def main():
actions = (
('n50', "Given FASTA or a list of contig sizes, calculate N50"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('prepare', 'parse list of count files and group per family'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# OM guided approach
('refine', 'find gaps within or near breakpoint regions'),
('patcher', 'given om alignment, prepare the patchers'),
# Gap filling through sequence matching
('fill', 'perform gap filling using one assembly vs the other'),
('install', 'install patches into backbone'),
# Placement through mates and manual insertions and deletions
('bambus', 'find candidate scaffolds to insert based on mates'),
('insert', 'insert scaffolds into assembly'),
('eject', 'eject scaffolds from assembly'),
('closest', 'find the nearest gaps flanking suggested regions'),
# Misc
('tips', 'append telomeric sequences based on patchers and complements'),
('gaps', 'create patches around OM gaps'),
# Touch-up
('pasteprepare', 'prepare sequences for paste'),
('paste', 'paste in good sequences in the final assembly'),
('pastegenes', 'paste in zero or low coverage genes'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('longest', 'label longest transcript per gene as full-length'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('needle', 'take protein pairs and needle them'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('blast', 'run blastn using query against reference'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('cat', 'concatenate pages from pdf files into a single pdf file'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('names', 'convert a list of names to sbt blocks'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Compile population data - pipeline: compilevcf->mergecsv->meta->data->mask
('bin', 'convert tsv to binary format'),
('filtervcf', 'filter lobSTR VCF'),
('compilevcf', "compile vcf results into master spreadsheet"),
('mergecsv', "combine csv into binary array"),
('meta', 'compute allele frequencies and write to meta'),
('data', 'filter data based on the meta calls'),
('mask', 'compute P-values based on meta calls and data'),
('treds', 'compile allele_frequency for TRED results'),
# lobSTR related
('lobstrindex', 'make lobSTR index'),
('batchlobstr', "run batch lobSTR"),
('lobstr', 'run lobSTR on a big BAM'),
('batchhtt', "run batch HTT caller"),
('htt', 'extract HTT region and run lobSTR'),
('stutter', 'extract info from lobSTR vcf file'),
# Specific markers
('liftover', 'liftOver CODIS/Y-STR markers'),
('trf', 'run TRF on FASTA files'),
('ystr', 'print out Y-STR info given VCF'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('prepare', 'prepare shell script to run trinity-dn/gg on a folder of reads'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('connect', 'connect contigs using long reads'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('patch', 'run PBJelly with reference and reads'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('rnaseq', 'evaluate completeness, contiguity, and chimer of RNAseq'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('rdotplot', 'dot plot based on lastz rdotplot output'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('bed', 'convert xml format into bed format'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Alter read names
('append', 'append or prepend string to read names'),
# Extract info
('bed', 'convert bam files to bed'),
('fastq', 'convert bam files to paired fastq'),
('pair', 'parse sam file and get pairs'),
('pairs', 'print paired-end reads from BAM file'),
('chimera', 'parse sam file from `bwasw` and list multi-hit reads'),
('noclip', 'remove clipped reads from bam'),
('ace', 'convert sam file to ace'),
('consensus', 'convert bam alignments to consensus FASTA'),
('fpkm', 'calculate FPKM values from BAM file'),
('coverage', 'calculate depth for BAM file'),
('vcf', 'call SNPs on a set of bam files'),
('mapped', 'extract mapped/unmapped reads from samfile'),
('count', 'count the number of reads mapped using htseq'),
('merge', 'merge bam files'),
# Convenience function
('index', 'convert to bam, sort and then index'),
('mini', 'extract mini-bam for a single region'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('fetch', 'fetch records from uniprot. input is a list of query terms'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Compile population data
