data: add microC chr17

R/globals.R

@@ -12,7 +12,8 @@ HiContactsDataFiles <- rbind(
     c('yeast_eco1', 'mcool', 'S288C', 'Eco1-AID+IAA', 'multi-res .mcool file', 'EH7704'),
     c('yeast_eco1', 'pairs.gz', 'S288C', 'Eco1-AID+IAA', 'only pairs from chrII are provided', 'EH7705'),
     c('mESCs', 'mcool', 'mm10', 'mESCs', 'multi-res .mcool file', 'EH7706'),
-    c('mESCs', 'pairs.gz', 'mm10', 'mESCs', 'only pairs from chr13 are provided', 'EH7707')
+    c('mESCs', 'pairs.gz', 'mm10', 'mESCs', 'only pairs from chr13 are provided', 'EH7707'), 
+    c('microC', 'mcool', 'GRCh38', 'HFFc6', 'multi-res .mcool file, only chr17 is provided', '')
 )
 colnames(HiContactsDataFiles) <- c(
     'sample', 'format', 'genome', 'condition', 'notes', 'EHID'

README.md

@@ -28,3 +28,6 @@ Several files are avaible using this function, namely:
 - From [Bonev et al., Cell 2017](https://doi.org/10.1016/j.cell.2017.09.043):
   - mESCs.mcool (`sample`: `mESCs`, `format` = `mcool`)
   - mESCs.pairs.gz for chr13 only (`sample`: `mESCs`, `format` = `pairs`)
+
+- From [Krietenstein et al., Mol. Cell 2020](https://doi.org/10.1016/j.molcel.2020.03.003):
+  - microC_HFFc6_chr17.mcool (`sample`: `microC`, `format` = `mcool`)

inst/extdata/metadata.csv

@@ -13,3 +13,4 @@
 "Eco1-AID yeast .pairs file","Hi-C performed on Eco1-AID mutant yeast strain upon IAA treatment processed with tinyMapper and represented as a filtered pairs file. Data representation derived from SRA run results SRR16250953.",3.16,"S288C","Zip","https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM5918405","Aug 17 2022","Saccharomyces cerevisiae",4932,"FALSE","Jacques Serizay","Jacques Serizay <[email protected]>","character","FilePath","HiContactsData/S288C_Eco1-AID.pairs.gz","HiCData"
 "mESC .mcool contact matrix","Hi-C performed on mouse embryonic stem cells (mESCs) processed with tinyMapper and represented as a multi-resolution mcool file. Data representation derived from SRA run results SRR5339749.",3.16,"mm10","HDF5","https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2533818","Aug 17 2022","Mus musculus",10090,"FALSE","Jacques Serizay","Jacques Serizay <[email protected]>","character","FilePath","HiContactsData/mESCs.mcool","HiCData"
 "mESC .pairs file","Hi-C performed on mouse embryonic stem cells (mESCs) processed with tinyMapper and represented as a filtered pairs file. Data representation derived from SRA run results SRR5339749.",3.16,"mm10","TXT","https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSM2533818","Aug 17 2022","Mus musculus",10090,"FALSE","Jacques Serizay","Jacques Serizay <[email protected]>","character","FilePath","HiContactsData/mESCs.pairs.gz","HiCData"
+"HFFc6 .mcool contact matrix","Hi-C performed on Human foreskin fibroblast cell line (HFFc6). Data obtained from 4DN data portal (ID 4DNFI9FVHJZQ) and filtered to only retain chr17.",3.18,"GRCh38","HDF5","https://data.4dnucleome.org/files-processed/4DNFI9FVHJZQ/","Aug 17 2022","Homo sapiens",9606,"FALSE","Jacques Serizay","Jacques Serizay <[email protected]>","character","FilePath","HiContactsData/microC_HFFc6_chr17.mcool","HiCData"

inst/scripts/make-data.R

@@ -15,7 +15,7 @@
 
 # curl -L ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR533/009/SRR5339749/SRR5339749_1.fastq.gz -o mESCs_R1.fq.gz
 # curl -L ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR533/009/SRR5339749/SRR5339749_2.fastq.gz -o mESC_R2.fq.gz
-# tinyMapper.sh --mode HiC --sample mESCs --genome ~/genomes/mm10/mm10 --output HiC --threads 16 --resolutions 10000,20000,40000,80000,160000,320000,640000,1280000,2560000
+# tinyMapper.sh --mode HiC --sample mESCs --genome ~/genomes/mm10/mm10 --output HiC --threads 16 --resolutions 10000
 
