elowy01

# general scatter plot
sns.scatterplot(data=ag1_df, x="ivaf", y="ovaf")

elowy01

1) Click on file in the repo
2) Click on the icon: 'Copy raw contents'

elowy01

import pdb

all_ids = set()
def parse_ids(ifile: str):
    """Parse ids from list. Ids are in first column"""
    info_d = dict()
    with open(ifile) as ifile1:
        for line in ifile1:
            line = line.rstrip("\n");
            if line.startswith("#"): continue

elowy01

import matplotlib.pyplot as plt
from matplotlib_venn import venn2

# Use the venn2 function
venn2(subsets = (10, 5, 2), set_labels = ('Group A', 'Group B'))
plt.show()

elowy01

# Good post at:
https://www.biostars.org/p/84686/

elowy01

// params defaults
params.help = false
params.cpus = 1
params.C = 'true'

def helpMessage() {
    log.info"""
    Pipeline to align FASTQ file/s to a reference file
    --------------------------------------------------
    Usage:

elowy01

# Extracted from : https://medium.com/analytics-vidhya/pandas-how-to-change-value-based-on-condition-fc8ee38ba529
import pandas as pd
import numpy as np

data = {'Stock': ['AAPL', 'IBM', 'MSFT', 'WMT'],
       'Price': [144.8, 141.61, 304.21, 139.5],
       'PE': [25, 21, 39, 16],  
       'TradingExchange': ['NASDAQ', 'NYSE', 'NASDAQ', 'NYSE']}

df = pd.DataFrame(data)

elowy01

# merge
bedtools merge -i ifile.bed -c 4 -o collapse # print the merged feature names (4th column)

# intersect
$ cat A.bed
chr1  10  20
chr1  30   40

$ cat B.bed
chr1  15  20

elowy01

from nucleus.io import vcf
from nucleus.util import variant_utils

with vcf.VcfReader('/home/ec2-user/DEEPVARIANT/NA12878_calls.vcf.gz') as reader:
  print('Sample names in VCF: ', ' '.join(reader.header.sample_names))
  for variant in reader:
      print(variant_utils.variant_type(variant)) # variant type
      print(variant.reference_name) # reference

elowy01

import keras
import pdb
from keras.datasets import mnist 
from keras.models import Sequential 
from keras.layers import Dense, Dropout 
from keras.optimizers import RMSprop 
import numpy as np

# Load mnist data
(x_train, y_train), (x_test, y_test) = mnist.load_data()