--- ncbi-tools6-6.1.20061015.orig/doc/man/sortbyquote.1
+++ ncbi-tools6-6.1.20061015/doc/man/sortbyquote.1
@@ -0,0 +1,32 @@
+.TH SORTBYQUOTE 1 2006-01-11 NCBI "NCBI Tools User's Manual"
+.SH NAME
+sortbyquote \- sort C/C++ code by quoted regions
+.SH SYNOPSIS
+.B sortbyquote
+[\|\fB\-\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-r\fP\|]
+.SH DESCRIPTION
+\fBsortbyquote\fP is a simple utility to sort a C or C++ code snippet
+so that the lines (typically elements of a static array for use in
+binary search) end up in case-insensitive order of the string literals
+they contain.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Input File Name (default = stdin)
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Output File Name (default = stdout)
+.TP
+\fB\-r\fP
+Reverse order
+.SH BUGS
+Escape sequences are not supported.
+.SH AUTHOR
+The National Center for Biotechnology Information.
--- ncbi-tools6-6.1.20061015.orig/doc/man/gbseqget.1
+++ ncbi-tools6-6.1.20061015/doc/man/gbseqget.1
@@ -1,4 +1,4 @@
-.TH GBSEQGET 1 2003-04-27 NCBI "NCBI Tools User's Manual"
+.TH GBSEQGET 1 2006-04-14 NCBI "NCBI Tools User's Manual"
 .SH NAME
 gbseqget \- format sequences from GenBank as an XML GBSet
 .SH SYNOPSIS
@@ -48,5 +48,11 @@
 .TP
 \fB\-v\fP
 Fetch SNP Variations
+.SH NOTES
+The GBSet format is deprecated in favor of INSDSet, which you can
+produce by running \fBinsdseqget\fP in place of \fBgbseqget\fP.
 .SH AUTHOR
 The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR asn2gb (1),
+.BR insdseqget (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/trna2sap.1
+++ ncbi-tools6-6.1.20061015/doc/man/trna2sap.1
@@ -0,0 +1,77 @@
+.TH TRNA2SAP 1 2006-01-11 NCBI "NCBI Tools User's Manual"
+.SH NAME
+trna2sap \- convert tRNAscan-SE output to an ASN.1 Seq-annot object
+.SH SYNOPSIS
+.B trna2sap
+[\|\fB\-\fP\|]
+[\|\fB\-a\fP\|]
+[\|\fB\-c\fP\ \fIstr\fP\|]
+[\|\fB\-f\fP\ \fIstr\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-j\fP\|]
+[\|\fB\-m\fP\ \fIstr\fP\|]
+[\|\fB\-n\fP\ \fIstr\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIdir\fP\|]
+[\|\fB\-r\fP\ \fIdir\fP\|]
+[\|\fB\-s\fP\|]
+[\|\fB\-t\fP\ \fIstr\fP\|]
+[\|\fB\-u\fP\|]
+[\|\fB\-x\fP\ \fIstr\fP\|]
+.SH DESCRIPTION
+\fBtrna2sap\fP reads a text file produced by tRNAscan-SE and produces
+a corresponding ASN.1 Seq-annot in the format understood by other NCBI
+tools.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-a\fP
+Add tRNAscan-SE citation
+.TP
+\fB\-c\fP\ \fIstr\fP
+Comment
+.TP
+\fB\-f\fP\ \fIstr\fP
+Substring Filter
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Single Input file (standard input by default)
+.TP
+\fB\-j\fP
+Just produce a five-column feature table, \(`a la \fBtrna2tbl\fP(1).
+.TP
+\fB\-m\fP\ \fIstr\fP
+ReMark
+.TP
+\fB\-n\fP\ \fIstr\fP
+Annotation Name (normally \(lqtRNA\(rq).
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Single Output file (standard output by default)
+.TP
+\fB\-p\fP\ \fIdir\fP
+Path to files
+.TP
+\fB\-r\fP\ \fIdir\fP
+Path for Results
+.TP
+\fB\-s\fP
+Ignore Pseudo tRNAs
+.TP
+\fB\-t\fP\ \fIstr\fP
+Annotation Title (normally \(lqtRNAscan-SE\(rq).
+.TP
+\fB\-u\fP
+Ignore Undetermined tRNAs
+.TP
+\fB\-x\fP\ \fIstr\fP
+File selection suffix with \fB-p\fP (\fB.trna\fP by default).
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR sequin (1),
+.BR tbl2asn (1),
+.BR trna2tbl (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/trna2tbl.1
+++ ncbi-tools6-6.1.20061015/doc/man/trna2tbl.1
@@ -0,0 +1,18 @@
+.TH TRNA2TBL 1 2005-11-04 NCBI "NCBI Tools User's Manual"
+.SH NAME
+trna2tbl \- convert tRNAscan-SE output to a Sequin feature table
+.SH SYNOPSIS
+.B trna2tbl
+.SH DESCRIPTION
+\fBtrna2tbl\fP is a filter that reads a text file produced by
+tRNAscan-SE from its standard input and yields a corresponding
+5-column feature table in the format understood by Sequin (and
+\fBtbl2asn\fP) on its standard output.
+.SH OPTIONS
+None.
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR sequin (1),
+.BR tbl2asn (1),
+.BR trna2sap (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/makemat.1
+++ ncbi-tools6-6.1.20061015/doc/man/makemat.1
@@ -1,4 +1,4 @@
-.TH MAKEMAT 1 2001-10-05 NCBI "NCBI Tools User's Manual"
+.TH MAKEMAT 1 2004-06-25 NCBI "NCBI Tools User's Manual"
 .SH NAME
 makemat \- convert binary profiles into portable ASCII form
 .SH SYNOPSIS
@@ -50,4 +50,4 @@
 .SH SEE ALSO
 .BR blast (1),
 .BR copymat (1),
-impala.txt
+impala.html
--- ncbi-tools6-6.1.20061015.orig/doc/man/insdseqget.1
+++ ncbi-tools6-6.1.20061015/doc/man/insdseqget.1
@@ -0,0 +1,55 @@
+.TH INSDSEQGET 1 2006-04-14 NCBI "NCBI Tools User's Manual"
+.SH NAME
+insdseqget \- format sequences from GenBank as an XML INSDSet
+.SH SYNOPSIS
+.B insdseqget
+[\|\fB\-\fP\|]
+[\|\fB\-d\fP\ \fIfilename\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-m\fP\ \fIn/p/b\fP\|]
+[\|\fB\-n\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-v\fP\|]
+.SH DESCRIPTION
+\fBinsdseqget\fP retrieves biological sequence data from GenBank
+(according to an input list of GI accession numbers) and prints it out
+as an XML INSDSet document.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-d\fP\ \fIfilename\fP
+Input file name for date list (desired accessions, one per line,
+followed by a blank line and a list of allowed dates, also one per line)
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Input file name for GI list (default = stdin)
+.TP
+\fB\-m\fP\ \fIn/p/b\fP
+Molecule type:
+.RS
+.PD 0
+.IP n
+Nucleotide (default)
+.IP p
+Protein
+.IP b
+Both
+.PD
+.RE
+.TP
+\fB\-n\fP
+Return only new records (for which the given GI refers to an old version)
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Output file name for the XML INSDSet (default = stdout)
+.TP
+\fB\-v\fP
+Fetch SNP Variations
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR asn2gb (1),
+.BR gbseqget (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/blastclust.1
+++ ncbi-tools6-6.1.20061015/doc/man/blastclust.1
@@ -1,4 +1,4 @@
-.TH BLASTCLUST 1 2002-08-30 NCBI "NCBI Tools User's Manual"
+.TH BLASTCLUST 1 2004-06-25 NCBI "NCBI Tools User's Manual"
 .SH NAME
 blastclust \- BLAST score-based single-linkage clustering
 .SH SYNOPSIS
@@ -92,5 +92,5 @@
 .ad l
 .BR blast (1),
 .BR formatdb (1),
-blastclust.txt,
+blastclust.html,
 <http://www.ncbi.nlm.nih.gov/BLAST/>
--- ncbi-tools6-6.1.20061015.orig/doc/man/nps2gps.1
+++ ncbi-tools6-6.1.20061015/doc/man/nps2gps.1
@@ -0,0 +1,55 @@
+.TH NPS2GPS 1 2005-11-04 NCBI "NCBI Tools User's Manual"
+.SH NAME
+nps2gps \- convert nucleotide-protein sets to ASN.1 genomic product sets
+.SH SYNOPSIS
+.B nps2gps
+[\|\fB\-\fP\|]
+[\|\fB\-L\fP\|]
+[\|\fB\-R\fP\|]
+[\|\fB\-f\fP\ \fIstr\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIstr\fP\|]
+[\|\fB\-r\fP\ \fIstr\fP\|]
+[\|\fB\-x\fP\ \fIstr\fP\|]
+.SH DESCRIPTION
+\fBnps2gps\fP converts NCBI Bioseq-sets from simple nucleotide-protein
+sets to full genomic product sets complete with mRNA transcripts,
+which it outputs as text ASN.1.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-L\fP
+Lock components in advance
+.TP
+\fB\-R\fP
+Enable Remote fetching from ID
+.TP
+\fB\-f\fP\ \fIstr\fP
+Substring filter
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Single input file (default = stdin)
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Single output file (default = stdout)
+.TP
+\fB\-p\fP\ \fIstr\fP
+Path to files for batch conversion
+.TP
+\fB\-r\fP\ \fIstr\fP
+Path for results of batch conversion
+.TP
+\fB\-x\fP\ \fIstr\fP
+File selection suffix for batch conversion (default = \fB.ent\fP)
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR asn2asn (1),
+.BR asn2ff (1),
+.BR asn2gb (1),
+.BR asn2xml (1),
+.BR asndhuff (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/spidey.1
+++ ncbi-tools6-6.1.20061015/doc/man/spidey.1
@@ -0,0 +1,279 @@
+.TH SPIDEY 1 2005-01-25 NCBI "NCBI Tools User's Manual"
+.SH NAME
+spidey \- align mRNA sequences to a genome
+.SH SYNOPSIS
+.B spidey
+[\|\fB\-\fP\|]
+[\|\fB\-F\fP\ \fIN\fP\|]
+[\|\fB\-G\fP\|]
+[\|\fB\-L\fP\ \fIN\fP\|]
+[\|\fB\-M\fP\ \fIfilename\fP\|]
+[\|\fB\-N\fP\ \fIfilename\fP\|]
+[\|\fB\-R\fP\ \fIfilename\fP\|]
+[\|\fB\-S\fP\ \fIp/m\fP\|]
+[\|\fB\-T\fP\ \fIN\fP\|]
+[\|\fB\-X\fP\|]
+[\|\fB\-a\fP\ \fIfilename\fP\|]
+[\|\fB\-c\fP\ \fIN\fP\|]
+[\|\fB\-d\fP\|]
+[\|\fB\-e\fP\ \fIX\fP\|]
+[\|\fB\-f\fP\ \fIX\fP\|]
+[\|\fB\-g\fP\ \fIX\fP\|]
+\fB\-i\fP\ \fIfilename\fP
+[\|\fB\-j\fP\|]
+[\|\fB\-k\fP\ \fIfilename\fP\|]
+[\|\fB\-l\fP\ \fIN\fP\|]
+\fB\-m\fP\ \fIfilename\fP
+[\|\fB\-n\fP\ \fIN\fP\|]
+[\|\fB\-o\fP\ \fIstr\fP\|]
+[\|\fB\-p\fP\ \fIN\fP\|]
+[\|\fB\-r\fP\ \fIc/d/m/p/v\fP\|]
+[\|\fB\-s\fP\|]
+[\|\fB\-t\fP\ \fIfilename\fP\|]
+[\|\fB\-u\fP\|]
+[\|\fB\-w\fP\|]
+.SH DESCRIPTION
+\fBspidey\fP is a tool for aligning one or more mRNA sequences to a
+given genomic sequence.  \fBspidey\fP was written with two main goals
+in mind: find good alignments regardless of intron size; and avoid
+getting confused by nearby pseudogenes and paralogs.  Towards the
+first goal, \fBspidey\fP uses BLAST and Dot View (another local
+alignment tool) to find its alignments; since these are both local
+alignment tools, \fBspidey\fP does not intrinsically favor shorter or
+longer introns and has no maximum intron size.  To avoid mistakenly
+including exons from paralogs and pseudogenes, \fBspidey\fP first
+defines windows on the genomic sequence and then performs the
+mRNA-to-genomic alignment separately within each window.  Because of
+the way the windows are constructed, neighboring paralogs or
+pseudogenes should be in separate windows and should not be included
+in the final spliced alignment.
+.SS Initial alignments and construction of genomic windows
+\fBspidey\fP takes as input a single genomic sequence and a set of
+mRNA accessions or FASTA sequences.  All processing is done one mRNA
+sequence at a time.  The first step for each mRNA sequence is a
+high-stringency BLAST against the genomic sequence.  The resulting
+hits are analyzed to find the genomic windows.
+.PP
+The BLAST alignments are sorted by score and then assigned into
+windows by a recursive function which takes the first alignment and
+then goes down the alignment list to find all alignments that are
+consistent with the first (same strand of mRNA, both the mRNA and
+genomic coordinates are nonoverlapping and linearly consistent).  On
+subsequent passes, the remaining alignments are examined and are put
+into their own nonoverlapping, consistent windows, until no alignments
+are left.  Depending on how many gene models are desired, the
+top \fIn\fP windows are chosen to go on to the next step and the others
+are deleted.
+.SS Aligning in each window
+Once the genomic windows are constructed, the initial BLAST alignments
+are freed and another BLAST search is performed, this time with the
+entire mRNA against the genomic region defined by the window, and at a
+lower stringency than the initial search.  \fBspidey\fP then uses a
+greedy algorithm to generate a high-scoring, nonoverlapping subset of
+the alignments from the second BLAST search.  This consistent set is
+analyzed carefully to make sure that the entire mRNA sequence is
+covered by the alignments.  When gaps are found between the
+alignments, the appropriate region of genomic sequence is searched
+against the missing mRNA, first using a very low-stringency BLAST and,
+if the BLAST fails to find a hit, using DotView functions to locate
+the alignment.  When gaps are found at the ends of the alignments, the
+BLAST and DotView searches are actually allowed to extend past the
+boundaries of the window.  If the 3' end of the mRNA does not align
+completely, it is first examined for the presence of a poly(A) tail.
