1#!/usr/local/bin/bash
2
3usage(){
4echo "
5Written by Brian Bushnell and Jonathan Rood
6Last modified February 19, 2020
7
8Description:  Accepts one or more files containing sets of sequences (reads or scaffolds).
9Removes duplicate sequences, which may be specified to be exact matches, subsequences, or sequences within some percent identity.
10Can also find overlapping sequences and group them into clusters.
11Please read bbmap/docs/guides/DedupeGuide.txt for more information.
12
13Usage:     dedupe.sh in=<file or stdin> out=<file or stdout>
14
15An example of running Dedupe for clustering short reads:
16dedupe.sh in=x.fq am=f ac=f fo c pc rnc=f mcs=4 mo=100 s=1 pto cc qin=33 csf=stats.txt pattern=cluster_%.fq dot=graph.dot
17
18Input may be fasta or fastq, compressed or uncompressed.
19Output may be stdout or a file.  With no output parameter, data will be written to stdout.
20If 'out=null', there will be no output, but statistics will still be printed.
21You can also use 'dedupe <infile> <outfile>' without the 'in=' and 'out='.
22
23I/O parameters:
24in=<file,file>        A single file or a comma-delimited list of files.
25out=<file>            Destination for all output contigs.
26pattern=<file>        Clusters will be written to individual files, where the '%' symbol in the pattern is replaced by cluster number.
27outd=<file>           Optional; removed duplicates will go here.
28csf=<file>            (clusterstatsfile) Write a list of cluster names and sizes.
29dot=<file>            (graph) Write a graph in dot format.  Requires 'fo' and 'pc' flags.
30threads=auto          (t) Set number of threads to use; default is number of logical processors.
31overwrite=t           (ow) Set to false to force the program to abort rather than overwrite an existing file.
32showspeed=t           (ss) Set to 'f' to suppress display of processing speed.
33minscaf=0             (ms) Ignore contigs/scaffolds shorter than this.
34interleaved=auto      If true, forces fastq input to be paired and interleaved.
35ziplevel=2            Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster.
36
37Output format parameters:
38storename=t           (sn) Store scaffold names (set false to save memory).
39#addpairnum=f         Add .1 and .2 to numeric id of read1 and read2.
40storequality=t        (sq) Store quality values for fastq assemblies (set false to save memory).
41uniquenames=t         (un) Ensure all output scaffolds have unique names.  Uses more memory.
42mergenames=f          When a sequence absorbs another, concatenate their headers.
43mergedelimiter=>      Delimiter between merged headers.  Can be a symbol name like greaterthan.
44numbergraphnodes=t    (ngn) Label dot graph nodes with read numbers rather than read names.
45sort=f                Sort output (otherwise it will be random).  Options:
46                         length:  Sort by length
47                         quality: Sort by quality
48                         name:    Sort by name
49                         id:      Sort by input order
50ascending=f           Sort in ascending order.
51ordered=f             Output sequences in input order.  Equivalent to sort=id ascending.
52renameclusters=f      (rnc) Rename contigs to indicate which cluster they are in.
53printlengthinedges=f  (ple) Print the length of contigs in edges.
54
55Processing parameters:
56absorbrc=t            (arc) Absorb reverse-complements as well as normal orientation.
57absorbmatch=t         (am) Absorb exact matches of contigs.
58absorbcontainment=t   (ac) Absorb full containments of contigs.
59#absorboverlap=f      (ao) Absorb (merge) non-contained overlaps of contigs (TODO).
60findoverlap=f         (fo) Find overlaps between contigs (containments and non-containments).  Necessary for clustering.
61uniqueonly=f          (uo) If true, all copies of duplicate reads will be discarded, rather than keeping 1.
62rmn=f                 (requirematchingnames) If true, both names and sequence must match.
63usejni=f              (jni) Do alignments in C code, which is faster, if an edit distance is allowed.
64                      This will require compiling the C code; details are in /jni/README.txt.
65
66Subset parameters:
67subsetcount=1         (sstc) Number of subsets used to process the data; higher uses less memory.
68subset=0              (sst) Only process reads whose ((ID%subsetcount)==subset).
69
70Clustering parameters:
71cluster=f             (c) Group overlapping contigs into clusters.
72pto=f                 (preventtransitiveoverlaps) Do not look for new edges between nodes in the same cluster.
73minclustersize=1      (mcs) Do not output clusters smaller than this.
74pbr=f                 (pickbestrepresentative) Only output the single highest-quality read per cluster.
75
76Cluster postprocessing parameters:
77processclusters=f     (pc) Run the cluster processing phase, which performs the selected operations in this category.