('bin', 'convert tsv to binary format'),
('mask', 'compute P-values based on meta and data'),
('filterloci', 'select subset of loci based on allele counts'),
('filterdata', 'select subset of data based on filtered loci'),
('filtervcf', 'filter lobSTR VCF'),
('compilevcf', "compile vcf results into master spreadsheet"),
('mergecsv', "combine csv into binary array"),
# lobSTR related
('lobstrindex', 'make lobSTR index'),
('batchlobstr', "run batch lobSTR"),
('lobstr', 'run lobSTR on a big BAM'),
('batchhtt', "run batch HTT caller"),
('htt', 'extract HTT region and run lobSTR'),
('stutter', 'extract info from lobSTR vcf file'),
# Specific markers
('liftover', 'liftOver CODIS/Y-STR markers'),
('trf', 'run TRF on FASTA files'),
('ystr', 'print out Y-STR info given VCF'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('table', 'convert HTML tables to csv'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('bed', 'parse gff and produce bed file for particular feature type'),
('bed12', 'produce bed12 file for coding features'),
('fromgtf', 'convert gtf to gff3 format'),
('gtf', 'convert gff3 to gtf format'),
('sort', 'sort the gff file'),
('filter', 'filter the gff file based on Identity and Coverage'),
('format', 'format the gff file, change seqid, etc.'),
('rename', 'change the IDs within the gff3'),
('uniq', 'remove the redundant gene models'),
('liftover', 'adjust gff coordinates based on tile number'),
('script', 'parse gmap gff and produce script for sim4db to refine'),
('note', 'extract certain attribute field for each feature'),
('load', 'extract the feature (e.g. CDS) sequences and concatenate'),
('extract', 'extract a particular contig from the gff file'),
('split', 'split the gff into one contig per file'),
('merge', 'merge several gff files into one'),
('parents', 'find the parents given a list of IDs'),
('children', 'find all children that belongs to the same parent'),
('fromgb', 'convert from gb format to gff3'),
('frombed', 'convert from bed format to gff3'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('libsvm', 'convert csv file to LIBSVM format'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('depth', 'calculate average depth per feature using coverageBed'),
('sort', 'sort bed file'),
('merge', 'merge bed files'),
('index', 'index bed file using tabix'),
('bins', 'bin bed lengths into each window'),
('summary', 'summarize the lengths of the intervals'),
('evaluate', 'make truth table and calculate sensitivity and specificity'),
('pile', 'find the ids that intersect'),
('pairs', 'estimate insert size between paired reads from bedfile'),
('mates', 'print paired reads from bedfile'),
('sizes', 'infer the sizes for each seqid'),
('uniq', 'remove overlapping features with higher scores'),
('longest', 'select longest feature within overlapping piles'),
('bedpe', 'convert to bedpe format'),
('distance', 'calculate distance between bed features'),
('sample', 'sample bed file and remove high-coverage regions'),
('refine', 'refine bed file using a second bed file'),
('flanking', 'get n flanking features for a given position'),
('some', 'get a subset of bed features given a list'),
('fix', 'fix non-standard bed files'),
('filter', 'filter the bedfile to retain records between size range'),
('random', 'extract a random subset of features'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('bed', 'get gene bed from phytozome'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('bed', 'Convert del.txt to del.bed'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('prepare', 'prepare TASSEL pipeline'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('posmap', 'QC based on indexed posmap file'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('wgsim', 'sample paired end reads using dwgsim'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('fragment', 'extract upstream and downstream seq of particular RE'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('prepare', 'prepare meraculous input'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('summary', 'provide summary on id% and cov%'),
('completeness', 'print completeness statistics for each query'),
('annotation', 'create tabular file with the annotations'),
('top10', 'count the most frequent 10 hits'),