+No attempt is made to align the portion of the mRNA that seems to be a
+poly(A) tail; sometimes there is a poly(A) tail that does align to the
+genomic sequence, and these are noted because they indicate the
+possibility of a pseudogene.
+.PP
+Now that the mRNA is completely covered by the set of alignments, the
+boundaries of the alignments (there should be one alignment per exon
+now) are adjusted so that the alignments abut each other precisely and
+so that they are adjacent to good splice donor and acceptor sites.
+Most commonly, two adjacent exons' alignments overlap by as much as 20
+or 30 base pairs on the mRNA sequence.  The true exon boundary may lie
+anywhere within this overlap, or (as we have seen empirically) even a
+few base pairs outside the overlap.  To position the exon boundaries,
+the overlap plus a few base pairs on each side is examined for splice
+donor sites, using functions that have different splice matrices
+depending on the organism chosen.  The top few splice donor sites (by
+score) are then evaluated as to how much they affect the original
+alignment boundaries.  The site that affects the boundaries the least
+is chosen, and is evaluated as to the presence of an acceptor site.
+The alignments are truncated or extended as necessary so that they
+terminate at the splice donor site and so that they do not overlap.
+.SS Final result
+The windows are examined carefully to get the percent identity per
+exon, the number of gaps per exon, the overall percent identity, the
+percent coverage of the mRNA, presence of an aligning or non-aligning
+poly(A) tail, number of splice donor sites and the presence or absence
+of splice donor and acceptor sites for each exon, and the occurrence
+of an mRNA that has a 5' or 3' end (or both) that does not align to
+the genomic sequence.  If the overall percent identity and percent
+length coverage are above the user-defined cutoffs, a summary report
+is printed, and, if requested, a text alignment showing identities and
+mismatches is also printed.
+.SS Interspecies alignments
+\fBspidey\fP is capable of performing interspecies alignments.  The
+major difference in interspecies alignments is that the mRNA-genomic
+identity will not be close to 100% as it is in intraspecies
+alignments; also, the alignments have numerous and lengthy gaps.  If
+\fBspidey\fP is used in its normal mode to do interspecies alignments,
+it produces gene models with many, many short exons.  When the
+interspecies flag is set, \fBspidey\fP uses different BLAST parameters
+to encourage longer and more gaps and to not penalize as heavily for
+mismatches.  This way, the alignments for the exons are much longer
+and more closely approximate the actual gene structure.
+.SS Extracting CDS alignments
+When \fBspidey\fP is run in network-aware mode or when ASN.1 files are
+used for the mRNA records, it is capable of extracting a CDS alignment
+from an mRNA alignment and printing the CDS information also.  Since
+the CDS alignment is just a subset of the mRNA alignment, it is
+relatively straightforward to truncate the exon alignments as
+necessary and to generate a CDS alignment.  Furthermore, the
+untranslated regions are now defined, so the percent identity for the
+5' and 3' untranslated regions is also calculated.
+.PP
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message.
+.TP
+\fB\-F\fP\ \fIN\fP
+Start of genomic interval desired (from; 0-based).
+.TP
+\fB\-G\fP
+Input file is a GI list.
+.TP
+\fB\-L\fP\ \fIN\fP
+The extra-large intron size to use (default = 220000).
+.TP
+\fB\-M\fP\ \fIfilename\fP
+File with donor splice matrix.
+.TP
+\fB\-N\fP\ \fIfilename\fP
+File with acceptor splice matrix.
+.TP
+\fB\-R\fP\ \fIfilename\fP
+File (including path) to repeat blast database for filtering.
+.TP
+\fB\-S\fP\ \fIp/m\fP
+Restrict to plus (p) or minus (m) strand of genomic sequence.
+.TP
+\fB\-T\fP\ \fIN\fP
+Stop of genomic interval desired (to; 0-based).
+.TP
+\fB\-X\fP
+Use extra-large intron sizes (increases the limit for initial and
+terminal introns from 100kb to 240kb and for all others from 35kb to
+120kb); may result in significantly longer compute times.
+.TP
+\fB\-a\fP\ \fIfilename\fP
+Output file for alignments when directed to a separate file with
+\fB-p\ 3\fP (default = spidey.aln).
+.TP
+\fB\-c\fP\ \fIN\fP
+Identity cutoff, in percent, for quality control purposes.
+.TP
+\fB\-d\fP
+Also try to align coding sequences corresponding to the given mRNA
+records (may require network access).
+.TP
+\fB\-e\fP\ \fIX\fP
+First-pass e-value (default = 1.0e-10).  Higher values increase speed
+at the cost of sensitivity.
+.TP
+\fB\-f\fP\ \fIX\fP
+Second-pass e-value (default = 0.001).
+.TP
+\fB\-g\fP\ \fIX\fP
+Third-pass e-value (default = 10).
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Input file containing the genomic sequence in ASN.1 or FASTA format.
+If your computer is running on a network that can access GenBank, you
+can substitute the desired accession number for the filename.
+.TP
+\fB\-j\fP
+Print ASN.1 alignment?
+.TP
+\fB\-k\fP\ \fIfilename\fP
+File for ASN.1 output with \fB-k\fP (default = spidey.asn).
+.TP
+\fB\-l\fP\ \fIN\fP
+Length coverage cutoff, in percent.
+.TP
+\fB\-m\fP\ \fIfilename\fP
+Input file containing the mRNA sequence(s) in ASN.1 or FASTA format,
+or a list of their accessions (with \fB-G\fP).  If your computer is
+running on a network that can access GenBank, you can substitute a
+single accession number for the filename.
+.TP
+\fB\-n\fP\ \fIN\fP
+Number of gene models to return per input mRNA (default = 1).
+.TP
+\fB\-o\fP\ \fIstr\fP
+Main output file (default = stdout; contents controlled by \fB-p\fP).
+.TP
+\fB\-p\fP\ \fIN\fP
+Print alignment?
+.RS
+.PD 0
+.IP \fB0\fP
+summary and alignments together (default)
+.IP \fB1\fP
+just the summary
+.IP \fB2\fP
+just the alignments
+.IP \fB3\fP
+summary and alignments in different files
+.PD
+.RE
+.TP
+\fB\-r\fP\ \fIc/d/m/p/v\fP
+Organism of genomic sequence, used to determine splice matrices.
+.RS
+.PD 0
+.IP \fBc\fP
+C. elegans
+.IP \fBd\fP
+Drosophila
+.IP \fBm\fP
+Dictyostelium discoideum
+.IP \fBp\fP
+plant
+.IP \fBv\fP
+vertebrate (default)
+.PD
+.RE
+.TP
+\fB\-s\fP
+Tune for interspecies alignments.
+.TP
+\fB\-t\fP\ \fIfilename\fP
+File with feature table, in 4 tab-delimited columns:
+.RS
+.PD 0
+.IP \fIseqid\fP
+(e.g., \fBNM_04377.1\fP)
+.IP \fIname\fP
+(only \fBrepetitive_region\fP is currently supported)
+.IP \fIstart\fP
+(0-based)
+.IP \fIstop\fP
+(0-based)
+.PD
+.RE
+.TP
+\fB\-u\fP
+Make a multiple alignment of all input mRNAs (which must overlap on
+the genomic sequence).
+.TP
+\fB\-w\fP
+Consider lowercase characters in input FASTA sequences to be masked.
+.SH AUTHOR
+Sarah Wheelan and others at the National Center for Biotechnology
+Information; Steffen Moeller contributed to this documentation.
+.SH SEE ALSO
+.BR blast (1),
+<http://www.ncbi.nlm.nih.gov/spidey>
--- ncbi-tools6-6.1.20061015.orig/doc/man/tbl2asn.1
+++ ncbi-tools6-6.1.20061015/doc/man/tbl2asn.1
@@ -1,14 +1,35 @@
-.TH TBL2ASN 1 2003-11-10 NCBI "NCBI Tools User's Manual"
+.TH TBL2ASN 1 2006-10-20 NCBI "NCBI Tools User's Manual"
 .SH NAME
 tbl2asn \- prepare a GenBank submission using an ASCII feature table
 .SH SYNOPSIS
 .B tbl2asn
 [\|\fB\-\fP\|]
+[\|\fB\-B\fP\ \fIstr\fP\|]
+[\|\fB\-C\fP\ \fIstr\fP\|]
+[\|\fB\-D\fP\ \fIfilename\fP\|]
+[\|\fB\-E\fP\ \fIstr\fP\|]
+[\|\fB\-F\fP\ \fIstr\fP|]
+[\|\fB\-G\fP\ \fIstr\fP\|]
+[\|\fB\-H\fP\|]
+[\|\fB\-L\fP\|]
+[\|\fB\-M\fP\ \fIstr\fP\|]
+[\|\fB\-P\fP\|]
+[\|\fB\-Q\fP\|]
+[\|\fB\-R\fP\|]
+[\|\fB\-S\fP\|]
+[\|\fB\-T\fP\|]
+[\|\fB\-U\fP\|]
+[\|\fB\-W\fP\|]
+[\|\fB\-X\fP\ \fIstr\fP\|]
+[\|\fB\-Y\fP\ \fIfilename\fP\|]
 [\|\fB\-a\fP\ \fIstr\fP\|]
 [\|\fB\-b\fP\|]
 [\|\fB\-c\fP\|]
 [\|\fB\-d\fP\|]
+[\|\fB\-e\fP\|]
+[\|\fB\-f\fP\ \fIfilename\fP\|]
 [\|\fB\-g\fP\|]
+[\|\fB\-h\fP\|]
 [\|\fB\-i\fP\ \fIfilename\fP\|]
 [\|\fB\-j\fP\ \fIstr\fP\|]
 [\|\fB\-k\fP\|]
@@ -21,9 +42,12 @@
 [\|\fB\-r\fP\ \fIstr\fP\|]
 [\|\fB\-s\fP\|]
 [\|\fB\-t\fP\ \fIfilename\fP\|]
+[\|\fB\-u\fP\|]
 [\|\fB\-v\fP\|]
+[\|\fB\-w\fP\ \fIN\fP\|]
 [\|\fB\-x\fP\ \fIstr\fP\|]
 [\|\fB\-y\fP\ \fIstr\fP\|]
+[\|\fB\-z\fP\|]
 .SH DESCRIPTION
 \fBtbl2asn\fP reads a template along with sequence and table files,
 and outputs ASN.1 for submission to GenBank. Thus, the submitter does
@@ -37,6 +61,60 @@
 \fB\-\fP
 Print usage message
 .TP
+\fB\-B\fP\ \fIstr\fP
+Alignment Beginning gap characters
+.TP
+\fB\-C\fP\ \fIstr\fP
+Genome Center tag
+.TP
+\fB\-D\fP\ \fIfilename\fP
+Descriptors file
+.TP
+\fB\-E\fP\ \fIstr\fP
+Alignment End gap characters
+.TP
+\fB\-F\fP
+Feature ID links (\fBo\fP by Overlap, \fBp\fP by Product)
+.TP
+\fB\-G\fP\ \fIstr\fP
+Alignment middle Gap characters
+.TP
+\fB\-H\fP
+Implicit gaps
+.TP
+\fB\-L\fP
+Force Local protein_id/transcript_id
+.TP
+\fB\-M\fP\ \fIstr\fP
+Alignment Match characters
+.TP
+\fB\-P\fP
+Alignment is Proteins
+.TP
+\fB\-Q\fP
+Special mRNA titles
+.TP
+\fB\-R\fP
+Remote fetching from ID
+.TP
+\fB\-S\fP
+Smart feature annotation
+.TP
+\fB\-T\fP
+Remote Taxonomy lookup
+.TP
+\fB\-U\fP
+Remove Unnecessary gene xref
+.TP
+\fB\-W\fP
+Log progress
+.TP
+\fB\-X\fP\ \fIstr\fP
+Alignment missing characters
+.TP
+\fB\-Y\fP\ \fIfilename\fP
+Read a comment string from \fIfilename\fP
+.TP
 \fB\-a\fP\ \fIstr\fP
 Accession
 .TP
@@ -49,9 +127,18 @@
 \fB\-d\fP
 Read FASTAs as Delta
 .TP
+\fB\-e\fP
+Read PHRAP/ACE format
+.TP
+\fB\-f\fP\ \fIfilename\fP
+Single table file
+.TP
 \fB\-g\fP
 Input is a genomic product set
 .TP
+\fB\-h\fP
+Convert general ID to note
+.TP
 \fB\-i\fP\ \fIfilename\fP
 Single input file
 .TP
@@ -88,16 +175,41 @@
 \fB\-t\fP\ \fIfilename\fP
 Read template from \fIfilename\fP
 .TP
+\fB\-u\fP
+Convert GenProdSet to NucProtSet
+.TP
 \fB\-v\fP
 Validate
 .TP
+\fB\-w\fP \fIN\fP
+FASTA set class
+.RS
+.PD 0
+.IP 0
+unspecified (default)
+.IP 1
+population study
+.IP 2
+phylogenetic study
+.IP 3
+set of mutations
+.IP 4
+ecological sample study
+.PD
+.RE
+.TP
 \fB\-x\fP\ \fIstr\fP
 Suffix (default = \fB.fsa\fP)
 .TP
 \fB\-y\fP\ \fIstr\fP
 Comment
+.TP
+\fB\-z\fP
+Read FASTAs with gap lines
 .SH AUTHOR
 The National Center for Biotechnology Information.
 .SH SEE ALSO
 .BR Psequin (1),
-<http://www.ncbi.nlm.nih.gov/Sequin/table.html>
+.BR sbtedit (1),
+tbl2asn.txt,
+<http://www.ncbi.nlm.nih.gov/Sequin/table.html>.
--- ncbi-tools6-6.1.20061015.orig/doc/man/fastacmd.1
+++ ncbi-tools6-6.1.20061015/doc/man/fastacmd.1
@@ -1,10 +1,10 @@
-.TH FASTACMD 1 2003-11-10 NCBI "NCBI Tools User's Manual"
+.TH FASTACMD 1 2005-11-04 NCBI "NCBI Tools User's Manual"
 .SH NAME
 fastacmd \- retrieve FASTA sequences from a BLAST database
 .SH SYNOPSIS
 .B fastacmd
 [\|\fB\-\fP\|]
-[\|\fB\-D\fP\|]
+[\|\fB\-D\fP\ \fIN\fP\fP\|]
 [\|\fB\-I\fP\|]
 [\|\fB\-L\fP\ \fIstart\fP,\fIstop\fP\|]
 [\|\fB\-P\fP\ \fIN\fP\|]
@@ -32,8 +32,18 @@
 \fB\-\fP
 Print usage message
 .TP
-\fB\-D\fP
-Dump the entire database in FASTA format
+\fB\-D\fP\ \fIN\fP
+Dump the entire database in some format:
+.RS
+.PD 0
+.IP 1
+fasta
+.IP 2
+GI list
+.IP 3
+Accession.version list
+.PD
+.RE
 .TP
 \fB\-I\fP
 Print database information only (overrides all other options)
@@ -69,7 +79,7 @@
 Database (default is nr)
 .TP
 \fB\-i\fP\ \fIstr\fP
-Input file wilth GIs/accessions/locuses for batch retrieval
+Input file with GIs/accessions/loci for batch retrieval
 .TP
 \fB\-l\fP\ \fIN\fP
 Line length for sequence (default = 80)
@@ -91,8 +101,9 @@
 .RE
 .TP
 \fB\-s\fP\ \fIstr\fP
-Search string: GIs, accessions and locuses may be used delimited by
-commas
+Comma-delimited search string(s).
+GIs, accessions, loci, or fullSeq-id strings may be used,
+\fIe.g.\fP, \fB555\fP, \fBAC147927\fP, \fB'gnl|dbname|tag'\fP
 .TP
 \fB\-t\fP
 Definition line should contain target GI only
@@ -115,4 +126,4 @@
 The National Center for Biotechnology Information.
 .SH SEE ALSO
 .BR blast (1),
-fastacmd.txt
+fastacmd.html.
--- ncbi-tools6-6.1.20061015.orig/doc/man/blast2.1
+++ ncbi-tools6-6.1.20061015/doc/man/blast2.1
@@ -0,0 +1 @@
+.so man1/blast.1
--- ncbi-tools6-6.1.20061015.orig/doc/man/sbtedit.1
+++ ncbi-tools6-6.1.20061015/doc/man/sbtedit.1
@@ -0,0 +1,15 @@
+.TH SBTEDIT 1 2005-11-04 NCBI "NCBI Tools User's Manual"
+.SH NAME
+sbtedit \- GenBank submission template editor
+.SH SYNOPSIS
+.B sbtedit
+.SH DESCRIPTION
+\fBPsbtedit\fP is a graphical editor for GenBank submission templates,
+which \fBPsequin\fP(1) and \fBPtbl2asn(1)\fP can combine with
+sequence-specific data to produce complete submissions.
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.ad l
+.BR sequin (1),
+.BR tbl2asn (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/formatdb.1
+++ ncbi-tools6-6.1.20061015/doc/man/formatdb.1
@@ -1,4 +1,4 @@
-.TH FORMATDB 1 2002-08-30 NCBI "NCBI Tools User's Manual"
+.TH FORMATDB 1 2006-10-20 NCBI "NCBI Tools User's Manual"
 .SH NAME
 formatdb \- format protein or nucleotide databases for BLAST
 .SH SYNOPSIS
@@ -7,6 +7,7 @@
 [\|\fB\-B\fP\ \fIfilename\fP\|]
 [\|\fB\-F\fP\ \fIfilename\fP\|]
 [\|\fB\-L\fP\ \fIfilename\fP\|]
+[\|\fB\-T\fP\ \fIfilename\fP\|]
 [\|\fB\-V\fP\|]
 [\|\fB\-a\fP\|]
 [\|\fB\-b\fP\|]
@@ -51,6 +52,10 @@
 Create an alias file named \fIfilename\fP, limiting the sequences
 searched to those specified by \fB\-F\fP.
 .TP
+\fB\-T\fP\ \fIfilename\fP
+Set the taxonomy IDs in ASN.1 deflines according to the table in
+\fIfilename\fP.
+.TP
 \fB\-V\fP
 Verbose: check for non-unique string ids in the database
 .TP
@@ -94,11 +99,14 @@
 .TP
 \fB\-v\fP\ \fIN\fP
 Break up large FASTA files into 'volumes' of size \fIN\fP million
-letters.  As part of the creation of a volume, \fBformatdb\fP writes a
-new type of BLAST database file, called an alias file, with the
-extension 'nal' or 'pal'.
+letters (4000 by default).  As part of the creation of a volume,
+\fBformatdb\fP writes a new type of BLAST database file, called an
+alias file, with the extension 'nal' or 'pal'.
 .SH AUTHOR
 The National Center for Biotechnology Information.
 .SH SEE ALSO
 .BR blast (1),
-formatdb.txt
+.BR copymat (1),
+.BR formatrpsdb (1),
+.BR makemat (1),
+formatdb.html.
--- ncbi-tools6-6.1.20061015.orig/doc/man/blastall_old.1
+++ ncbi-tools6-6.1.20061015/doc/man/blastall_old.1
@@ -0,0 +1 @@
+.so man1/blast.1
--- ncbi-tools6-6.1.20061015.orig/doc/man/formatrpsdb.1
+++ ncbi-tools6-6.1.20061015/doc/man/formatrpsdb.1
@@ -0,0 +1,94 @@
+.TH FORMATRPSDB 1 2004-10-20 NCBI "NCBI Tools User's Manual"
+.SH NAME
+formatrpsdb \- Build databases for RPS Blast
+.SH SYNOPSIS
+.B formatrpsdb
+[\|\fB\-\fP\|]
+[\|\fB\-E\fP\ \fIN\fP\|]
+[\|\fB\-G\fP\ \fIN\fP\|]
+[\|\fB\-S\fP\ \fIX\fP\|]
+[\|\fB\-U\fP\ \fIstr\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-f\fP\ \fIX\fP\|]
+\fB\-i\fP\ \fIfilename\fP
+[\|\fB\-l\fP\ \fIfilename\fP\|]
+[\|\fB\-n\fP\ \fIstr\fP\|]
+[\|\fB\-o\fP\|]
+[\|\fB\-t\fP\ \fIstr\fP\|]
+[\|\fB\-v\fP\ \fIN\fP\|]
+.SH DESCRIPTION
+\fBFormatrpsdb\fP is a utility that converts a collection of input
+sequences into a database suitable for use with Reverse Position
+Specific (RPS) Blast.
+Each input sequence, together with its position-specific scoring
+matrix (PSSM), is ASN.1 encoded into a PssmWithParameters (or
+'scoremat') object and resides in a separate file.
+Scoremat objects can be created using \fBblastpgp\fP.
+\fBFormatrpsdb\fP is given a list of these files and produces the 
+corresponding database. 
+
+\fBFormatrpsdb\fP is designed to perform the work of \fBformatdb\fP,
+\fBmakemat\fP and \fBcopymat\fP simultaneously, without generating the
+large number of intermediate files these utilities would need to
+create an RPS Blast database.
+Further, scoremat objects are in more general use than the binary
+format makemat requires.
+It is hoped that direct manipulation of scoremat objects will
+encourage conversion of more diverse sequence collections into RPS
+Blast databases.
+
+Databases generated by formatrpsdb are binary compatible with
+databases generated by \fBformatdb\fP/\fBmakemat\fP/\fBcopymat\fP,
+although the database files will in general not be byte- for-byte
+identical.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-E\fP\ \fIN\fP
+The gap extension penalty (if not specified in the scoremat; default = 1)
+.TP
+\fB\-G\fP\ \fIN\fP
+The gap opening penalty (if not specified in the scoremat; default = 11)
+.TP
+\fB\-S\fP\ \fIX\fP
+For scoremats that contain only residue frequencies, the scaling
+factor to apply when creating PSSMs (default = 100)
+.TP
+\fB\-U\fP\ \fIstr\fP
+Underlying score matrix (if not specified in the scoremat; default = BLOSUM62)
+.TP
+\fB\-b\fP
+Scoremat files are binary (vs. text) ASN1.
+.TP
+\fB\-f\fP\ \fIX\fP
+Threshold for extending hits for RPS database (default = 11)
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Input file containing list of ASN.1 Scoremat filenames
+.TP
+\fB\-l\fP\ \fIfilename\fP
+Log file name (default = formatrpsdb.log)
+.TP
+\fB\-n\fP\ \fIstr\fP
+Base name of output database (same as input file if not specified)
+.TP
+\fB\-o\fP
+Create index files for database
+.TP
+\fB\-t\fP\ \fIstr\fP
+Title for database file
+.TP
+\fB\-v\fP\ \fIN\fP
+Database volume size in millions of letters (default = 0, which really
+means no limit)
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR blast (1),
+.BR copymat (1),
+.BR formatdb (1),
+.BR makemat (1),
+formatrpsdb.html
--- ncbi-tools6-6.1.20061015.orig/doc/man/Psequin.1
+++ ncbi-tools6-6.1.20061015/doc/man/Psequin.1
@@ -1,4 +1,4 @@
-.TH PSEQUIN 1 2003-04-26 NCBI "NCBI Tools User's Manual"
+.TH PSEQUIN 1 2005-11-04 NCBI "NCBI Tools User's Manual"
 .SH NAME
 Psequin \- submit sequences to Genbank, EMBL, and DDBJ
 .SH SYNOPSIS
@@ -91,6 +91,7 @@
 The National Center for Biotechnology Information.
 .SH SEE ALSO
 .ad l
+.BR sbtedit (1),
 .BR tbl2asn (1),
 sequin.htm,
-<http://www.ncbi.nlm.nih.gov/Sequin/>
+<http://www.ncbi.nlm.nih.gov/Sequin/>.
--- ncbi-tools6-6.1.20061015.orig/doc/man/cleanasn.1
+++ ncbi-tools6-6.1.20061015/doc/man/cleanasn.1
@@ -0,0 +1,125 @@
+.TH CLEANASN 1 2006-10-20 NCBI "NCBI Tools User's Manual"
+.SH NAME
+cleanasn \- clean up irregularities in NCBI ASN.1 objects
+.SH SYNOPSIS
+.B cleanasn
+[\|\fB\-\fP\|]
+[\|\fB\-F\fP\ \fIstr\fP\|]
+[\|\fB\-K\fP\ \fIstr\fP\|]
+[\|\fB\-N\fP\ \fIstr\fP\|]
+[\|\fB\-R\fP\|]
+[\|\fB\-T\fP\|]
+[\|\fB\-a\fP\ \fIstr\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-c\fP\|]
+[\|\fB\-f\fP\ \fIstr\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-l\fP\ \fIfilename\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIpath\fP\|]
+[\|\fB\-r\fP\ \fIpath\fP\|]
+[\|\fB\-x\fP\ \fIext\fP\|]
+.SH DESCRIPTION
+\fBcleanasn\fP is a utility program to clean up irregularities in NCBI
+ASN.1 objects.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-F\fP\ \fIstr\fP
+Clean up features, per the flags in str:
+.RS
+.PD 0
+.IP u
+Remove User-objects
+.IP d
+Remove db_xrefs
+.IP r
+Remove redundant gene xrefs
+.PD
+.RE
+.TP
+\fB\-K\fP\ \fIstr\fP
+Perform a general cleanup, per the flags in str:
+.RS
+.PD 0
+.IP b
+BasicSeqEntryCleanup
+.IP s
+SeriousSeqEntryCleanup
+.PD
+.RE
+.TP
+\fB\-N\fP\ \fIstr\fP
+Clean up links, per the flags in str:
+.RS
+.PD 0
+.IP o
+LinkCDSmRNAbyOverlap
+.IP p
+LinkCDSmRNAbyProduct
+.IP r
+ReassignFeatureIDs
+.IP c
+ClearFeatureIDs
+.PD
+.RE
+.TP
+\fB\-R\fP
+Remote fetching from ID (NCBI sequence databases)
+.TP
+\fB\-T\fP
+Taxonomy Lookup
+.TP
+\fB\-a\fP\ \fIstr\fP
+ASN.1 type
+.RS
+.PD 0
+.IP a
+Any (default)
+.IP e
+Seq-entry
+.IP b
+Bioseq
+.IP s
+Bioseq-set
+.IP m
+Seq-submit
+.IP t
+Batch Processing [String]
+.PD
+.RE
+.TP
+\fB\-b\fP
+Input ASN.1 is Binary
+.TP
+\fB\-c\fP
+Input ASN.1 is Compressed
+.TP
+\fB\-f\fP\ \fIstr\fP
+Substring filter
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Single input file (defaults to stdin)
+.TP
+\fB\-l\fP\ \fIfilename\fP
+Log file
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Single output file (defaults to stdout)
+.TP
+\fB\-p\fP\ \fIpath\fP
+Process all matching files in \fIpath\fP
+.TP
+\fB\-r\fP\ \fIpath\fP
+Path for results
+.TP
+\fB\-x\fP\ \fIext\fP
+File selection suffix for use with \fB\-p\fP (defaults to \fB.ent\fP)
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+asnval (1),
+sequin (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/asntool.1
+++ ncbi-tools6-6.1.20061015/doc/man/asntool.1
@@ -1,4 +1,4 @@
-.TH ASNTOOL 1 2001-12-28 NCBI "NCBI Tools User's Manual"
+.TH ASNTOOL 1 2005-05-16 NCBI "NCBI Tools User's Manual"
 .SH NAME
 asntool \- process ASN.1 module specifications
 .SH SYNOPSIS
@@ -15,6 +15,7 @@
 [\|\fB\-P\fP\ \fIstr\fP\|]
 [\|\fB\-S\fP\ \fIfilename\fP\|]
 [\|\fB\-T\fP\ \fIfilename\fP\|]
+[\|\fB\-V\fP\|]
 [\|\fB\-X\fP\ \fIfilename\fP\|]
 [\|\fB\-Z\fP\|]
 [\|\fB\-b\fP\ \fIN\fP\|]
@@ -82,6 +83,10 @@
 \fB\-T\fP\ \fIfilename\fP
 Dump ASN.1 tree to \fIfilename\fP
 .TP
+\fB\-V\fP
+Force CHOICE objects to use custom structures rather than ValNodePtrs,
+for compatibility with some old hand-coded object loaders.
