HOME  ›   release notes
If your question is not answered here, please email us at:  ${email.software}

Cell Ranger


Loupe

10x Genomics
Single Cell Gene Expression

Build Notes for Reference Packages

10x Genomics offers pre-built Cell Ranger reference packages from the downloads page. For purposes of reproducibility, the exact build steps are provided here.

References - 2020-A (July 7, 2020)

References - 3.1.0 (July 24, 2019)

References - 3.0.0 (November 19, 2018)

References - 2.1.0 (February 7, 2018)

References - 1.2.0 (November 16, 2016)


References - 2020-A (July 8, 2020)

# Genome metadata
genome="GRCh38"
version="2020-A"

# Set up source and build directories build="GRCh38-2020-A_build" mkdir -p "$build"
# Download source files if they do not exist in reference_sources/ folder source="reference_sources" mkdir -p "$source"
fasta_url="http://ftp.ensembl.org/pub/release-98/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz" fasta_in="${source}/Homo_sapiens.GRCh38.dna.primary_assembly.fa" gtf_url="http://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_32/gencode.v32.primary_assembly.annotation.gtf.gz" gtf_in="${source}/gencode.v32.primary_assembly.annotation.gtf"
if [ ! -f "$fasta_in" ]; then curl -sS "$fasta_url" | zcat > "$fasta_in" fi if [ ! -f "$gtf_in" ]; then curl -sS "$gtf_url" | zcat > "$gtf_in" fi
# Modify sequence headers in the Ensembl FASTA to match the file # "GRCh38.primary_assembly.genome.fa" from GENCODE. Unplaced and unlocalized # sequences such as "KI270728.1" have the same names in both versions. # # Input FASTA: # >1 dna:chromosome chromosome:GRCh38:1:1:248956422:1 REF # # Output FASTA: # >chr1 1 fasta_modified="$build/$(basename "$fasta_in").modified" # sed commands: # 1. Replace metadata after space with original contig name, as in GENCODE # 2. Add "chr" to names of autosomes and sex chromosomes # 3. Handle the mitochrondrial chromosome cat "$fasta_in" \ | sed -E 's/^>(\S+).*/>\1 \1/' \ | sed -E 's/^>([0-9]+|[XY]) />chr\1 /' \ | sed -E 's/^>MT />chrM /' \ > "$fasta_modified"
# Remove version suffix from transcript, gene, and exon IDs in order to match # previous Cell Ranger reference packages # # Input GTF: # ... gene_id "ENSG00000223972.5"; ... # Output GTF: # ... gene_id "ENSG00000223972"; gene_version "5"; ... gtf_modified="$build/$(basename "$gtf_in").modified" # Pattern matches Ensembl gene, transcript, and exon IDs for human or mouse: ID="(ENS(MUS)?[GTE][0-9]+)\.([0-9]+)" cat "$gtf_in" \ | sed -E 's/gene_id "'"$ID"'";/gene_id "\1"; gene_version "\3";/' \ | sed -E 's/transcript_id "'"$ID"'";/transcript_id "\1"; transcript_version "\3";/' \ | sed -E 's/exon_id "'"$ID"'";/exon_id "\1"; exon_version "\3";/' \ > "$gtf_modified"
# Define string patterns for GTF tags # NOTES: # - Since GENCODE release 31/M22 (Ensembl 97), the "lincRNA" and "antisense" # biotypes are part of a more generic "lncRNA" biotype. # - These filters are relevant only to GTF files from GENCODE. The GTFs from # Ensembl release 98 have the following differences: # - The names "gene_biotype" and "transcript_biotype" are used instead of # "gene_type" and "transcript_type". # - Readthrough transcripts are present but are not marked with the # "readthrough_transcript" tag. # - Only the X chromosome versions of genes in the pseudoautosomal regions # are present, so there is no "PAR" tag. BIOTYPE_PATTERN=\ "(protein_coding|lncRNA|\ IG_C_gene|IG_D_gene|IG_J_gene|IG_LV_gene|IG_V_gene|\ IG_V_pseudogene|IG_J_pseudogene|IG_C_pseudogene|\ TR_C_gene|TR_D_gene|TR_J_gene|TR_V_gene|\ TR_V_pseudogene|TR_J_pseudogene)" GENE_PATTERN="gene_type \"${BIOTYPE_PATTERN}\"" TX_PATTERN="transcript_type \"${BIOTYPE_PATTERN}\"" READTHROUGH_PATTERN="tag \"readthrough_transcript\"" PAR_PATTERN="tag \"PAR\""
# Construct the gene ID allowlist. We filter the list of all transcripts # based on these criteria: # - allowable gene_type (biotype) # - allowable transcript_type (biotype) # - no "PAR" tag (only present for Y chromosome PAR) # - no "readthrough_transcript" tag # We then collect the list of gene IDs that have at least one associated # transcript passing the filters. cat "$gtf_modified" \ | awk '$3 == "transcript"' \ | grep -E "$GENE_PATTERN" \ | grep -E "$TX_PATTERN" \ | grep -Ev "$READTHROUGH_PATTERN" \ | grep -Ev "$PAR_PATTERN" \ | sed -E 's/.*(gene_id "[^"]+").*/\1/' \ | sort \ | uniq \ > "${build}/gene_allowlist"
# Filter the GTF file based on the gene allowlist gtf_filtered="${build}/$(basename "$gtf_in").filtered" # Copy header lines beginning with "#" grep -E "^#" "$gtf_modified" > "$gtf_filtered" # Filter to the gene allowlist grep -Ff "${build}/gene_allowlist" "$gtf_modified" \ >> "$gtf_filtered"
# Create reference package cellranger mkref --ref-version="$version" \ --genome="$genome" --fasta="$fasta_modified" --genes="$gtf_filtered"

