New port: biology/consed viewing and editing workbench for sequence

assembly

	Consed is a tool for viewing, editing, and finishing sequence
	assemblies.

	The port is constituted of 4 parts:
	biology/phred: base caller with quality evaluation
	biology/phrap: sequence assembler for shotgun sequencing
	biology/consed: workbench
	biology/phd2fasta: small utility

	All these can be used separately; however, most function
	of consed depends on the others.

	Although these programs are licensed freely for academic
	and nonprofit purposes, users have to contact the authors
	to get the softwares.
	Phred (including phd2fasta) and phrap are emailed,
	and consed can be downloaded to a restricted IP address.
	For commercial users, the licensing fee is ca. $10,000 at
	the time of writing.

PR:		ports/118548
Submitted by:	Motomichi Matsuzaki <mzaki@biol.s.u-tokyo.ac.jp>

biology/Makefile

@@ -66,6 +66,7 @@
     SUBDIR += paml
     SUBDIR += phd2fasta
     SUBDIR += phrap
+    SUBDIR += phred
     SUBDIR += phylip
     SUBDIR += platon
     SUBDIR += povchem

biology/phrap/Makefile

@@ -0,0 +1,62 @@
+# New ports collection makefile for:	phrap
+# Date created:		21 June 2005
+# Whom:			Motomichi Matsuzaki <mzaki@biol.s.u-tokyo.ac.jp>
+#
+# $FreeBSD$
+#
+
+PORTNAME=	phrap
+PORTVERSION=	0.990329
+CATEGORIES=	biology
+MASTER_SITES=	# put the tarball manually
+DISTFILES=	distrib.tar.Z
+DIST_SUBDIR=	${PORTNAME}
+
+MAINTAINER=	mzaki@biol.s.u-tokyo.ac.jp
+COMMENT=	Phrap is a program for assembling shotgun DNA sequence data
+
+RESTRICTED=	Redistribution is not permitted in any form. You must request the tarball via e-mail. Free for academic use.
+
+NO_WRKSUBDIR=	yes
+
+MAKEFILE=	makefile
+ALL_TARGET=	all manyreads
+
+BINARIES=	cluster cross_match cross_match.manyreads loco \
+		phrap phrap.longreads phrap.manyreads swat
+SCRIPTS=	phrapview
+.for f in ${BINARIES} ${SCRIPTS}
+PLIST_FILES+=	bin/${f}
+.endfor
+
+PORTDATA=	BLOSUM50 BLOSUM62 PAM250 mat50 mat70 penalty2 vector.seq
+PORTDOCS=	general.doc phrap.doc swat.doc
+
+.include <bsd.port.pre.mk>
+
+.for f in ${DISTFILES}
+.if !exists(${DISTDIR}/${DIST_SUBDIR}/${f})
+IGNORE=	you must request the source code \(${DISTFILES}\) via e-mail, place it manually in ${DISTDIR}/${DIST_SUBDIR}, and then try it again
+.endif
+.endfor
+
+do-install:
+.for f in ${BINARIES}
+	@${INSTALL_PROGRAM} ${WRKSRC}/${f} ${PREFIX}/bin/
+	@${CHMOD} a-r ${PREFIX}/bin/${f} # as required by the agreement
+.endfor
+.for f in ${SCRIPTS}
+	@${INSTALL_SCRIPT} ${WRKSRC}/${f} ${PREFIX}/bin/
+.endfor
+	@${MKDIR} ${DATADIR}
+.for f in ${PORTDATA}
+	@${INSTALL_DATA} ${WRKSRC}/${f} ${DATADIR}
+.endfor
+.if !defined(NOPORTDOCS)
+	@${MKDIR} ${DOCSDIR}
+.for f in ${PORTDOCS}
+	@${INSTALL_DATA} ${WRKSRC}/${f} ${DOCSDIR}
+.endfor
+.endif
+
+.include <bsd.port.post.mk>

