|
jpayne@69
|
1 #!/bin/bash
|
|
jpayne@69
|
2
|
|
jpayne@69
|
3 usage(){
|
|
jpayne@69
|
4 echo "
|
|
jpayne@69
|
5 Written by Brian Bushnell
|
|
jpayne@69
|
6 Last modified July 28, 2022
|
|
jpayne@69
|
7
|
|
jpayne@69
|
8 Description: Compares reads to the kmers in a reference dataset, optionally
|
|
jpayne@69
|
9 allowing an edit distance. Splits the reads into two outputs - those that
|
|
jpayne@69
|
10 match the reference, and those that don't. Can also trim (remove) the matching
|
|
jpayne@69
|
11 parts of the reads rather than binning the reads.
|
|
jpayne@69
|
12 Please read bbmap/docs/guides/BBDukGuide.txt for more information.
|
|
jpayne@69
|
13
|
|
jpayne@69
|
14 Usage: bbduk.sh in=<input file> out=<output file> ref=<contaminant files>
|
|
jpayne@69
|
15
|
|
jpayne@69
|
16 Input may be stdin or a fasta or fastq file, compressed or uncompressed.
|
|
jpayne@69
|
17 If you pipe via stdin/stdout, please include the file type; e.g. for gzipped
|
|
jpayne@69
|
18 fasta input, set in=stdin.fa.gz
|
|
jpayne@69
|
19
|
|
jpayne@69
|
20 Input parameters:
|
|
jpayne@69
|
21 in=<file> Main input. in=stdin.fq will pipe from stdin.
|
|
jpayne@69
|
22 in2=<file> Input for 2nd read of pairs in a different file.
|
|
jpayne@69
|
23 ref=<file,file> Comma-delimited list of reference files.
|
|
jpayne@69
|
24 In addition to filenames, you may also use the keywords:
|
|
jpayne@69
|
25 adapters, artifacts, phix, lambda, pjet, mtst, kapa
|
|
jpayne@69
|
26 literal=<seq,seq> Comma-delimited list of literal reference sequences.
|
|
jpayne@69
|
27 touppercase=f (tuc) Change all bases upper-case.
|
|
jpayne@69
|
28 interleaved=auto (int) t/f overrides interleaved autodetection.
|
|
jpayne@69
|
29 qin=auto Input quality offset: 33 (Sanger), 64, or auto.
|
|
jpayne@69
|
30 reads=-1 If positive, quit after processing X reads or pairs.
|
|
jpayne@69
|
31 copyundefined=f (cu) Process non-AGCT IUPAC reference bases by making all
|
|
jpayne@69
|
32 possible unambiguous copies. Intended for short motifs
|
|
jpayne@69
|
33 or adapter barcodes, as time/memory use is exponential.
|
|
jpayne@69
|
34 samplerate=1 Set lower to only process a fraction of input reads.
|
|
jpayne@69
|
35 samref=<file> Optional reference fasta for processing sam files.
|
|
jpayne@69
|
36
|
|
jpayne@69
|
37 Output parameters:
|
|
jpayne@69
|
38 out=<file> (outnonmatch) Write reads here that do not contain
|
|
jpayne@69
|
39 kmers matching the database. 'out=stdout.fq' will pipe
|
|
jpayne@69
|
40 to standard out.
|
|
jpayne@69
|
41 out2=<file> (outnonmatch2) Use this to write 2nd read of pairs to a
|
|
jpayne@69
|
42 different file.
|
|
jpayne@69
|
43 outm=<file> (outmatch) Write reads here that fail filters. In default
|
|
jpayne@69
|
44 kfilter mode, this means any read with a matching kmer.
|
|
jpayne@69
|
45 In any mode, it also includes reads that fail filters such
|
|
jpayne@69
|
46 as minlength, mingc, maxgc, entropy, etc. In other words,
|
|
jpayne@69
|
47 it includes all reads that do not go to 'out'.
|
|
jpayne@69
|
48 outm2=<file> (outmatch2) Use this to write 2nd read of pairs to a
|
|
jpayne@69
|
49 different file.
|
|
jpayne@69
|
50 outs=<file> (outsingle) Use this to write singleton reads whose mate
|
|
jpayne@69
|
51 was trimmed shorter than minlen.
|
|
jpayne@69
|
52 stats=<file> Write statistics about which contamininants were detected.
|
|
jpayne@69
|
53 refstats=<file> Write statistics on a per-reference-file basis.