# Genome metadata
genome="mm10"
version="2020-A"

# Set up source and build directories build="mm10-2020-A_build" mkdir -p "$build"
# Download source files if they do not exist in reference_sources/ folder source="reference_sources" mkdir -p "$source"
fasta_url="http://ftp.ensembl.org/pub/release-98/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz" fasta_in="${source}/Mus_musculus.GRCm38.dna.primary_assembly.fa" gtf_url="http://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_mouse/release_M23/gencode.vM23.primary_assembly.annotation.gtf.gz" gtf_in="${source}/gencode.vM23.primary_assembly.annotation.gtf"
if [ ! -f "$fasta_in" ]; then curl -sS "$fasta_url" | zcat > "$fasta_in" fi if [ ! -f "$gtf_in" ]; then curl -sS "$gtf_url" | zcat > "$gtf_in" fi
# Modify sequence headers in the Ensembl FASTA to match the file # "GRCm38.primary_assembly.genome.fa" from GENCODE. Unplaced and unlocalized # sequences such as "GL456210.1" have the same names in both versions. # # Input FASTA: # >1 dna:chromosome chromosome:GRCm38:1:1:195471971:1 REF # # Output FASTA: # >chr1 1 fasta_modified="$build/$(basename "$fasta_in").modified" # sed commands: # 1. Replace metadata after space with original contig name, as in GENCODE # 2. Add "chr" to names of autosomes and sex chromosomes # 3. Handle the mitochrondrial chromosome cat "$fasta_in" \ | sed -E 's/^>(\S+).*/>\1 \1/' \ | sed -E 's/^>([0-9]+|[XY]) />chr\1 /' \ | sed -E 's/^>MT />chrM /' \ > "$fasta_modified"
# Remove version suffix from transcript, gene, and exon IDs in order to match # previous Cell Ranger reference packages # # Input GTF: # ... gene_id "ENSMUSG00000102693.1"; ... # Output GTF: # ... gene_id "ENSMUSG00000102693"; gene_version "1"; ... gtf_modified="$build/$(basename "$gtf_in").modified" # Pattern matches Ensembl gene, transcript, and exon IDs for human or mouse: ID="(ENS(MUS)?[GTE][0-9]+)\.([0-9]+)" cat "$gtf_in" \ | sed -E 's/gene_id "'"$ID"'";/gene_id "\1"; gene_version "\3";/' \ | sed -E 's/transcript_id "'"$ID"'";/transcript_id "\1"; transcript_version "\3";/' \ | sed -E 's/exon_id "'"$ID"'";/exon_id "\1"; exon_version "\3";/' \ > "$gtf_modified"
# Define string patterns for GTF tags # NOTES: # - Since GENCODE release 31/M22 (Ensembl 97), the "lincRNA" and "antisense" # biotypes are part of a more generic "lncRNA" biotype. # - These filters are relevant only to GTF files from GENCODE. The GTFs from # Ensembl release 98 have the following differences: # - The names "gene_biotype" and "transcript_biotype" are used instead of # "gene_type" and "transcript_type". # - Readthrough transcripts are present but are not marked with the # "readthrough_transcript" tag. BIOTYPE_PATTERN=\ "(protein_coding|lncRNA|\ IG_C_gene|IG_D_gene|IG_J_gene|IG_LV_gene|IG_V_gene|\ IG_V_pseudogene|IG_J_pseudogene|IG_C_pseudogene|\ TR_C_gene|TR_D_gene|TR_J_gene|TR_V_gene|\ TR_V_pseudogene|TR_J_pseudogene)" GENE_PATTERN="gene_type \"${BIOTYPE_PATTERN}\"" TX_PATTERN="transcript_type \"${BIOTYPE_PATTERN}\"" READTHROUGH_PATTERN="tag \"readthrough_transcript\""
# Construct the gene ID allowlist. We filter the list of all transcripts # based on these criteria: # - allowable gene_type (biotype) # - allowable transcript_type (biotype) # - no "readthrough_transcript" tag # We then collect the list of gene IDs that have at least one associated # transcript passing the filters. cat "$gtf_modified" \ | awk '$3 == "transcript"' \ | grep -E "$GENE_PATTERN" \ | grep -E "$TX_PATTERN" \ | grep -Ev "$READTHROUGH_PATTERN" \ | sed -E 's/.*(gene_id "[^"]+").*/\1/' \ | sort \ | uniq \ > "${build}/gene_allowlist"
# Filter the GTF file based on the gene allowlist gtf_filtered="${build}/$(basename "$gtf_in").filtered" # Copy header lines beginning with "#" grep -E "^#" "$gtf_modified" > "$gtf_filtered" # Filter to the gene allowlist grep -Ff "${build}/gene_allowlist" "$gtf_modified" \ >> "$gtf_filtered"
# Create reference package cellranger mkref --ref-version="$version" \ --genome="$genome" --fasta="$fasta_modified" --genes="$gtf_filtered"

