Deep learning spectrum prediction

[henninggaertner]

Hi future project :wave:

Description

This adds the deep learning spectrum prediction of my bachelors thesis, which is the process of using DL to predict the fragmented mass spectrum of a peptide precursor with a given charge and sequence given some additional meta parameters about the mass spectrometry machine. This can then be plotted to visualize the peptide fragments and their intensity. This was implemented with an API by Koina, and the resulting spectra can be exported to various file formats commonly used by researchers.

Changes

• new file: ms_constants.py, which should be used in the future for often repeated strings
• new FileOutput in disk_operator, which nicely integrates with the "Show table" option to show what is actually in there
• new steps in DataAnalysis
• adapted the evidence import in peptide_import.py
• add new django form field, which can display just text in a text box (like an info field)
• some minor improvements, like logging in the run.py
• new example files for the tests
• new workflow

Testing

Tests were made. Other than that:

1. create a new run with the spectrum prediction workflow
2. import the evidence data (evidence.txt)
3. predict using any (except TMT, as that needs special data. or get the data and try that, no guarantees.)

PR checklist

Development

• [ ] If necessary, I have updated the documentation (README, docstrings, etc.)
• [x] If necessary, I have created / updated tests.

Mergeability

• [x] main-branch has been merged into local branch to resolve conflicts
• [x] The tests and linter have passed AFTER local merge
• [x] The code has been formatted with black

Code review

• [x] I have self-reviewed my code.
• [ ] At least one other developer reviewed and approved the changes

[github-actions[bot]]

Coverage report

Click to see where and how coverage changed

File	Statements	Missing	Coverage	Coverage (new stmts)	Lines missing
protzilla
disk_operator.py					77-78, 84-91, 103, 224, 230, 291-298
run.py
run_helper.py
protzilla/data_analysis
differential_expression_helper.py					125, 143
differential_expression_kruskal_wallis.py					227
differential_expression_mann_whitney.py					266
differential_expression_t_test.py
predict_spectra.py					45, 70-71, 123-231, 243-372, 387-457, 461-493, 516-683
protein_graphs.py
ptm_analysis.py					56, 123-125
protzilla/data_analysis/spectrum_prediction
spectrum.py					65, 70-71, 86, 126, 129, 134, 139, 144-146, 195, 290, 319-333, 340-341, 348-354, 378, 380, 415-418, 425
protzilla/data_integration
di_plots.py
protzilla/data_preprocessing
outlier_detection.py
transformation.py
protzilla/importing
ms_data_import.py					122, 276
protzilla/methods
data_analysis.py					205, 310, 869-887, 935, 938-948, 970, 973-1014, 1033, 1036-1050, 1100
data_preprocessing.py
importing.py					144
protzilla/utilities
transform_dfs.py
ui/main
settings.py
ui/runs
fields.py
views.py					2, 11, 23-26, 254, 288, 362, 532-553
views_helper.py
ui/runs/forms
custom_fields.py					142-143, 159
data_analysis.py					320-324, 381, 431-435, 470, 518, 1176-1188, 1218-1253, 1305-1395, 1462-1470, 1508, 1530
Project Total

The report is truncated to 25 files out of 61. To see the full report, please visit the workflow summary page.

This report was generated by python-coverage-comment-action