0.2.2

Minor changes only

Fixed

• now compatible with new Tensorflow 2.6, also checked by additional CI runs for Tensorflow 2.4, 2.5 and 2.6 #92

0.2.1

This release does not change any functionality, but improves speed of spectrum binning.

Changed

• Speed improvement of spectrum binning step #90

0.2.0

This release expands the functionalities of MS2DeepScore. Most important is the option to use Monte-Carlo Dropout for uncertainty evaluation of the predicted spectral similarity scores.

Added

• MS2DeepScoreMonteCarlo Monte-Carlo dropout based ensembling do obtain mean/median score and STD #65
• choice between median (default) and mean ensemble score which come with IQR and STD as uncertainty measures #86
• dropout_in_first_layer option for SiameseModel (default is False) #86
• use_fixed_set option for data generators to create deterministic training/testing data with fixed random seed #73

Changed

• small update of create_histograms_plot to make the plot prettier/better to read #85

Fixed

• solved minor unclarity with the pair selection for non-available reference scores #79
• solved minor unclarity with the addition of noise peaks during data augmentation #78

0.1.3

This release is about expanding the possible architecture choices for SiameseModel.

Changed

• Allow users to define L1 and L2 regularization of SiameseModel #67
• Allow users to define number and size of SiameseModel #64

0.1.2

Only minor additions.

Added

• create_confusion_matrix_plot in plotting #58

0.1.1

Added

• noise peak addition during training via data generators #55
• L1 and L2 regularization for first dense layer #55

Changed

• move vector calculation to separate calculate_vectors method #52

0.1.0

First working version of MS2DeepScore.