Metadata-Version: 2.1
Name: PSIMPL
Version: 0.0.2
Summary: Peptide-Spectrum match IMPutation Library
Home-page: https://github.com/johnhalloran321/psimpl
Author: John T. Halloran
Author-email: johnhalloran321@gmail.com
License: Apache 2.0
Platform: any
Classifier: Natural Language :: English
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: Unix
Classifier: Programming Language :: Python :: 3 :: Only
Description-Content-Type: text/markdown
License-File: LICENSE

# Peptide-Spectrum match IMPutation Library (PSIMPL)
PSIMPL is a python library for easy imputation of missing PSM data.  Given an input PIN file, PSIMPL determines which features contain missing values.  PSIMPL then performs imputation by training a regressor on fully observed feature samples.

PSIMPL's API offers a high degree of flexibility, including a large number of state-of-the-art regression algorithms such as:
-Linear Regression
-Ridge Regression
-Lasso (i.e., L1 regularization)
-ElasticNet (i.e., L1+L2 regularization)

Future work: cross-validation (CV) for hyperparameter optimization, XGBoost/DNN/Support Vector Regression


