wflynny

# Visit the Ensembl ftp site.
# ftp://ftp.ensembl.org/pub/release-95/
#
# You want to find data under the following two URLs:
# 1.  ftp://ftp.ensembl.org/pub/release-95/fasta/[YOUR_SPECIES_HERE]/dna/
# 2.  ftp://ftp.ensembl.org/pub/release-95/gtf/[YOUR_SPECIES_HERE]/
#
# The first file of interest is under the fasta URL:
#     [YOUR_SPECIES_HERE].[ASSEMBLY].dna.primary_assembly.fa.gz
# or, if that doesn't exist,

wflynny

import scanpy.api as sc
import matplotlib.pyplot as plt
import seaborn as sns

def get_cluster_proportions(adata,
                            cluster_key="cluster_final",
                            sample_key="replicate",
                            drop_values=None):
    """
    Input

wflynny

# Find myself referring to this thread a lot:
# https://www.biostars.org/p/198143/
# However updating codes with what I see at JAX
@Mxxxx - MiSeq
@Dxxxx - HiSeq 2500
@Kxxxx - HiSeq 4000
@NSxxx - NextSeq 500/550
@Axxxxx - NovaSeq

wflynny

# I usually put this in my ~/.bash_aliases
# A portion of our GPFS storage removes files after 21 days of creation.
# `stat` does not show creation time, so we have to resort to parsing the
# output of `mmlsattr`

ftime() {
    # Usage: 
    #   ftime path/to/file
    # 
    # Outputs:

wflynny

# Some universal variables
NCELLS=6000
OUTPUT_NAME="nice-name"
FASTQ_DIR="/path/to/fastqs"
REFERENCE_GENOME="/path/to/reference_dir"
[[ -z "${PBS_NUM_PPN}" ]] && NCORES=20 || NCORES=${PBS_NUM_PPN}

# When reads look like:
# sample-name_S?_L00?_R1_001.fastq.gz
# sample-name_S?_L00?_R2_001.fastq.gz