#################### SETUP ####################

human_genome="GRCh38" mouse_genome="mm10" version="2020-A"
build="GRCh38_and_mm10-2020-A_build" mkdir -p "$build"
# Download source files if they do not exist in reference_sources/ folder source="reference_sources" mkdir -p "$source"
human_fasta_url="http://ftp.ensembl.org/pub/release-98/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz" human_fasta_in="${source}/Homo_sapiens.GRCh38.dna.primary_assembly.fa" human_gtf_url="http://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_32/gencode.v32.primary_assembly.annotation.gtf.gz" human_gtf_in="${source}/gencode.v32.primary_assembly.annotation.gtf" mouse_fasta_url="http://ftp.ensembl.org/pub/release-98/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz" mouse_fasta_in="${source}/Mus_musculus.GRCm38.dna.primary_assembly.fa" mouse_gtf_url="http://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_mouse/release_M23/gencode.vM23.primary_assembly.annotation.gtf.gz" mouse_gtf_in="${source}/gencode.vM23.primary_assembly.annotation.gtf"
if [ ! -f "$human_fasta_in" ]; then curl -sS "$human_fasta_url" | zcat > "$human_fasta_in" fi if [ ! -f "$human_gtf_in" ]; then curl -sS "$human_gtf_url" | zcat > "$human_gtf_in" fi if [ ! -f "$mouse_fasta_in" ]; then curl -sS "$mouse_fasta_url" | zcat > "$mouse_fasta_in" fi if [ ! -f "$mouse_gtf_in" ]; then curl -sS "$mouse_gtf_url" | zcat > "$mouse_gtf_in" fi
# String patterns used for both genomes ID="(ENS(MUS)?[GTE][0-9]+)\.([0-9]+)"
BIOTYPE_PATTERN=\ "(protein_coding|lncRNA|\ IG_C_gene|IG_D_gene|IG_J_gene|IG_LV_gene|IG_V_gene|\ IG_V_pseudogene|IG_J_pseudogene|IG_C_pseudogene|\ TR_C_gene|TR_D_gene|TR_J_gene|TR_V_gene|\ TR_V_pseudogene|TR_J_pseudogene)" GENE_PATTERN="gene_type \"${BIOTYPE_PATTERN}\"" TX_PATTERN="transcript_type \"${BIOTYPE_PATTERN}\"" READTHROUGH_PATTERN="tag \"readthrough_transcript\"" PAR_PATTERN="tag \"PAR\""
#################### HUMAN #################### # Please see the GRCh38-2020-A build documentation for details on these steps.
