# Spike mutations from hodcroftlab and Wikipeda # January 2020, Kate # RM #26782 cd /hive/data/genomes/wuhCor1/bed/spikeMuts # Manually screenscrape from these URL' # Compute chromStart # 14 total foreach m (222 477 501 69 439 453 98 484 80 626 112 701 681 614) @ start = ( ($m * 3) + 21559) @ end = ( $start + 3 ) echo "$m $start $end" end 222 22225 22228 477 22990 22993 501 23062 23065 69 21766 21769 439 22876 22879 453 22918 22921 98 21853 21856 484 23011 23014 80 21799 21802 626 23437 23440 112 21895 21898 701 23662 23665 681 23602 23605 614 23401 23404 # download spreadsheet to spikeMuts.tsv and make into BED 4+6 dos2unix spikeMuts.tab # edit to populate N501S and N501T (using N501Y) chrom, start, end, name with extra fields: source, clinicalNotes, geographyNotes, geographyChartsUrl, nextstrainBuildUrl, publicationsUrls # strip first line awk -F"\t" '{OFS="\t"; print "NC_045512v2", $3, $3 + 3, $1, $2, $5, $4, $8, $7, $6}' spikeMuts.tab > spikeMuts.bed # correct H69- chromEnd (add 3) bedSort spikeMuts.bed spikeMuts.sorted.bed bedToBigBed -tab -type=bed4+5 -as=spikeMuts.as spikeMuts.sorted.bed ../../chrom.sizes spikeMuts.bb mkdir /gbdb/wuhCor1/spikeMuts ln -s `pwd`/spikeMuts.bb /gbdb/wuhCor1/spikeMuts/spikeMuts.bb ##### add first detection date (outside China) from hodcroftlab, wikipedia, the web. Assign # colors: blue for old (Jan-June 2020), red for new (fall/winter 2020-2021) and purple for between (summer 2020) # create BED 9+7, with extra fields: # seqDate, source, clinicalNotes, geographyNotes, geographyChartsUrl, nextstrainBuildUrl, publicationsUrls awk -F"\t" '{OFS="\t"; print $3, $4, $5, $6, "0", ".", $4, $5, $1, $2, $7, $8, $9, $10, $11, $12}' spikeMuts.new.tab > spikeMuts.bed bedSort spikeMuts.bed spikeMuts.sorted.bed bedToBigBed -tab -type=bed9+7 -as=spikeMuts.as spikeMuts.sorted.bed ../../chrom.sizes spikeMuts.bb bedToBigBed -extraIndex=name -tab -type=bed9+7 -as=spikeMuts.as spikeMuts.sorted.bed ../../chrom.sizes spikeMuts.bb # create trix file for searches on variations of mutation name awk '{print $4}' spikeMuts.bed > spikeMutsSearch.txt # NOTE: adding original name to aliases list # edit to add aliases ixIxx spikeMutsSearch.txt spikeMutsSearch.ix spikeMutsSearch.ixx ln -s `pwd`/spikeMutsSearch.ix /gbdb/wuhCor1/spikeMuts ln -s `pwd`/spikeMutsSearch.ixx /gbdb/wuhCor1/spikeMuts ################################################################ # February update (kate) # Update to include: # 1. New mutations at Hodcroft site # 2 Mutations in VOC track # Change color scheme (by 'danger') # Add mut nicknames # Edit spikeMuts.bed file cd /hive/data/genomes/wuhCor1/bed/spikeMuts mkdir feb21 cd feb21 cp ../spikeMuts.bed . wc -l spikeMuts.bed # 14 spikeMuts.bed # New from covariants.org: L452R chromStart = (452 * 3) + 21559 = 22915 chromEnd = 22918 CLinical notes: In a study co-incubating psueotyped virus with SARS-CoV-2 spike proteins and monocolonal antibodies, viruses with