|
|
jpayne@69
|
54 rpkm=<file> Write RPKM for each reference sequence (for RNA-seq).
|
|
jpayne@69
|
55 dump=<file> Dump kmer tables to a file, in fasta format.
|
|
jpayne@69
|
56 duk=<file> Write statistics in duk's format. *DEPRECATED*
|
|
jpayne@69
|
57 nzo=t Only write statistics about ref sequences with nonzero hits.
|
|
jpayne@69
|
58 overwrite=t (ow) Grant permission to overwrite files.
|
|
jpayne@69
|
59 showspeed=t (ss) 'f' suppresses display of processing speed.
|
|
jpayne@69
|
60 ziplevel=2 (zl) Compression level; 1 (min) through 9 (max).
|
|
jpayne@69
|
61 fastawrap=70 Length of lines in fasta output.
|
|
jpayne@69
|
62 qout=auto Output quality offset: 33 (Sanger), 64, or auto.
|
|
jpayne@69
|
63 statscolumns=3 (cols) Number of columns for stats output, 3 or 5.
|
|
jpayne@69
|
64 5 includes base counts.
|
|
jpayne@69
|
65 rename=f Rename reads to indicate which sequences they matched.
|
|
jpayne@69
|
66 refnames=f Use names of reference files rather than scaffold IDs.
|
|
jpayne@69
|
67 trd=f Truncate read and ref names at the first whitespace.
|
|
jpayne@69
|
68 ordered=f Set to true to output reads in same order as input.
|
|
jpayne@69
|
69 maxbasesout=-1 If positive, quit after writing approximately this many
|
|
jpayne@69
|
70 bases to out (outu/outnonmatch).
|
|
jpayne@69
|
71 maxbasesoutm=-1 If positive, quit after writing approximately this many
|
|
jpayne@69
|
72 bases to outm (outmatch).
|
|
jpayne@69
|
73 json=f Print to screen in json format.
|
|
jpayne@69
|
74
|
|
jpayne@69
|
75 Histogram output parameters:
|
|
jpayne@69
|
76 bhist=<file> Base composition histogram by position.
|
|
jpayne@69
|
77 qhist=<file> Quality histogram by position.
|
|
jpayne@69
|
78 qchist=<file> Count of bases with each quality value.
|
|
jpayne@69
|
79 aqhist=<file> Histogram of average read quality.
|
|
jpayne@69
|
80 bqhist=<file> Quality histogram designed for box plots.
|
|
jpayne@69
|
81 lhist=<file> Read length histogram.
|
|
jpayne@69
|
82 phist=<file> Polymer length histogram.
|
|
jpayne@69
|
83 gchist=<file> Read GC content histogram.
|
|
jpayne@69
|
84 enthist=<file> Read entropy histogram.
|
|
jpayne@69
|
85 ihist=<file> Insert size histogram, for paired reads in mapped sam.
|
|
jpayne@69
|
86 gcbins=100 Number gchist bins. Set to 'auto' to use read length.
|
|
jpayne@69
|
87 maxhistlen=6000 Set an upper bound for histogram lengths; higher uses
|
|
jpayne@69
|
88 more memory. The default is 6000 for some histograms
|
|
jpayne@69
|
89 and 80000 for others.
|
|
jpayne@69
|
90
|
|
jpayne@69
|
91 Histograms for mapped sam/bam files only:
|
|
jpayne@69
|
92 histbefore=t Calculate histograms from reads before processing.
|
|
jpayne@69
|
93 ehist=<file> Errors-per-read histogram.
|
|
jpayne@69
|
94 qahist=<file> Quality accuracy histogram of error rates versus quality
|
|
jpayne@69
|
95 score.
|
|
jpayne@69
|
96 indelhist=<file> Indel length histogram.
|
|
jpayne@69
|
97 mhist=<file> Histogram of match, sub, del, and ins rates by position.
|
|
jpayne@69
|
98 idhist=<file> Histogram of read count versus percent identity.
|
|
jpayne@69
|
99 idbins=100 Number idhist bins. Set to 'auto' to use read length.
|
|
jpayne@69
|
100 varfile=<file> Ignore substitution errors listed in this file when
|
|
jpayne@69
|
101 calculating error rates. Can be generated with
|
|
jpayne@69
|
102 CallVariants.
|
|
jpayne@69
|
103 vcf=<file> Ignore substitution errors listed in this VCF file
|
|
jpayne@69
|
104 when calculating error rates.
