New upstream version 4.8.1

CC = g++ -Wall -ggdb

CC = g++ -pg

CC = g++

# without OpenMP

# default with OpenMP

# with OpenMP

# in command line: 

# make openmp=yes

  CCFLAGS = -fopenmp

endif

#LDFLAGS = -static -lz -o

#LDFLAGS = /usr/lib/x86_64-linux-gnu/libz.a -o

# default with zlib

# without zlib

# in command line:

# make zlib=no

ifeq ($(zlib),no)

  CCFLAGS += 

  LDFLAGS += -o

else

  CCFLAGS += -DWITH_ZLIB

  LDFLAGS += -lz -o

endif

# support debugging

# in command line:

# make debug=yes

CCFLAGS += -DMAX_SEQ=$(MAX_SEQ)

endif

#LDFLAGS = -static -o

LDFLAGS += -o

PROGS = cd-hit cd-hit-est cd-hit-2d cd-hit-est-2d cd-hit-div cd-hit-454

# Propagate hardening flags

For cd-hit

How to compile?

Requirements

Since 4.8.1, cd-hit supports .gz format input file. This requires zlib library. zlib should

be install in most Linux systems, so cd-hit should be compiled without issue. If your system

don't have zlib, please install it first. 

    * On Ubuntu, to install zlib:

        sudo apt install zlib1g-dev

    * On CentOS, to install zlib:

        sudo yum install zlib-devel 

How to compile

  1. Compile with multi-threading support (default): make

  2. Compile without multi-threading support (if you are on very old systems): make openmp=no

  3. Compile without zlib (if you can not install zlib): make zlib=no

Having problems to compile

Please contact the author

For cd-hit-auxtools

  make

For psi-cd-hit

  please download legacy BLAST (not BLAST+) and install the executables in your $PATH

Compile cd-hit on MacOS

To install CD-HIT on MacOS, first install gcc on your system.

To use Homebrew (https://brew.sh/), see https://brewformulas.org/gcc. 

Then locate the path to your g++ executable, (e.g. /usr/local/Cellar/gcc/6.3.0_1/bin/g++-6, 

note: yours g++ path is likely to be different), then use command like this:

  make CC=/usr/local/Cellar/gcc/6.3.0_1/bin/g++-6

For psi-cd-hit

  please download BLAST+ (not legacy BLAST) and install the executables in your $PATH

For more information, please visit http://cd-hit.org

#!/usr/bin/perl

#

my $rep;

my @non_reps = ();

my @aln_info = ();

while($ll=<>){

  if ($ll =~ /^>/ ) {

    if (@non_reps) {

      for ($i=0; $i<@non_reps; $i++) {

        print "$non_reps[$i]\t$rep\t$aln_info[$i]\n";

      }

    }

    $rep = "";

    @non_reps = ();

    @aln_info = ();

  }

  else {

    chop($ll);

    if ($ll =~ />(.+)\.\.\./ ) {

      my $id = $1;

      if ($ll =~ /\*$/) { $rep = $id}

      else              { 

        push(@non_reps, $id);

        my @lls = split(/\s+/, $ll);

        my ($a, $iden) = split(/\//, $lls[-1]);

        chop($iden); ### removing % sign

        my ($qb, $qe, $sb, $se) = split(/:/, $a);

        my $alnln = $qe-$qb+1;

        my $mis = int($alnln * (100-$iden) / 100);

        my $gap = 0;

        my $exp = 0;

        my $bit = $alnln*3 - $mis*6; #### very rough

        push(@aln_info, "$iden\t$alnln\t$mis\t$gap\t$qb\t$qe\t$sb\t$se\t$exp\t$bit");

      }

    }

#>Cluster 582

#0       6671aa, >gi|302514050|uid|51... *

#1       339aa, >SRS584717|scaffold|... at 2:332:4020:4356/89.32%

#2       182aa, >SRS584717|scaffold|... at 1:182:6490:6671/100.00%

#3       367aa, >SRS584717|scaffold|... at 1:332:4543:4874/90.66%

#4       109aa, >SRS584717|scaffold|... at 1:108:5782:5889/97.22%

  }

}

    if (@non_reps) {

      for ($i=0; $i<@non_reps; $i++) {

        print "$non_reps[$i]\t$rep\t$aln_info[$i]\n";

      }

    }

#query                          subject         %       alnln   mis     gap     q_b     q_e     s_b     s_e     expect  bits

##0                              1               2       3       4       5       6       7       8       9       10      11

#mHE-SRS012902|scaffold|86.16    gnl|CDD|226997  47.62   42      17      2       164     201     210     250     5e-04   37.6

#mHE-SRS012902|scaffold|109.23   gnl|CDD|225183  47.46   236     122     1       1       236     475     708     1e-92    284

#mHE-SRS012902|scaffold|109.23   gnl|CDD|224055  44.35   239     130     2       1       239     332     567     2e-84    259

#mHE-SRS012902|scaffold|109.23   gnl|CDD|227321  39.50   238     140     3       1       238     324     557     9e-69    218

#include<stdint.h>

#include<time.h>

#ifdef WITH_ZLIB

#include<zlib.h>

#endif

#include<valarray>

#include<vector>

#include<map>

#define CDHIT_VERSION  "4.7"

#define CDHIT_VERSION  "4.8.1"

#ifndef MAX_SEQ

#define MAX_SEQ 655360

		~SequenceDB(){ Clear(); }

		void Read( const char *file, const Options & options );

		void Readgz( const char *file, const Options & options );

		void Read( const char *file, const char *file2, const Options & options );

		void Readgz( const char *file, const char *file2, const Options & options );

		void WriteClusters( const char *db, const char *newdb, const Options & options );

		void WriteClustersgz( const char *db, const char *newdb, const Options & options );

		void WriteClusters( const char *db, const char *db_pe, const char *newdb, const char *newdb_pe, const Options & options );

		void WriteClustersgz( const char *db, const char *db_pe, const char *newdb, const char *newdb_pe, const Options & options );

		void WriteExtra1D( const Options & options );

		void WriteExtra2D( SequenceDB & other, const Options & options );

		void DivideSave( const char *db, const char *newdb, int n, const Options & options );