S:L452R mutations escaped neutralization by monoclonal antibodies SARS2-01, SARS-02, and SARS2-32 and some convalescent sera. Additionally, this study found modest increase in infectivity as measured by soluble mACE2 Geographic notes: First sequenced in the US. On January 17, the California Dept. of Public Health announced that an L452R variant is increasingly being identified by viral genomic sequencing in multiple counties across the state. Link to charts: https://github.com/hodcroftlab/covariants/blob/master/cluster_tables/S.L452R_table.md Nextstrain link: https://nextstrain.org/groups/neherlab/ncov/S.L452R Refs: https://www.biorxiv.org/content/10.1101/2020.11.06.372037v1 https://www.medrxiv.org/content/10.1101/2021.01.18.21249786v1 bedSort spikeMuts.bed spikeMuts.sorted.bed bedToBigBed -extraIndex=name -tab -type=bed9+7 -as=../spikeMuts.as spikeMuts.sorted.bed \ ../../../chrom.sizes spikeMuts.Feb21.bb #ln -s `pwd`/spikeMuts.Feb21.bb /gbdb/wuhCor1/spikeMuts # edit to recolor: red for RBD colocated, with overlap to Bloom antibody escape, # purple for RBD alone, blue for outside RBD mv spikeMuts.Feb21.bb spikeMuts.Feb21.colorByDate.bb bedToBigBed -extraIndex=name -tab -type=bed9+7 -as=../spikeMuts.as spikeMuts.danger.sorted.bed \ ../../../chrom.sizes spikeMuts.Feb21.colorByDanger.bb rm /gbdb/wuhCor1/spikeMuts/spikeMuts.Feb21.bb ln -s spikeMuts.Feb21.colorByDanger.bb spikeMuts.Feb21.bb ln -s `pwd`/spikeMuts.Feb21.bb /gbdb/wuhCor1/spikeMuts Mutation nicknames https://twitter.com/andrewjpage/status/1360152742707265540 D614G (Doug) D614N (Dan) E484K (Eeek) F888L (Fidel) N501Y (Nelly) P681H (Pooh) N439K (Nick), K417N (Karen), L18F (Leif) B.1.1.7 + E484K (Bleek) cp ../spikeMutsSearch.txt . # edit to add L425R entry, and nicknames (Doug, Eeek, Nelly, Pooh,Nick ixIxx spikeMutsSearch.txt spikeMutsSearch.ix spikeMutsSearch.ixx ln -s `pwd`/spikeMutsSearch.ix /gbdb/wuhCor1/spikeMuts/spikeMutsSearch.Feb21.ix ln -s `pwd`/spikeMutsSearch.ixx /gbdb/wuhCor1/spikeMuts/spikeMutsSearch.Feb21.ixx # Moving older version to archive dir # Find older version on download server: http://hgdownload.soe.ucsc.edu/gbdb/wuhCor1/spikeMuts/ # Files are .bb, .ix and .ixx # Just save .bb cd /data/apache/htdocs-hgdownload/goldenPath/archive mkdir -p wuhCor1/2020-01-12 cd wuhCor1/2020-01-12 ln -s /hive/data/gbdb/wuhCor1/spikeMuts/spikeMuts.bb . ln -s /hive/data/gbdb/wuhCor1/spikeMuts/spikeMutsSearch.ix . ln -s /hive/data/gbdb/wuhCor1/spikeMuts/spikeMutsSearch.ixx . # roll back trackDb to get older version for download # dump to downloads file hgsql wuhCor1 -e "select * from trackDb_kate where tableName='spikeMuts'" > spikeMuts.trackDb.tab gzip spikeMuts.trackDb.tab #################### # Fix typo in L452R (L453R) (2021-03-10 kate) # edit manually vim spikeMuts.danger.sorted.bed bedToBigBed -extraIndex=name -tab -type=bed9+7 -as=../spikeMuts.as spikeMuts.danger.sorted.bed \ ../../../chrom.sizes spikeMuts.Feb21.colorByDanger.bb