Dear All, We wanted to make participants aware of a small change to the code in the [GitHub repository](https://github.com/Sage-Bionetworks-Challenges/Anti-PD1-DREAM-Examples) that acts as a Docker example of Shirley Liu's TIDE model. Output values from TIDE are normally lower when they predict response to ICI's and higher when they predict non-response (this can be seen at about 3 minutes and 30 seconds into their [tutorial video](http://tide.dfci.harvard.edu/)). We have added to code to flip this such that it corresponds to what is expected in this Challenge. The specific change is [here](https://github.com/Sage-Bionetworks-Challenges/Anti-PD1-DREAM-Examples/blob/d580259752f2d3bc540b5d5e2b65443d7dabfb77/tide/run_tide.py#L51). We apologize for any confusion this may have caused. Kind Regards, Mike