brantfaircloth

#!/usr/bin/env python
# encoding: utf-8
"""
Created by Brant Faircloth on May 9, 2024 at 14:00:38 CDT
Copyright (c) 2024 Brant C. Faircloth. All rights reserved.

Description: 

"""

brantfaircloth

#!/usr/bin/env python
# encoding: utf-8
"""
bed_from_genbank.py

grab the gene records from a genbank file (edit for other record types).

- requires:  biopython

"""

brantfaircloth

##GTR lset applyto=() nst=6 # GTR lset applyto=() nst=6 rates=propinv # GTR + I lset applyto=() nst=6 rates=gamma # GTR + gamma lset applyto=() nst=6 rates=invgamma # GTR + I + gamma

##SYM

lset applyto=() nst=6                           # SYM

prset applyto=() statefreqpr=fixed(equal)

brantfaircloth

from Bio import SeqIO

# create a dict to hold our new GI:names mapping, which looks like so, in 
# this case (from sheep)
#
# gi|289623201|gb|CM000885.1|   299839927   chr1
# gi|289623190|gb|CM000894.1|   94216033     chr10
# gi|289623189|gb|CM000895.1|   67137890     chr11
# gi|289623188|gb|CM000896.1|   86457535     chr12
data = {}

brantfaircloth

import time
import random
from multiprocessing import Process, Queue, JoinableQueue, cpu_count

""" Adjust time.sleep() values to see action of consumer """

def work(id, jobs, result):
    while True:
        task = jobs.get()
        if task is None:

brantfaircloth

Install dependencies and Casava

The following assumes you are converting BCL files containing PE100 reads with a 10 nt index read. You can allow Casava to demultiplex for you or do it on your own, later. You can adjust values below if you are doing something different (e.g. shorter reads, longer indexes) but be careful.

• You need a pretty beefy machine. Illumina recommends something with multiple cores and 48 GB RAM, running Centos 5. Centos 6 also works just fine. See their recommendations here:

brantfaircloth

From Rick James @ http://dev.mysql.com/doc/refman/5.0/en/group-by-functions.html

• Mode

    SELECT trimmed_len, COUNT(trimmed_len) AS mode FROM sequence GROUP BY trimmed_len ORDER BY mode DESC LIMIT 1;
  

From Michael Stassen @ http://lists.mysql.com/mysql/155540

• Median

CREATE TEMPORARY TABLE tmp (n INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY, value VARCHAR(99) NOT NULL );

brantfaircloth

text = Query id, Subject id, % identity, alignment length, mismatches, gap openings, q. start, q. end, s. start, s. end, e-value, bit score
csv = "Query id","Subject id","% identity","alignment length","mismatches","gap openings","q. start","q. end","s. start","s. end","e-value","bit score"

brantfaircloth

# assume the following directory structure where contents of doc/ 
# and source/ are already checked into repo., with the exception 
# of the _build directory (i,e. you can check in _themes or _sources 
# or whatever else).
#
# proj/
#    source/
#    doc/

# remove doc/_build/html if present

brantfaircloth

Disclaimer

Before using this for samples that are precious, you should thoroughly test the solution that you make. The best way to do that would be a side-by-side with commercial RNALater.

Source

The following recipe is from the patent. It always pays to read these.

In a beaker, combine 40 ml 0.5 M EDTA, 25 ml 1M Sodium Citrate, 700 gm Ammonium Sulfate