sminot

# Plot the distribution of CAG sizes
def plot_cag_size(hdf_fp, pdf=None, min_size=5, alpha=0.25):
    cag_annot = pd.read_hdf(hdf_fp, "/annot/cag/all").set_index("CAG")
    
    # Calculate the log10 size (number of genes per CAG)
    cag_annot = cag_annot.assign(
        size_log10 = cag_annot["size"].apply(np.log10)
    )
    
    # Filter by CAG size

sminot

# Plot the number of genes detected and the proportion of reads aligned
def plot_specimen_summary(hdf_fp, pdf=None, alpha = 0.85):
    
    specimen_summary = pd.read_hdf(hdf_fp, "/summary/all").set_index("specimen")
    
    specimen_summary = specimen_summary.assign(
        prop_reads = specimen_summary["aligned_reads"] / specimen_summary["n_reads"]
    )
    
    for col_name, axis_title in [

sminot

# Read in data from the HDF store
assert os.path.exists(hdf_fp)
cag_annot = pd.read_hdf(hdf_fp, "/annot/cag/all").set_index("CAG")
cag_abund = pd.read_hdf(hdf_fp, "/abund/cag/wide").set_index("CAG")
corncob_df = pd.read_hdf(hdf_fp, "/stats/cag/corncob")
betta_df = pd.read_hdf(hdf_fp, "/stats/enrichment/betta")
manifest = pd.read_hdf(hdf_fp, "/manifest").set_index("specimen")
specimen_summary = pd.read_hdf(hdf_fp, "/summary/all").set_index("specimen")

sminot

from functools import lru_cache
from collections import defaultdict
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
import matplotlib.patches as mpatches
from scipy import stats
import seaborn as sns
import os

sminot

jupyter nbconvert --ExecutePreprocessor.timeout=-1 --to notebook --inplace --execute NOTEBBOOK

sminot

paste -d '' <(bunzip2 -c Raw_Read2_Barcodes.fq.bz2 | awk '{if(NR % 4 == 2 || NR % 4 == 4){print}else{print ""}}') <(bunzip2 -c Raw_Read1.fq.bz2) | fastx_barcode_splitter.pl --bcfile barcodes.tsv --prefix PREFIX --suffix _R1.fastq --bol

sminot

import io
import boto3
import pandas as pd

def read_csv_from_s3(s3_url, s3=None, sep=","):
    assert s3_url.startswith("s3://")
    bucket_name, key_name = s3_url[5:].split("/", 1)

    if s3 is None:
        s3 = boto3.client('s3')

sminot

import boto3

def aws_s3_ls(bucket, prefix):
    conn = boto3.client('s3')
    
    fps = []
    
    r = conn.list_objects_v2(
        Bucket=bucket, 
        Prefix=prefix

sminot

#!/usr/bin/env python
"""Convert GlimmerHMM GFF3 gene predictions into protein sequences.

This works with the GlimmerHMM GFF3 output format:

##gff-version 3
##sequence-region Contig5.15 1 47390
Contig5.15      GlimmerHMM      mRNA    323     325     .       +       .       ID=Contig5.15.path1.gene1;Name=Contig5.15.path1.gene1
Contig5.15      GlimmerHMM      CDS     323     325     .       +       0       ID=Contig5.15.cds1.1;Parent=Contig5.15.path1.gene1;Name=Contig5.15.path1.gene1;Note=final-exon

sminot

#!/bin/bash

set -e

bucket=$1
prefix=$2

(( ${#bucket} > 0 ))
(( ${#prefix} > 0 ))