('filter', 'filter BLAST file (based on score, id%, alignlen)'),
('covfilter', 'filter BLAST file (based on id% and cov%)'),
('cscore', 'calculate C-score for BLAST pairs'),
('best', 'get best BLAST hit per query'),
('pairs', 'print paired-end reads of BLAST tabular file'),
('bed', 'get bed file from BLAST tabular file'),
('condense', 'group HSPs together for same query-subject pair'),
('chain', 'chain adjacent HSPs together'),
('swap', 'swap query and subjects in BLAST tabular file'),
('sort', 'sort lines so that query grouped together and scores desc'),
('subset', 'extract hits from some query and subject chrs'),
('mismatches', 'print out histogram of mismatches of HSPs'),
('annotate', 'annotate overlap types in BLAST tabular file'),
('score', 'add up the scores for each query seq'),
('rbbh', 'find reciprocal-best blast hits'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
("rename", "rename genes for annotation release"),
# perform following actions on list files
("reindex", "reindex isoforms per gene locus"),
("publocus",
"create pub_locus identifiers according to GenBank specs"),
# Medicago gene renumbering
("annotate", "annotation new bed file with features from old"),
("renumber", "renumber genes for annotation updates"),
("instantiate", "instantiate NEW genes tagged by renumber"),
("plot", "plot gene identifiers along certain chromosome"),
# External gene prediction programs
("augustus", "convert augustus output into gff3"),
("tRNAscan", "convert tRNAscan-SE output into gff3"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('rename', 'rename genes for annotation release'),
# perform following actions on list files
('reindex', 'reindex isoforms per gene locus'),
('publocus',
'create pub_locus identifiers according to GenBank specs'),
# Medicago gene renumbering
('annotate', 'annotation new bed file with features from old'),
('renumber', 'renumber genes for annotation updates'),
('instantiate', 'instantiate NEW genes tagged by renumber'),
('plot', 'plot gene identifiers along certain chromosome'),
# External gene prediction programs
('augustus', 'convert augustus output into gff3'),
('tRNAscan', 'convert tRNAscan-SE output into gff3'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('pairwise', 'convert a list of IDs into all pairs'),
('split', 'split large file into N chunks'),
('reorder', 'reorder columns in tab-delimited files'),
('flatten', 'convert a list of IDs into one per line'),
('unflatten', 'convert lines to a list of IDs on single line'),
('group', 'group elements in a table based on key (groupby) column'),
('setop', 'set operations on files'),
('join', 'join tabular-like files based on common column'),
('subset', 'subset tabular-like files based on common column'),
('truncate', 'remove lines from end of file'),
('append', 'append a column with fixed value'),
('seqids', 'make a list of seqids for graphics.karyotype'),
('mergecsv', 'merge a set of tsv files'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('tracedb', 'convert trace archive files to frg file'),
('clr', 'prepare vector clear range file based on BLAST to vectors'),
('fasta', 'convert fasta to frg file'),
('sff', 'convert 454 reads to frg file'),
('fastq', 'convert Illumina reads to frg file'),
('shred', 'shred contigs into pseudo-reads'),
('astat', 'generate the coverage-rho scatter plot'),
('unitigs', 'output uniquely extended unitigs based on best.edges'),
('merger', 'merge reads into unitigs offline'),
('removecontains', 'remove contained reads from gkpStore'),
('graph', 'visualize best.edges'),
('prune', 'prune overlap graph'),
('overlap', 'visualize overlaps for a given fragment'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
("pairwise", "convert a list of IDs into all pairs"),
("split", "split large file into N chunks"),
("reorder", "reorder columns in tab-delimited files"),
("flatten", "convert a list of IDs into one per line"),
("unflatten", "convert lines to a list of IDs on single line"),
("group", "group elements in a table based on key (groupby) column"),
("setop", "set operations on files"),
("join", "join tabular-like files based on common column"),
("subset", "subset tabular-like files based on common column"),
("truncate", "remove lines from end of file"),
("append", "append a column with fixed value"),
