synchronized with minion

.hgignore → .gitignore

@@ -6,8 +6,9 @@ syntax: glob
 *.pyo
 *.sqlite3
 *~
-201?/*
+20??/*
 cleanup.log
 hardlink.log
 latest
 tmp
+wget-log

sources

@@ -1,3 +1,6 @@
+## 2020-02-01: NCBI moved "old" refseq to genomes/archive/old_refseq/
+## see ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/00__README_archiving_notice.txt
+
 gene/DATA/GENE_INFO/Mammalia/Homo_sapiens.gene_info.gz
 gene/DATA/gene2accession.gz
 gene/DATA/gene2refseq.gz
@@ -7,13 +10,14 @@ gene/GeneRIF/interactions.gz
 gene/README
 
 genomes/all/GCF/000/001/405/*/*assembly_report.txt
-genomes/H_sapiens/CHR_*/hs*.fa.gz
-genomes/H_sapiens/protein/protein.fa.gz
 
-pub/clinvar/xml/
-pub/clinvar/xml/_README
-pub/clinvar/vcf_GRCh37/clinvar*
-pub/clinvar/vcf_GRCh38/clinvar*
+# fasta assembly with latest patches of build 38:
+genomes/refseq/vertebrate_mammalian/Homo_sapiens/annotation_releases/current/GCF_000001405.*_GRCh38.p13/GCF_000001405.*_GRCh38.p13_genomic.fna.gz
+
+# fasta assembly of build 37, which was archived in Feb 2020
+# see: https://ftp.ncbi.nlm.nih.gov/genomes/archive/old_refseq/Homo_sapiens/00__README_archiving_notice.txt
+genomes/archive/old_refseq/Homo_sapiens/ARCHIVE/BUILD.37.3/CHR_*/hs*.fa.gz
+genomes/archive/old_refseq/Homo_sapiens/ARCHIVE/BUILD.37.3/protein/protein.fa.gz
 
 refseq/H_sapiens/README
 refseq/H_sapiens/RefSeqGene/*.gz
@@ -22,9 +26,20 @@ refseq/H_sapiens/RefSeqGene/gene_RefSeqGene
 refseq/H_sapiens/alignments
 refseq/H_sapiens/mRNA_Prot
 
-snp/organisms/human_9606/VCF/All*.vcf*
-snp/organisms/human_9606/XML/*xml.gz
-snp/organisms/human_9606_b147_GRCh37p13/VCF/All*.vcf*
-snp/organisms/human_9606_b147_GRCh37p13/XML/*xml.gz
-snp/organisms/human_9606_b147_GRCh38p2/VCF/All*.vcf*
-snp/organisms/human_9606_b147_GRCh38p2/XML/*xml.gz
+
+#pub/clinvar/xml/
+#pub/clinvar/xml/_README
+#pub/clinvar/vcf_GRCh37/clinvar*
+#pub/clinvar/vcf_GRCh38/clinvar*
+
+## 2020-02-01: NCBI moved "old" refseq to genomes/archive/old_refseq/
+## see ftp://ftp.ncbi.nlm.nih.gov/genomes/H_sapiens/00__README_archiving_notice.txt
+# genomes/H_sapiens/CHR_*/hs*.fa.gz
+# genomes/H_sapiens/protein/protein.fa.gz
+
+#snp/organisms/human_9606/VCF/All*.vcf*
+#snp/organisms/human_9606/XML/*xml.gz
+#snp/organisms/human_9606_b147_GRCh37p13/VCF/All*.vcf*
+#snp/organisms/human_9606_b147_GRCh37p13/XML/*xml.gz
+#snp/organisms/human_9606_b147_GRCh38p2/VCF/All*.vcf*
+#snp/organisms/human_9606_b147_GRCh38p2/XML/*xml.gz