+.TP
 \fB\-X\fP\ \fIfilename\fP
 Write XML DTD to \fIfilename\fP.  If \fIfilename\fP is "m", print each
 module to a separate file.
--- ncbi-tools6-6.1.20061015.orig/doc/man/copymat.1
+++ ncbi-tools6-6.1.20061015/doc/man/copymat.1
@@ -1,4 +1,4 @@
-.TH COPYMAT 1 2002-04-28 NCBI "NCBI Tools User's Manual"
+.TH COPYMAT 1 2004-06-25 NCBI "NCBI Tools User's Manual"
 .SH NAME
 copymat \- convert ASCII matrices into a database suitable for quick reading
 .SH SYNOPSIS
@@ -37,4 +37,4 @@
 .SH SEE ALSO
 .BR impala (1),
 .BR makemat (1),
-impala.txt
+impala.html
--- ncbi-tools6-6.1.20061015.orig/doc/man/asn2ff.1
+++ ncbi-tools6-6.1.20061015/doc/man/asn2ff.1
@@ -1,4 +1,4 @@
-.TH ASN2FF 1 2002-08-30 NCBI "NCBI Tools User's Manual"
+.TH ASN2FF 1 2005-05-16 NCBI "NCBI Tools User's Manual"
 .SH NAME
 asn2ff \- convert ASN.1 biological data to a flat format (old version)
 .SH SYNOPSIS
@@ -168,7 +168,9 @@
 .SH AUTHOR
 The National Center for Biotechnology Information.
 .SH SEE ALSO
+.BR asn2all (1),
 .BR asn2asn (1),
+.BR asn2fsa (1),
 .BR asn2gb (1),
 .BR asn2xml (1),
-.BR asndhuff (1)
+.BR asndhuff (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/asn2gb.1
+++ ncbi-tools6-6.1.20061015/doc/man/asn2gb.1
@@ -1,9 +1,10 @@
-.TH ASN2GB 1 2003-11-10 NCBI "NCBI Tools User's Manual"
+.TH ASN2GB 1 2006-10-20 NCBI "NCBI Tools User's Manual"
 .SH NAME
 asn2gb \- convert ASN.1 biological data to a GenBank-style flat format
 .SH SYNOPSIS
 .B asn2gb
 [\|\fB\-\fP\|]
+[\|\fB\-A\fP\ \fIaccession\fP\|]
 [\|\fB\-a\fP\ \fIasn-type\fP\|]
 [\|\fB\-b\fP\|]
 [\|\fB\-c\fP\|]
@@ -16,6 +17,7 @@
 [\|\fB\-k\fP\ \fIN\fP\|]
 [\|\fB\-l\fP\ \fIfilename\fP\|]
 [\|\fB\-m\fP\ \fImode\fP\|]
+[\|\fB\-n\fP\ \fIfilename\fP\|]
 [\|\fB\-o\fP\ \fIfilename\fP\|]
 [\|\fB\-p\fP\|]
 [\|\fB\-q\fP\ \fIfilename\fP\|]
@@ -35,28 +37,35 @@
 \fB\-\fP
 Print usage message
 .TP
+\fB\-A\fP\ \fIaccession\fP
+Accession to fetch
+.TP
 \fB\-a\fP\ \fIasn-type\fP
 ASN.1 Type:
 .RS
 .PD 0
 .IP a
-Any (default)
+Any (autodetected; default)
 .IP e
-Seq-entry
+seq-Entry
 .IP b
 Bioseq
 .IP s
-Bioseq-set
+bioseq-Set
 .IP m
-Seq-submit
+seq-subMit
+.IP t
+baTch bioseq-set
+.IP u
+batch seq-sUbmit
 .PD
 .RE
 .TP
 \fB\-b\fP
-Bioseq-set is binary
+Input file is binary
 .TP
 \fB\-c\fP
-Bioseq-set is compressed
+Batch file is compressed
 .TP
 \fB\-d\fP
 Seq-loc minus strand
@@ -67,14 +76,26 @@
 .PD 0
 .IP b
 GenBank (default)
+.IP "bp or pb"
+GenBank and GenPept
 .IP e
 EMBL
 .IP p
 GenPept
+.IP q
+nucleotide GBSet (XML)
+.IP r
+protein GBSet (XML)
 .IP t
 Feature table only
 .IP x
-GBSet (XML)
+nucleotide INSDSet (XML)
+.IP y
+tiny seq (XML)
+.IP Y
+FASTA
+.IP z
+protein INSDSet (XML)
 .PD
 .RE
 .TP
@@ -135,6 +156,9 @@
 .PD
 .RE
 .TP
+\fB\-n\fP\ \fIfilename\fP
+Asn2Flat Executable (default = asn2flat)
+.TP
 \fB\-o\fP\ \fIfilename\fP
 Output file name (default = stdout)
 .TP
@@ -142,7 +166,7 @@
 Propagate top descriptors
 .TP
 \fB\-q\fP\ \fIfilename\fP
-Gbdjoin Executable (default = gbdjoin)
+Ffdiff Executable (default = /netopt/genbank/subtool/bin/ffdiff)
 .TP
 \fB\-r\fP
 Enable remote fetching
@@ -170,16 +194,26 @@
 Report
 .IP 2
 Sequin/Release
+.IP 3
+asn2gb/asn2flat
+.IP 4
+asn2flat BSEC/nocleanup
+.IP 5
+oldasn2gb/newasn2gb
 .PD
 .RE
 \fB\-u\fP\ \fIN\fP
 Custom flags (all default to off):
 .RS
 .PD 0
-.IP 2
-Hide most imported features
 .IP 4
-Hide SNP features
+Hide features
+.IP 1792
+Hide references
+.IP 8192
+Hide sources
+.IP 262144
+Hide translations
 .PD
 .RE
 .\" .TP
@@ -191,7 +225,11 @@
 .SH AUTHOR
 The National Center for Biotechnology Information.
 .SH SEE ALSO
+.BR asn2all (1),
 .BR asn2asn (1),
 .BR asn2ff (1),
+.BR asn2fsa (1),
 .BR asn2xml (1),
-.BR asndhuff (1)
+.BR asndhuff (1),
+.BR insdseqget (1),
+asn2gb.txt.
--- ncbi-tools6-6.1.20061015.orig/doc/man/blast.1
+++ ncbi-tools6-6.1.20061015/doc/man/blast.1
@@ -1,6 +1,6 @@
-.TH BLAST 1 2003-11-10 NCBI "NCBI Tools User's Manual"
+.TH BLAST 1 2006-10-20 NCBI "NCBI Tools User's Manual"
 .SH NAME
-bl2seq, blast, blastall, blastcl3, blastpgp, impala, megablast, rpsblast, seedtop \- Basic Local Alignment Search Tool
+bl2seq, blast2, blastall, blastall_old, blastcl3, blastpgp, impala, megablast, rpsblast, seedtop \- Basic Local Alignment Search Tool
 .SH SYNOPSIS
 .B bl2seq
 [\|\fB\-\fP\|]
@@ -9,12 +9,13 @@
 [\|\fB\-E\fP\ \fIN\fP\|]
 [\|\fB\-F\fP\ \fIstr\fP\|]
 [\|\fB\-G\fP\ \fIN\fP\|]
-[\|\fB\-I\fP\ \fIstr\fP\|]
-[\|\fB\-J\fP\ \fIstr\fP\|]
+[\|\fB\-I\fP\ \(dq\fIstart\ stop\fP\(dq\|]
+[\|\fB\-J\fP\ \(dq\fIstart\ stop\fP\(dq\|]
 [\|\fB\-M\fP\ \fIstr\fP\|]
 [\|\fB\-S\fP\ \fIN\fP\|]
 [\|\fB\-T\fP\|]
 [\|\fB\-U\fP\|]
+[\|\fB\-V\fP\|]
 [\|\fB\-W\fP\ \fIN\fP\|]
 [\|\fB\-X\fP\ \fIN\fP\|]
 [\|\fB\-Y\fP\ \fIX\fP\|]
@@ -31,26 +32,31 @@
 [\|\fB\-r\fP\ \fIN\fP\|]
 [\|\fB\-t\fP\ \fIN\fP\|]
 .PP
-.B blast
+.B blast2
 [\|\fB\-\fP\|]
-[\|\fB\-A\ F\fP\|]
+[\|\fB\-B\fP\ \fIN\fP\|]
 [\|\fB\-D\fP\ \fIN\fP\|]
+[\|\fB\-C\fP\ \fIx\fP\|]
 [\|\fB\-E\fP\ \fIN\fP\|]
 [\|\fB\-F\fP\ \fIstr\fP\|]
 [\|\fB\-G\fP\ \fIN\fP\|]
 [\|\fB\-H\fP\|]
+[\|\fB\-I\fP\ \(dq\fIstart\ stop\fP\(dq\|]
+[\|\fB\-J\fP\ \(dq\fIstart\ stop\fP\(dq\|]
+[\|\fB\-K\fP\ \fIN\fP\|]
 [\|\fB\-L\fP\|]
 [\|\fB\-M\fP\ \fIstr\fP\|]
-[\|\fB\-O\fP\ \fIfilename\fP\|]
+[\|\fB\-N\fP\|]
 [\|\fB\-P\fP\ \fIX\fP\|]
 [\|\fB\-Q\fP\ \fIN\fP\|]
+[\|\fB\-R\fP\|]
 [\|\fB\-S\fP\ \fIN\fP\|]
 [\|\fB\-T\fP\ \fIN\fP\|]
-[\|\fB\-V\fP\|]
 [\|\fB\-W\fP\ \fIN\fP\|]
 [\|\fB\-X\fP\ \fIN\fP\|]
 [\|\fB\-Y\fP\ \fIX\fP\|]
 [\|\fB\-Z\fP\ \fIN\fP\|]
+[\|\fB\-a\fP\ \fIN\fP\|]
 [\|\fB\-b\fP\ \fIN\fP\|]
 [\|\fB\-c\fP\|]
 [\|\fB\-d\fP\ \fIstr\fP\|]
@@ -62,21 +68,24 @@
 [\|\fB\-j\fP\ \fIfilename\fP\|]
 [\|\fB\-k\fP\ \fIstr\fP\|]
 [\|\fB\-m\fP\ \fIN\fP\|]
+[\|\fB\-n\fP\|]
 [\|\fB\-o\fP\ \fIfilename\fP\|]
 \fB\-p\fP\ \fIstr\fP
 [\|\fB\-q\fP\ \fIN\fP\|]
 [\|\fB\-r\fP\ \fIN\fP\|]
-[\|\fB\-s\fP\ \fIN\fP\|]
+[\|\fB\-s\fP\fP\|]
 [\|\fB\-t\fP\ \fIN\fP\|]
 [\|\fB\-u\fP\|]
 [\|\fB\-v\fP\ \fIN\fP\|]
 [\|\fB\-w\fP\ \fIN\fP\|]
 [\|\fB\-y\fP\ \fIN\fP\|]
+[\|\fB\-z\fP\ \fIN\fP\|]
 .PP
 .B blastall
 [\|\fB\-\fP\|]
 [\|\fB\-A\fP\ \fIN\fP\|]
 [\|\fB\-B\fP\ \fIN\fP\|]
+[\|\fB\-C\fP\ \fIx\fP\|]
 [\|\fB\-D\fP\ \fIN\fP\|]
 [\|\fB\-E\fP\ \fIN\fP\|]
 [\|\fB\-F\fP\ \fIstr\fP\|]
@@ -93,6 +102,7 @@
 [\|\fB\-S\fP\|]
 [\|\fB\-T\fP\|]
 [\|\fB\-U\fP\|]
+[\|\fB\-V\fP\|]
 [\|\fB\-W\fP\ \fIN\fP\|]
 [\|\fB\-X\fP\ \fIN\fP\|]
 [\|\fB\-Y\fP\ \fIX\fP\|]
@@ -111,16 +121,63 @@
 \fB\-p\fP\ \fIstr\fP
 [\|\fB\-q\fP\ \fIN\fP\|]
 [\|\fB\-r\fP\ \fIN\fP\|]
+[\|\fB\-s\fP\|]
 [\|\fB\-t\fP\ \fIN\fP\|]
 [\|\fB\-v\fP\ \fIN\fP\|]
 [\|\fB\-w\fP\ \fIN\fP\|]
 [\|\fB\-y\fP\ \fIX\fP\|]
 [\|\fB\-z\fP\ \fIX\fP\|]
 .PP
-.B blastcl3
+.B blastall_old
 [\|\fB\-\fP\|]
 [\|\fB\-A\fP\ \fIN\fP\|]
 [\|\fB\-B\fP\ \fIN\fP\|]
+[\|\fB\-C\fP\ \fIx\fP\|]
+[\|\fB\-D\fP\ \fIN\fP\|]
+[\|\fB\-E\fP\ \fIN\fP\|]
+[\|\fB\-F\fP\ \fIstr\fP\|]
+[\|\fB\-G\fP\ \fIN\fP\|]
+[\|\fB\-I\fP\|]
+[\|\fB\-J\fP\|]
+[\|\fB\-K\fP\ \fIN\fP\|]
+[\|\fB\-L\fP\ \fIstart,stop\fP\|]
+[\|\fB\-M\fP\ \fIstr\fP\|]
+[\|\fB\-O\fP\ \fIfilename\fP\|]
+[\|\fB\-P\fP\ \fIN\fP\|]
+[\|\fB\-Q\fP\ \fIN\fP\|]
+[\|\fB\-R\fP\ \fIfilename\fP\|]
+[\|\fB\-S\fP\|]
+[\|\fB\-T\fP\|]
+[\|\fB\-U\fP\|]
+[\|\fB\-W\fP\ \fIN\fP\|]
+[\|\fB\-X\fP\ \fIN\fP\|]
+[\|\fB\-Y\fP\ \fIX\fP\|]
+[\|\fB\-Z\fP\ \fIN\fP\|]
+[\|\fB\-a\fP\ \fIN\fP\|]
+[\|\fB\-b\fP\ \fIN\fP\|]
+[\|\fB\-d\fP\ \fIstr\fP\|]
+[\|\fB\-e\fP\ \fIX\fP\|]
+[\|\fB\-f\fP\ \fIN\fP\|]
+[\|\fB\-g\ F\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-l\fP\ \fIstr\fP\|]
+[\|\fB\-m\fP\ \fIN\fP\|]