|
|
jpayne@69
|
105 ignorevcfindels=t Also ignore indels listed in the VCF.
|
|
jpayne@69
|
106
|
|
jpayne@69
|
107 Processing parameters:
|
|
jpayne@69
|
108 k=27 Kmer length used for finding contaminants. Contaminants
|
|
jpayne@69
|
109 shorter than k will not be found. k must be at least 1.
|
|
jpayne@69
|
110 rcomp=t Look for reverse-complements of kmers in addition to
|
|
jpayne@69
|
111 forward kmers.
|
|
jpayne@69
|
112 maskmiddle=t (mm) Treat the middle base of a kmer as a wildcard, to
|
|
jpayne@69
|
113 increase sensitivity in the presence of errors.
|
|
jpayne@69
|
114 minkmerhits=1 (mkh) Reads need at least this many matching kmers
|
|
jpayne@69
|
115 to be considered as matching the reference.
|
|
jpayne@69
|
116 minkmerfraction=0.0 (mkf) A reads needs at least this fraction of its total
|
|
jpayne@69
|
117 kmers to hit a ref, in order to be considered a match.
|
|
jpayne@69
|
118 If this and minkmerhits are set, the greater is used.
|
|
jpayne@69
|
119 mincovfraction=0.0 (mcf) A reads needs at least this fraction of its total
|
|
jpayne@69
|
120 bases to be covered by ref kmers to be considered a match.
|
|
jpayne@69
|
121 If specified, mcf overrides mkh and mkf.
|
|
jpayne@69
|
122 hammingdistance=0 (hdist) Maximum Hamming distance for ref kmers (subs only).
|
|
jpayne@69
|
123 Memory use is proportional to (3*K)^hdist.
|
|
jpayne@69
|
124 qhdist=0 Hamming distance for query kmers; impacts speed, not memory.
|
|
jpayne@69
|
125 editdistance=0 (edist) Maximum edit distance from ref kmers (subs
|
|
jpayne@69
|
126 and indels). Memory use is proportional to (8*K)^edist.
|
|
jpayne@69
|
127 hammingdistance2=0 (hdist2) Sets hdist for short kmers, when using mink.
|
|
jpayne@69
|
128 qhdist2=0 Sets qhdist for short kmers, when using mink.
|
|
jpayne@69
|
129 editdistance2=0 (edist2) Sets edist for short kmers, when using mink.
|
|
jpayne@69
|
130 forbidn=f (fn) Forbids matching of read kmers containing N.
|
|
jpayne@69
|
131 By default, these will match a reference 'A' if
|
|
jpayne@69
|
132 hdist>0 or edist>0, to increase sensitivity.
|
|
jpayne@69
|
133 removeifeitherbad=t (rieb) Paired reads get sent to 'outmatch' if either is
|
|
jpayne@69
|
134 match (or either is trimmed shorter than minlen).
|
|
jpayne@69
|
135 Set to false to require both.
|
|
jpayne@69
|
136 trimfailures=f Instead of discarding failed reads, trim them to 1bp.
|
|
jpayne@69
|
137 This makes the statistics a bit odd.
|
|
jpayne@69
|
138 findbestmatch=f (fbm) If multiple matches, associate read with sequence
|
|
jpayne@69
|
139 sharing most kmers. Reduces speed.
|
|
jpayne@69
|
140 skipr1=f Don't do kmer-based operations on read 1.
|
|
jpayne@69
|
141 skipr2=f Don't do kmer-based operations on read 2.
|
|
jpayne@69
|
142 ecco=f For overlapping paired reads only. Performs error-
|
|
jpayne@69
|
143 correction with BBMerge prior to kmer operations.
|
|
jpayne@69
|
144 recalibrate=f (recal) Recalibrate quality scores. Requires calibration
|
|
jpayne@69
|
145 matrices generated by CalcTrueQuality.
|
|
jpayne@69
|
146 sam=<file,file> If recalibration is desired, and matrices have not already
|
|
jpayne@69
|
147 been generated, BBDuk will create them from the sam file.
|
|
jpayne@69
|
148 amino=f Run in amino acid mode. Some features have not been
|
|
jpayne@69
|
149 tested, but kmer-matching works fine. Maximum k is 12.
