The bioBakery help forum

Analysis scripts - Gut microbiome structure and metabolic activity in inflammatory bowel disease

I have recently read your paper:“Gut microbiome structure and metabolic activity in inflammatory bowel disease”, which published in " Analysis scripts employing these packages (and associated usage notes) are available from the authors upon request ". I want study from you , I am wondering if you could kindly send me the scripts program and the necessary information about it.

Hi user,

I have provided the read access to the https://github.com/biobakery/prism_metabolites repository. Please accept the github invitation in your email and feel free to continue this thread if any questions.

Thanks,
Sagun

I’m very interested “RandomForestClassifier” in rf.py script .But I can’t handle file correct file to input ,and could you send me an example file ?

I’ll caution that these scripts were part of a specific analysis workflow and not necessarily intended to take generic inputs.

That said, the RF script is taking a feature x sample table as input; the top M rows are assumed to be metadata and the remaining N rows are for training. One of the M metadata rows (diagnosis) is being selected as the property to predict.

Dear Sagun Maharjan ,
I ran ‘rf.py;’ follow your instructions,the running program reported an error ,‘run.log’ shown in the attachment , ‘test.tsv’ is my test data 。
Could you take a look at it for me?

Thank you for your assistance.
GuoqiLiu
Best wishes!

test.tsv (112 KB)

(Attachment run.log is missing)

Hi,Sagun Maharjan
My run error log as follows , please help me how to modify test.tsv file ?
test.tsv : new table with size <308 ROW x 80 COL>
test.tsv : applying head index= supplement {‘invert’: True}
test.tsv : → reduced size is <308 ROW x 80 COL>
test.tsv : applying head index= Diagnosis {‘invert’: True}
test.tsv : → reduced size is <307 ROW x 80 COL>
test.tsv : applying grep index= headers patterns= [‘A’] {‘transposed’: True, ‘in_place’: False}
test.tsv : transposed the table
test.tsv : transposed the table
: new table with size <18 ROW x 307 COL>
: transposed the table
test.tsv : applying grep index= headers patterns= [‘D’] {‘transposed’: True, ‘in_place’: False}
test.tsv : transposed the table
test.tsv : transposed the table
: new table with size <18 ROW x 307 COL>
: transposed the table
Traceback (most recent call last):
File “rf.py”, line 95, in
for train, test in skf( y1, c_folds ):
File “/usr/bin/lib/python2.7/site-packages/sklearn/model_selection/_split.py”, line 623, in init
if n_splits == ‘warn’:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()