+[\|\fB\-n\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+\fB\-p\fP\ \fIstr\fP
+[\|\fB\-q\fP\ \fIN\fP\|]
+[\|\fB\-r\fP\ \fIN\fP\|]
+[\|\fB\-s\fP\|]
+[\|\fB\-t\fP\ \fIN\fP\|]
+[\|\fB\-v\fP\ \fIN\fP\|]
+[\|\fB\-w\fP\ \fIN\fP\|]
+[\|\fB\-y\fP\ \fIX\fP\|]
+[\|\fB\-z\fP\ \fIX\fP\|]
+.PP
+.B blastcl3
+[\|\fB\-\fP\|]
+[\|\fB\-A\fP\ \fIN\fP\|]
+[\|\fB\-C\fP\ \fIx\fP\|]
 [\|\fB\-D\fP\ \fIN\fP\|]
 [\|\fB\-E\fP\ \fIN\fP\|]
 [\|\fB\-F\fP\ \fIstr\fP\|]
@@ -153,8 +210,9 @@
 \fB\-p\fP\ \fIstr\fP
 [\|\fB\-q\fP\ \fIN\fP\|]
 [\|\fB\-r\fP\ \fIN\fP\|]
-[\|\fB\-u\fP\ \fIstr\fP\|]
+[\|\fB\-s\fP\|]
 [\|\fB\-t\fP\ \fIN\fP\|]
+[\|\fB\-u\fP\ \fIstr\fP\|]
 [\|\fB\-v\fP\ \fIN\fP\|]
 [\|\fB\-w\fP\ \fIN\fP\|]
 [\|\fB\-y\fP\ \fIX\fP\|]
@@ -192,7 +250,6 @@
 [\|\fB\-d\fP\ \fIstr\fP\|]
 [\|\fB\-e\fP\ \fIX\fP\|]
 [\|\fB\-f\fP\ \fIN\fP\|]
-[\|\fB\-g\ F\fP\|]
 [\|\fB\-h\fP\ \fIX\fP\|]
 [\|\fB\-i\fP\ \fIfilename\fP\|]
 [\|\fB\-j\fP\ \fIN\fP\|]
@@ -201,8 +258,10 @@
 [\|\fB\-m\fP\ \fIN\fP\|]
 [\|\fB\-o\fP\ \fIfilename\fP\|]
 [\|\fB\-p\fP\ \fIstr\fP\|]
+[\|\fB\-q\fP\ \fIN\fP\|]
 [\|\fB\-s\fP\|]
-[\|\fB\-t\ F\fP\|]
+[\|\fB\-t\fP\ \fIN\fP[\|\fBu\fP\|]\|]
+[\|\fB\-u\fP\ \fIN\fP\|]
 [\|\fB\-v\fP\ \fIN\fP\|]
 [\|\fB\-y\fP\ \fIX\fP\|]
 [\|\fB\-z\fP\ \fIN\fP\|]
@@ -252,15 +311,17 @@
 [\|\fB\-S\fP\ \fIN\fP\|]
 [\|\fB\-T\fP\|]
 [\|\fB\-U\fP\|]
+[\|\fB\-V\fP\|]
 [\|\fB\-W\fP\ \fIN\fP\|]
 [\|\fB\-X\fP\ \fIN\fP\|]
+[\|\fB\-Y\fP\ \fIX\fP\|]
 [\|\fB\-Z\fP\ \fIN\fP\|]
 [\|\fB\-a\fP\ \fIN\fP\|]
 [\|\fB\-b\fP\ \fIN\fP\|]
 [\|\fB\-d\fP\ \fIstr\fP\|]
 [\|\fB\-e\fP\ \fIX\fP\|]
 [\|\fB\-f\fP\|]
-[\|\fB\-g\fP\|]
+[\|\fB\-g\ F\fP\|]
 [\|\fB\-i\fP\ \fIfilename\fP\|]
 [\|\fB\-l\fP\ \fIstr\fP\|]
 [\|\fB\-m\fP\ \fIN\fP\|]
@@ -286,6 +347,7 @@
 [\|\fB\-P\fP\ \fIN\fP\|]
 [\|\fB\-T\fP\|]
 [\|\fB\-U\fP\|]
+[\|\fB\-V\fP\|]
 [\|\fB\-X\fP\ \fIN\fP\|]
 [\|\fB\-Y\fP\ \fIX\fP\|]
 [\|\fB\-Z\fP\ \fIN\fP\|]
@@ -293,7 +355,6 @@
 [\|\fB\-b\fP\ \fIN\fP\|]
 \fB\-d\fP\ \fIfilename\fP
 [\|\fB\-e\fP\ \fIX\fP\|]
-[\|\fB\-g\ F\fP\|]
 [\|\fB\-i\fP\ \fIfilename\fP\|]
 [\|\fB\-l\fP\ \fIfilename\fP\|]
 [\|\fB\-m\fP\ \fIN\fP\|]
@@ -316,16 +377,15 @@
 [\|\fB\-O\fP\ \fIfilename\fP\|]
 [\|\fB\-S\fP\ \fIN\fP\|]
 [\|\fB\-X\fP\ \fIN\fP\|]
-[\|\fB\-b\fP\ \fIN\fP\|]
 [\|\fB\-d\fP\ \fIstr\fP\|]
 [\|\fB\-e\fP\ \fIX\fP\|]
+[\|\fB\-f\fP\|]
 [\|\fB\-i\fP\ \fIfilename\fP\|]
 [\|\fB\-k\fP\ \fIfilename\fP\|]
 [\|\fB\-o\fP\ \fIfilename\fP\|]
 [\|\fB\-p\fP\ \fIstr\fP\|]
 [\|\fB\-q\fP\ \fIN\fP\|]
 [\|\fB\-r\fP\ \fIN\fP\|]
-[\|\fB\-v\fP\ \fIN\fP\|]
 .SH DESCRIPTION
 This manual page documents briefly the commands \fBbl2seq\fP, \fBblast\fP,
 \fBblastall\fP, \fBblastcl3\fP, \fBblastpgp\fP, \fBimpala\fP,
@@ -336,13 +396,16 @@
 the blastn or blastp algorithm.  Both sequences must be either
 nucleotides or proteins.
 .PP
-\fBblast\fP compares a sequence against either a local database or a
+\fBblast2\fP compares a sequence against either a local database or a
 second sequence; it incorporates most of the functionality of both
 \fBbl2seq\fP and \fBblastall\fP, but uses a semi-experimental new
 internal engine.
 .PP
-\fBblastall\fP finds the best matches in a local database for a
-sequence.
+\fBblastall\fP and \fBblastall_old\fP find the best matches in a
+local database for a sequence.
+\fBblastall\fP uses a newer engine than \fBblastall_old\fP by default,
+but supports using the older engine as well (when invoked with the
+option \fB-V\ F\fP).
 .PP
 \fBblastcl3\fP accesses the newest NCBI BLAST search engine (version
 2.0).  The software behind BLAST version 2.0 was written from scratch
@@ -419,20 +482,58 @@
 \fB\-A\fP (bl2seq)
 Input sequences in the form of accession.version
 .TP
-\fB\-A\ F\fP (blast)
-Do not use AG BLAST approach to database scanning
+\fB\-A\fP\ \fIN\fP (blastall, blastall_old, blastcl3, blastpgp, megablast)
+Multiple Hits window size; generally defaults to 0 (for single-hit
+extensions), but defaults to 40 when using discontiguous templates.
 .TP
-\fB\-A\fP\ \fIN\fP (blastall, blastcl3, blastpgp, megablast) Multiple
-Hits window size (default is 40 for blastpgp and 0 for other command,
-but blastall and blastcl3 interpret 0 as 40 for all programs but blastn
-and megablast)
+\fB\-B\fP\ \fIN\fP (blast2)
+Produce on-the-fly output:
+.RS
+.PD 0
+.IP 0
+none (default)
+.IP 1
+table of offsets and quality values
+.IP 2
+add sequence data
+.IP 3
+text ASN.1
+.IP 4
+binary ASN.1
+.PD
+.RE
 .TP
-\fB\-B\fP\ \fIN\fP (blastall, blastcl3)
+\fB\-B\fP\ \fIN\fP (blastall, blastall_old)
 Number of concatenated queries, in blastn or tblastn mode
 .TP
 \fB\-B\fP\ \fIfilename\fP (blastpgp)
 Input Alignment File for PSI-BLAST Restart
 .TP
+\fB\-C\fP\ \fIX\fP (blast2, blastall, blastall_old, blastcl3)
+Use composition-based statistics for blastpgp (except in blast2) or tblastn:
+.RS
+.PD 0
+.IP "D or d"
+Default (equivalent to F)
+.IP "0, F, or f"
+No composition-based statistics
+.IP "1, T, or t"
+Composition-based statistics as in \fINAR\fP 29:2994-3005, 2001
+.IP 2
+Composition-based score adjustment as in \fIBioinformatics\fP 21:902-911,
+2005, conditioned on sequence properties
+.IP 3
+Composition-based score adjustment as in \fIBioinformatics\fP 21:902-911,
+2005, unconditionally
+.PD
+.RE
+.RS
+When enabling statistics in blastall, blastall_old, or blastcl3 (\fIi.e.\fP,
+not blast2), appending \fBu\fP (case-insensitive) to the mode enables
+use of unified p-values combining alignment and compositional p-values
+in round 1 only.
+.RE
+.TP
 \fB\-C\fP\ \fIfilename\fP (blastpgp)
 Output File for PSI-BLAST Checkpointing
 .TP
@@ -450,7 +551,7 @@
 .PD
 .RE
 .TP
-\fB\-D\fP\ \fIN\fP (blast, blastall, blastcl3)
+\fB\-D\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3)
 Translate sequences in the database according to genetic code \fIN\fP
 in /usr/share/ncbi/data/gc.prt (default is 1; only applies to tblast*)
 .TP
@@ -459,51 +560,53 @@
 .RS
 .PD 0
 .IP 0
-alignment endpoints and score (default)
+alignment endpoints and score
 .IP 1
-all ungapped segments endpoints,
+all ungapped segments endpoints
 .IP 2
-traditional BLAST output,
+traditional BLAST output (default)
 .IP 3
 tab-delimited one line format
+.IP 4
+incremental text ASN.1
+.IP 5
+incremental binary ASN.1
 .PD
 .RE
 .TP
 \fB\-D\fP\ \fIN\fP (seedtop)
 Cost decline to align (default = 99999)
 .TP
-\fB\-E\fP\ \fIN\fP (bl2seq)
-Extending a gap costs \fIN\fP (-1 invokes default behavior; anything
-else can result in unreliable statistics)
-.TP
-\fB\-E\fP\ \fIN\fP (blast, blastall, blastcl3, megablast)
-Extending a gap costs \fIN\fP (zero invokes default behavior:
-non-affine if greedy, 2 otherwise, at least for blast)
+\fB\-E\fP\ \fIN\fP (bl2seq, blastcl3, megablast)
+Extending a gap costs \fIN\fP (-1 invokes default behavior)
+.TP
+\fB\-E\fP\ \fIN\fP (blast2, blastall, blastall_old)
+Extending a gap costs \fIN\fP (-1 invokes default behavior:
+non-affine if greedy, 2 otherwise)
 .TP
 \fB\-E\fP\ \fIN\fP (blastpgp, impala, seedtop)
 Extending a gap costs \fIN\fP (default is 1)
 .TP
-\fB\-F\fP\ \fIstr\fP (bl2seq, blast, blastall, blastpgp, blastcl3, impala,
-megablast, rpsblast)
+\fB\-F\fP\ \fIstr\fP (bl2seq, blast2, blastall, blastall_old, blastpgp,
+blastcl3, impala, megablast, rpsblast)
 Filter options for DUST or SEG; defaults to \fBT\fP for bl2seq,
-blast, blastall, blastcl3, and megablast, and to \fBF\fP for blastpgp,
-impala, and rpsblast.
+blast2, blastall, blastall_old, blastcl3, and megablast, and to
+\fBF\fP for blastpgp, impala, and rpsblast.
 .TP
 \fB\-F\fP (seedtop)
 Filter sequence with SEG.
