SMLG (Statistical Machine Learning Group) Discussion Forum

This week I spent time normalizing my data according to Dr. Yoo's feedback.
My data had missing values and needed additional GPL's to fill in gaps.
GSE 20926 contained data that I ended up discarding due to containing NULL values.
Additional, I was able to meet with Efrain and discuss how to remove replicates and obtain z-scores with averaged raw scores.
My next step will be to gather all my datasets and generate a file with exposed vs controlled with hourly
The code was able to remove and clean the series matrix file and it should be ready
Best,

Juan Morales

This week I did a Pearson Correlation based scatterplot of all 20,478 transcripts measured by RNAseq on my patient population. The plot shows that none of the transcripts on their own show a strong linear correlation with either the discretized OS or the OS (months) treated as a continuous variable because in both cases the highest absolute values of Pearson correlation coefficients reached somewhere between 0.3 and 0.4 max.

I am also looking a bit further into the patterns observed within the Banjo based networks I have generated thus far - this should take a considerable amount of time.

This week I worked on trying to learn a little bit about the theory behind different types of scoring methods including BD, BDe, and BDeU - and I learnt from Lauren the log normalization technique that the SML group uses to compare BDe scores and to determine the likelihood of a particular network truly being the best among all the networks scanned.

This week I have been able to install Putty in my workstation but I still need to master the coding for Ubuntu
I also ran static simulations in Banjo 1 hour each.
Chemicals involved were Nickel, Lead, Arsenic and Cadmium
The next step will be to obtain my output since I left them running.
I encountered problems were Banjo did not detect the directory were my observational data was situated.
Later I realized that it was a simple syntax error. I also sat down with Lauren and Kaumudi but need more time to evaluate my results.
There were other errors in regards to the number of columns not matching the variables.

Best,
Juan

Hello~

I post the naive manual to help beginners who start to learn Bayesian, Banjo, GeNIe, Cytoscape and other code.

I hop to help you~