirection, "^[0-1]{1}$", MMseqsParameter::COMMAND_CLUSTLINEAR | MMseqsParameter::COMMAND_EXPERT),
@@ -155,9 +155,9 @@
         PARAM_CONTIG_START_MODE(PARAM_CONTIG_START_MODE_ID, "--contig-start-mode", "Contig start mode", "Contig start can be 0: incomplete, 1: complete, 2: both", typeid(int), (void *) &contigStartMode, "^[0-2]{1}"),
         PARAM_CONTIG_END_MODE(PARAM_CONTIG_END_MODE_ID, "--contig-end-mode", "Contig end mode", "Contig end can be 0: incomplete, 1: complete, 2: both", typeid(int), (void *) &contigEndMode, "^[0-2]{1}"),
         PARAM_ORF_START_MODE(PARAM_ORF_START_MODE_ID, "--orf-start-mode", "Orf start mode", "Orf fragment can be 0: from start to stop, 1: from any to stop, 2: from last encountered start to stop (no start in the middle)", typeid(int), (void *) &orfStartMode, "^[0-2]{1}"),
-        PARAM_ORF_FORWARD_FRAMES(PARAM_ORF_FORWARD_FRAMES_ID, "--forward-frames", "Forward frames", "Comma-seperated list of frames on the forward strand to be extracted", typeid(std::string), (void *) &forwardFrames, ""),
-        PARAM_ORF_REVERSE_FRAMES(PARAM_ORF_REVERSE_FRAMES_ID, "--reverse-frames", "Reverse frames", "Comma-seperated list of frames on the reverse strand to be extracted", typeid(std::string), (void *) &reverseFrames, ""),
-        PARAM_USE_ALL_TABLE_STARTS(PARAM_USE_ALL_TABLE_STARTS_ID, "--use-all-table-starts", "Use all table starts", "Use all alteratives for a start codon in the genetic table, if false - only ATG (AUG)", typeid(bool), (void *) &useAllTableStarts, ""),
+        PARAM_ORF_FORWARD_FRAMES(PARAM_ORF_FORWARD_FRAMES_ID, "--forward-frames", "Forward frames", "Comma-separated list of frames on the forward strand to be extracted", typeid(std::string), (void *) &forwardFrames, ""),
+        PARAM_ORF_REVERSE_FRAMES(PARAM_ORF_REVERSE_FRAMES_ID, "--reverse-frames", "Reverse frames", "Comma-separated list of frames on the reverse strand to be extracted", typeid(std::string), (void *) &reverseFrames, ""),
+        PARAM_USE_ALL_TABLE_STARTS(PARAM_USE_ALL_TABLE_STARTS_ID, "--use-all-table-starts", "Use all table starts", "Use all alternatives for a start codon in the genetic table, if false - only ATG (AUG)", typeid(bool), (void *) &useAllTableStarts, ""),
         PARAM_TRANSLATE(PARAM_TRANSLATE_ID, "--translate", "Translate orf", "Translate ORF to amino acid", typeid(int), (void *) &translate, "^[0-1]{1}"),
         PARAM_CREATE_LOOKUP(PARAM_CREATE_LOOKUP_ID, "--create-lookup", "Create lookup", "Create database lookup file (can be very large)", typeid(int), (void *) &createLookup, "^[0-1]{1}", MMseqsParameter::COMMAND_EXPERT),
         // indexdb
@@ -233,7 +233,7 @@
         // filtertaxdb
         PARAM_TAXON_LIST(PARAM_TAXON_LIST_ID, "--taxon-list", "Selected taxa", "Taxonomy ID, possibly multiple values separated by ','", typeid(std::string), (void *) &taxonList, ""),
         // view
-        PARAM_ID_LIST(PARAM_ID_LIST_ID, "--id-list", "Selected entries with key", "Entries to be printed seperated by ','", typeid(std::string), (void *) &idList, ""),
+        PARAM_ID_LIST(PARAM_ID_LIST_ID, "--id-list", "Selected entries with key", "Entries to be printed separated by ','", typeid(std::string), (void *) &idList, ""),