 .TP
-\fB\-G\fP\ \fIN\fP (bl2seq)
-Opening a gap costs \fIN\fP (-1 invokes default behavior; anything
-else can result in unreliable statistics)
-.TP
-\fB\-G\fP\ \fIN\fP (blast, blastall, blastcl3, megablast)
-Opening a gap costs \fIN\fP (zero invokes default behavior: non-affine
-if greedy, 5 if using dynamic programming, at least for blast)
+\fB\-G\fP\ \fIN\fP (bl2seq, blastcl3, megablast)
+Opening a gap costs \fIN\fP (-1 invokes default behavior)
+.TP
+\fB\-G\fP\ \fIN\fP (blast2, blastall, blastall_old)
+Opening a gap costs \fIN\fP (-1 invokes default behavior: non-affine
+if greedy, 5 if using dynamic programming)
 .TP
 \fB\-G\fP\ \fIN\fP (blastpgp, impala, seedtop)
 Opening a gap costs \fIN\fP (default is 11)
 .TP
-\fB\-H\fP (blast)
+\fB\-H\fP (blast2)
 Produce HTML output
 .TP
 \fB\-H\fP\ \fIN\fP (blastpgp)
@@ -515,33 +618,42 @@
 \fB\-H\fP\ \fIN\fP (megablast)
 Maximal number of HSPs to save per database sequence (default is 0, unlimited)
 .TP
-\fB\-I\fP\ \fIstr\fP (bl2seq)
-Location on first sequence
+\fB\-I\fP\ \(dq\fIstart\ stop\fP\(dq (bl2seq, blast2)
+Location on first (query) sequence (applies only if file specified
+with \fB-i\fP contains a single sequence)
 .TP
-\fB\-I\fP (blastall, blastcl3, blastpgp, impala, megablast, rpsblast, seedtop)
-Show GI's in deflines
+\fB\-I\fP (blastall, blastall_old, blastcl3, blastpgp, impala, megablast,
+rpsblast, seedtop)
+Show GIs in deflines
 .TP
-\fB\-J\fP\ \fIstr\fP (bl2seq)
-Location on second sequence
+\fB\-J\fP\ \(dq\fIstart\ stop\fP\(dq (bl2seq, blast2)
+Location on second (subject) sequence (applies only if file specified
+with \fB-j\fP contains a single sequence)
 .TP
-\fB\-J\fP (blastall, blastcl3, blastpgp, impala, megablast, rpsblast, seedtop)
+\fB\-J\fP (blastall, blastall_old, blastcl3, blastpgp, impala, megablast,
+rpsblast, seedtop)
 Believe the query defline
 .TP
-\fB\-K\fP\ \fIN\fP (blastall, blastcl3, blastpgp)
+\fB\-K\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3, blastpgp)
 Number of best hits from a region to keep (off by default, if used a
 value of 100 is recommended)
 .TP
-\fB\-L\fP (blast)
+\fB\-L\fP (blast2)
 Use (classical Mega BLAST) lookup table with width 12
 .TP
-\fB\-L\fP\ \fIstart,stop\fP (blastall, blastcl3, megablast, rpsblast)
+\fB\-L\fP\ \fIstart,stop\fP (blastall, blastall_old, blastcl3, megablast,
+rpsblast)
 Location on query sequence (for rpsblast, only valid in blastp mode)
 .TP
-\fB\-M\fP\ \fIstr\fP (bl2seq, blast, blastall, blastcl3, blastpgp, impala, seedtop)
+\fB\-M\fP\ \fIstr\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+blastpgp, impala, seedtop)
 Use matrix \fIstr\fP (default = BLOSUM62)
 .TP
 \fB\-M\fP\ \fIN\fP (megablast)
-Maximal total length of queries for a single search (default = 20000000)
+Maximal total length of queries for a single search (default = 5000000)
+.TP
+\fB\-N\fP (blast2)
+Show only accessions for sequence IDs in tabular output
 .TP
 \fB\-N\fP\ \fIX\fP (blastpgp, rpsblast)
 Number of bits to trigger gapping (default = 22.0)
@@ -559,16 +671,18 @@
 .PD
 .RE
 .TP
-\fB\-O\fP\ \fIfilename\fP (blast, blastall, blastcl3, blastpgp, impala, megablast, rpsblast, seedtop)
+\fB\-O\fP\ \fIfilename\fP (blastall, blastall_old, blastcl3,
+blastpgp, impala, megablast, rpsblast, seedtop)
 Write (ASN.1) sequence alignments to \fIfilename\fP; only valid for
 blastpgp, impala, rpsblast, and seedtop with \fB\-J\fP, and only valid
 for megablast with \fB\-D2\fP.
 .TP
-\fB\-P\fP\ \fIX\fP (blast)
+\fB\-P\fP\ \fIX\fP (blast2)
 Identity percentage cut-off
 .TP
-\fB\-P\fP\ \fIN\fP (blastall, blastpgp, rpsblast)
-Set to 1 for single-hit mode or 0 for multiple-hit mode (default)
+\fB\-P\fP\ \fIN\fP (blastall, blastall_old, blastcl3, blastpgp, rpsblast)
+Set to 1 for single-hit mode or 0 for multiple-hit mode (default).
+Does not apply to blastn.
 .TP
 \fB\-P\fP\ \fIfilename\fP (impala)
 Read matrix profiles from database \fIfilename\fP
@@ -576,7 +690,7 @@
 \fB\-P\fP\ \fIN\fP (megablast)
 Maximal number of positions for a hash value (set to 0 [default] to ignore)
 .TP
-\fB\-Q\fP\ \fIN\fP (blast, blastall, blastcl3)
+\fB\-Q\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3)
 Translate query according to genetic code \fIN\fP in
 /usr/share/ncbi/data/gc.prt (default is 1)
 .TP
@@ -584,9 +698,13 @@
 Output File for PSI-BLAST Matrix in ASCII
 .TP
 \fB\-Q\fP\ \fIfilename\fP (megablast)
-Masked query output
+Masked query output; requires \fB-D\ 2\fP
 .TP
-\fB\-R\fP\ \fIfilename\fP (blastall)
+\fB\-R\fP (blast2)
+Compute locally optimal Smith-Waterman alignments.
+(This option is only available for gapped tblastn.)
+.TP
+\fB\-R\fP\ \fIfilename\fP (blastall, blastall_old)
 Read PSI-TBLASTN checkpoint file \fIfilename\fP
 .TP
 \fB\-R\fP (blastcl3)
@@ -598,7 +716,8 @@
 \fB\-R\fP (megablast)
 Report the log information at the end of output
 .TP
-\fB\-S\fP\ \fIN\fP (bl2seq, blast, blastall, blastcl3, megablast)
+\fB\-S\fP\ \fIN\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+megablast)
 Query strands to search against database for blastn, blastx, tblastx:
 .RS
 .PD 0
@@ -617,10 +736,11 @@
 \fB\-S\fP\ \fIN\fP (seedtop)
 Cutoff cost (default = 30)
 .TP
-\fB\-T\fP (bl2seq, blastall, blastcl3, blastpgp, megablast, rpsblast)
+\fB\-T\fP (bl2seq, blastall, blastall_old, blastcl3, blastpgp, megablast,
+rpsblast)
 Produce HTML output
 .TP
-\fB\-T\fP\ \fIN\fP (blast)
+\fB\-T\fP\ \fIN\fP (blast2)
 Type of a discontiguous word template:
 .RS
 .PD 0
@@ -633,44 +753,54 @@
 .PD
 .RE
 .TP
-\fB\-U\fP (bl2seq, blastall, blastcl3, blastpgp, megablast, rpsblast)
+\fB\-U\fP (bl2seq, blastall, blastall_old, blastcl3, blastpgp, megablast,
+rpsblast)
 Use lower case filtering for the query sequence
 .TP
-\fB\-V\fP (blast)
+\fB\-V\fP (bl2seq, blastall, megablast, rpsblast)
+Force use of legacy engine
+.TP
+\fB\-V\fP (blast2)
 Use variable word size approach to database scanning
 .TP
-\fB\-W\fP\ \fIN\fP (bl2seq, blast, blastall, blastcl3, blastpgp, megablast, rpsblast)
+\fB\-W\fP\ \fIN\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+blastpgp, megablast, rpsblast)
 Use words of size \fIN\fP (length of best perfect match; zero invokes
 default behavior, except with megablast, which defaults to 28, and
 blastpgp, which defaults to 3.  The default values for the other
 commands vary with "program": 11 for blastn, 28 for megablast, and 3
 for everything else.)
 .TP
-\fB\-X\fP\ \fIN\fP (bl2seq, blast, blastall, blastcl3, blastpgp, megablast, rpsblast, seedtop)
+\fB\-X\fP\ \fIN\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+blastpgp, megablast, rpsblast, seedtop)
 X dropoff value for gapped alignment (in bits) (zero invokes default
 behavior, except with megablast, which defaults to 20, and rpsblast
 and seedtop, which default to 15.  The default values for the other
 commands vary with "program": 30 for blastn, 20 for megablast, 0 for
 tblastx, and 15 for everything else.)
 .TP
-\fB\-Y\fP\ \fIX\fP (bl2seq, blast, blastall, blastcl3, blastpgp, rpsblast)
+\fB\-Y\fP\ \fIX\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+blastpgp, megablast, rpsblast)
 Effective length of the search space (use zero for the real size)
 .TP
-\fB\-Z\fP\ \fIN\fP (blast, blastall, blastcl3, blastpgp, megablast, rpsblast)
+\fB\-Z\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+megablast, rpsblast)
 X dropoff value for final [dynamic programming?] gapped alignment in
 bits (default is 50 for blastn and megablast, 0 for tblastx, 25 for
 others)
 .TP
 \fB\-a\fP\ \fIfilename\fP (bl2seq)
-Write SeqAnnot output to \fIfilename\fP
+Write text ASN.1 output to \fIfilename\fP
 .TP
-\fB\-a\fP\ \fIN\fP (blastall, blastcl3, blastpgp, impala, megablast, rpsblast)
-Number of processors to use (default is one)
+\fB\-a\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+impala, megablast, rpsblast)
+Number of threads to use (default is one)
 .TP
-\fB\-b\fP\ \fIN\fP (blast, blastall, blastcl3, blastpgp, impala, megablast, rpsblast, seedtop)
+\fB\-b\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+impala, megablast, rpsblast)
 Number of database sequences to show alignments for (B) (default is 250)
 .TP
-\fB\-c\fP (blast)
+\fB\-c\fP (blast2)
 Mask lower case
 .TP
 \fB\-c\fP\ \fIN\fP (blastpgp, impala)
@@ -679,18 +809,18 @@
 \fB\-d\fP\ \fIN\fP (bl2seq)
 Use theoretical DB size of \fIN\fP (zero stands for the real size)
 .TP
-\fB\-d\fP\ \fIstr\fP (blast, blastall, blastcl3, blastpgp, impala, megablast, seedtop)
-Database to use (default is nr for all executables except blast,
+\fB\-d\fP\ \fIstr\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+impala, megablast, seedtop)
+Database to use (default is nr for all executables except blast2,
 which requires a second FASTA sequence if this is not set)
 .TP
 \fB\-d\fP\ \fIfilename\fP (rpsblast)
 RPS BLAST Database
 .TP
 \fB\-e\fP\ \fIX\fP
-Expectation value (E) (default = 1e6 for megablast, 10.0 for
-everything else)
+Expectation value (E) (default = 10.0)
 .TP
-\fB\-f\fP\ \fIN\fP (blastall, blastcl3)
+\fB\-f\fP\ \fIN\fP (blastall, blastall_old, blastcl3)
 Threshold for extending hits, default if zero: 0 for blastn and
 megablast, 11 for blastp, 12 for blastx, and 13 for tblasn and
 tblastx.
@@ -701,10 +831,13 @@
 \fB\-f\fP (megablast)
 Show full IDs in the output (default - only GIs or accessions)
 .TP
-\fB\-g\ F\fP (bl2seq, blastall, blastcl3, blastpgp, rpsblast)
+\fB\-f\fP (seedtop)
+Force searching for patterns even if they are too likely
+.TP
+\fB\-g\ F\fP (bl2seq, blastall, blastall_old, blastcl3)
 Do not perform gapped alignment (N/A for tblastx)
 .TP
-\fB\-g\fP\ \fIN\fP (blast)
+\fB\-g\fP\ \fIN\fP (blast2)
 Use greedy algorithm for gapped extensions:
 .RS
 .PD 0
@@ -719,10 +852,11 @@
 .PD
 .RE
 .TP
-\fB\-g\fP (megablast)
-Generate words for every base of the database (default is every 4th)
+\fB\-g\ F\fP (megablast)
+Generate words for every fourth base of the database (only relevant
+for discontiguous words)
 .TP
-\fB\-h\fP\ \fIN\fP (blast)
+\fB\-h\fP\ \fIN\fP (blast2)
 Frame shift penalty for out-of-frame gapping (blastx, tblastn only;
 default is zero)
 .TP
@@ -731,30 +865,32 @@
 for blastpgp, 0.005 for impala)
 .TP
 \fB\-i\fP\ \fIfilename\fP
-Read (first) sequence from \fIfilename\fP (default is stdin)
+Read (first, query) sequence or set from \fIfilename\fP (default is
+stdin; not needed for blastpgp if restarting from scoremat)
 .TP
-\fB\-j\fP\ \fIfilename\fP (bl2seq, blast)
-Read second sequence from \fIfilename\fP
+\fB\-j\fP\ \fIfilename\fP (bl2seq, blast2)
+Read second (subject) sequence or set from \fIfilename\fP
 .TP
 \fB\-j\fP\ \fIN\fP (blastpgp)
 Maximum number of passes to use in multipass version (default = 1)
 .TP
-\fB\-k\fP\ \fIstr\fP (blast)
+\fB\-k\fP\ \fIstr\fP (blast2)
 Pattern for PHI-BLAST
 .TP
 \fB\-k\fP\ \fIfilename\fP (blastpgp, seedtop)
 Input hit file for PHI-BLAST (default = hit_file)
 .TP
-\fB\-l\fP\ \fIstr\fP (blastall, blastpgp, megablast)
+\fB\-l\fP\ \fIstr\fP (blastall, blastall_old, blastpgp, megablast)
 Restrict search of database to list of GI's [String]
 .TP
 \fB\-l\fP\ \fIfilename\fP (rpsblast)
-Logfile name (default is rpsblast.log)
+Log messages to \fIfilename\fP rather than standard error.
 .TP
 \fB\-m\fP (bl2seq)
 Use Mega Blast for search
 .TP
-\fB\-m\fP\ \fIN\fP (blast, blastall, blastcl3, blastpgp, impala, megablast, rpsblast)
+\fB\-m\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+impala, megablast, rpsblast)
 alignment view options:
 .RS
 .PD 0
@@ -785,7 +921,10 @@
 .PD
 .RE
 .TP
-\fB\-n\fP (blastall, blastcl3)
+\fB\-n\fP (blast2)
+Show GIs in sequence IDs
+.TP
+\fB\-n\fP (blastall, blastall_old, blastcl3)
 MegaBlast search
 .TP
 \fB\-n\fP (megablast)
@@ -794,7 +933,7 @@
 \fB\-o\fP\ \fIfilename\fP
 Write final alignment report to \fIfilename\fP rather than stdout
 .TP
-\fB\-p\fP\ \fIstr\fP (bl2seq, blast, blastall, blastcl3)
+\fB\-p\fP\ \fIstr\fP (bl2seq, blast2, blastall, blastall_old, blastcl3)
 Use the "program" (comparison type) \fIstr\fP.  The \fBDESCRIPTION\fP
 section covers this option in more detail.
