If I have two inter-specie gene expression data, what are the metrics to use and how do I get such metrics to determine interaction between the genes.
Is gene expression level sufficient to base an interaction ?
I want a machine learning approach and not homology/interolog search approach that can also do this. Practical approach that highlights step by step procedure of achieving the task.
Hello Jummy, there are lots of similarity measures that could be used to find correlation between items in a dataset. Here are examples of such metrics:
Cosine Similarity, Pearson Coefficient, Euclidean Distance, Jaccard Coefficient, Tanimoto Coefficient (the first three are commonly used. Also, the nature of your datasets will also dictate too.). Some of these metrics are also explained further below.
https://reference.wolfram.com/language/guide/DistanceAndSimilarityMeasures.html
http://mines.humanoriented.com/classes/2010/fall/csci568/portfolio_exports/mvoget/similarity/similarity.html
Best!
Thanks. The metrics I'm actually talking about had to do with biological metrics because i'm dealing with biological datasets. Like kind of feature selection. Example, gene expression levels etc
- Badges
- Science topic