linah73 Goto Github PK

cadd

AI/ML drug discovery. Machine learning model to predict activity of anti-cancer compounds and library generation of kinase inhibitors targeting CDK9/cyclin T1..

cancer_mortality_prediction

Built a regression model to predict regional cancer mortality rate in the United States and analyzed the impact of contributing factors such as healthcare accessibility and socioeconomic status. Employed XGBoost regression algorithm to build the optimized model.

datascienceguidedcapstone

dsc_v5

Files relating to DSC V5 Curriculum

google-analytics-insights

Google analytics

identifying-immune-boosting-foods

Developed a Random Forest classification model to classify grocery food items based on their immune-boosting properties using CDC NHANES clinical data. Determined the relative micronutrient contribution to immunity strength and developed a food scoring system based on the on the weighted importance of the micronutrient content.

sales-forecasting-pharma-

Time-series analyses and forecasts of monthly sales of drugs used to treat obstructive airway diseases. Analyzed sales data for one pharmacy over six years. Applied Seasonal ARIMA to make sales prediction.

springboard

Data analytics and data science case study completed projects

supermarket-sales-prediction

Exploratory data analysis of sales for a supermarket chain store and regression model to predict yearly sales.

synthea

Exploratory data analysis of healthcare records using Synthea synthetic EHR data. Built a classification models to predict diabetes using EHR data. Employed logistic regression and Random forest algorithms.