Metadata-Version: 2.1
Name: deeplc
Version: 0.1.2
Summary: DeepLC: Retention time prediction for (modified) peptides using Deep Learning.
Home-page: http://compomics.github.io/projects/DeepLC
Author: Robbin Bouwmeester, Niels Hulstaert, Ralf Gabriels, Prof. Lennart Martens, Prof. Sven Degroeve
Author-email: Robbin.Bouwmeester@UGent.be
License: apache-2.0
Project-URL: Documentation, http://compomics.github.io/projects/DeepLC
Project-URL: Source, https://github.com/compomics/DeepLC
Project-URL: Tracker, https://github.com/compomics/DeepLC/issues
Keywords: DeepLC,Proteomics,deep learning,peptides,retention time,prediction
Platform: UNKNOWN
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Development Status :: 4 - Beta
Requires-Python: >=3.6,<3.8
Description-Content-Type: text/markdown
Requires-Dist: setuptools (>=42.0.1)
Requires-Dist: tensorflow (<3,>=1.14.0)
Requires-Dist: scipy (<2,>=1.3.1)
Requires-Dist: matplotlib (<4,>=3)
Requires-Dist: numpy (<2,>=1.17)
Requires-Dist: pandas (<1,>=0.25)

<img src="https://github.com/compomics/DeepLC/raw/master/img/deeplc_logo.png"
width="150" height="150" /> <br/><br/>

![PyPI - Python Version](https://img.shields.io/pypi/pyversions/deeplc?style=flat-square)
[![PyPI](https://img.shields.io/pypi/v/deeplc?style=flat-square)](https://pypi.org/project/deeplc/)
[![Conda](https://img.shields.io/conda/vn/bioconda/deeplc?style=flat-square)](https://bioconda.github.io/recipes/deeplc/README.html)
[![GitHub release](https://img.shields.io/github/v/release/compomics/DeepLC?include_prereleases&style=flat-square)](https://github.com/compomics/DeepLC/releases/latest/)
[![Build Status](https://img.shields.io/github/workflow/status/compomics/DeepLC/Python%20package%20test?style=flat-square)](https://github.com/compomics/DeepLC/actions?query=workflow%3A%22Python+package+test%22)
[![GitHub issues](https://img.shields.io/github/issues/compomics/DeepLC?style=flat-square)](https://github.com/compomics/DeepLC/issues)
[![GitHub](https://img.shields.io/github/license/compomics/DeepLC.svg?style=flat-square)](https://www.apache.org/licenses/LICENSE-2.0)

DeepLC: Retention time prediction for (modified) peptides using Deep Learning.

---

- [Introduction](#introduction)
- [Graphical user interface](#graphical-user-interface)
- [Python package](#python-package)
  - [Installation](#installation)
  - [Command line interface](#command-line-interface)
  - [Python module](#python-module)
- [Input files](#input-files)
- [Prediction models](#prediction-models)

---

## Introduction

DeepLC is a retention time predictor for (modified) peptides that employs Deep
Learning. It's strength lies in the fact that it can accurately predict
retention times for modified peptides, even if hasn't seen said modification
during training.

DeepLC can be run with a graphical user interface (GUI) or as a Python package.
In the latter case, DeepLC can be used from the command line, or as a python
module.

## Graphical user interface
### Installation

[![Download GUI](https://img.shields.io/badge/download-GUI-green?style=flat-square)](https://github.com/compomics/DeepLC/releases/latest/)

1. Download `deeplc_gui.zip` from the
[latest release](https://github.com/compomics/DeepLC/releases/latest/) and
unzip.
2. Install DeepLC GUI with `install_gui_windows.bat` or `install_gui_linux.sh`,
depending on your operating system.
3. Run DeepLC GUI by running the `deeplc_gui.jar`.


## Python package

### Installation

[![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat-square)](http://bioconda.github.io/recipes/deeplc/README.html)
[![install with pip](https://img.shields.io/badge/install%20with-pip-blue.svg?style=flat-square)](http://bioconda.github.io/recipes/deeplc/README.html)
[![container](https://img.shields.io/badge/pull&nbsp;docker-biocontainers-green?style=flat-square)](https://quay.io/repository/biocontainers/deeplc)

Install with conda, using the bioconda and conda-forge channels:  
`conda install -c bioconda -c conda-forge deeplc`

Or install with pip:  
`pip install deeplc`

### Command line interface

To use the DeepLC CLI, run:

```sh
deeplc --file_pred <path/to/peptide_file.csv>
```

We highly recommend to add a peptide file with known retention times for
calibration:

```sh
deeplc --file_pred  <path/to/peptide_file.csv> --file_cal <path/to/peptide_file_with_tr.csv>
```

For an overview of all CLI arguments, run `deeplc --help`.

### Python module

Minimal example:

```python
import pandas as pd
from deeplc import DeepLC

peptide_file = "datasets/test_pred.csv"
calibration_file = "datasets/test_train.csv"

pep_df = pd.read_csv(peptide_file, sep=",")
pep_df['modifications'] = pep_df['modifications'].fillna("")

cal_df = pd.read_csv(calibration_file, sep=",")
cal_df['modifications'] = cal_df['modifications'].fillna("")

dlc = DeepLC()
dlc.calibrate_preds(seq_df=cal_df)
preds = dlc.make_preds(seq_df=pep_df)
```

For a more elaborate example, see
[examples/deeplc_example.py](https://github.com/compomics/DeepLC/blob/master/examples/deeplc_example.py)
.

## Input files

DeepLC expects comma-separated values (CSV) with the following columns:

- `seq`: unmodified peptide sequences
- `modifications`: MS2PIP-style formatted modifications: Every modification is
  listed as `location|name`, separated by a pipe (`|`) between the location, the
  name, and other modifications. `location` is an integer counted starting at 1
  for the first AA. 0 is reserved for N-terminal modifications, -1 for
  C-terminal modifications. `name` has to correspond to a Unimod (PSI-MS) name.
- `tr`: retention time (only required for calibration)

For example:

```csv
seq,modifications,tr
AAGPSLSHTSGGTQSK,,12.1645
AAINQKLIETGER,6|Acetyl,34.095
AANDAGYFNDEMAPIEVKTK,12|Oxidation|18|Acetyl,37.3765
```

See
[examples/datasets](https://github.com/compomics/DeepLC/tree/master/examples/datasets)
for more examples.

## Prediction models

DeepLC comes with multiple CNN models trained on data from various experimental
settings:

| Model filename | Experimental settings | Publication |
| - | - | - |
| full_hc_dia_fixed_mods.hdf5 | Reverse phase | [Rosenberger et al. 2014](https://doi.org/10.1038/sdata.2014.31) |
| full_hc_LUNA_HILIC_fixed_mods.hdf5 | HILIC | [Spicer et al. 2018](https://doi.org/10.1016/j.chroma.2017.12.046) |
| full_hc_LUNA_SILICA_fixed_mods.hdf5 | HILIC | [Spicer et al. 2018](https://doi.org/10.1016/j.chroma.2017.12.046) |
| full_hc_PXD000954_fixed_mods.hdf5 | Reverse phase | [Rosenberger et al. 2014](https://doi.org/10.1038/sdata.2014.31) |

By default, DeepLC selects the best model based on the calibration dataset. If
no calibration is performed, the first default model is selected. Always keep
note of the used models and the DeepLC version.