# Process FASTA -- translate chromosome names human_fasta_modified="$build/$(basename "$human_fasta_in").modified" cat "$human_fasta_in" \ | sed -E 's/^>(\S+).*/>\1 \1/' \ | sed -E 's/^>([0-9]+|[XY]) />chr\1 /' \ | sed -E 's/^>MT />chrM /' \ > "$human_fasta_modified"
# Process GTF -- split Ensembl IDs from version suffixes human_gtf_modified="$build/$(basename "$human_gtf_in").modified" cat "$human_gtf_in" \ | sed -E 's/gene_id "'"$ID"'";/gene_id "\1"; gene_version "\3";/' \ | sed -E 's/transcript_id "'"$ID"'";/transcript_id "\1"; transcript_version "\3";/' \ | sed -E 's/exon_id "'"$ID"'";/exon_id "\1"; exon_version "\3";/' \ > "$human_gtf_modified"
# Process GTF -- filter based on gene/transcript tags cat "$human_gtf_modified" \ | awk '$3 == "transcript"' \ | grep -E "$GENE_PATTERN" \ | grep -E "$TX_PATTERN" \ | grep -Ev "$READTHROUGH_PATTERN" \ | grep -Ev "$PAR_PATTERN" \ | sed -E 's/.*(gene_id "[^"]+").*/\1/' \ | sort \ | uniq \ > "${build}/gene_allowlist"
human_gtf_filtered="${build}/$(basename "$human_gtf_in").filtered" grep -E "^#" "$human_gtf_modified" > "$human_gtf_filtered" grep -Ff "${build}/gene_allowlist" "$human_gtf_modified" \ >> "$human_gtf_filtered"
#################### MOUSE #################### # Please see the mm10-2020-A build documentation for details on these steps.
# Process FASTA -- translate chromosome names mouse_fasta_modified="$build/$(basename "$mouse_fasta_in").modified" cat "$mouse_fasta_in" \ | sed -E 's/^>(\S+).*/>\1 \1/' \ | sed -E 's/^>([0-9]+|[XY]) />chr\1 /' \ | sed -E 's/^>MT />chrM /' \ > "$mouse_fasta_modified"
# Process GTF -- split Ensembl IDs from version suffixes mouse_gtf_modified="$build/$(basename "$mouse_gtf_in").modified" cat "$mouse_gtf_in" \ | sed -E 's/gene_id "'"$ID"'";/gene_id "\1"; gene_version "\3";/' \ | sed -E 's/transcript_id "'"$ID"'";/transcript_id "\1"; transcript_version "\3";/' \ | sed -E 's/exon_id "'"$ID"'";/exon_id "\1"; exon_version "\3";/' \ > "$mouse_gtf_modified"
# Process GTF -- filter based on gene/transcript tags cat "$mouse_gtf_modified" \ | awk '$3 == "transcript"' \ | grep -E "$GENE_PATTERN" \ | grep -E "$TX_PATTERN" \ | grep -Ev "$READTHROUGH_PATTERN" \ | sed -E 's/.*(gene_id "[^"]+").*/\1/' \ | sort \ | uniq \ > "${build}/gene_allowlist"
mouse_gtf_filtered="${build}/$(basename "$mouse_gtf_in").filtered" grep -E "^#" "$mouse_gtf_modified" > "$mouse_gtf_filtered" grep -Ff "${build}/gene_allowlist" "$mouse_gtf_modified" \ >> "$mouse_gtf_filtered"
#################### MKREF ####################
cellranger mkref --ref-version="$version" \ --genome="$human_genome" --fasta="$human_fasta_modified" --genes="$human_gtf_filtered" \ --genome="$mouse_genome" --fasta="$mouse_fasta_modified" --genes="$mouse_gtf_filtered"

