Closed Leon-Bichmann closed 5 years ago
I have never seen this issue before. Can you reproduce a minimal example? With so few decoys, there is probably an issue, e.g. too many identical data points, in one of the folds.
I see - so you mean I should reduce the number of targets in the library to a similar range and test it again?
What could be the reason for so few decoy hits?
What kind of data are you using? Is this DIA, SRM or DDA? Are the scores generated by OpenSWATH or a different tool?
How big is the library?
I am analysing DIA Data generated with the OpenSWATH tools in OpenMS.
The library contains 6800 transitions with 50% decoys, each with min and max 6 transitions.
Probably you have nan
or some inf
etc values in the matrix which pyprophet
passes to the LDA
implementation from scikit-learn
.
You might use a debugger and set a breakpoint at https://github.com/PyProphet/pyprophet/blob/master/pyprophet/classifiers.py#L70 to see what features and labels you pass to the classifier.
Ok, running it inside the pyprophet/master docker container worked fine. Maybe there is a problem with my local installation.
Hi,
I'm getting a couple of problems when trying to run pyprophet on my data:
My target - decoy distribution is quite uneven, which is maybe the source of the problem:
When running pyprophet I often run into a SVD convergence problem:
or a segmentation fault:
However after trying a couple of times it also works sometimes..