Category: Originals
-
![Iterative Knockout for Feature Importance in Neural Networks [Python] [Keras]](https://piper-writes.blog/wp-content/uploads/2018/05/system-2660914_1920.jpg?w=1024)
Iterative Knockout for Feature Importance in Neural Networks [Python] [Keras]
Python package/scripts for determining feature importance and high order interactions in a recurrent neural network in Keras.
-

Genome Wide Association Study & Manhattan Plot Tutorial
Using Gemma to calculate association between phenotypes and genetic variants. Manhattan plots in Python as well.
-

Linkage Disequilibrium, Human Population Diversity, and the Hemoglobin Gene
Introduction Linkage disequilibrium is a somewhat rudimentary, but effective way to measure of the evolution of a population. It is, essentially, a quantification of the association between alleles (which, in this case, includes single nucleotide variants) as they exist in a population. In a fixed, non-evolving population, there should, theoretically be no association, and all…
-

Tracking the Flu with Twitter & Machine Learning
Scraping, geolocating, and classifying tweets to survey cases of the flu.
-

Population STRUCTURE of Arctic Dogs & Wolves – How Similar Are They?
Overview Arctic dogs are now lovable pets, but were once bred for their ability to pull a sled around. What’s more interesting, at least to me, is that they share a high degree of genetic similarity with wolves. Here, I’m going to be looking at the Arctic Dog clade to understand the relationships between the…
-

Using Coalescent Analysis to Map the 2016 Zika Virus Outbreak
In this write-up, I’ll retrieve and process Zika genome data, use Bayesian software to generate a Zika gene tree, and propose a route that Zika took to get from Africa to the Americas.
-

Creating Baroque Music with a Recurrent Neural Network
Training a recurrent neural network to generate baroque music in Python.