|
|
jpayne@69
|
150
|
|
jpayne@69
|
151 Speed and Memory parameters:
|
|
jpayne@69
|
152 threads=auto (t) Set number of threads to use; default is number of
|
|
jpayne@69
|
153 logical processors.
|
|
jpayne@69
|
154 prealloc=f Preallocate memory in table. Allows faster table loading
|
|
jpayne@69
|
155 and more efficient memory usage, for a large reference.
|
|
jpayne@69
|
156 monitor=f Kill this process if it crashes. monitor=600,0.01 would
|
|
jpayne@69
|
157 kill after 600 seconds under 1% usage.
|
|
jpayne@69
|
158 minrskip=1 (mns) Force minimal skip interval when indexing reference
|
|
jpayne@69
|
159 kmers. 1 means use all, 2 means use every other kmer, etc.
|
|
jpayne@69
|
160 maxrskip=1 (mxs) Restrict maximal skip interval when indexing
|
|
jpayne@69
|
161 reference kmers. Normally all are used for scaffolds<100kb,
|
|
jpayne@69
|
162 but with longer scaffolds, up to maxrskip-1 are skipped.
|
|
jpayne@69
|
163 rskip= Set both minrskip and maxrskip to the same value.
|
|
jpayne@69
|
164 If not set, rskip will vary based on sequence length.
|
|
jpayne@69
|
165 qskip=1 Skip query kmers to increase speed. 1 means use all.
|
|
jpayne@69
|
166 speed=0 Ignore this fraction of kmer space (0-15 out of 16) in both
|
|
jpayne@69
|
167 reads and reference. Increases speed and reduces memory.
|
|
jpayne@69
|
168 Note: Do not use more than one of 'speed', 'qskip', and 'rskip'.
|
|
jpayne@69
|
169
|
|
jpayne@69
|
170 Trimming/Filtering/Masking parameters:
|
|
jpayne@69
|
171 Note - if ktrim, kmask, and ksplit are unset, the default behavior is kfilter.
|
|
jpayne@69
|
172 All kmer processing modes are mutually exclusive.
|
|
jpayne@69
|
173 Reads only get sent to 'outm' purely based on kmer matches in kfilter mode.
|
|
jpayne@69
|
174
|
|
jpayne@69
|
175 ktrim=f Trim reads to remove bases matching reference kmers, plus
|
|
jpayne@69
|
176 all bases to the left or right.
|
|
jpayne@69
|
177 Values:
|
|
jpayne@69
|
178 f (don't trim),
|
|
jpayne@69
|
179 r (trim to the right),
|
|
jpayne@69
|
180 l (trim to the left)
|
|
jpayne@69
|
181 ktrimtips=0 Set this to a positive number to perform ktrim on both
|
|
jpayne@69
|
182 ends, examining only the outermost X bases.
|
|
jpayne@69
|
183 kmask= Replace bases matching ref kmers with another symbol.
|
|
jpayne@69
|
184 Allows any non-whitespace character, and processes short
|
|
jpayne@69
|
185 kmers on both ends if mink is set. 'kmask=lc' will
|
|
jpayne@69
|
186 convert masked bases to lowercase.
|
|
jpayne@69
|
187 maskfullycovered=f (mfc) Only mask bases that are fully covered by kmers.
|
|
jpayne@69
|
188 ksplit=f For single-ended reads only. Reads will be split into
|
|
jpayne@69
|
189 pairs around the kmer. If the kmer is at the end of the
|
|
jpayne@69
|
190 read, it will be trimmed instead. Singletons will go to
|
|
jpayne@69
|
191 out, and pairs will go to outm. Do not use ksplit with
|
|
jpayne@69
|
192 other operations such as quality-trimming or filtering.
|
|
jpayne@69
|
193 mink=0 Look for shorter kmers at read tips down to this length,
|
|
jpayne@69
|
194 when k-trimming or masking. 0 means disabled. Enabling
|
|
jpayne@69
|
195 this will disable maskmiddle.
|
|
jpayne@69
|
196 qtrim=f Trim read ends to remove bases with quality below trimq.
|
|
jpayne@69
|
197 Performed AFTER looking for kmers. Values:
|
|
jpayne@69
|
198 rl (trim both ends),
|
|
jpayne@69
|
199 f (neither end),
|
|
jpayne@69
|
200 r (right end only),
|
|
jpayne@69
|
201 l (left end only),
|
|
jpayne@69
|
202 w (sliding window).
