ccwang002

import numpy as np
rs = np.random.RandomState(seed=5566)
n_conditions = 10

# Here we simulate a complex computation, for example, analogy of the magnitude
# of gradient decent which expects to be strictly positive. But from the result
# we find that it seems to be sometimes negative, we wish to find out when and
# what condition our program produces bogus ouput.
#
# This is the case to use pdb and condition break point

ccwang002

from datetime import datetime
from pytz import timezone  # pip install pytz


# Setup remote time
remote_tz = timezone('US/Pacific')                           # PST for example
remote_dt = remote_tz.localize(datetime(2015, 5, 1, 14, 0))  # May 1, 2015 PM2:00 PST

# Setup Taipei local time
tpe = timezone('Asia/Taipei')

ccwang002

Keybase proof

I hereby claim:

• I am ccwang002 on github.
• I am liang2 (https://keybase.io/liang2) on keybase.
• I have a public key ASA_ZHu4l91A5bKbiWrZkL-zyJD9mvEUNQpsaW3LjmvcqQo

To claim this, I am signing this object:

ccwang002

import pandas as pd
import os
from pathlib import Path

# Export Zotero library as CSV
ZOTERO_LIBRARY_PTH = '/Users/liang/Desktop/My Library.csv'
REFERENCES_ROOT = Path('/Users/liang/Dropbox/References/')


df = pd.read_csv(ZOTERO_LIBRARY_PTH)

ccwang002

# The Snakefile that loads raw data and genome reference locally
GENOME_FA = "griffithlab_brain_vs_uhr/GRCh38_Ens87_chr22_ERCC/chr22_ERCC92.fa"
GENOME_GTF = "griffithlab_brain_vs_uhr/GRCh38_Ens87_chr22_ERCC/genes_chr22_ERCC92.gtf"
HISAT2_INDEX_PREFIX = "hisat2_index/chr22_ERCC92"

SAMPLES, *_ = glob_wildcards('griffithlab_brain_vs_uhr/HBR_UHR_ERCC_ds_10pc/{sample}.read1.fastq.gz')

from pathlib import Path

ccwang002

from pathlib import Path
from snakemake.remote.GS import RemoteProvider as GSRemoteProvider
GS = GSRemoteProvider()


GS_PREFIX = "lbwang-playground/snakemake_rnaseq"
GENOME_FA =  GS.remote(f"{GS_PREFIX}/griffithlab_brain_vs_uhr/GRCh38_Ens87_chr22_ERCC/chr22_ERCC92.fa")
GENOME_GTF = GS.remote(f"{GS_PREFIX}/griffithlab_brain_vs_uhr/GRCh38_Ens87_chr22_ERCC/genes_chr22_ERCC92.gtf")
HISAT2_INDEX_PREFIX = "hisat2_index/chr22_ERCC92"
FULL_HISAT2_INDEX_PREFIX = "dinglab/lbwang/snakemake_demo/hisat2_index/chr22_ERCC92"

ccwang002

from itertools import combinations, product


def gen_pos_sets_to_sub(barcode, max_sub=1):
    """
    Generate all the possible position combinations (sets) within
    the given maximal number of substitutions.

    Examples:

ccwang002

ccwang002

"""Find the possible Ensembl releases of the given IDs.

The script uses Ensembl Tark APIs to subset the possible Ensembl releases
that cover all the given Ensembl IDs. Usually it can pinpoint the right release
using less than 30 IDs. Feeding more IDs may exceed the API call rate limit.

Known issues:
* The API doesn't handle ENSGR (chrY PAR genes)
"""
import argparse