("seqids", "make a list of seqids for graphics.karyotype"),
("mergecsv", "merge a set of tsv files"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
("tracedb", "convert trace archive files to frg file"),
("clr", "prepare vector clear range file based on BLAST to vectors"),
("fasta", "convert fasta to frg file"),
("sff", "convert 454 reads to frg file"),
("fastq", "convert Illumina reads to frg file"),
("shred", "shred contigs into pseudo-reads"),
("astat", "generate the coverage-rho scatter plot"),
("unitigs", "output uniquely extended unitigs based on best.edges"),
("merger", "merge reads into unitigs offline"),
("removecontains", "remove contained reads from gkpStore"),
("graph", "visualize best.edges"),
("prune", "prune overlap graph"),
("overlap", "visualize overlaps for a given fragment"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('size', 'total base pairs in the fastq files'),
('shuffle', 'shuffle paired reads into the same file interleaved'),
('split', 'split paired reads into two files'),
('splitread', 'split appended reads (from JGI)'),
('pair', 'pair up two fastq files and combine pairs'),
('unpair', 'unpair pairs.fastq files into 1.fastq and 2.fastq'),
('pairinplace', 'collect pairs by checking adjacent ids'),
('convert', 'convert between illumina and sanger offset'),
('filter', 'filter to get high qv reads'),
('trim', 'trim reads using fastx_trimmer'),
('some', 'select a subset of fastq reads'),
('deconvolute', 'split fastqfile into subsets'),
('guessoffset', 'guess the quality offset of the fastq records'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Identify true gene loss
('loss', 'extract likely gene loss candidates'),
('validate', 'confirm synteny loss against CDS bed overlaps'),
('summary', 'provide summary of fractionation'),
('gaps', 'check gene locations against gaps'),
# Gene specific status
('gffselect', 'dump gff for the missing genes'),
('genestatus', 'tag genes based on translation from GMAP models'),
# Specific study for napus (requires specific datasets)
('napus', 'extract gene loss vs diploid ancestors (napus)'),
('merge', 'merge protein quartets table with registry (napus)'),
('segment', 'merge adjacent gene loss into segmental loss (napus)'),
('offdiag', 'find gene pairs that are off diagonal'),
('diff', 'calculate diff of size of syntenic regions'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('compile', "compile vcf results into master spreadsheet"),
('bin', 'convert tsv to binary format'),
('mergecsv', "combine csv into binary array"),
('mask', 'compute P-values based on meta and data'),
('filterloci', 'select subset of loci based on allele counts'),
('filterdata', 'select subset of data based on filtered loci'),
('batchlobstr', "run batch lobSTR"),
('batchhtt', "run batch HTT caller"),
('htt', 'extract HTT region and run lobSTR'),
('liftover', 'liftOver CODIS/Y-STR markers'),
('lobstr', 'run lobSTR on a big BAM'),
('lobstrindex', 'make lobSTR index'),
('trf', 'run TRF on FASTA files'),
('ystr', 'print out Y-STR info given VCF'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
("cartoon", "generate cartoon illustration of SynFind"),
("ecoli", "gene presence absence analysis in ecoli"),
("grass", "validate SynFind pan-grass set against James"),
("coge", "prepare coge datasets"),
# For benchmarking
("synfind", "prepare input for SynFind"),
("iadhore", "prepare input for iADHoRe"),
("mcscanx", "prepare input for MCScanX"),
("cyntenator", "prepare input for Cyntenator"),
("athalianatruth", "prepare truth pairs for At alpha/beta/gamma"),
("yeasttruth", "prepare truth pairs for 14 yeasts"),
("grasstruth", "prepare truth pairs for 4 grasses"),
("benchmark", "compare SynFind, MCScanX, iADHoRe and OrthoFinder"),
("venn", "display benchmark results as Venn diagram"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Identify true gene loss
("loss", "extract likely gene loss candidates"),
("validate", "confirm synteny loss against CDS bed overlaps"),
("summary", "provide summary of fractionation"),
("gaps", "check gene locations against gaps"),
# Gene specific status
("gffselect", "dump gff for the missing genes"),
("genestatus", "tag genes based on translation from GMAP models"),
# Specific study for napus (requires specific datasets)
("napus", "extract gene loss vs diploid ancestors (napus)"),
