# Comparing Neural Networks and Naive Bayes in the Prediction of Drug Gene Interactions of Type 4 Collagenase for Gingival Epithelialization

## TL;DR

This study compares neural networks and Naive Bayes in predicting drug-gene interactions for type 4 collagenase in oral health.

## Contribution

The study evaluates and contrasts the performance of neural networks and Naive Bayes for drug-gene interaction prediction in gingival epithelialization.

## Key findings

- Naive Bayes outperforms neural networks in accuracy, precision, F1 score, and recall.
- Neural networks show high complexity but lower specificity, leading to higher false-positive rates.
- The models can aid in personalized medicine by identifying drug targets and biological pathways.

## Abstract

This study aims to compare the predictive abilities of neural networks and Naive Bayes in forecasting drug–gene interactions of type 4 collagenase in gingival epithelialization.

This study examines drug–gene interactions in type 4 collagen using a dataset encompassing drugs, genes, biochemical activity, mode of action, and molecular activity. Data normalization and handling of missing values are conducted to minimize the influence of larger variables. Machine learning algorithms such as neural networks and Naïve Bayes forecast or categorize drug–gene interactions. The neural network architecture, featuring 10 hidden layers, the ReLU activation function, the Adam optimizer, regularization, and a maximum of 100 iterations, is adept at solving complex problems.

Naive Bayes demonstrates a high area under the curve of 0.995 and notable classification accuracy (CA), but registers low overall accuracy and F1 score. It outperforms the Neural Network model in accuracy, precision, F1 score, and recall, but exhibits low specificity, potentially leading to elevated false‐positive rates.

Predictions of drug–gene interactions for type 4 collagen hold promise for understanding biological pathways, identifying drug targets, designing targeted therapies, understanding disease mechanisms, and facilitating personalized medicine. The predictive models employed provide potential applications in personalized medicine, facilitating targeted therapies and disease management strategies. By elucidating biological pathways and drug targets, this research holds promise for advancing clinical interventions and improving patient outcomes in oral health care.