Dear MetaboAnalyst team,
Thank you for maintaining MetaboAnalyst, which we use regularly for our metabolomics analyses.
After the recent platform update, we noticed that the PERMANOVA reported in the PCA module (Statistical Analysis [one factor]) is now based on 199 permutations, whereas before the update the same analysis was based on 999 permutations. We re-uploaded the exact same dataset that previously gave 999 permutations and obtained 199, so the change does not seem to be related to our data or group labels.
Current output:
[PERMANOVA] F-value: 44.672; R-squared: 0.95132; p-value (based on 199 permutations): 0.005
With 199 permutations, the smallest attainable p-value is 0.005, which is exactly the value we obtain. For publication, we would prefer to report results based on 999 permutations and get a p-value of 0.001.
Could you please confirm whether this change was intentional, and whether there is a way to set the number of permutations to 999?
Thank you very much in advance,
Inés