mdshw5

import simplesam

barcodes = {}
with open('read_id_barcode_umi.txt') as barcodes_file:
  for line in barcodes_file:
    # should check the delimiter in this file. If it's ' ' or \t or ','
    read_id, umi, barcode = line.rstrip().split()
    barcode[read_id] = (umi, barcode)
    # reading this entire file could use a TON of memory if
    # if you have lots of reads

mdshw5

from pyfaidx import Fasta
with Fasta('input.fasta') as fasta:
  with open('pos.txt', 'r') as nucleotides:
    for line in nucleotides:
      chrom, pos = line.rstrip().split()
      nuc = fasta[chrom][int(pos)].seq
      print("{chrom}\t{pos}\t{nuc}".format(**locals())) 

mdshw5

from pyfaidx import Fasta

with Fasta("file_2.fasta") as records:
  with open("file_1") as content:
    for line in content:
      _, ec, filename = line.rstrip().split()
      with open(filename, "w") as out_file:
        for record in records:
          if ec in record.name:
            out_file.write(repr(record))

mdshw5

GRUB_CMDLINE_LINUX_DEFAULT="rootflags=degraded,subvol=@ intel_iommu=on,igfx_off vfio_iommu_type1.allow_unsafe_interrupts=1 pcie_acs_override=downstream"

mdshw5

<domain type='kvm'>
  <name>Steam</name>
  <uuid>90325573-ce4b-4ffc-875e-ca31f2d2f859</uuid>
  <memory unit='KiB'>2097152</memory>
  <currentMemory unit='KiB'>2097152</currentMemory>
  <vcpu placement='static'>4</vcpu>
  <os>
    <type arch='x86_64' machine='pc-q35-2.5'>hvm</type>
    <loader readonly='yes' type='pflash'>/usr/share/OVMF/OVMF_CODE.fd</loader>
    <nvram>/var/lib/libvirt/qemu/nvram/Steam_VARS.fd</nvram>

mdshw5

## This is a rule for use in Snakemake
rule create_canvas_xml:                                                                                                                                                                       
    input: fasta=config["mouse_fasta"]                                                                                                                                                        
    output: xml="GenomeSize.xml", genome="genome.fa"                                                                                                                                          
    params: runtime="7200", memory="2G"                                                                                                                                                       
    run:                                                                                                                                                                                      
        from pyfaidx import Fa

mdshw5

from pyfaidx import Fasta

with Fasta('1st.fa') as first, Fasta('2nd.fa') as second, open('result.fa', 'w') as result:
  for a, b in zip(first, second):
    result.write('>' + a.name)
    result.write(str(a))
    result.write('>' + b.name)
    result.write(str(b))

mdshw5

from pyfaidx import FastaVariant
import vcf

samples = vcf.Reader(open('calls.vcf.gz', 'r')).samples

for sample in samples:
  with FastaVariant('reference.fasta', 'calls.vcf.gz', sample=sample, het=True, hom=True) as consensus:
    with open(sample + '.fasta', 'w') as sample_fasta:
      for record in consensus:
        sample_fasta.write('>' + record.long_name)

mdshw5

from pyfaidx import FastaVariant
with FastaVariant('genome.fasta', 'tabix_indexed_variants.vcf.gz', het=True, hom=True) as consensus:
  for chromosome in consensus:
    for site in chromosome.variant_sites:
      flanking = chromosome[site-2:site+1]
      ## do something with flanking sequence
      print(flanking.seq)  ## ATG

mdshw5

pip install pyfaidx
faidx --transform nucleotide giant.fasta > base_counts.txt
cat base_counts.txt | awk '{if ($8 == 0); print $1}' > seqs_without_n.txt
xargs faidx giant.fasta < seqs_without_n.txt