|
|
jpayne@69
|
203 trimq=6 Regions with average quality BELOW this will be trimmed,
|
|
jpayne@69
|
204 if qtrim is set to something other than f. Can be a
|
|
jpayne@69
|
205 floating-point number like 7.3.
|
|
jpayne@69
|
206 trimclip=f Trim soft-clipped bases from sam files.
|
|
jpayne@69
|
207 minlength=10 (ml) Reads shorter than this after trimming will be
|
|
jpayne@69
|
208 discarded. Pairs will be discarded if both are shorter.
|
|
jpayne@69
|
209 mlf=0 (minlengthfraction) Reads shorter than this fraction of
|
|
jpayne@69
|
210 original length after trimming will be discarded.
|
|
jpayne@69
|
211 maxlength= Reads longer than this after trimming will be discarded.
|
|
jpayne@69
|
212 minavgquality=0 (maq) Reads with average quality (after trimming) below
|
|
jpayne@69
|
213 this will be discarded.
|
|
jpayne@69
|
214 maqb=0 If positive, calculate maq from this many initial bases.
|
|
jpayne@69
|
215 minbasequality=0 (mbq) Reads with any base below this quality (after
|
|
jpayne@69
|
216 trimming) will be discarded.
|
|
jpayne@69
|
217 maxns=-1 If non-negative, reads with more Ns than this
|
|
jpayne@69
|
218 (after trimming) will be discarded.
|
|
jpayne@69
|
219 mcb=0 (minconsecutivebases) Discard reads without at least
|
|
jpayne@69
|
220 this many consecutive called bases.
|
|
jpayne@69
|
221 ottm=f (outputtrimmedtomatch) Output reads trimmed to shorter
|
|
jpayne@69
|
222 than minlength to outm rather than discarding.
|
|
jpayne@69
|
223 tp=0 (trimpad) Trim this much extra around matching kmers.
|
|
jpayne@69
|
224 tbo=f (trimbyoverlap) Trim adapters based on where paired
|
|
jpayne@69
|
225 reads overlap.
|
|
jpayne@69
|
226 strictoverlap=t Adjust sensitivity for trimbyoverlap mode.
|
|
jpayne@69
|
227 minoverlap=14 Require this many bases of overlap for detection.
|
|
jpayne@69
|
228 mininsert=40 Require insert size of at least this for overlap.
|
|
jpayne@69
|
229 Should be reduced to 16 for small RNA sequencing.
|
|
jpayne@69
|
230 tpe=f (trimpairsevenly) When kmer right-trimming, trim both
|
|
jpayne@69
|
231 reads to the minimum length of either.
|
|
jpayne@69
|
232 forcetrimleft=0 (ftl) If positive, trim bases to the left of this position
|
|
jpayne@69
|
233 (exclusive, 0-based).
|
|
jpayne@69
|
234 forcetrimright=0 (ftr) If positive, trim bases to the right of this position
|
|
jpayne@69
|
235 (exclusive, 0-based).
|
|
jpayne@69
|
236 forcetrimright2=0 (ftr2) If positive, trim this many bases on the right end.
|
|
jpayne@69
|
237 forcetrimmod=0 (ftm) If positive, right-trim length to be equal to zero,
|
|
jpayne@69
|
238 modulo this number.
|
|
jpayne@69
|
239 restrictleft=0 If positive, only look for kmer matches in the
|
|
jpayne@69
|
240 leftmost X bases.
|
|
jpayne@69
|
241 restrictright=0 If positive, only look for kmer matches in the
|
|
jpayne@69
|
242 rightmost X bases.
|
|
jpayne@69
|
243 NOTE: restrictleft and restrictright are mutually exclusive. If trimming
|
|
jpayne@69
|
244 both ends is desired, use ktrimtips.
|
|
jpayne@69
|
245 mingc=0 Discard reads with GC content below this.
|
|
jpayne@69
|
246 maxgc=1 Discard reads with GC content above this.
|
|
jpayne@69
|
247 gcpairs=t Use average GC of paired reads.
|
|
jpayne@69
|
248 Also affects gchist.
|
|
jpayne@69
|
249 tossjunk=f Discard reads with invalid characters as bases.
|
|
jpayne@69
|
250 swift=f Trim Swift sequences: Trailing C/T/N R1, leading G/A/N R2.
|
|
jpayne@69
|
251
|
|
jpayne@69
|
252 Header-parsing parameters - these require Illumina headers:
|
|
jpayne@69
|
253 chastityfilter=f (cf) Discard reads with id containing ' 1:Y:' or ' 2:Y:'.
