# Input for Trainning MelonnPan

**URL:** <https://forum.biobakery.org/t/input-for-trainning-melonnpan/2905>\
**Category:** MelonnPan\
**Created:** [December 16, 2021, 1:16am UTC](https://forum.biobakery.org/t/input-for-trainning-melonnpan/2905 "2021-12-16T01:16:04Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![y3zhu](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.biobakery.org/y3zhu/32/1080_2.png) [@y3zhu](https://forum.biobakery.org/u/y3zhu)\
**Post date:** [December 16, 2021, 1:16am UTC](https://forum.biobakery.org/t/input-for-trainning-melonnpan/2905/1 "2021-12-16T01:16:04Z")

</div>

Hi there, @himel.mallick

I am working on metagenomic samples from patients with a disease other than IBD. I want to get the predicted metabolome of the samples. What input do I need to give MelonnPan to train the model: metabolomic data from the disease I’m working with? If I couldn’t collect the metabolomic data, is there another way to train the model?

Thank you very much.