Hello,
I am new to Songbird. I am trying to use the standalone version of Songbird to perform a multivariate analyzis on our 16S sequencing data.
Following the tutorial (https://github.com/biocore/songbird), I first ran an null model using the command below:
##Null Model
songbird multinomial
–input-biom Collapsed-only-horns_no-miss-table-dada2.biom
–metadata-file POSTPARTUM_mapping_sample_key.txt
–formula “1”
–epochs 10000
–differential-prior 0.5
–summary-interval 1
–summary-dir Null_results
And got the following output (first page only):
Then, I ran two extra models. One full model (all covariates included) and another model removing only one covariate.
##Full model example
songbird multinomial
–input-biom Collapsed-only-horns_no-miss-table-dada2.biom
–metadata-file POSTPARTUM_mapping_sample_key.txt
–formula “OBS+Class+TRT+Cow_ID+Site+Cycling”
–epochs 10000
–differential-prior 0.5
–summary-interval 1
–summary-dir results
In the Cross validation graphs, the CV error is much higher than the one shown in the tutorial. Are my results for this first two models within the acceptable range? Any recommendations for improvement?
Based on the pictures above, it doesn’t seem to be a big difference between “results_full_formula_10_12_2020” and the “results_no-TRT” (perhaps the latter slightly better).
I also ran a third model excluding an additional covariate. However, the results showing on TensorBoard included only the null model and the last one I ran (the two previous models were not available on Tensorboard). Is there a way to fix this so I can compare multiple models in Tensorboard?
Using Gneiss, it’s very easy to check the effect of each covariate using the regression summary output. Is there a equivalente way in Songbird to evaluate the effect of individual covariates included in the model?
@mortonjt - If at all possible, I would really appreciate to hear your thoughts on this!