|
|
jpayne@69
|
254 barcodefilter=f Remove reads with unexpected barcodes if barcodes is set,
|
|
jpayne@69
|
255 or barcodes containing 'N' otherwise. A barcode must be
|
|
jpayne@69
|
256 the last part of the read header. Values:
|
|
jpayne@69
|
257 t: Remove reads with bad barcodes.
|
|
jpayne@69
|
258 f: Ignore barcodes.
|
|
jpayne@69
|
259 crash: Crash upon encountering bad barcodes.
|
|
jpayne@69
|
260 barcodes= Comma-delimited list of barcodes or files of barcodes.
|
|
jpayne@69
|
261 xmin=-1 If positive, discard reads with a lesser X coordinate.
|
|
jpayne@69
|
262 ymin=-1 If positive, discard reads with a lesser Y coordinate.
|
|
jpayne@69
|
263 xmax=-1 If positive, discard reads with a greater X coordinate.
|
|
jpayne@69
|
264 ymax=-1 If positive, discard reads with a greater Y coordinate.
|
|
jpayne@69
|
265
|
|
jpayne@69
|
266 Polymer trimming:
|
|
jpayne@69
|
267 trimpolya=0 If greater than 0, trim poly-A or poly-T tails of
|
|
jpayne@69
|
268 at least this length on either end of reads.
|
|
jpayne@69
|
269 trimpolygleft=0 If greater than 0, trim poly-G prefixes of at least this
|
|
jpayne@69
|
270 length on the left end of reads. Does not trim poly-C.
|
|
jpayne@69
|
271 trimpolygright=0 If greater than 0, trim poly-G tails of at least this
|
|
jpayne@69
|
272 length on the right end of reads. Does not trim poly-C.
|
|
jpayne@69
|
273 trimpolyg=0 This sets both left and right at once.
|
|
jpayne@69
|
274 filterpolyg=0 If greater than 0, remove reads with a poly-G prefix of
|
|
jpayne@69
|
275 at least this length (on the left).
|
|
jpayne@69
|
276 Note: there are also equivalent poly-C flags.
|
|
jpayne@69
|
277
|
|
jpayne@69
|
278 Polymer tracking:
|
|
jpayne@69
|
279 pratio=base,base 'pratio=G,C' will print the ratio of G to C polymers.
|
|
jpayne@69
|
280 plen=20 Length of homopolymers to count.
|
|
jpayne@69
|
281
|
|
jpayne@69
|
282 Entropy/Complexity parameters:
|
|
jpayne@69
|
283 entropy=-1 Set between 0 and 1 to filter reads with entropy below
|
|
jpayne@69
|
284 that value. Higher is more stringent.
|
|
jpayne@69
|
285 entropywindow=50 Calculate entropy using a sliding window of this length.
|
|
jpayne@69
|
286 entropyk=5 Calculate entropy using kmers of this length.
|
|
jpayne@69
|
287 minbasefrequency=0 Discard reads with a minimum base frequency below this.
|
|
jpayne@69
|
288 entropytrim=f Values:
|
|
jpayne@69
|
289 f: (false) Do not entropy-trim.
|
|
jpayne@69
|
290 r: (right) Trim low entropy on the right end only.
|
|
jpayne@69
|
291 l: (left) Trim low entropy on the left end only.
|
|
jpayne@69
|
292 rl: (both) Trim low entropy on both ends.
|
|
jpayne@69
|
293 entropymask=f Values:
|
|
jpayne@69
|
294 f: (filter) Discard low-entropy sequences.
|
|
jpayne@69
|
295 t: (true) Mask low-entropy parts of sequences with N.
|
|
jpayne@69
|
296 lc: Change low-entropy parts of sequences to lowercase.
|
|
jpayne@69
|
297 entropymark=f Mark each base with its entropy value. This is on a scale
|
|
jpayne@69
|
298 of 0-41 and is reported as quality scores, so the output
|
|
jpayne@69
|
299 should be fastq or fasta+qual.
|
|
jpayne@69
|
300 NOTE: If set, entropytrim overrides entropymask.
|
|
jpayne@69
|
301
|
|
jpayne@69
|
302 Cardinality estimation:
|
|
jpayne@69
|
303 cardinality=f (loglog) Count unique kmers using the LogLog algorithm.
