# "task 7 failed - "y is constant; gaussian glmnet fails at standardization step"

**URL:** <https://forum.biobakery.org/t/task-7-failed-y-is-constant-gaussian-glmnet-fails-at-standardization-step/272>\
**Category:** MelonnPan\
**Created:** [March 12, 2020, 3:00pm UTC](https://forum.biobakery.org/t/task-7-failed-y-is-constant-gaussian-glmnet-fails-at-standardization-step/272 "2020-03-12T15:00:11Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Chris\_T](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.biobakery.org/chris_t/32/145_2.png) [@Chris\_T](https://forum.biobakery.org/u/Chris_T)\
**Post date:** [March 12, 2020, 3:00pm UTC](https://forum.biobakery.org/t/task-7-failed-y-is-constant-gaussian-glmnet-fails-at-standardization-step/272/1 "2020-03-12T15:00:11Z")

</div>

I’m trying to run melonnpan.train on a filtered list of UniRef90 and metabolite features. Has anyone run into this problem before?

Error in { :  
task 309 failed - “task 7 failed - “y is constant; gaussian glmnet fails at standardization step””

---

<div class="post-metadata">

**Author:** ![himel.mallick](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.biobakery.org/himel.mallick/32/1757_2.png) [@himel.mallick](https://forum.biobakery.org/u/himel.mallick)\
**Post date:** [March 12, 2020, 3:24pm UTC](https://forum.biobakery.org/t/task-7-failed-y-is-constant-gaussian-glmnet-fails-at-standardization-step/272/2 "2020-03-12T15:24:59Z")

</div>

Hi @Chris_T - this will happen if, during the cross-validation, any of the response variables (i.e. metabolites) only contains a few non-unique values within a fold. Could you please make sure the metabolites have at least 5 or 10 unique values post-filtering as glmnet and melonnpan.train does 10-fold CV by default? Alternatively, you could also do a 3-fold or 5-fold CV if further filtering is not feasible. Hope this helps. Thanks!