 .TP
@@ -818,58 +957,116 @@
 .PD
 .RE
 .TP
-\fB\-q\fP\ \fIN\fP (bl2seq, blast, blastall, blastcl3, megablast, seedtop)
+\fB\-q\fP\ \fIN\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+megablast, seedtop)
 Penalty for a nucleotide mismatch (blastn only) (default = -10 for
 seedtop, -3 for everything else)
 .TP
-\fB\-r\fP\ \fIN\fP (bl2seq, blast, blastall, blastcl3, megablast, seedtop)
+\fB\-q\fP\ \fIN\fP (blastpgp)
+ASN.1 Scoremat input of checkpoint data:
+.RS
+.PD 0
+.IP 0
+no scoremat input (default)
+.IP 1
+restart from ASCII scoremat checkpoint file
+.IP 2
+restart from binary scoremat checkpoint file
+.PD
+.RE
+.TP
+\fB\-r\fP\ \fIN\fP (bl2seq, blast2, blastall, blastall_old, blastcl3,
+megablast, seedtop)
 Reward for a nucleotide match (blastn only) (default = 10 for seedtop,
 -10 for everything else)
 .TP
-\fB\-s\fP\ \fIN\fP (blast)
-Database scanning stride (0 for default behavior)
-.TP
-\fB\-s\fP (blastpgp)
-Compute locally optimal Smith-Waterman alignments
+\fB\-s\fP (blast2)
+Generate words for every base of the database (default is every 4th;
+may only be used with discontiguous words)
+.TP
+\fB\-s\fP (blastall, blastall_old, blastcl3, blastpgp)
+Compute locally optimal Smith-Waterman alignments.
+For blastall, blastall_old, and blastcl3, this is only available in gapped
+tblastn mode.
 .TP
 \fB\-s\fP\ \fIN\fP (megablast)
 Minimal hit score to report (0 for default behavior)
 .TP
-\fB\-t\fP\ \fIN\fP (bl2seq, blast, blastall, blastcl3)
+\fB\-t\fP\ \fIN\fP (bl2seq, blast2, blastall, blastall_old, blastcl3)
 Length of a discontiguous word template (the largest intron allowed in
-tblastn for linking HSPs; default = 0)
-.TP
-\fB\-t\ F\fP (blastpgp)
-Do not use composition-based statistics
+a translated nucleotide sequence when linking multiple distinct
+assignments; default = 0; negative values disable linking for blastall,
+blastall_old, and blastcl3.)
+.TP
+\fB\-t\fP\ \fIN\fP[\|\fBu\fP\|] (blastpgp)
+Composition-based statistics mode.  The first character is interpreted
+as follows:
+.RS
+.PD 0
+.IP "0, F, or f"
+no composition-based statistics
+.IP "1, T, or t"
+composition-based statistics as in \fINAR\fP 29:2994\-3005, 2001
+.IP 2
+composition-based score adjustment as in \fIBioinformatics\fP
+21:902-911, 2005, conditioned on sequence properties in round 1
+.IP 3
+composition-based score adjustment as in \fIBioinformatics\fP
+21:902-911, 2005, unconditionally in round 1
+.PD
+.P
+When composition-based statistics are in use, appending \fBu\fP
+(case-insensitive) to the argument requests unified p-value combining
+alignment p-value and compositional p-value in round 1 only.
+.RE
 .TP
 \fB\-t\fP\ \fIN\fP (megablast)
 Length of a discontiguous word template (contiguous word if 0 [default])
 .TP
-\fB\-u\fP (blast)
+\fB\-u\fP (blast2)
 Do only ungapped alignment (always TRUE for tblastx)
 .TP
 \fB\-u\fP\ \fIstr\fP (blastcl3)
 Restrict search of database to results of Entrez2 lookup
 .TP
-\fB\-v\fP\ \fIN\fP (blast, blastall, blastcl3, blastpgp, impala, megablast,
-rpsblast, seedtop)
+\fB\-u\fP\ \fIN\fP (blastpgp)
+ASN.1 Scoremat output of checkpoint data:
+.RS
+.PD 0
+.IP 0
+no scoremat output (default)
+.IP 1
+output ASCII scoremat checkpoint file (requires \fB-J\fP)
+.IP 2
+output binary scoremat checkpoint file (requires \fB-J\fP)
+.PD
+.RE
+.TP
+\fB\-v\fP\ \fIN\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+impala, megablast, rpsblast)
 Number of one-line descriptions to show (V) (default = 500)
 .TP
-\fB\-w\fP\ \fIN\fP (blast)
+\fB\-w\fP\ \fIN\fP (blast2)
 Window size (max. allowed distance between a pair of initial hits; 0
-invokes default behavior)
+invokes default behavior, -1 turns off multiple hits)
 .TP
-\fB\-w\fP\ \fIN\fP (blastall, blastcl3)
+\fB\-w\fP\ \fIN\fP (blastall, blastall_old, blastcl3)
 Frame shift penalty (OOF algorithm for blastx)
 .TP
-\fB\-y\fP\ \fIX\fP (blast, blastall, blastcl3, blastpgp, impala, rpsblast)
+\fB\-y\fP\ \fIX\fP (blast2, blastall, blastall_old, blastcl3, blastpgp,
+impala, rpsblast)
 X dropoff for ungapped extensions in bits (0.0 invokes default
 behavior: 20 for blastn, 10 for megablast, and 7 for all others.)
 .TP
 \fB\-y\fP\ \fIN\fP (megablast)
 X dropoff value for ungapped extension (default is 10)
 .TP
-\fB\-z\fP\ \fIN\fP (blastall, blastcl3, blastpgp, impala, megablast, rpsblast)
+\fB\-z\fP\ \fIN\fP (blast2)
+Longest intron length for uneven gap HSP linking (tblastn only;
+default is 0)
+.TP
+\fB\-z\fP\ \fIN\fP (blastall, blastall_old, blastcl3, blastpgp, impala,
+megablast, rpsblast)
 Effective length of the database (use zero for the real size)
 .SH BUGS
 This manual page is long and confusing; individual pages might be better.
@@ -881,6 +1078,8 @@
 .BR copymat (1),
 .BR fastacmd (1),
 .BR formatdb (1),
+.BR formatrpsdb (1),
 .BR makemat (1),
-blast.txt,
-<http://www.ncbi.nlm.nih.gov/BLAST/>
+blast.html,
+seedtop.html,
+<http://www.ncbi.nlm.nih.gov/BLAST/>.
--- ncbi-tools6-6.1.20061015.orig/doc/man/fa2htgs.1
+++ ncbi-tools6-6.1.20061015/doc/man/fa2htgs.1
@@ -1,4 +1,4 @@
-.TH FA2HTGS 1 2002-04-28 NCBI "NCBI Tools User's Manual"
+.TH FA2HTGS 1 2006-05-29 NCBI "NCBI Tools User's Manual"
 .SH NAME
 fa2htgs \- formatter for high throughput genome sequencing project submissions
 .SH SYNOPSIS
@@ -27,6 +27,7 @@
 \fB\-g\fP\ \fIstr\fP
 [\|\fB\-h\fP\ \fIstr\fP\|]
 [\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-k\fP\ \fIstr\fP\|]
 [\|\fB\-l\fP\ \fIN\fP\|]
 [\|\fB\-m\fP\|]
 [\|\fB\-n\fP\ \fIstr\fP\|]
@@ -171,6 +172,9 @@
 Filename for fasta input (default is stdin; mutually exclusive with
 \fB\-A\fP and \fB\-T\fP)
 .TP
+\fB\-k\fP\ \fIstr\fP
+Add the supplied string as a keyword.
+.TP
 \fB\-l\fP\ \fIN\fP
 Length of sequence in bp (default = 0). The length is checked against
 the actual number of bases we get. For phase 1 and 2 sequence it is
--- ncbi-tools6-6.1.20061015.orig/doc/man/asn2all.1
+++ ncbi-tools6-6.1.20061015/doc/man/asn2all.1
@@ -0,0 +1,183 @@
+.TH ASN2ALL 1 2005-05-16 NCBI "NCBI Tools User's Manual"
+.SH NAME
+asn2all \- generate reports from ASN.1 biological data
+.SH SYNOPSIS
+.B asn2all
+[\|\fB\-\fP\|]
+[\|\fB\-A\fP\ \fIacc\fP\|]
+[\|\fB\-T\fP\|]
+[\|\fB\-X\fP\|]
+[\|\fB\-a\fP\ \fItype\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-c\fP\|]
+[\|\fB\-d\fP\ \fIpath\fP\|]
+[\|\fB\-f\fP\ \fIformat\fP\|]
+[\|\fB\-h\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-l\fP\|]
+[\|\fB\-n\fP\ \fIpolicy\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIpath\fP\|]
+[\|\fB\-r\fP\|]
+[\|\fB\-v\fP\ \fIfilename\fP\|]
+[\|\fB\-x\fP\ \fIext\fP\|]
+.SH DESCRIPTION
+\fBasn2all\fP is primarily intended for generating reports from the
+binary ASN.1 Bioseq-set release files downloaded from the NCBI ftp
+site (ncbi-asn1 directory).
+It can produce GenBank and GenPept flatfiles, FASTA sequence files,
+INSDSet structured XML, TinySeq XML, and Sequin-style 5-column feature
+tables.
+.PP
+The release files (which have the extension \fB.aso.gz\fP) should be
+uncompressed with
+.BR gunzip (1),
+resulting in files with the extension \fB.aso\fP.
+For example, \fBgbpri1.aso\fP is the first file in the primate
+division, and the command
+.RS
+.sp
+gunzip gbpri1.aso.gz
+.sp
+.RE
+will result in \fBgbpri1.aso\fP being created.
+The original \fBgbpri1.aso.gz\fP file is removed after successful
+decompression.
+.PP
+In \fBasn2all\fP, the name of the file to be processed is specified by
+the \fB\-i\fP command line argument.
+Use \fB-a\ t\fP to indicate that it is a release file and \fB-b\fP to
+indicate that it is binary ASN.1.
+A text ASN.1 file obtained from Entrez can be processed by using
+\fB-a\ a\fP instead of \fB-a\ t\ -b\fP.
+.PP
+Nucleotide and protein records can be processed simultaneously.
+Use the \fB-o\fP argument to indicate the nucleotide output file, and
+the \fB-v\fP argument for the protein output file.
+.PP
+The \fB-f\fP argument determines the format to be generated, and is
+documented in more detail (along with other options) in the following
+section.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-A\fP\ \fIacc\fP
+Accession to fetch
+.TP
+\fB\-T\fP
+Use Threads
+.TP
+\fB\-X\fP
+EXtended qualifier output
+.TP
+\fB\-a\fP\ \fItype\fP
+Input ASN.1 type:
+.RS
+.PD 0
+.IP a
+any (autodetected; default)
+.IP e
+Seq-entry
+.IP b
+Bioseq
+.IP s
+Bioseq-set
+.IP m
+Seq-submit
+.IP t
+batch processing (suitable for official releases; autodetects specific type)
+.PD
+.RE
+.TP
+\fB\-b\fP
+Bioseq-set is Binary
+.TP
+\fB\-c\fP
+Bioseq-set is Compressed
+.TP
+\fB\-d\fP\ \fIpath\fP
+Path to indexed binary ASN.1 Data
+.TP
+\fB\-f\fP\ \fIformat\fP
+Output Format:
+.RS
+.PD 0
+.IP g
+GenBank/GenPept (default)
+.IP f
+FASTA
+.IP t
+Sequin-style 5-column feature table
+.IP y
+TinySet XML (akin to FASTA)
+.IP s
+INSDSet XML (akin to GenBank/GenPept)
+.IP a
+structurally equivalent text ASN.1
+.IP x
+structurally equivalent XML
+.IP c
+cache components
+.PD
+.RE
+.TP
+\fB\-h\fP
+Display extra Help message
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Input file name (standard input by default)
+.TP
+\fB\-l\fP
+Lock components in advance
+.TP
+\fB\-n\fP\ \fIpolicy\fP
+Near FASTA policy:
+.RS
+.PD 0
+.IP a
+All
+.IP n
+Near only (default)
+.IP f
+Far only
+.PD
+.RE
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Nucleotide Output file name
+.TP
+\fB\-p\fP\ \fIpath\fP
+Path to files
+.TP
+\fB\-r\fP
+Enable Remote fetching
+.TP
+\fB\-v\fP\ \fIfilename\fP
+Protein output file name
+.TP
+\fB\-x\fP\ \fIext\fP
+File selection suffix when working with entire directories.
+(default is \fB.aso\fP)
+.SH EXAMPLES
+The command
+.RS
+.sp
+  asn2all -i gbpri1.aso -a t -b -f g -o gbpri1.nuc -v gbpri1.prt
+.sp
+.RE
+will generate GenBank and GenPept reports from \fBgbpri1.aso\fP.
