Confirm growth for the csc031-gem model

djinnome commented 1 month ago

The model grows using cobra, but we have yet to confirm growth in memote.

djinnome commented 1 month ago

In memote, we have the following report.

https://pnnl-predictive-phenomics.github.io/csc031-gem/diff5788e60b72070a4f7f6a353a1364c693c036bd0f

Even though we have an accuracy of 63%, it is attained without any true positives or false positives: the genome-scale model for csc031 can't grow under any condition

{"model.xml":{"TP":[],
"TN":[3,6,8,9,11,16,18,19,20,21,23,24,26,27,28,29,31,32,33,34,35,36,37,38,39,40,41,42,43,44,47,48,49,53,56,57,58],
"FP":[],
"FN":[0,1,2,4,5,7,10,12,13,14,15,17,22,25,30,45,46,50,51,52,54,55],
"TPR":0,"TNR":1,"PPV":null,"FDR":null,
"ACC":0.6271186440677966,"MCC":null}}

mcnaughtonadm commented 1 month ago

Good catch, this is something happening for I believe all the models. We are getting only True/False Negatives and no True/False Positives.

JamesPino commented 1 month ago

You can check the media. This happened when using some m9 media for one of the other models. Turns out it was using default media, not the one supplied in experimental.yml. There's also a growth rate you can set in that file that if you set too high all fails. If you don't set one, it runs the model and uses a threshold to that growth value.

On Fri, Aug 2, 2024, 18:01 Andrew McNaughton @.***> wrote:

Good catch, this is something happening for I believe all the models. We are getting only True/False Negatives and no True/False Positives.

— Reply to this email directly, view it on GitHub https://github.com/pnnl-predictive-phenomics/csc031-gem/issues/2#issuecomment-2266195266, or unsubscribe https://github.com/notifications/unsubscribe-auth/AA6NQWD45IEBHOHAOZERW73ZPP6T5AVCNFSM6AAAAABKASTO7CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENRWGE4TKMRWGY . You are receiving this because you are subscribed to this thread.Message ID: @.***>

pnnl-predictive-phenomics / csc031-gem

Confirm growth for the csc031-gem model #2