| # Derived from https://towardsdatascience.com/how-to-fine-tune-gpt-2-for-text-generation-ae2ea53bc272 | |
| import os | |
| import pandas as pd | |
| from transformers import GPT2LMHeadModel, GPT2Tokenizer | |
| import numpy as np | |
| import random | |
| import torch | |
| from torch.utils.data import Dataset, DataLoader |
| /* | |
| From [this stackover post](https://stackoverflow.com/questions/2418527/sql-server-query-to-get-the-list-of-columns-in-a-table-along-with-data-types-no) | |
| */ | |
| SELECT | |
| c.name 'Column Name', | |
| t.Name 'Data type', | |
| c.max_length 'Max Length', | |
| c.precision , | |
| c.scale , |
| # Create a new fasta file given a fasta file and list of sequence names | |
| # - outputting the long_name does/did not seem to work properly in the faidx script that is packaged with pyfaidx | |
| from pyfaidx import * | |
| # read fasta file | |
| fa = Fasta('test.fa') |
| # From [this tutorial](https://www.tecmint.com/clear-ram-memory-cache-buffer-and-swap-space-on-linux/) | |
| sync; echo 1 > /proc/sys/vm/drop_caches | |
SAM and BAM filtering one-liners
@author: David Fredman, david.fredmanAAAAAA@gmail.com (sans poly-A tail)
@dependencies: http://sourceforge.net/projects/bamtools/ and http://samtools.sourceforge.net/
Please extend with additional/faster/better solutions via a pull request!
BWA mapping (using piping for minimal disk I/O)
| #!/usr/bin/env perl | |
| use warnings;use strict; | |
| my ($header,$sequence); | |
| $header = <>; | |
| chomp $header; | |
| while(my $line = <>){ | |
| chomp $line; | |
| if($line =~ /^>/){ |
| #!/bin/bash | |
| # From: http://www.cyberciti.biz/faq/exclude-certain-files-when-creating-a-tarball-using-tar-command/ | |
| tar --exclude-vcs --exclude='nohup.out' -cjf ~/tmp/whatever.tar.bz2 ./* | |
| ## If python 3.5, say, has been installed but you want to use v2.7 for | |
| ## a particular project | |
| # Create environment for different (or specific) version of python: | |
| conda create -n py27 python=2.7 anaconda | |
| # Check available environments (optional) | |
| # conda info --envs |
| import(rtracklayer) | |
| # Where syn is a list of GRanges objects: | |
| test = GenomicRangesList(syn) | |
| export.gff(test,"~/tmp/tmp.gff3", version="3") | |
| # ... or a single GRanges element: | |
| export.gff(syn[[1]],"~/tmp/tmp.gff3", version="3") | |