Merge branch 'master' of https://github.com/hildebra/lotus2

lotus2

@@ -3190,12 +3190,12 @@ my %workflow_options = (
   '-keepUnclassified <0|1>', '(1) Includes unclassified OTUs (i.e. no match in RDP/Blast database) in OTU and taxa abundance matrix calculations. (0) does not take these OTUs into account. (Default: 1)',
   '-tolerateCorruptFq <0|1>', '(1) Continue reading fastq files, even if single entries are incomplete (e.g. half of qual values missing). (0) Abort lotus run, if fastq file is corrupt. (Default: 0)',
   '-useVsearch <0|1>', '(0) Use usearch for internal tasks such as remapping reads on OTUs, chimera checks. (1) will use vsearch for these tasks. This option is independent of the -CL UPARSE/UNOISE option, and -taxAligner assignment usearch/vsearch options. (Default: 0)',
-  '-mergePreClusterReads <0|1>', '(0) no merging or reads pre OTU/ASV/zOTU seq clustering, BUT read mergning after seq clustering (to get better representative sequence). (1) Merge reads prior to seq clustering. WARNING!! This will considerably reduce the number of valid read pairs, as additional quality filters will be applied, algorithm is still in development !! (Default: 0)'
+  '-mergePreClusterReads <0|1>', '(0) no merging or reads pre OTU/ASV/zOTU seq clustering, BUT read merging after seq clustering (to get better representative sequence). (1) Merge reads prior to seq clustering. WARNING!! This will considerably reduce the number of valid read pairs, as additional quality filters will be applied, algorithm is still in development !! (Default: 0)'
 );
 
 my $taxonomy_heading = "Taxonomy Options";
 my %taxonomy_options = (
-  '-refDB <SLV|GG|HITdb|PR2|UNITE|beetax>', '(SLV) Silva LSU (23/28S) or SSU (16/18S), (GG greengenes (only SSU available), (HITdb) (SSU, human gut specific), (PR2) LSU spezialized on Ocean environmentas, (UNITE) ITS fungi specific, (beetax) bee gut specific database and tax names. \nDecide which reference DB will be used for a similarity based taxonomy annotation. Databases can be combined, with the first having the highest prioirty. E.g. "PR2,SLV" would first use PR2 to assign OTUs and all unaasigned OTUs would be searched for with SILVA, given that \"-amplicon_type LSU\" was set. Can also be a custom fasta formatted database: in this case provide the path to the fasta file as well as the path to the taxonomy for the sequences using -tax4refDB. See also online help on how to create a custom DB. (Default: SLV)',
+  '-refDB <SLV|GG|HITdb|PR2|UNITE|beetax>', '(SLV) Silva LSU (23/28S) or SSU (16/18S), (GG greengenes (only SSU available), (HITdb) (SSU, human gut specific), (PR2) LSU spezialized on Ocean environmentas, (UNITE) ITS fungi specific, (beetax) bee gut specific database and tax names. \nDecide which reference DB will be used for a similarity based taxonomy annotation. Databases can be combined, with the first having the highest priority. E.g. "PR2,SLV" would first use PR2 to assign OTUs and all unaasigned OTUs would be searched for with SILVA, given that \"-amplicon_type LSU\" was set. Can also be a custom fasta formatted database: in this case provide the path to the fasta file as well as the path to the taxonomy for the sequences using -tax4refDB. See also online help on how to create a custom DB. (Default: SLV)',
   '-tax4refDB <file>', 'In conjunction with a custom fasta file provided to argument -refDB, this file contains for each fasta entry in the reference DB a taxonomic annotation string, with the same number of taxonomic levels for each, tab separated.',
   '-amplicon_type <SSU|LSU|ITS|ITS1|ITS2>', '(SSU) small subunit (16S/18S), (LSU) large subunit (23S/28S) or internal transcribed spacer (ITS|ITS1|ITS2). (Default: SSU)',
   '-tax_group <bacteria|fungi>', '(bacteria) bacterial 16S rDNA annnotation, (fungi) fungal 18S/23S/ITS annotation. (Default: bacteria)',
@@ -3210,12 +3210,12 @@ my %taxonomy_options = (
   '-ITSx <0|1>', '(1) use ITSx to only retain OTUs fitting to ITS1/ITS2 hmm models; (0) deactivate. (Default: 1)',
   '-itsx_partial <0-100>', 'Parameters for ITSx to extract partial (%) ITS regions as well. (0) deactivate. (Default: 0)',
   '-lulu <0|1>', '(1) use LULU (https://github.com/tobiasgf/lulu) to merge OTUs based on their occurrence. (Default: 1)',
-  '-buildPhylo <0,1,2,>','(0) do not build OTU phylogeny; (1) use fasttree2; (2) use IQ-TREE 2. (Default: 1)',
+  '-buildPhylo <0,1,2,>','(0) do not build OTU phylogeny; (1) use fasttree2; (2) use IQ-TREE 2. (Default: 1). We recommend the cautious usage of the phylogenetic tree for ITS (recommended mostly for visualization purposes) because high variation of ITS sequences may lead to erroneous trees. Phylogenetic trees can be of use for 16S data depending on the aim of the analysis.',
 );
 
 my $clustering_heading = "Clustering Options";
 my %clustering_options = (
-  '-CL|-clustering <uparse|swarm|cdhit|unoise|dada2>', 'Sequence clustering algorithm: (1) UPARSE, (2) swarm, (3) cd-hit, (6) unoise3, (7) dada2. Short keyword or number can be used to indicate clustering (Default: uparse)',
+  '-CL|-clustering <uparse|swarm|cdhit|unoise|dada2>', 'Sequence clustering algorithm: (1) UPARSE, (2) swarm, (3) cd-hit, (6) unoise3, (7) dada2, (8) VSEARCH. Short keyword or number can be used to indicate clustering (Default: UPARSE)',
   '-id <0-1>', 'Clustering threshold for OTUs. (Default: 0.97)',
   '-swarm_distance <1,2,3,..> ', 'Clustering distance for OTUs when using swarm clustering. (Default: 1)',
   '-chim_skew <num>', 'Skew in chimeric fragment abundance (uchime option). (Default: 2)',