gravatar

JamesENelson

Jim Nelson

Recently Published

ML using Decision Trees to Predict NASH from Hepatic NGS GE Profiles
Goal is to create a model using decision trees to predict the presence of definitive NASH from NGS data of the top 25 most significantly differentialy expressed genes
Random Forest Plot for NASH model using NGS data
Example plot of RF model testing 3 features at each split summary: Number of cases in table: 48 Number of factors: 2 Test for independence of all factors: Chisq = 19.601, df = 1, p-value = 9.543e-06
Random Forest Bagging Model Result Plot
model to predict the presence of NASH from the GE profile data
Rpart Decision Tree Plot Hepatic NGS GE data
model to predict the presence of NASH from the GE profile data
Kaggle Titanic project Rpart plot
Recursive Partitioning Model using Rpart,rattle and rpart.plot R packages
Hepatic GE profiles kmeans plot
Serum miR Dataset kmeans plot
Hepatic GE profiles MDS plot
3 centers
Hierarchical Clustering - Dendrogram Showing Euclidean Distances for NGS Data
Serum miR Dataset MDS
4 centers
PCA Plot Hepatic Gene Expression (NGS) Data
Hepatic GE HeatMap2
Serum miR Dataset HeatMap
Serum miR Dataset Hierarchical Clustering - Dendrogram Showing Euclidean Distances
serum miR dataset PCA Plot
Hierarchical Clustering - Heat Map of Hepatic Gene Expression (NGS) Data
Differential Gene Expression Analysis of Hepatic NGS Data Using DESeq2
DSDHT week 4 Cheminformatics
Kaggle Titanic Survivor Prediction: Comparison of Machine Learning Methods
OBJECTIVES 1. Demonstrate proficiency in R. 2. Demonstrate ability to perform appropriate data transformations and creative feature engineering. 3. Compare performance of several R Machine Learning packages. 4. Submit models to Kaggle to assess performance and obtain challenge ranking.