biology/phrap/distinfo

@@ -0,0 +1,3 @@
+MD5 (phrap/distrib.tar.Z) = 35175595801cafd22ec348fb9dba0ce4
+SHA256 (phrap/distrib.tar.Z) = e0be79818e3a8ca17391f42cc0ffbaf1a63299c8845a0b9ac3aaeb3cac641fcc
+SIZE (phrap/distrib.tar.Z) = 366163

biology/phrap/files/patch-makefile

@@ -0,0 +1,27 @@
+--- makefile.orig	1999-03-11 15:13:20.000000000 +0900
++++ makefile	2007-12-11 13:19:39.000000000 +0900
+@@ -23,8 +23,8 @@
+ #*****************************************************************************/
+ 
+ # Makefile for swat, phrap, cross_match, phrapview; also swprobs (currently inactivated)
+-CC= cc
+-CFLAGS= -O2
++CC?= cc
++#CFLAGS= -O2
+ LFLAGS= -lm
+ 
+ SWATOBJS= swat.o weibull.o
+@@ -55,11 +55,11 @@
+ 
+ manyreads:  
+ 	touch swat.h;
+-	make CFLAGS="-O2 -DMANYREADS" phrap cross_match;
++	make CFLAGS="$(CFLAGS) -DMANYREADS" phrap cross_match;
+ 	mv phrap phrap.manyreads;
+ 	mv cross_match cross_match.manyreads;
+ 	touch swat.h;
+-	make CFLAGS="-O2 -DLONGREADS" phrap;
++	make CFLAGS="$(CFLAGS) -DLONGREADS" phrap;
+ 	mv phrap phrap.longreads;
+ 	touch swat.h;
+ 	make phrap cross_match;

biology/phrap/pkg-descr

@@ -0,0 +1,21 @@
+Phrap is a program for assembling shotgun DNA sequence data.
+Among other features, it allows use of the entire read and not just the
+trimmed high quality part, it uses a combination of user-supplied and
+internally computed data quality information to improve assembly accuracy
+in the presence of repeats, it constructs the contig sequence as a mosaic
+of the highest quality read segments rather than a consensus, it provides
+extensive assembly information to assist in trouble-shooting assembly
+problems, and it handles large datasets.
+
+This package also contains Swat and Cross_match.
+Swat is a program for searching one or more DNA or protein query sequences
+against a sequence database, using (an efficient implementation of) the
+Smith-Waterman-Gotoh algorithm.
+Cross_Match is a general-purpose utility based on Swat for comparing any
+two sets of DNA sequences, and it can be used to:
+* produce vector-masked versions of a set of reads
+* compare a set of cDNA sequences to a set of cosmids
+* compare contigs found by two altanative assembly procedures to each other
+* compare phrap contigs to the final edited cosmid sequence.
+
+WWW: http://www.phrap.org/phredphrapconsed.html