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR asn2asn (1),
+.BR asn2ff (1),
+.BR asn2fsa (1),
+.BR asn2gb (1),
+.BR asn2idx (1),
+.BR asn2xml (1),
+.BR asndhuff (1),
+.BR gene2xml (1),
+.BR gunzip (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/asn2fsa.1
+++ ncbi-tools6-6.1.20061015/doc/man/asn2fsa.1
@@ -0,0 +1,138 @@
+.TH ASN2FSA 1 2005-05-16 NCBI "NCBI Tools User's Manual"
+.SH NAME
+asn2fsa \- convert biological sequence data from ASN.1 to FASTA
+.SH SYNOPSIS
+.B asn2fsa
+[\|\fB\-\fP\|]
+[\|\fB\-A\fP\ \fIacc\fP\|]
+[\|\fB\-D\fP\|]
+[\|\fB\-L\fP\ \fIfilename\fP\|]
+[\|\fB\-T\fP\|]
+[\|\fB\-a\fP\ \fItype\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-c\fP\|]
+[\|\fB\-d\fP\ \fIpath\fP\|]
+[\|\fB\-e\fP\ \fIN\fP\|]
+[\|\fB\-f\fP\ \fIpath\fP\|]
+[\|\fB\-g\fP\|]
+[\|\fB\-h\fP\ \fIfilename\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-k\fP\|]
+[\|\fB\-l\fP\|]
+[\|\fB\-m\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIpath\fP\|]
+[\|\fB\-q\fP\ \fIfilename\fP\|]
+[\|\fB\-r\fP\|]
+[\|\fB\-s\fP\|]
+[\|\fB\-u\fP\|]
+[\|\fB\-v\fP\ \fIfilename\fP\|]
+[\|\fB\-x\fP\ \fIstr\fP\|]
+[\|\fB\-z\fP\|]
+.SH DESCRIPTION
+\fBasn2fsa\fP converts biological sequence data from ASN.1 to FASTA.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-A\fP\ \fIacc\fP
+Accession to fetch
+.TP
+\fB\-D\fP
+Use Dash for Gap
+.TP
+\fB\-L\fP\ \fIfilename\fP
+Log file
+.TP
+\fB\-T\fP
+Use Threads
+.TP
+\fB\-a\fP\ \fItype\fP
+Input ASN.1 type:
+.RS
+.PD 0
+.IP a
+any (autodetected; default)
+.IP e
+Seq-entry
+.IP b
+Bioseq
+.IP s
+Bioseq-set
+.IP m
+Seq-submit
+.IP t
+batch processing (suitable for official releases; autodetects specific type)
+.PD
+.RE
+.TP
+\fB\-b\fP
+Bioseq-set is Binary
+.TP
+\fB\-c\fP
+Bioseq-set is Compressed
+.TP
+\fB\-d\fP\ \fIpath\fP
+Path to ReadDB Database
+.TP
+\fB\-e\fP\ \fIN\fP
+Line length (70 by default; may range from 10 to 120)
+.TP
+\fB\-f\fP\ \fIpath\fP
+Path to indexed FASTA data
+.TP
+\fB\-g\fP
+Expand delta gaps into \fBN\fPs
+.TP
+\fB\-h\fP\ \fIfilename\fP
+Far component cache output file name
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Single input file (standard input by default)
+.TP
+\fB\-k\fP
+Local fetching
+.TP
+\fB\-l\fP
+Lock components in advance
+.TP
+\fB\-m\fP
+Master style for near segmented sequences
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Nucleotide Output file name
+.TP
+\fB\-p\fP\ \fIpath\fP
+Path to ASN.1 Files
+.TP
+\fB\-q\fP\ \fIfilename\fP
+Quality score output file name
+.TP
+\fB\-r\fP
+Remote fetching from NCBI
+.TP
+\fB\-s\fP
+Far genomic contig for quality scores
+.TP
+\fB\-u\fP
+Recurse
+.TP
+\fB\-v\fP\ \fIfilename\fP
+Protein output file name
+.TP
+\fB\-x\fP\ \fIstr\fP
+File selection substring (\fB.ent\fP by default) [String]
+.TP
+\fB\-z\fP
+Print quality score gap as -1
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR asn2all (1),
+.BR asn2asn (1),
+.BR asn2ff (1),
+.BR asn2gb (1),
+.BR asn2xml (1),
+.BR asndhuff (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/asn2idx.1
+++ ncbi-tools6-6.1.20061015/doc/man/asn2idx.1
@@ -0,0 +1,41 @@
+.TH ASN2IDX 1 2005-05-16 NCBI "NCBI Tools User's Manual"
+.SH NAME
+asn2idx \- index ASN.1 Bioseq-sets for fast access to individual sequences
+.SH SYNOPSIS
+.B asn2idx
+[\|\fB\-\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-d\fP\ \fIstr\fP\|]
+\fB\-p\fP\ \fIstr\fP
+[\|\fB\-t\fP\|]
+[\|\fB\-x\fP\ \fIstr\fP\|]
+.SH DESCRIPTION
+\fBasn2idx\fP indexes ASN.1 Bioseq-sets (such as GenBank release
+files) to speed retrieval of the individual sequences they contain.
+For each file that it processes, it yields an output file in the same
+directory with the extension \fB.idx\fP.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-b\fP
+Bioseq-sets are Binary
+.TP
+\fB\-d\fP\ \fIstr\fP
+Required Subdirectory
+.TP
+\fB\-p\fP\ \fIstr\fP
+Path to Files
+.TP
+\fB\-t\fP
+Recurse
+.TP
+\fB\-x\fP\ \fIstr\fP
+File Selection Substring (default = .aso)
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR asn2asn (1),
+.BR asndhuff (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/gene2xml.1
+++ ncbi-tools6-6.1.20061015/doc/man/gene2xml.1
@@ -0,0 +1,74 @@
+.TH GENE2XML 1 2005-05-16 NCBI "NCBI Tools User's Manual"
+.SH NAME
+gene2xml \- convert NCBI Entrez Gene ASN.1 into XML
+.SH SYNOPSIS
+.B gene2xml
+[\|\fB\-\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-c\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-l\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIpath\fP\|]
+[\|\fB\-r\fP\ \fIpath\fP\|]
+[\|\fB\-t\fP\ \fIN\fP\|]
+[\|\fB\-x\fP\|]
+[\|\fB\-y\fP\|]
+[\|\fB\-z\fP\|]
+.SH DESCRIPTION
+\fBgene2xml\fP is a stand-alone program that converts Entrez Gene
+ASN.1 into XML.
+Entrez Gene data are stored as compressed binary Entrezgene-Set ASN.1 files
+on the NCBI ftp site, and have the suffix \fB.ags.gz\fP.
+These are several-fold smaller than compressed XML files, resulting in
+a significant savings of disk storage and network bandwidth.
+Normal processing by gene2xml produces text XML files with the same
+name but with \fB.xgs\fP as the suffix.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-b\fP
+File is Binary
+.TP
+\fB\-c\fP
+File is Compressed
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Single Input file (standard input by default) when not using \fB-p\fP
+.TP
+\fB\-l\fP
+Log processing (list files processed when using \fB-p\fP)
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Single Output file (standard output by default) when not using \fB-p\fP
+.TP
+\fB\-p\fP\ \fIpath\fP
+Path to Files (if processing an entire directory)
+.TP
+\fB\-r\fP\ \fIpath\fP
+Path for Results when using \fB-p\fP; defaults to the input directory
+.TP
+\fB\-t\fP\ \fIN\fP
+Limit to the given Taxon ID (per \fBhttp://www.ncbi.nlm.nih.gov/Taxonomy/\fP)
+.TP
+\fB\-x\fP
+Extract .ags -> text .agc (format previously distributed)
+.TP
+\fB\-y\fP
+Combine .agc -> text .ags (for testing)
+.TP
+\fB\-z\fP
+Combine .agc -> binary .ags, then gzip
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.ad l
+.BR asn2all (1),
+.BR asn2asn (1),
+.BR asn2xml (1),
+.BR asndhuff (1),
+gene2xml.txt,
+ncbixml.txt
--- ncbi-tools6-6.1.20061015.orig/doc/man/asnval.1
+++ ncbi-tools6-6.1.20061015/doc/man/asnval.1
@@ -0,0 +1,163 @@
+.TH ASNVAL 1 2006-10-20 NCBI "NCBI Tools User's Manual"
+.SH NAME
+asnval \- validate ASN.1 biological sequence records
+.SH SYNOPSIS
+.B asnval
+[\|\fB\-\fP\|]
+[\|\fB\-A\fP\|]
+[\|\fB\-C\fP\ \fIN\fP\|]
+[\|\fB\-E\fP\ \fIstr\fP\|]
+[\|\fB\-G\fP\|]
+[\|\fB\-J\fP\|]
+[\|\fB\-L\fP\ \fIfilename\fP\|]
+[\|\fB\-M\fP\|]
+[\|\fB\-P\fP\ \fIN\fP\|]
+[\|\fB\-Q\fP\ \fIN\fP\|]
+[\|\fB\-R\fP\ \fIN\fP\|]
+[\|\fB\-S\fP\ \fIN\fP\|]
+[\|\fB\-T\fP\|]
+[\|\fB\-X\fP\|]
+[\|\fB\-Y\fP\|]
+[\|\fB\-Z\fP\|]
+[\|\fB\-a\fP\ \fItype\fP\|]
+[\|\fB\-b\fP\|]
+[\|\fB\-c\fP\|]
+[\|\fB\-e\fP\|]
+[\|\fB\-i\fP\ \fIfilename\fP\|]
+[\|\fB\-k\fP\|]
+[\|\fB\-l\fP\|]
+[\|\fB\-o\fP\ \fIfilename\fP\|]
+[\|\fB\-p\fP\ \fIpath\fP\|]
+[\|\fB\-r\fP\|]
+[\|\fB\-u\fP\|]
+[\|\fB\-v\fP\ \fIN\fP\|]
+[\|\fB\-x\fP\ \fIstr\fP\|]
+.SH DESCRIPTION
+\fBasnval\fP is a command-line tool to validate ASN.1-format
+biological sequence records.
+.SH OPTIONS
+A summary of options is included below.
+.TP
+\fB\-\fP
+Print usage message
+.TP
+\fB\-A\fP
+Validate Alignments
+.TP
+\fB\-C\fP\ \fIN\fP
+Max count
+.TP
+\fB\-E\fP\ \fIstr\fP
+Only Error Code to Show
+.TP
+\fB\-G\fP
+GI lookup from accession
+.TP
+\fB\-J\fP
+Require ISO-JTA?
+.TP
+\fB\-L\fP\ \fIfilename\fP
+Log File
+.TP
+\fB\-M\fP
+Match locus_tag against General ID
+.TP
+\fB\-P\fP\ \fIN\fP
+Highest severity for error to show:
+.RS
+.PD 0
+.IP 0
+none
+.IP 1
+informational
+.IP 2
+warning
+.IP 3
+error (default for \fB-Q\fP)
+.IP 4
+grounds for rejection (default for \fB-P\fP, \fB-R\fP)
+.PD
+.RE
+.TP
+\fB\-Q\fP\ \fIN\fP
+Lowest severity for error to show, per \fBP\fP
+.TP
+\fB\-R\fP\ \fIN\fP
+Severity for error in return code, per \fBP\fP
+.TP
+\fB\-S\fP\ \fIN\fP
+Skip count
+.TP
+\fB\-T\fP
+Use Threads
+.TP
+\fB\-X\fP
+Exon splice check
+.TP
+\fB\-Y\fP
+Check against old IDs
+.TP
+\fB\-Z\fP
+Remote CDS product fetch
+.TP
+\fB\-a\fP\ \fItype\fP
+Input ASN.1 type:
+.RS
+.PD 0
+.IP a
+Any (autodetected; default)
+.IP e
+seq-Entry
+.IP b
+Bioseq
+.IP s
+bioseq-Set
+.IP m
+seq-subMit
+.IP t
+baTch bioseq-set
+.IP u
+batch seq-sUbmit
+.PD
+.RE
+.TP
+\fB\-b\fP
+Batch file is Binary
+.TP
+\fB\-c\fP
+Batch file is Compressed
+.TP
+\fB\-e\fP
+Ignore transcription/translation Exceptions
+.TP
+\fB\-i\fP\ \fIfilename\fP
+Single input file (standard input by default)
+.TP
+\fB\-k\fP
+Local fetching
+.TP
+\fB\-l\fP
+Lock components in advance
+.TP
+\fB\-o\fP\ \fIfilename\fP
+Single output file
+.TP
+\fB\-p\fP\ \fIpath\fP
+Path to ASN.1 Files [String]
+.TP
+\fB\-r\fP
+Remote Fetching from ID
+.TP
+\fB\-u\fP
+Recurse
+.TP
+\fB\-v\fP\ \fIN\fP
+Verbosity, from 0 (default) to 3
+.TP
+\fB\-x\fP\ \fIstr\fP
+File selection substring (\fB.ent\fP by default)
+.SH AUTHOR
+The National Center for Biotechnology Information.
+.SH SEE ALSO
+.BR cleanasn (1),
+.BR sequin (1).
--- ncbi-tools6-6.1.20061015.orig/doc/man/idfetch.1
+++ ncbi-tools6-6.1.20061015/doc/man/idfetch.1
@@ -1,9 +1,10 @@
-.TH IDFETCH 1 2001-10-05 NCBI "NCBI Tools User's Manual"
+.TH IDFETCH 1 2006-10-20 NCBI "NCBI Tools User's Manual"
 .SH NAME
 idfetch \- retrieve biological data from the NCBI ID1 server
 .SH SYNOPSIS
 .B idfetch
 [\|\fB\-\fP\|]
+[\|\fB\-F\fP\ \fIstr\fP\|]
 [\|\fB\-G\fP\ \fIfilename\fP\|]
 [\|\fB\-Q\fP\ \fIfilename\fP\|]
 [\|\fB\-c\fP\ \fIN\fP\|]
@@ -27,6 +28,10 @@
 \fB\-\fP
 Print usage message
 .TP
+\fB\-F\fP\ \fIstr\fP
+Add the specified feature types (comma-delimited); allowed values are
+CDD, SNP, SNP_graph, MGC, HPRD, STS, tRNA, and microRNA.
+.TP
 \fB\-G\fP\ \fIfilename\fP
 File with list of GIs, (versioned) accessions, FASTA SeqID's to dump
 .TP
--- ncbi-tools6-6.1.20061015.orig/doc/man/asn2xml.1
+++ ncbi-tools6-6.1.20061015/doc/man/asn2xml.1
@@ -1,4 +1,4 @@
-.TH ASN2XML 1 2003-07-12 NCBI "NCBI Tools User's Manual"
+.TH ASN2XML 1 2005-05-16 NCBI "NCBI Tools User's Manual"
 .SH NAME
 asn2xml \- translate biological data from ASN.1 to XML
 .SH SYNOPSIS
@@ -42,9 +42,12 @@
 The National Center for Biotechnology Information.
 .SH SEE ALSO
 .ad l
+.BR asn2all (1),
 .BR asn2asn (1),
 .BR asn2ff (1),
+.BR asn2fsa (1),
 .BR asn2gb (1),
 .BR asndhuff (1),
+.BR gene2xml (1),
 README.asn2xml,
 ncbixml.txt