Hello, I'm a biologist interested in machine learning application in genomic data; specifically, I'm trying to apply clustering techniques to differential gene expression data.
I started by understand the basics of unsupervised learning and clustering algorithms with random datasets, but now I need to apply some of that algorithms (k-means, PAM, CLARA, SOM, DBSCAN...) to differential gene expression data and, honestly, I don't know where to begin, so I'd be grateful if someone can recommend me some tutorials or textbooks, or give me some tips.
Thank you for your time!
PD: I'm mainly using R language, but if Python tutorials are also OK for me.
Hello!
Differential expression analysis - https://master.bioconductor.org/help/search/index.html?q=differential+gene+expression/
Example:
https://master.bioconductor.org/packages/release/workflows/vignettes/rnaseqGene/inst/doc/rnaseqGene.html
Dear Antonio Manuel Parra Sevilla,
Look the link, please.
https://books.google.az/books?id=Xb3IeXdtQVwC&pg=PA204&lpg=PA204&dq=clustering+DGE+datasets&source=bl&ots=K_n5fHquEL&sig=ACfU3U3j9Mt9kROY3PzZ2OO0ADUuHHaWbA&hl=ru&sa=X&ved=2ahUKEwikrrHdq7HkAhVOwqYKHcFoBFoQ6AEwD3oECAkQAQ#v=onepage&q=clustering%20DGE%20datasets&f=false
Regards,
Shafagat
For a quick analysis you can visit this website
https://software.broadinstitute.org/morpheus/
Regards,
Pratyay
Anton N. Gvozdetsky , Shafagat Mahmudova , Pratyay Sengupta thank you all so much!
Regards,
Antonio
I'm not sure if this is what you mean, but clustering only the DGEs (meaning only the genes that are significantly different), would violate clustering's assumptions about not knowing (being agnostic to) treatment group labels. I'm not saying it's not useful, but the interpretation of the output is not the same as clustering the whole data set.
In addition to above suggestions, the older stand-alone version of Multi-experiment viewer (MEV- free) can also do K-means, SOM, hierarchical support trees, and some others. (here- https://sourceforge.net/projects/mev-tm4/). It IS free, and can be buggy- hasn't been updated since 2017. With that caveat said...
To get started, save your dataset as a tab-delimited text file (first row is sample names, first column is gene IDs- you can have more label rows and columns but it gets messy). Download the MEV folder to your desktop from source forge, open the folder, double click 'MeV', a Multi-experiment viewer menu bar opens, click 'File', click 'New Multiple Array Viewer', this opens a new window. Inside that window, click File -> Load Data->Browse, navigate to your text file (make sure you're 'single color' radio button is selected, unclick 'load annotations').
A preview of your file will appear in the preview window- click the upper left-most cell with data in it, click LOAD. You should see a heatmap of your data with a navigation panel along the left side, and a series of options for different approaches at the top. Once you select an analysis, a dialog box for that analysis opens, select your preferences and click 'OK'. Pay attention to the left side navigation panel, a new selection will appear when your analysis is complete.
Hope that helps.
Thank you so much, Eric M Blalock ! It is very useful for my work!
And yes, you're right: I'm actually applying clustering algorithms on all RNA-Seq data (not just on differential expressed genes).
I guess what you mean is clustering the expression pattern of your transcriptome. In this case, I recommend you M-fuzzy package in R. This package was especially designed for RNA expression. Its soft clustering and have a fancy output. The tool itself is user friendly and the manual is well described. If you have any question, just let me know.
Best
DNA Methylation Data Analysis Workshop
How to use bisulfite-treated sequencing to study DNA methylation
When?
12-15 November 2019
Where?
Berlin, Germany
Link?
https://www.ecseq.com/workshops/workshop_2019-07-NGS-DNA-Methylation-Data-Analysis
An earlier workshop free of charges on the same topic as David Langenberger mentioned is taking place next week at the University of Freiburg.
https://www.denbi.de/training/663-galaxy-for-linking-bisulfite-sequencing-with-rna-sequencing
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Bioinformatics
- Bioinformatic Tools