fairfolio
Saved Projects
← Back to Explore

Novel Stacked Ensemble Machine Learning (SEML) Model for Prediction of Viral Zoonoses

JSHS · 2023

Benjamin Li, Mr. Christopher Cook · Millburn High School, Millburn, NJ

Overview

75% of newly emerging infectious diseases, including Ebola and Rabies, are zoonotic. Originating from animals, zoonotic diseases comprise over 2 billion cases of illness and 2.7 million deaths annually. Traditionally, predicting viral zoonotic status requires laboratory experiments and field surveillance, which are time-consuming and expensive. Existing computational algorithms improve the speed of prediction, but are trained on insufficient datasets, lack feature exploration for transforming genomic sequence data, and utilize basic machine learning architectures that limit performance. This study remedies these limitations using a novel stacked ensemble machine learning (SEML) model trained on a merged genomic sequence dataset containing new feature definitions to better anticipate the zoonotic potential of viruses. The base models within the SEML model - extreme gradient boosting (XGBoost), multi-layer perceptron (MLP), and random forest - were optimized through hyperparameter tuning and balancing to avoid overfitting. Predictions generated from the base models were used to train the meta learner of the SEML model, logistic regression. Results show that the SEML model has great potential to provide reliable and robust results, improving precision-recall AUC by 80% over some previous literature’s models and 10% over its base models. This novel SEML model has the potential to advance and expedite the research of zoonotic viruses.

Competition history

  • JSHS 2023 Category not listed

Resources

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Source: Junior Science and Humanities Symposium

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google