GCGC is a preprocessing library for biological sequence model development.


Keywords
gcgc, bioinformatics, biological-sequences, deep-learning, genomics, machine-learning, nlp, protein-design
License
MIT
Install
pip install gcgc==0.12.2.dev4

Documentation

GCGC

GCGC is a tool for feature processing on Biological Sequences.

code style black

Installation

GCGC is primarily intended to be used as part of a larger workflow inside Python.

To install via pip:

$ pip install gcgc

If you'd like to use code that helps gcgc's tokenizers integrate with common third party libraries, either install those packages separately, or use gcgc's extras.

$ pip install 'gcgc[hf]'

Documentation

The GCGC documentation is at gcgc.trenthauck.com, please see it for examples.

Quick Start

The easiest way to get started is to import the kmer tokenizer, configure it, then start tokenizing.

from gcgc import KmerTokenizer

kmer_tokenizer = KmerTokenizer(alphabet="unambiguous_dna")
encoded = kmer_tokenizer.encode("ATCG")
print(encoded)

sample output:

[1, 6, 7, 8, 5, 2]

This output includes the "bos" token, the "eos" token, and the four nucleotide tokens in between.

You can go the other way and convert the integers to strings.

from gcgc import KmerTokenizer

kmer_tokenizer = KmerTokenizer(alphabet="unambiguous_dna")
decoded = kmer_tokenizer.decode(kmer_tokenizer.encode("ATCG"))
print(decoded)

sample output:

['>', 'A', 'T', 'C', 'G', '<']

There's also the vocab for the kmer tokenizer.

from gcgc import KmerTokenizer

kmer_tokenizer = KmerTokenizer(alphabet="unambiguous_dna")
print(kmer_tokenizer.vocab.stoi)

sample output:

{'|': 0, '>': 1, '<': 2, '#': 3, '?': 4, 'G': 5, 'A': 6, 'T': 7, 'C': 8}