78                      For example, pc AND cc must be enabled to perform cc.
79fixmultijoins=t       (fmj) Remove redundant overlaps between the same two contigs.
80removecycles=t        (rc) Remove all cycles so clusters form trees.
81cc=t                  (canonicizeclusters) Flip contigs so clusters have a single orientation.
82fcc=f                 (fixcanoncontradictions) Truncate graph at nodes with canonization disputes.
83foc=f                 (fixoffsetcontradictions) Truncate graph at nodes with offset disputes.
84mst=f                 (maxspanningtree) Remove cyclic edges, leaving only the longest edges that form a tree.
85
86Overlap Detection Parameters
87exact=t               (ex) Only allow exact symbol matches.  When false, an 'N' will match any symbol.
88touppercase=t         (tuc) Convert input bases to upper-case; otherwise, lower-case will not match.
89maxsubs=0             (s) Allow up to this many mismatches (substitutions only, no indels).  May be set higher than maxedits.
90maxedits=0            (e) Allow up to this many edits (subs or indels).  Higher is slower.
91minidentity=100       (mid) Absorb contained sequences with percent identity of at least this (includes indels).
92minlengthpercent=0    (mlp) Smaller contig must be at least this percent of larger contig's length to be absorbed.
93minoverlappercent=0   (mop) Overlap must be at least this percent of smaller contig's length to cluster and merge.
94minoverlap=200        (mo) Overlap must be at least this long to cluster and merge.
95depthratio=0          (dr) When non-zero, overlaps will only be formed between reads with a depth ratio of at most this.
96                      Should be above 1.  Depth is determined by parsing the read names; this information can be added
97                      by running KmerNormalize (khist.sh, bbnorm.sh, or ecc.sh) with the flag 'rename'
98k=31                  Seed length used for finding containments and overlaps.  Anything shorter than k will not be found.
99numaffixmaps=1        (nam) Number of prefixes/suffixes to index per contig. Higher is more sensitive, if edits are allowed.
100hashns=f              Set to true to search for matches using kmers containing Ns.  Can lead to extreme slowdown in some cases.
101#ignoreaffix1=f       (ia1) Ignore first affix (for testing).
102#storesuffix=f        (ss) Store suffix as well as prefix.  Automatically set to true when doing inexact matches.
103
104Other Parameters
105qtrim=f               Set to qtrim=rl to trim leading and trailing Ns.
106trimq=6               Quality trim level.
107forcetrimleft=-1      (ftl) If positive, trim bases to the left of this position (exclusive, 0-based).
108forcetrimright=-1     (ftr) If positive, trim bases to the right of this position (exclusive, 0-based).
109
110Note on Proteins / Amino Acids
111Dedupe supports amino acid space via the 'amino' flag.  This also changes the default kmer length to 10.
112In amino acid mode, all flags related to canonicity and reverse-complementation are disabled,
113and nam (numaffixmaps) is currently limited to 2 per tip.
114
115Java Parameters:
116-Xmx                  This will set Java's memory usage, overriding autodetection.
117                      -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
118                    The max is typically 85% of physical memory.
119-eoom                 This flag will cause the process to exit if an out-of-memory exception occurs.  Requires Java 8u92+.
120-da                   Disable assertions.
121
122Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
123"
124}
125
126#This block allows symlinked shellscripts to correctly set classpath.
127pushd . > /dev/null
128DIR="${BASH_SOURCE[0]}"
129while [ -h "$DIR" ]; do
130  cd "$(dirname "$DIR")"
131  DIR="$(readlink "$(basename "$DIR")")"
132done
133cd "$(dirname "$DIR")"
134DIR="$(pwd)/"
135popd > /dev/null
136
137#DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
138CP="$DIR""current/"
139JNI="-Djava.library.path=""$DIR""jni/"
140JNI=""
141
142z="-Xmx1g"
143z2="-Xms1g"
144set=0
145
146if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
147	usage
148	exit
149fi
150
151calcXmx () {
152	source "$DIR""/calcmem.sh"
153	setEnvironment
154	parseXmx "$@"
155	if [[ $set == 1 ]]; then
156	return
157	fi
158	freeRam 3200m 84
159	z="-Xmx${RAM}m"
160	z2="-Xms${RAM}m"
161}
162calcXmx "$@"
163
164dedupe() {
165	local CMD="java $JNI $EA $EOOM $z $z2 -cp $CP jgi.Dedupe $@"
166	echo $CMD >&2
167	eval $CMD
168}
169
170dedupe "$@"
171