############################################################################### # # ______ ____ ____ ____ ____ ______ __ __ # | || \ | || \ | || || | | # | || D ) | | | _ | | | | || | | # |_| |_|| / | | | | | | | |_| |_|| ~ | # | | | \ | | | | | | | | | |___, | # | | | . \ | | | | | | | | | | | # |__| |__|\_||____||__|__||____| |__| |____/ # ############################################################################### # # Required: # # --seqType <string> :type of reads: ( cfa, cfq, fa, or fq ) # --kmer_method <string> :method for k-mer counting. Choose among # jellyfish, meryl, or inchworm. (and see # method-specific opts below) # All kmer counting methods are functionally equivalent, but they # differ in speed according to: jellyfish > meryl >> inchworm # # If paired reads: # --left <string> :left reads # --right <string> :right reads # # Or, if unpaired reads: # --single <string> :single reads # #################################### ## Misc: ######################### # # --SS_lib_type <string> :Strand-specific RNA-Seq read orientation. # if paired: RF or FR, # if single: F or R. (dUTP method = RF) # See web documentation. # --output <string> :name of directory for output (will be # created if it doesn't already exist) # default( "trinity_out_dir" ) # --CPU <int> :number of CPUs to use, default: 2 # --min_contig_length <int> :minimum assembled contig length to report # (def=200) # --jaccard_clip :option, set if you have paired reads and # you expect high gene density with UTR # overlap (use FASTQ input file format # for reads). # (note: jaccard_clip is an expensive # operation, so avoid using it unless # necessary due to finding excessive fusion # transcripts w/o it.) # --cite :get the Trinity literature citation and those of tools leveraged within. # #################################################### # Inchworm and K-mer counting-related options: ##### # # --min_kmer_cov <int> :min count for K-mers to be assembled by # Inchworm (default: 1) # Jellyfish: # --max_memory <string> :number of GB of system memory to use for # k-mer counting by jellyfish (eg. 10G) *include the 'G' char # # Meryl: # --meryl_opts <string> :pass on any meryl-specific options # directly to meryl. Meryl documentation: # http://sourceforge.net/apps/mediawiki/kmer/index.php?title=Getting_Started_with_Meryl # ################################### # Chrysalis-related options: ###### # # --min_glue <int> :min number of reads needed to glue two inchworm contigs # together. (default: 2) # --min_iso_ratio <float> :min fraction of average kmer coverage between two iworm contigs # required for gluing. (default: 0.05) # --glue_factor <float> :fraction of max (iworm pair coverage) for read glue support (default: 0.05) # --max_reads_per_graph <int> :maximum number of reads to anchor within # a single graph (default: 20000000) # --max_reads_per_loop <int> :maximum number of reads to read into # memory at once (default: 1000000) # --min_pct_read_mapping <int> :minimum percent of a reads kmers that must map to an # inchworm bundle (aka. component) default: 0 # # --no_run_chrysalis :stop Trinity after Inchworm and before # running Chrysalis # --no_run_quantifygraph :stop Trinity just before running the # parallel QuantifyGraph computes, to # leverage a compute farm and massively # parallel execution.. ##################################### ### Butterfly-related options: #### # # --bfly_opts <string> :additional parameters to pass through to butterfly # (see butterfly documentation). # --max_number_of_paths_per_node <int> :only most supported (N) paths are extended from node A->B, # mitigating combinatoric path explorations. (default: 10) # --group_pairs_distance <int> :maximum length expected between fragment pairs (default: 500) # # --path_reinforcement_distance <int> :minimum overlap of reads with growing transcript # path (default: 75) # # --lenient_path_extension :require minimal read overlap to allow for path extensions. # (equivalent to --path_reinforcement_distance=1) # # --bflyHeapSpaceMax <string> :java max heap space setting for butterfly # (default: 20G) => yields command # 'java -Xmx20G -jar Butterfly.jar ... $bfly_opts' # --bflyHeapSpaceInit <string> :java initial hap space settings for # butterfly (default: 1G) => yields command # 'java -Xms1G -jar Butterfly.jar ... $bfly_opts' # --bflyGCThreads <int> :threads for garbage collection # (default, not specified, so java decides) # --bflyCPU <int> :CPUs to use (default will be normal # number of CPUs; e.g., 2) # --bflyCalculateCPU :Calculate CPUs based on 80% of max_memory # divided by maxbflyHeapSpaceMax # --no_run_butterfly :stops after the Chrysalis stage. You'll # need to run the Butterfly computes # separately, such as on a computing grid. # Then, concatenate all the Butterfly assemblies by running: # 'find trinity_out_dir/ -name "*allProbPaths.fasta" # -exec cat {} + > trinity_out_dir/Trinity.fasta' # ################################# # Grid-computing options: ####### # # --grid_computing_module <string> : Perl module in /Users/bhaas/sVN/trinityrnaseq/trunk/PerlLibAdaptors/ # that implements 'run_on_grid()' # for naively parallel cmds. (eg. 'BroadInstGridRunner') # # ############################################################################### # # *Note, a typical Trinity command might be: # Trinity.pl --seqType fq --kmer_method jellyfish --max_memory 100G --left reads_1.fq --right reads_2.fq --CPU 6 # Or, using Meryl # Trinity.pl --seqType fq --kmer_method meryl --left reads_1.fq --right reads_2.fq --CPU 6 # # see: /Users/bhaas/sVN/trinityrnaseq/trunk/sample_data/test_Trinity_Assembly/ # for sample data and 'runMe.sh' for example Trinity execution # For more details, visit: http://trinityrnaseq.sf.net # ###############################################################################