biology/phred/Makefile

@@ -0,0 +1,67 @@
+# New ports collection makefile for:	phred
+# Date created:		6 December 2007
+# Whom:			Motomichi Matsuzaki <mzaki@biol.s.u-tokyo.ac.jp>
+#
+# $FreeBSD$
+#
+
+PORTNAME=	phred
+PORTVERSION=	0.020425.c
+CATEGORIES=	biology
+MASTER_SITES=	# put the tarball manually
+DISTNAME=	${PORTNAME}-dist-${PORTVERSION:S/0.//}-acd
+EXTRACT_SUFX=	.tar.Z
+
+MAINTAINER=	mzaki@biol.s.u-tokyo.ac.jp
+COMMENT=	Base calling and quality value assignment on DNA sequencing
+
+RESTRICTED=	Redistribution is not permitted in any form. You must request the tarball via e-mail. Free for academic use.
+
+NO_WRKSUBDIR=	yes
+
+ALL_TARGET=	phred daev
+
+BINMODE=	0111	# avoid copying binaries as required by the agreement
+BINARIES=	phred daev
+.for f in ${BINARIES}
+PLIST_FILES+=	bin/${f}
+.endfor
+
+DATADIR=	${PREFIX}/etc/PhredPar
+DATAFILES=	phredpar.dat
+.for f in ${DATAFILES}
+PORTDATA+=	${f}.dist
+.endfor
+
+PORTDOCS=	NEWS PHRED.DOC DAEV.DOC
+
+.include <bsd.port.pre.mk>
+
+.for f in ${DISTFILES}
+.if !exists(${DISTDIR}/${f})
+IGNORE=	you must request the source code \(${f}\) via e-mail, place it manually in ${DISTDIR}, and then try it again
+.endif
+.endfor
+
+do-install:
+.for f in ${BINARIES}
+	@${INSTALL_PROGRAM} ${WRKSRC}/${f} ${PREFIX}/bin/
+.endfor
+	@${MKDIR} ${DATADIR}
+.for f in ${DATAFILES}
+	@${INSTALL_DATA} ${WRKSRC}/${f} ${DATADIR}/${f}.dist
+.endfor
+.if !defined(NOPORTDOCS)
+	@${MKDIR} ${DOCSDIR}
+.for f in ${PORTDOCS}
+	@${INSTALL_DATA} ${WRKSRC}/${f} ${DOCSDIR}
+.endfor
+.endif
+	@${ECHO} "---------------------------------------------------------------------------"
+	@${ECHO} "You must set PHRED_PARAMETER_FILE environment variable."
+	@${ECHO} ""
+	@${ECHO} "The default parameter file in the distribution is located at:"
+	@${ECHO} "  ${DATADIR}/phredpar.dat.dist"
+	@${ECHO} "---------------------------------------------------------------------------"
+
+.include <bsd.port.post.mk>

biology/phred/distinfo

@@ -0,0 +1,3 @@
+MD5 (phred-dist-020425.c-acd.tar.Z) = f6f86e14b6283d4797a5872a8d44a358
+SHA256 (phred-dist-020425.c-acd.tar.Z) = c7a7773447376c024212b680e1ce1e52c30ad8e18dee317ba863bc10db94f6c9
+SIZE (phred-dist-020425.c-acd.tar.Z) = 547645

biology/phred/files/patch-Makefile

@@ -0,0 +1,13 @@
+--- Makefile.orig	2002-07-27 07:22:10.000000000 +0900
++++ Makefile	2007-12-06 16:41:35.000000000 +0900
+@@ -12,8 +12,8 @@
+ 
+ # UNIX specific definitions (default)
+ #
+-CC= cc
+-CFLAGS= -O -DANSI_C $(LXFLAGS)
++CC?= cc
++CFLAGS+= -DANSI_C $(LXFLAGS)
+ CLIB= -lm
+ 
+ # Windows 'nmake' specific definitions

biology/phred/pkg-descr

@@ -0,0 +1,24 @@
+Phred reads DNA sequencer trace data, calls bases, assigns quality values
+to the bases, and writes the base calls and quality values to output files.
+
+Trace data is read from chromatogram files in the SCF, ABI, and EST formats,
+even if they were compressed using gzip, bzip2, or UNIX compress.
+Quality values are written to FASTA format files or PHD files, which can be
+used by the Phrap sequence assembly program in order to increase the accuracy
+of the assembled sequence.
+
+Base calling and quality value accuracies tested for:
+  ABI models 373, 377, and 3700
+  Molecular Dynamics MegaBACE
+  LI-COR 4000
+
+Base calling accuracies tested for:
+  ABI model 3100
+  Beckman CEQ
+
+It contains also a data evaluation program called 'daev'.
+See DAEV.DOC for more information.
+
+You must obtain the tarball via e-mail to build. See the web site below.
+
+WWW: http://www.phrap.org/phredphrapconsed.html