 ### ----------  Subset and compress files
 
@@ -58,3 +58,10 @@
 #    --hicpro_maps \
 #    --max_cpus 18 \
 #    --max_memory '32.GB'
+
+### ----------  Filter microC mcool
+
+# cooler dump -t chroms /.cache/R/fourDNData/4d434d8538a0_4DNFI9FVHJZQ.mcool::/resolutions/250000 | grep -P 'chr17\t' > inst/extdata/chromsizes
+# cooler dump -t pixels -r chr17 --join /.cache/R/fourDNData/4d434d8538a0_4DNFI9FVHJZQ.mcool::/resolutions/5000 > inst/extdata/chr17_5000.bg2
+# cooler cload pairs inst/extdata/chromsizes:5000 inst/extdata/chr17_5000.bg2 -c1 1 -p1 2 -c2 4 -p2 5 -0 inst/extdata/chr17.cool
+# cooler zoomify --resolutions 5000,100000,250000 --balance inst/extdata/chr17.cool -o inst/extdata/chr17.mcool

inst/scripts/make-metadata.R

@@ -237,6 +237,23 @@ toydata <- list(
         DispatchClass = "FilePath",
         RDataPath = "HiContactsData/mESCs.pairs.gz",
         Tags = "HiCData"
+    ), 
+    list(Title = "HFFc6 .mcool contact matrix",
+        Description = "Hi-C performed on Human foreskin fibroblast cell line (HFFc6). Data obtained from 4DN data portal (ID 4DNFI9FVHJZQ) and filtered to only retain chr17.",
+        BiocVersion = "3.16",
+        Genome = "GRCh38",
+        SourceType = "HDF5",
+        SourceUrl = "https://data.4dnucleome.org/files-processed/4DNFI9FVHJZQ/",
+        SourceVersion = "Aug 17 2022",
+        Species = "Homo sapiens",
+        TaxonomyId = "9606",
+        Coordinate_1_based = "FALSE",
+        DataProvider = "Jacques Serizay",
+        Maintainer = "Jacques Serizay <[email protected]>",
+        RDataClass = "character",
+        DispatchClass = "FilePath",
+        RDataPath = "HiContactsData/microC_HFFc6_chr17.mcool",
+        Tags = "HiCData"
     )
 )
 toydata <- do.call(rbind, toydata) |> as.data.frame() |> apply(2, unlist) |> as.data.frame()

vignettes/HiContactsData.Rmd

@@ -45,9 +45,11 @@ Several files are avaible using this function, namely:
 - S288C_Eco1-AID.pairs.gz for chrII only (`sample`: `yeast_Eco1`, `format` = `pairs`)
 - mESCs.mcool (`sample`: `mESCs`, `format` = `mcool`)
 - mESCs.pairs.gz for chr13 only (`sample`: `mESCs`, `format` = `pairs`)
+- microC_HFFc6_chr17.mcool (`sample`: `microC`, `format` = `mcool`)
 
 Yeast data comes from [Bastie, Chapard et al., Nature Structural & Molecular Biology 2022](https://doi.org/10.1038/s41594-022-00780-0) 
-and mouse ESC data comes from [Bonev et al., Cell 2017](https://doi.org/10.1016/j.cell.2017.09.043).
+and mouse ESC data comes from [Bonev et al., Cell 2017](https://doi.org/10.1016/j.cell.2017.09.043). 
+Human HcFF6 micro-C data comes from [Krietenstein et al., Mol. Cell 2020](https://doi.org/10.1016/j.molcel.2020.03.003).
 
 To download one of these files, one can specify a `sample` and a file `format`: