ff57913e526139de4da96e2984cd89f8c15a0df0 hiram Fri Aug 30 15:26:42 2019 -0700 correct biosample URL to NCBI refs #23771 diff --git src/hg/utils/automation/makeDownloads.pl src/hg/utils/automation/makeDownloads.pl index 73a47ba..822293a 100755 --- src/hg/utils/automation/makeDownloads.pl +++ src/hg/utils/automation/makeDownloads.pl @@ -623,30 +623,31 @@ my ($Organism, $assemblyDate, $assemblyLabel, $organism, $consortium, $sequencingCenter, $projectUrl) = &getDescriptives(); my $fh = &HgAutomate::mustOpen(">$runDir/README.database.txt"); print $fh <<_EOF_ This directory contains a dump of the UCSC genome annotation database for the $assemblyDate assembly of the $organism genome ($db, $assemblyLabel) $consortium. The annotations were generated by UCSC and collaborators worldwide. For more information about this assembly, please note the NCBI resources: https://www.ncbi.nlm.nih.gov/genome/$ncbiGenomeId https://www.ncbi.nlm.nih.gov/genome/assembly/$ncbiAssemblyId https://www.ncbi.nlm.nih.gov/bioproject/$ncbiBioProject + https://www.ncbi.nlm.nih.gov/biosample/$ncbiBioSample Files included in this directory (updated nightly): - *.sql files: the MySQL commands used to create the tables - *.txt.gz files: the database tables in a tab-delimited format compressed with gzip. To see descriptions of the tables underlying Genome Browser annotation tracks, select the table in the Table Browser: http://genome.ucsc.edu/cgi-bin/hgTables?db=$db and click the "describe table schema" button. There is also a "view table schema" link on the configuration page for each track. --------------------------------------------------------------- @@ -717,31 +718,31 @@ $emblLib = `head -100 /hive/data/staging/data/RepeatMasker/Libraries/RepeatMaskerLib.embl | grep -w RELEASE`; chomp $emblLib; $emblLib =~ s/CC\s*//; $emblLib =~ s/;\s*.*//; my $fh = &HgAutomate::mustOpen(">$runDir/README.bigZips.txt"); print $fh <<_EOF_ This directory contains the $assemblyDate assembly of the $organism genome ($db, $assemblyLabel), as well as repeat annotations and GenBank sequences. For more information about this assembly, please note the NCBI resources: https://www.ncbi.nlm.nih.gov/genome/$ncbiGenomeId https://www.ncbi.nlm.nih.gov/genome/assembly/$ncbiAssemblyId https://www.ncbi.nlm.nih.gov/bioproject/$ncbiBioProject - https://www.ncbi.nlm.nih.gov/bioproject/$ncbiBioSample + https://www.ncbi.nlm.nih.gov/biosample/$ncbiBioSample Files included in this directory: $db.2bit - contains the complete $organism/$db genome sequence in the 2bit file format. Repeats from RepeatMasker and Tandem Repeats Finder (with period of 12 or less) are shown in lower case; non-repeating sequence is shown in upper case. The utility program, twoBitToFa (available from the kent src tree), can be used to extract .fa file(s) from this file. A pre-compiled version of the command line tool can be found at: http://hgdownload.soe.ucsc.edu/admin/exe/linux.x86_64/ See also: http://genome.ucsc.edu/admin/git.html http://genome.ucsc.edu/admin/jk-install.html @@ -925,31 +926,31 @@ # Dump out a README.txt for chromsomes/ . my ($runDir) = @_; my ($Organism, $assemblyDate, $assemblyLabel, $organism, $consortium, $sequencingCenter, $projectUrl) = &getDescriptives(); my $fh = &HgAutomate::mustOpen(">$runDir/README.chromosomes.txt"); print $fh <<_EOF_ This directory contains the $assemblyDate assembly of the $organism genome ($db, $assemblyLabel) in one gzip-compressed FASTA file per chromosome. For more information about this assembly, please note the NCBI resources: https://www.ncbi.nlm.nih.gov/genome/$ncbiGenomeId https://www.ncbi.nlm.nih.gov/genome/assembly/$ncbiAssemblyId https://www.ncbi.nlm.nih.gov/bioproject/$ncbiBioProject - https://www.ncbi.nlm.nih.gov/bioproject/$ncbiBioSample + https://www.ncbi.nlm.nih.gov/biosample/$ncbiBioSample Repeats from RepeatMasker and Tandem Repeats Finder (with period of 12 or less) are shown in lower case; non-repeating sequence is shown in upper case. This assembly was produced by $sequencingCenter. For more information on the $organism genome, see the project website: $projectUrl Files included in this directory: - chr*.fa.gz: compressed FASTA sequence of each chromosome. _EOF_ ;