Skip to main content

Classifying Antibodies for Expression

Project description

cafe: Classifying Antibodies for Expression

About

A Python package, or wrapper, that transforms FASTA files into a data format suitable for machine learning classification.

This is a research project during my computational biology internship at EMD Serono, Research and Development Institute in Billerica, MA under Dr. Yves Fomekong Nanfack. The idea is to have each amino acid as a feature (with its respective numerical value based on solubility, hydrophobicity, etc. from the literature) and see if it is possible to predict antibodies that have high affinity or other ideal characteristics.

The data_transform module reads in FASTA files, extracts the amino acid sequence, splits each amino acid into its own columns, replaces each amino acid with a value provided by the user (as a file), and outputs a pandas dataframe(s).

The ml module performs classic machine learning tasks such as splitting the data, standardizing the data, model selection, training, and evaluating.

Installation

Please have Python 3.7 installed.

Once Python 3.7 is installed, you can install the package as so:

pip3 install cafe

Usage

Please see the examples folder.# cafe

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cafe-2.0.7.tar.gz (16.5 MB view details)

Uploaded Source

File details

Details for the file cafe-2.0.7.tar.gz.

File metadata

  • Download URL: cafe-2.0.7.tar.gz
  • Upload date:
  • Size: 16.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/45.2.0 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.5

File hashes

Hashes for cafe-2.0.7.tar.gz
Algorithm Hash digest
SHA256 ea31115f97f947db52e34fe93a38748ee004affb3ad935f4e3f4bd2bc483decb
MD5 fdf853df2c6342220f2a80b0582bc64a
BLAKE2b-256 76eea48e384fb85e78821026e393a2e7b359e1a359542d89e4328370006c1ccf

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page