Leveraging Scheme for Cross-Study Microbiome Machine Learning Prediction and Feature Evaluations

Abstract

The microbiota has proved to be one of the critical factors for many diseases, and researchers have been using microbiome data for disease prediction. However, models trained on one independent microbiome study may not be easily applicable to other independent studies due to the high level of variability in microbiome data. In this study, we developed a method for improving the generalizability and interpretability of machine learning models for predicting three different diseases (colorectal cancer, Crohn’s disease, and immunotherapy response) using nine independent microbiome datasets. Our method involves combining a smaller dataset with a larger dataset, and we found that using at least 25% of the target samples in the source data resulted in improved model performance. We determined random forest as our top model and employed feature selection to identify common and important taxa for disease prediction across the different studies. Our results suggest that this leveraging scheme is a promising approach for improving the accuracy and interpretability of machine learning models for predicting diseases based on microbiome data.

Decreased Gene Expression of Antiangiogenic Factors in Endometrial Cancer: qPCR Analysis and Machine Learning Modelling

“…Additionally, in order to be able to model the combined data from the TCGA dataset and the data from our study, a novel approach to data merging (and normalisation) was utilised, building upon previous ideas on combining different datasets [25,28]. As the results are promising, a further study to identify whether the method could be generalised might be interesting.…”

“…Combining a generally available dataset with a part of the target dataset to increase dataset size and reduce model overfitting has been described previously [25], however, with directly mergeable data. Since TCGA and study data were measured using a different approach, a normalisation process needed to be devised to allow the data to be merged.…”