         PARAM_IDX_ENTRY_TYPE(PARAM_IDX_ENTRY_TYPE_ID, "--idx-entry-type", "Index entry type", "0: sequence, 1: src sequence, 2: header, 3: src header", typeid(int), (void *) &idxEntryType, "^[0-3]{1}$"),
         // lca and addtaxonomy
         PARAM_PICK_ID_FROM(PARAM_PICK_ID_FROM_ID, "--pick-id-from", "Extract mode", "Query 1, Target 2", typeid(int), (void *) &pickIdFrom, "^[1-2]{1}$"),
@@ -247,9 +247,9 @@
         PARAM_REPORT_MODE(PARAM_REPORT_MODE_ID, "--report-mode", "Report mode", "Taxonomy report mode 0: Kraken 1: Krona", typeid(int), (void *) &reportMode, "^[0-1]{1}$"),
         // createtaxdb
         PARAM_NCBI_TAX_DUMP(PARAM_NCBI_TAX_DUMP_ID, "--ncbi-tax-dump", "NCBI tax dump directory", "NCBI tax dump directory. The tax dump can be downloaded here \"ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz\"", typeid(std::string), (void *) &ncbiTaxDump, ""),
-        PARAM_TAX_MAPPING_FILE(PARAM_TAX_MAPPING_FILE_ID, "--tax-mapping-file", "Taxonomical mapping file", "File to map sequence identifer to taxonomical identifier", typeid(std::string), (void *) &taxMappingFile, ""),
+        PARAM_TAX_MAPPING_FILE(PARAM_TAX_MAPPING_FILE_ID, "--tax-mapping-file", "Taxonomical mapping file", "File to map sequence identifier to taxonomical identifier", typeid(std::string), (void *) &taxMappingFile, ""),
         // expandaln
-        PARAM_EXPANSION_MODE(PARAM_EXPANSION_MODE_ID, "--expansion-mode", "Expansion mode", "Update score, E-value, and sequence identity by 0: input alignment 1: rescoring the infered backtrace", typeid(int), (void *) &expansionMode, "^[0-2]{1}$"),
+        PARAM_EXPANSION_MODE(PARAM_EXPANSION_MODE_ID, "--expansion-mode", "Expansion mode", "Update score, E-value, and sequence identity by 0: input alignment 1: rescoring the inferred backtrace", typeid(int), (void *) &expansionMode, "^[0-2]{1}$"),
         // taxonomy
         PARAM_LCA_MODE(PARAM_LCA_MODE_ID, "--lca-mode", "LCA mode", "LCA Mode 1: Single Search LCA , 2: 2bLCA, 3: approx. 2bLCA, 4: top hit", typeid(int), (void *) &taxonomySearchMode, "^[1-4]{1}$"),
         PARAM_TAX_OUTPUT_MODE(PARAM_TAX_OUTPUT_MODE_ID, "--tax-output-mode", "Taxonomy output mode", "0: output LCA, 1: output alignment 2: output both", typeid(int), (void *) &taxonomyOutpuMode, "^[0-2]{1}$"),
--- mmseqs2.orig/src/commons/ProfileStates.cpp
+++ mmseqs2/src/commons/ProfileStates.cpp
@@ -120,7 +120,7 @@
 
     if (nalph != 20)
     {
-        Debug(Debug::WARNING) << "Alphabet size of serialized context profile should be " << 20 << " but is acutally "<< nalph <<"!\n";
+        Debug(Debug::WARNING) << "Alphabet size of serialized context profile should be " << 20 << " but is actually "<< nalph <<"!\n";
         return -1;
     }
 
--- mmseqs2.orig/src/taxonomy/aggregatetax.cpp
+++ mmseqs2/src/taxonomy/aggregatetax.cpp
@@ -227,7 +227,7 @@
         outDbStr = par.db5;
         outDbIndexStr = par.db5Index;
     } else if (par.voteMode == Parameters::AGG_TAX_MINUS_LOG_EVAL) {
-        Debug(Debug::ERROR) << "voteMode is evalue-based but no alignment databse was provided. consider calling aggregatetaxweights\n";
+        Debug(Debug::ERROR) << "voteMode is evalue-based but no alignment database was provided. consider calling aggregatetaxweights\n";
         EXIT(EXIT_FAILURE);
     }
 