("merge", "merge protein quartets table with registry (napus)"),
("segment", "merge adjacent gene loss into segmental loss (napus)"),
("offdiag", "find gene pairs that are off diagonal"),
("diff", "calculate diff of size of syntenic regions"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('cartoon', 'generate cartoon illustration of SynFind'),
('ecoli', 'gene presence absence analysis in ecoli'),
('grass', 'validate SynFind pan-grass set against James'),
('coge', 'prepare coge datasets'),
# For benchmarking
('synfind', 'prepare input for SynFind'),
('iadhore', 'prepare input for iADHoRe'),
('mcscanx', 'prepare input for MCScanX'),
('cyntenator', 'prepare input for Cyntenator'),
('athalianatruth', 'prepare truth pairs for At alpha/beta/gamma'),
('yeasttruth', 'prepare truth pairs for 14 yeasts'),
('grasstruth', 'prepare truth pairs for 4 grasses'),
('benchmark', 'compare SynFind, MCScanX, iADHoRe and OrthoFinder'),
('venn', 'display benchmark results as Venn diagram'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('bed', 'convert bam files to bed'),
('pair', 'parse sam file and get pairs'),
('pairs', 'print paired-end reads from BAM file'),
('chimera', 'parse sam file from `bwasw` and list multi-hit reads'),
('ace', 'convert sam file to ace'),
('index', 'convert to bam, sort and then index'),
('consensus', 'convert bam alignments to consensus FASTA'),
('fpkm', 'calculate FPKM values from BAM file'),
('coverage', 'calculate depth for BAM file'),
('vcf', 'call SNPs on a set of bam files'),
('mapped', 'extract mapped/unmapped reads from samfile'),
('count', 'count the number of reads mapped using htseq'),
('merge', 'merge bam files'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# LACHESIS output processing
('agp', 'generate AGP file based on LACHESIS output'),
('score', 'score the current LACHESIS CLM'),
# Simulation
('simulate', 'simulate CLM data'),
# Scaffolding
('optimize', 'optimize the contig order and orientation'),
('density', 'estimate link density of contigs'),
# Plotting
('movieframe', 'plot heatmap and synteny for a particular tour'),
('movie', 'plot heatmap optimization history in a tourfile'),
# Reference-based analytics
('bam2mat', 'convert bam file to .npy format used in plotting'),
('mergemat', 'combine counts from multiple .npy data files'),
('heatmap', 'plot heatmap based on .npy file'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Epoch paper (Woodhouse et al., 2012 Plant Cell)
('epoch', 'show the methods used in epoch paper'),
# Cotton paper (Paterson et al., 2012 Nature)
('cotton', 'plot cotton macro- and micro-synteny (requires data)'),
# Amborella paper (Albert et al., 2013 Science)
('amborella', 'plot amborella macro- and micro-synteny (requires data)'
),
# Mt4.0 paper (Tang et al., 2014 BMC Genomics)
('mtdotplots', 'plot Mt3.5 and Mt4.0 side-by-side'),
# Oropetium paper (Vanburen et al., 2015 Nature)
('oropetium', 'plot oropetium micro-synteny (requires data)'),
# Unpublished
('birch', 'plot birch macro-synteny (requires data)'),
('litchi', 'plot litchi micro-synteny (requires data)'),
('utricularia', 'plot utricularia micro-synteny (requires data)'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('summary', 'provide summary on id% and cov%'),
('completeness', 'print completeness statistics for each query'),
('annotation', 'create tabular file with the annotations'),
('top10', 'count the most frequent 10 hits'),
('filter', 'filter BLAST file (based on score, id%, alignlen)'),
('covfilter', 'filter BLAST file (based on id% and cov%)'),
('cscore', 'calculate C-score for BLAST pairs'),
('best', 'get best BLAST hit per query'),
('pairs', 'print paired-end reads of BLAST tabular file'),
('bed', 'get bed file from BLAST tabular file'),
('chain', 'chain adjacent HSPs together'),
('swap', 'swap query and subjects in BLAST tabular file'),
('sort', 'sort lines so that query grouped together and scores desc'),
('mismatches', 'print out histogram of mismatches of HSPs'),
('annotate', 'annotate overlap types in BLAST tabular file'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# Prepare data
('simulate', 'simulate bams with varying inserts with dwgsim'),
('mergebam', 'merge sets of BAMs to make diploid'),
# Compile results
('batchlobstr', 'run lobSTR on a list of BAMs'),
('compilevcf', 'compile vcf outputs into lists'),