|
|
jpayne@69
|
304 cardinalityout=f (loglogout) Count unique kmers in output reads.
|
|
jpayne@69
|
305 loglogk=31 Use this kmer length for counting.
|
|
jpayne@69
|
306 loglogbuckets=2048 Use this many buckets for counting.
|
|
jpayne@69
|
307 khist=<file> Kmer frequency histogram; plots number of kmers versus
|
|
jpayne@69
|
308 kmer depth. This is approximate.
|
|
jpayne@69
|
309 khistout=<file> Kmer frequency histogram for output reads.
|
|
jpayne@69
|
310
|
|
jpayne@69
|
311 Java Parameters:
|
|
jpayne@69
|
312
|
|
jpayne@69
|
313 -Xmx This will set Java's memory usage, overriding autodetection.
|
|
jpayne@69
|
314 -Xmx20g will
|
|
jpayne@69
|
315 specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
|
|
jpayne@69
|
316 The max is typically 85% of physical memory.
|
|
jpayne@69
|
317 -eoom This flag will cause the process to exit if an
|
|
jpayne@69
|
318 out-of-memory exception occurs. Requires Java 8u92+.
|
|
jpayne@69
|
319 -da Disable assertions.
|
|
jpayne@69
|
320
|
|
jpayne@69
|
321 Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
|
|
jpayne@69
|
322 "
|
|
jpayne@69
|
323 }
|
|
jpayne@69
|
324
|
|
jpayne@69
|
325 #This block allows symlinked shellscripts to correctly set classpath.
|
|
jpayne@69
|
326 pushd . > /dev/null
|
|
jpayne@69
|
327 DIR="${BASH_SOURCE[0]}"
|
|
jpayne@69
|
328 while [ -h "$DIR" ]; do
|
|
jpayne@69
|
329 cd "$(dirname "$DIR")"
|
|
jpayne@69
|
330 DIR="$(readlink "$(basename "$DIR")")"
|
|
jpayne@69
|
331 done
|
|
jpayne@69
|
332 cd "$(dirname "$DIR")"
|
|
jpayne@69
|
333 DIR="$(pwd)/"
|
|
jpayne@69
|
334 popd > /dev/null
|
|
jpayne@69
|
335
|
|
jpayne@69
|
336 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
|
|
jpayne@69
|
337 CP="$DIR""current/"
|
|
jpayne@69
|
338 JNI="-Djava.library.path=""$DIR""jni/"
|
|
jpayne@69
|
339 JNI=""
|
|
jpayne@69
|
340
|
|
jpayne@69
|
341 z="-Xmx1g"
|
|
jpayne@69
|
342 z2="-Xms1g"
|
|
jpayne@69
|
343 set=0
|
|
jpayne@69
|
344 silent=0
|
|
jpayne@69
|
345 json=0
|
|
jpayne@69
|
346
|
|
jpayne@69
|
347 if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
|
|
jpayne@69
|
348 usage
|
|
jpayne@69
|
349 exit
|
|
jpayne@69
|
350 fi
|
|
jpayne@69
|
351
|
|
jpayne@69
|
352 calcXmx () {
|
|
jpayne@69
|
353 source "$DIR""/calcmem.sh"
|
|
jpayne@69
|
354 setEnvironment
|
|
jpayne@69
|
355 parseXmx "$@"
|
|
jpayne@69
|
356 if [[ $set == 1 ]]; then
|
|
jpayne@69
|
357 return
|
|
jpayne@69
|
358 fi
|
|
jpayne@69
|
359 freeRam 1400m 42
|
|
jpayne@69
|
360 z="-Xmx${RAM}m"
|
|
jpayne@69
|
361 z2="-Xms${RAM}m"
|
|
jpayne@69
|
362 }
|
|
jpayne@69
|
363 calcXmx "$@"
|
|
jpayne@69
|
364
|
|
jpayne@69
|
365 bbduk() {
|
|
jpayne@69
|
366 local CMD="java $EA $EOOM $z $z2 $JNI -cp $CP jgi.BBDuk $@"
|
|
jpayne@69
|
367 if [[ $silent == 0 ]] && [[ $json == 0 ]]; then
|
|
jpayne@69
|
368 echo $CMD >&2
|
|
jpayne@69
|
369 fi
|
|
jpayne@69
|
370 eval $CMD
|
|
jpayne@69
|
371 }
|
|
jpayne@69
|
372
|
|
jpayne@69
|
373 bbduk "$@"
|
