Skip to main content

Posts

Showing posts from May, 2017

Results from Classification Analysis

As discussed in the previous post, Vitamin K appears to be one of the important topics according to the Network Analysis that has been performed. I wanted to see whether this would be the case using Classification Algorithms.

Below is a sample run with several algorithms being applied using Scikit-Learn (some topics found are not disclosed).




We see that TYRO3, GAS6, GRB2 are among Topics that are considered highly relevant to this Research. Recall that these are Vitamin K related Genes as discussed in the previous post. However we see more new Topics coming up and these are :
1) Liver Disease
2) Mitochondria
3) Norepinephrine
4) ROS (Reactive Oxygen Species)

See below Dr Ron Davis, discussing latest findings of  Research done at Stanford regarding Chronic Fatigue Syndrome. He mentions TCA Cycle :

https://www.youtube.com/watch?v=sGBXXlQO49g&feature=youtu.be&t=463


From wikipedia, regarding TCA Cycle we read :


The citric acid cycle is a key metabolic pathway that connects carbohydr…

Machine Learning, NLP and Network Analysis-Guided Medical Research : A Case Study

Can Machine Learning help us in identifying the origin of several Medical Syndromes?

In previous posts we have seen how approximately 8 Million PubMed abstracts were collected and analyzed using Natural Language Processing (NLP) techniques. This NLP Processing is the basis for generating Data that may then be used as Input to several Machine Learning algorithms.

In this Case Study our Goal is to identify relevant Medical Topics (Topics include Genes, Biological Pathways, etc) that are most likely to direct Medical Researchers towards the origin(s) of the following Syndromes :

-Post-Finasteride Syndrome
-Post-Accutane Syndrome
-Chronic Fatigue Syndrome
-Fibromyalgia
-Gulf-War Syndrome
-Post-Treatment Lyme disease Syndrome

Before continuing, please read the following post for important disclaimershere


Note that the results shown below originate strictly from output of Machine Learning Algorithms / Network Analysis. No Human intervention has been made apart from the fact that Candidate T…