# Plotting
('evidences', 'plot distribution of evidences'),
('compare', 'compare callers on fake HD patients'),
('compare2', 'compare TREDPARSE and lobSTR on fake HD patients'),
('compare3', 'compare TREDPARSE on fake HD patients adding evidence'),
('compare4', 'compare TREDPARSE on fake HD patients adding coverage'),
('allelefreq', 'plot the allele frequencies of some STRs'),
# Diagram
('diagram', 'plot the predictive power of various evidences'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('sort', 'sort bed file'),
('index', 'index bed file using tabix'),
('bins', 'bin bed lengths into each window'),
('summary', 'summarize the lengths of the intervals'),
('evaluate',
'make truth table and calculate sensitivity and specificity'),
('pile', 'find the ids that intersect'),
('pairs', 'estimate insert size between paired reads from bedfile'),
('mates', 'print paired reads from bedfile'),
('sizes', 'infer the sizes for each seqid'),
('uniq', 'remove overlapping features with higher scores'),
('bedpe', 'convert to bedpe format'),
('distance', 'calculate distance between bed features'),
('sample', 'sample bed file and remove high-coverage regions'),
('refine', 'refine bed file using a second bed file'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('scan', 'get anchor list using single-linkage algorithm'),
('summary', 'provide statistics for pairwise blocks'),
('liftover', 'given anchor list, pull adjacent pairs from blast file'),
('mcscan', 'stack synteny blocks on a reference bed'),
('mcscanq', 'query multiple synteny blocks'),
('screen', 'extract subset of blocks from anchorfile'),
('simple', 'convert anchorfile to simple block descriptions'),
('stats', 'provide statistics for mscan blocks'),
('depth', 'calculate the depths in the two genomes in comparison'),
('breakpoint', 'identify breakpoints where collinearity ends'),
('matrix', 'make oxford grid based on anchors file'),
('coge', 'convert CoGe file to anchors file'),
('spa', 'convert chr ordering from SPA to simple lists'),
('rebuild', 'rebuild anchors file from prebuilt blocks file'),
('fromaligns', 'convert aligns file to anchors file'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# K-mer counting
('jellyfish', 'count kmers using `jellyfish`'),
('meryl', 'count kmers using `meryl`'),
('kmc', 'count kmers using `kmc`'),
('kmcunion', 'union kmc indices'),
('bed', 'map kmers on FASTA'),
# K-mer histogram
('histogram', 'plot the histogram based on meryl K-mer distribution'),
('multihistogram', 'plot histogram across a set of K-mer sizes'),
# These forms a pipeline to count K-mers for given FASTA seq
('dump', 'convert FASTA sequences to list of K-mers'),
('bin', 'serialize counts to bitarrays'),
('bincount', 'count K-mers in the bin'),
('count', 'run dump - jellyfish - bin - bincount in serial'),
('logodds', 'compute log likelihood between two db'),
('model', 'model kmer distribution given error rate'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('size', 'total base pairs in the fastq files'),
('shuffle', 'shuffle paired reads into the same file interleaved'),
('split', 'split paired reads into two files'),
('splitread', 'split appended reads (from JGI)'),
('catread', 'cat pairs together (reverse of splitread)'),
('pairinplace', 'collect pairs by checking adjacent ids'),
('convert', 'convert between illumina and sanger offset'),
('first', 'get first N reads from file'),
('filter', 'filter to get high qv reads'),
('suffix', 'filter reads based on suffix'),
('trim', 'trim reads using fastx_trimmer'),
('some', 'select a subset of fastq reads'),
('guessoffset', 'guess the quality offset of the fastq records'),
('readlen', 'calculate read length'),
('format', 'format fastq file, convert header from casava 1.8+ to older format'),
('fasta', 'convert fastq to fasta and qual file'),
('fromsra', 'convert sra to fastq using `fastq-dump`'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# K-mer counting
("jellyfish", "count kmers using `jellyfish`"),
("meryl", "count kmers using `meryl`"),
("kmc", "count kmers using `kmc`"),
("kmcop", "intersect or union kmc indices"),
("entropy", "calculate entropy for kmers from kmc dump"),
("bed", "map kmers on FASTA"),
# K-mer histogram
("histogram", "plot the histogram based on meryl K-mer distribution"),
("multihistogram", "plot histogram across a set of K-mer sizes"),
