Implement machine learning prediction

[rvhonorato]

This PR adds the feature to use a machine-learning based approach using the results of the predictors as features.

Adds keras_classifier_scriber_ispred4_sppider_csm_potential_scannet model

[codecov]

Codecov Report

Patch coverage: 89.03% and project coverage change: +0.63% 🎉

Comparison is base (25c807c) 75.85% compared to head (89a6fd4) 76.48%.

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #75      +/-   ##
==========================================
+ Coverage   75.85%   76.48%   +0.63%     
==========================================
  Files          26       28       +2     
  Lines        1354     1428      +74     
==========================================
+ Hits         1027     1092      +65     
- Misses        327      336       +9     

Flag	Coverage Δ
unittests	76.48% <89.03%> (+0.63%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files Changed	Coverage Δ
setup.py	0.00% <ø> (ø)
src/cport/modules/predict.py	77.78% <77.78%> (ø)
tests/test_predict.py	96.56% <96.56%> (ø)
src/cport/modules/ispred4.py	74.36% <100.00%> (ø)
src/cport/modules/predictprotein_api.py	79.37% <100.00%> (ø)
src/cport/modules/scannet.py	62.83% <100.00%> (+1.49%)	⬆️
src/cport/modules/sppider.py	78.09% <100.00%> (ø)
src/cport/modules/utils.py	73.65% <100.00%> (+0.55%)	⬆️
src/cport/modules/whiscy.py	44.80% <100.00%> (+1.79%)	⬆️

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[rvhonorato]

@AldovdN please add some more information about how the model was trained as a new comment here (: