cory-weller

@HD	VN:1.5	SO:unsorted
@SQ	SN:chr1	LN:248956422	M5:6aef897c3d6ff0c78aff06ac189178dd	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr2	LN:242193529	M5:f98db672eb0993dcfdabafe2a882905c	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr3	LN:198295559	M5:76635a41ea913a405ded820447d067b0	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr4	LN:190214555	M5:3210fecf1eb92d5489da4346b3fddc6e	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr5	LN:181538259	M5:a811b3dc9fe66af729dc0dddf7fa4f13	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr6	LN:170805979	M5:5691468a67c7e7a7b5f2a3a683792c29	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr7	LN:159345973	M5:cc044cc2256a1141212660fb07b6171e	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	SP:Homo sapiens
@SQ	SN:chr8	LN:145138636	M5:c67955b5f7815a9a1edfaa15893d3616	AS:20	UR:/seq/references/kendrix/v0/kendrix.fasta	S

cory-weller

Overview

script_specific.sh is an example for extracting sequences between two anchors.

The output is a three-column tab-delimited table in the format

| anchor1 | insert | anchor2 |

Only lines that match the pattern are included.

min_insert is the minimum number of characters needed to be a match.

cory-weller

library(abind)
library(annotate)
library(AnnotationDbi)
library(AnnotationFilter)
library(askpass)
library(Azimuth)
library(backports)
library(base64enc)
library(beachmat)
library(BH)

cory-weller

#!/usr/bin/env bash

# DETAILS: Functions by setting the field separator to a regular expression capturing ">", tab, and space.
# For each row in the file, if it is a header (begins with ">"), update the value of variable s
# to be equal to the first word in the header, and write a header line only containing that first word.
# Every line is written to a file <first_word_in_header>.fa, splitting the file into separate contigs.

awk -F "(^>|\t| )" '{if($0 ~ /^>/) {s=$2".fa";  print ">"$2 > s} else print > s}' ${inFasta}

cory-weller

#!/usr/bin/env bash

# Installs singularity

sudo apt-get update

sudo apt-get install -y --no-install-recommends \
    build-essential \
    libssl-dev \
    uuid-dev \

cory-weller

Instructions based on those from the Biowulf team

You must be on the NIH network on campus, or connected to VPN.

Then, start an interactive session from the command-line on Biowulf:

# On BIOWULF:
sinteractive --mem 20G --time 8:00:00 --gres lscratch:20 --tunnel

cory-weller

#!/usr/bin/env bash

echo "Running ampliconsplit.sh $@"

## convenience functions for arg parsing
usage_error () { echo >&2 "ERROR:  $1"; exit 2; }
assert_argument () { test "$1" != "$EOL" || usage_error "$2 requires an argument. Try --help"; }

# Parse Arguments
## import $@

cory-weller

SYMBOL	ENSEMBL	seqnames	start	end	width	strand
	ENSG00000243485	chr1	29554	31109	1556	+
FAM138A	ENSG00000237613	chr1	34554	36081	1528	-
OR4F5	ENSG00000186092	chr1	65419	71585	6167	+
	ENSG00000238009	chr1	89295	133723	44429	-
	ENSG00000239945	chr1	89551	91105	1555	-
	ENSG00000239906	chr1	139790	140339	550	-
	ENSG00000241860	chr1	141474	173862	32389	-
	ENSG00000241599	chr1	160446	161525	1080	+
	ENSG00000286448	chr1	266855	268655	1801	+

cory-weller

#!/usr/bin/env Rscript
library(Seurat)
library(DoubletFinder)

## Standard pre-processing
seurat_obj <- CreateSeuratObject(kidney.data)
seurat_obj <- NormalizeData(seurat_obj)
seurat_obj <- FindVariableFeatures(seurat_obj, selection.method = "vst", nfeatures = 2000)

cory-weller

#!/usr/bin/env python
'''finds a header within a given fasta file, then prints the desired nucleotide ranges to STDOUT'''

import sys
import argparse
import regex as re

def wrap_fasta(seq):
    '''wraps sequence every 80 characters with newlines'''
    return '\n'.join([seq[x:x+80] for x in range(0,len(seq),80)])