# These forms a pipeline to count K-mers for given FASTA seq
("dump", "convert FASTA sequences to list of K-mers"),
("bin", "serialize counts to bitarrays"),
("bincount", "count K-mers in the bin"),
("count", "run dump - jellyfish - bin - bincount in serial"),
("logodds", "compute log likelihood between two db"),
("model", "model kmer distribution given error rate"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# OM guided approach
('refine', 'find gaps within or near breakpoint regions'),
('patcher', 'given om alignment, prepare the patchers'),
# Gap filling through sequence matching
('fill', 'perform gap filling using one assembly vs the other'),
('install', 'install patches into backbone'),
# Placement through mates and manual insertions and deletions
('bambus', 'find candidate scaffolds to insert based on mates'),
('insert', 'insert scaffolds into assembly'),
('eject', 'eject scaffolds from assembly'),
('closest', 'find the nearest gaps flanking suggested regions'),
# Misc
('tips', 'append telomeric sequences based on patchers and complements'
),
('gaps', 'create patches around OM gaps'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
('cib', 'convert bam to cib'),
('coverage', 'plot coverage along chromosome'),
('cn', 'correct cib according to GC content'),
('mergecn', 'compile matrix of GC-corrected copy numbers'),
('hmm', 'run cnv segmentation'),
# Gene copy number
('exonunion', 'collapse overlapping exons within the same gene'),
('gcn', 'gene copy number based on Canvas results'),
('summarycanvas', 'count different tags in Canvas vcf'),
# Interact with CCN script
('batchccn', 'run CCN script in batch'),
('batchcn', 'run HMM in batch'),
('plot', 'plot some chromosomes for visual proof'),
# Benchmark, training, etc.
('sweep', 'write a number of commands to sweep parameter space'),
('compare', 'compare cnv output to ground truths'),
# Plots
('gcdepth', 'plot GC content vs depth for genomic bins'),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
("cib", "convert bam to cib"),
("coverage", "plot coverage along chromosome"),
("cn", "correct cib according to GC content"),
("mergecn", "compile matrix of GC-corrected copy numbers"),
("hmm", "run cnv segmentation"),
# Gene copy number
("exonunion", "collapse overlapping exons within the same gene"),
("gcn", "gene copy number based on Canvas results"),
("summarycanvas", "count different tags in Canvas vcf"),
# Interact with CCN script
("batchccn", "run CCN script in batch"),
("batchcn", "run HMM in batch"),
("plot", "plot some chromosomes for visual proof"),
# Benchmark, training, etc.
("sweep", "write a number of commands to sweep parameter space"),
("compare", "compare cnv output to ground truths"),
# Plots
("gcdepth", "plot GC content vs depth for genomic bins"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (
# OM guided approach
("refine", "find gaps within or near breakpoint regions"),
("patcher", "given om alignment, prepare the patchers"),
# Gap filling through sequence matching
("fill", "perform gap filling using one assembly vs the other"),
("install", "install patches into backbone"),
# Placement through mates and manual insertions and deletions
("bambus", "find candidate scaffolds to insert based on mates"),
("insert", "insert scaffolds into assembly"),
("eject", "eject scaffolds from assembly"),
("closest", "find the nearest gaps flanking suggested regions"),
# Misc
("tips", "append telomeric sequences based on patchers and complements"),
("gaps", "create patches around OM gaps"),
# Touch-up
("pasteprepare", "prepare sequences for paste"),
("paste", "paste in good sequences in the final assembly"),
("pastegenes", "paste in zero or low coverage genes"),
)
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (('blast', 'convert back to BLAST -m8 format'), )
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (('prepare', 'parse list of count files and group per family'),
('mergeclean', 'clean redundant merged bam files'))
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (("cat",
"concatenate pages from pdf files into a single pdf file"), )
p = ActionDispatcher(actions)
p.dispatch(globals())
def main():
actions = (('scaffold',
'run bambus on set of contigs, reads and read mappings'), )
p = ActionDispatcher(actions)
p.dispatch(globals())
