Niek de Jonge

It might also be possible to add a method for required pre filtering for each filter step, that specify which other filter steps are expected to already have been done....

I agree that SpectrumProcessor and the regrouping of the filters solve the most important points already. I did not think of the decorator option before, but that might indeed be...

We have something like this also implemented in MS2Query as well: https://github.com/iomega/ms2query/blob/main/ms2query/run_ms2query.py Here we do not use the latest version available on Zenodo, but this can be done by changing...

In the branch #129 I have implemented a method for training MS2Deepscore that should automatically store the .spectrum_binner information in the correct way. The important part is to save the...

Yes that certainly makes sense. I was thinking by having a default function other developers could use this function as starting point before altering binning choices and network dimension.

@hechth Looks good, thanks! I added a few comments, with a few small changes. I did approve the tests running: https://github.com/iomega/spec2vec/actions/runs/10367293699/job/28705599784 but it seems there is still something going wrong...

@hechth linting passes, but I don't have the rights to add secrets to fix the sonarcloud issue. I have now just removed sonarcloud and created an issue #96 to repair...

The issue with Pypi is an open issue: https://github.com/pypa/readme_renderer/issues/304

@florian-huber I have some new PRs I have to open, to make the branch structure not too complex I will already merge this PR. I will create an issue, to...

A similar issue was mentioned before in #608 For loading MSP files we could change: with open(filename, 'r', encoding='utf-8') as f: in line 58 to with open(filename, 'r', encoding='utf-8', errors="ignore")...