References - 3.1.0 (July 24, 2019)

wget ftp://ftp.ensembl.org/pub/release-93/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/release-93/gtf/homo_sapiens/Homo_sapiens.GRCh38.93.gtf.gz gunzip Homo_sapiens.GRCh38.93.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
wget ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz gunzip Mus_musculus.GRCm38.93.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh38.93.gtf Homo_sapiens.GRCh38.93.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkgtf Mus_musculus.GRCm38.93.gtf Mus_musculus.GRCm38.93.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=GRCh38 \ --fasta=Homo_sapiens.GRCh38.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh38.93.filtered.gtf \ --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.93.filtered.gtf \ --ref-version=3.1.0

References - 3.0.0 (November 19, 2018)

wget ftp://ftp.ensembl.org/pub/release-93/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/release-93/gtf/homo_sapiens/Homo_sapiens.GRCh38.93.gtf.gz gunzip Homo_sapiens.GRCh38.93.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh38.93.gtf Homo_sapiens.GRCh38.93.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=GRCh38 \ --fasta=Homo_sapiens.GRCh38.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh38.93.filtered.gtf \ --ref-version=3.0.0

wget ftp://ftp.ensembl.org/pub/grch37/release-87/fasta/homo_sapiens/dna/Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/grch37/release-87/gtf/homo_sapiens/Homo_sapiens.GRCh37.87.gtf.gz gunzip Homo_sapiens.GRCh37.87.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh37.87.gtf Homo_sapiens.GRCh37.87.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense
cellranger mkref --genome=hg19 \ --fasta=Homo_sapiens.GRCh37.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh37.87.filtered.gtf \ --ref-version=3.0.0

wget ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz gunzip Mus_musculus.GRCm38.93.gtf.gz
cellranger mkgtf Mus_musculus.GRCm38.93.gtf Mus_musculus.GRCm38.93.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.93.filtered.gtf \ --ref-version=3.0.0

wget ftp://ftp.ensembl.org/pub/grch37/release-87/fasta/homo_sapiens/dna/Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/grch37/release-87/gtf/homo_sapiens/Homo_sapiens.GRCh37.87.gtf.gz gunzip Homo_sapiens.GRCh37.87.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-93/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
wget ftp://ftp.ensembl.org/pub/release-93/gtf/mus_musculus/Mus_musculus.GRCm38.93.gtf.gz gunzip Mus_musculus.GRCm38.93.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh37.87.gtf Homo_sapiens.GRCh37.87.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkgtf Mus_musculus.GRCm38.93.gtf Mus_musculus.GRCm38.93.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=hg19 \ --fasta=Homo_sapiens.GRCh37.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh37.87.filtered.gtf \ --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.93.filtered.gtf \ --ref-version=3.0.0

References - 2.1.0 (February 7, 2018)

wget ftp://ftp.ensembl.org/pub/release-84/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/release-84/gtf/mus_musculus/Mus_musculus.GRCm38.84.gtf.gz gunzip Mus_musculus.GRCm38.84.gtf.gz
cellranger mkgtf Mus_musculus.GRCm38.84.gtf Mus_musculus.GRCm38.84.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.84.filtered.gtf \ --ref-version=2.1.0

wget ftp://ftp.ensembl.org/pub/grch37/release-84/fasta/homo_sapiens/dna/Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/grch37/release-84/gtf/homo_sapiens/Homo_sapiens.GRCh37.82.gtf.gz gunzip Homo_sapiens.GRCh37.82.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-84/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
wget ftp://ftp.ensembl.org/pub/release-84/gtf/mus_musculus/Mus_musculus.GRCm38.84.gtf.gz gunzip Mus_musculus.GRCm38.84.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh37.82.gtf Homo_sapiens.GRCh37.82.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkgtf Mus_musculus.GRCm38.84.gtf Mus_musculus.GRCm38.84.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=hg19 \ --fasta=Homo_sapiens.GRCh37.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh37.82.filtered.gtf \ --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.84.filtered.gtf \ --ref-version=2.1.0

References - 1.2.0 (November 16, 2016)

wget ftp://ftp.ensembl.org/pub/release-84/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/release-84/gtf/homo_sapiens/Homo_sapiens.GRCh38.84.gtf.gz gunzip Homo_sapiens.GRCh38.84.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh38.84.gtf Homo_sapiens.GRCh38.84.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense \ --attribute=gene_biotype:IG_LV_gene \ --attribute=gene_biotype:IG_V_gene \ --attribute=gene_biotype:IG_V_pseudogene \ --attribute=gene_biotype:IG_D_gene \ --attribute=gene_biotype:IG_J_gene \ --attribute=gene_biotype:IG_J_pseudogene \ --attribute=gene_biotype:IG_C_gene \ --attribute=gene_biotype:IG_C_pseudogene \ --attribute=gene_biotype:TR_V_gene \ --attribute=gene_biotype:TR_V_pseudogene \ --attribute=gene_biotype:TR_D_gene \ --attribute=gene_biotype:TR_J_gene \ --attribute=gene_biotype:TR_J_pseudogene \ --attribute=gene_biotype:TR_C_gene
cellranger mkref --genome=GRCh38 \ --fasta=Homo_sapiens.GRCh38.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh38.84.filtered.gtf \ --ref-version=1.2.0

wget ftp://ftp.ensembl.org/pub/grch37/release-84/fasta/homo_sapiens/dna/Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/grch37/release-84/gtf/homo_sapiens/Homo_sapiens.GRCh37.82.gtf.gz gunzip Homo_sapiens.GRCh37.82.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh37.82.gtf Homo_sapiens.GRCh37.82.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense
cellranger mkref --genome=hg19 \ --fasta=Homo_sapiens.GRCh37.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh37.82.filtered.gtf \ --ref-version=1.2.0

wget ftp://ftp.ensembl.org/pub/release-84/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/release-84/gtf/mus_musculus/Mus_musculus.GRCm38.84.gtf.gz gunzip Mus_musculus.GRCm38.84.gtf.gz
cellranger mkgtf Mus_musculus.GRCm38.84.gtf Mus_musculus.GRCm38.84.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense
cellranger mkref --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.84.filtered.gtf \ --ref-version=1.2.0

wget ftp://ftp.ensembl.org/pub/grch37/release-84/fasta/homo_sapiens/dna/Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh37.dna.primary_assembly.fa.gz

wget ftp://ftp.ensembl.org/pub/grch37/release-84/gtf/homo_sapiens/Homo_sapiens.GRCh37.82.gtf.gz gunzip Homo_sapiens.GRCh37.82.gtf.gz
wget ftp://ftp.ensembl.org/pub/release-84/fasta/mus_musculus/dna/Mus_musculus.GRCm38.dna.primary_assembly.fa.gz gunzip Mus_musculus.GRCm38.dna.primary_assembly.fa.gz
wget ftp://ftp.ensembl.org/pub/release-84/gtf/mus_musculus/Mus_musculus.GRCm38.84.gtf.gz gunzip Mus_musculus.GRCm38.84.gtf.gz
cellranger mkgtf Homo_sapiens.GRCh37.82.gtf Homo_sapiens.GRCh37.82.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense
cellranger mkgtf Mus_musculus.GRCm38.84.gtf Mus_musculus.GRCm38.84.filtered.gtf \ --attribute=gene_biotype:protein_coding \ --attribute=gene_biotype:lincRNA \ --attribute=gene_biotype:antisense
cellranger mkref --genome=hg19 \ --fasta=Homo_sapiens.GRCh37.dna.primary_assembly.fa \ --genes=Homo_sapiens.GRCh37.82.filtered.gtf \ --genome=mm10 \ --fasta=Mus_musculus.GRCm38.dna.primary_assembly.fa \ --genes=Mus_musculus.GRCm38.84.filtered.gtf \ --ref-version=1.2.0

cellranger mkref --genome=ercc92 \
                 --fasta=ercc92.fa \
                 --genes=ercc92.gtf \
                 --ref-version=1.2.0