DLOmix is a python framework for Deep Learning in Proteomics. Initially built ontop of TensorFlow/Keras, support for PyTorch can however be integrated once the main API is established.
Experiment a simple retention time prediction use-case using Google Colab
A version that includes experiment tracking with Weights and Biases is available here
Resources Repository
More learning resources can be found in the dlomix-resources repository.
Run the following to install:
$ pip install dlomixGeneral Overview
data: structures for modelling the input data, currently based ontf.Dataseteval: classes for evaluating models and reporting resultslayers: custom layers used for building models, based ontf.keras.layers.Layerlosses: custom losses to be use for training withmodel.fit()models: common model architectures for the relevant use-cases based ontf.keras.Modelto allow for using the Keras training APIpipelines: an exemplary high-level pipeline implementationreports: classes for generating reports related to the different tasksconstants.py: constants and configuration valuesutils.py: utility functions
Use-cases
- Retention Time Prediction:
- a regression problem where the the retention time of a peptide sequence is to be predicted.
To-Do
Functionality:
- integrate prosit
- extend pipeline for different types of models and backbones
- extend pipeline to allow for fine-tuning with custom datasets
- add residual plots to reporting, possibly other regression analysis tools
- output reporting results as PDF
- extend data representation to include modifications
Package structure:
- integrate
deeplc.pyintomodels.py, preferably introduce a package structure (e.g.models.retention_time) - add references for implemented models in the ReadMe
- introduce a style guide and checking (e.g. PEP)
- plan documentation (sphinx and readthedocs)
To install dlomix, along with the the tools needed to develop and run tests, run the following command in your virtualenv:
$ pip install -e .[dev]References:
[Prosit]
[1] Gessulat, S., Schmidt, T., Zolg, D. P., Samaras, P., Schnatbaum, K., Zerweck, J., ... & Wilhelm, M. (2019). Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning. Nature methods, 16(6), 509-518.
[DeepLC]
[2] DeepLC can predict retention times for peptides that carry as-yet unseen modifications Robbin Bouwmeester, Ralf Gabriels, Niels Hulstaert, Lennart Martens, Sven Degroeve bioRxiv 2020.03.28.013003; doi: 10.1101/2020.03.28.013003
[3] Bouwmeester, R., Gabriels, R., Hulstaert, N. et al. DeepLC can predict retention times for peptides that carry as-yet unseen modifications. Nat Methods 18, 1363–1369 (2021). https://doi.org/10.1038/s41592-021-01301-5