Towards Personalized Medicine: Using Machine Learning to Predict Immunotherapy Effectiveness on Heterogenous Tumors in silico
JSHS · 2023
Overview
Personalized medicine has the potential to revolutionize patient care using targeted therapeutics. Within the field of personalized medicine, simulation of tissue-scale biological systems has shown great potential in analyzing the effects of therapeutics. PhysiCell, an open-source agent-based modeling simulation platform, has the capability to model interactions of immune and cancer cells. However, PhysiCell simulations are time-consuming due to the millions of interacting cells. Machine learning presents a promising solution to predict the efficacy of a cancer treatment without running a PhysiCell simulation. Using PhysiCell, a training data set composed of 2000 immunosurveillance simulations was created with various parameters values. The simulations were run with two separate tumor morphologies based on histopathological images of pancreatic adenocarcinoma. Training data was used to create both a random forest classifier and a random forest regressor for each morphology. These trees predict the fraction of dead cancer cells based on parameter values and rank the parameter importance in predicting the fraction of dead cancer cells. The classifier predicted the fraction of dead cancer cells with accuracies of 70.91% and 84.55% for Morphologies One and Two, respectively. The regressor predicted the fraction of dead cancer cells with accuracies of 69.39% and 84.55% for Morphologies One and Two, respectively. The parameter importance rankings for regression and classification showed similarities within each morphology, while the parameters of importance varied between the two morphologies. Also, the regressor generates a prediction in under 10 seconds for a parameter set, while a PhysiCell simulation can take up to 40 minutes.
Competition history
- JSHS 2023
Resources
Related projects
ISEF · 2021
Machine Learning to Predict Response to Anti-PD1 in Melanoma Using Genetic Biomarkers
ISEF · 2024
Unraveling the Complex Interplay Between Immune Cells and Cancer Progression Utilizing a Novel Application of an Artificial Neural Network
ISEF · 2016
Predictive Modeling of Optimal Cancer Therapies
ISEF · 2017
A Novel Pan-Cancer Approach to Quantify Tumor Mutational Burden and Clinical Data Predictors for Immunotherapy Response towards Personalized Medicine
ISEF · 2025
Machine Learning for Increasing the Response Rate of Breast Cancer Patients to Neoadjuvant Therapy
ISEF · 2016
A Machine Learning Approach for Predicting Drug Efficacy
ISEF · 2020
A Real-Time miRNA-based Machine Learning Approach for Precision Cancer Therapeutics
ISEF · 2023
Identifying Relationships Between the Gut Microbiome and Melanoma Patients' Responses to Immunotherapy Using Machine Learning Techniques
Closest projects by meaning, across every fair and year in the corpus.