# An optimized deep-forest algorithm using a modified differential evolution optimization algorithm: A case of host-pathogen protein-protein interaction prediction

## TL;DR

This paper introduces a modified differential evolution algorithm to optimize a deep forest model for predicting host-pathogen protein interactions, achieving high accuracy and efficiency.

## Contribution

A novel modified differential evolution algorithm is introduced to improve hyperparameter optimization in deep forest models for protein-protein interaction prediction.

## Key findings

- The modified DE algorithm outperformed traditional optimization methods in accuracy, sensitivity, and precision.
- The optimized model predicted seven novel host-pathogen interactions.
- The model was implemented as a web application for practical use.

## Abstract

Deep Forest employs forest structures and leverages deep architecture to learn feature vector information adaptively. However, deep forest-based models have limitations such as manual hyperparameter optimization and time and memory usage inefficiencies. Bayesian optimization is a widely used model-based hyperparameter optimization method. Evolutionary algorithms such as Differential Evolution (DE) have recently been introduced to improve Bayesian optimization’s acquisition function. Despite its effectiveness, DE has a significant drawback as it relies on randomly selecting indices from the population of target vectors to construct donor vectors in search of optimal solutions. This randomness is ineffective, as suboptimal or redundant indices may be selected. Therefore, in this research we developed a modified differential evolution (DE) acquisition function for improved host-pathogen protein-protein interaction prediction. The modified DE introduces a weighted and adaptive donor vector technique that selects the best-fitted donor vectors as opposed to the random approach. This modified optimization approach was implemented in a deep forest model for automatic hyperparameter optimization. The performance of the optimized deep forest model was evaluated on human-Plasmodium falciparum protein sequence datasets using 10-fold cross-validation. The results were compared with standard optimization methods such as traditional Bayesian optimization, genetic algorithms, evolutionary strategies, and other machine learning models. The optimized model achieved an accuracy of 89.3 %, outperforming other models across all metrics, including a sensitivity of 85.4 % and a precision of 91.6 %. Additionally, the optimized model predicted seven novel host-pathogen interactions. Finally, the model was implemented as a web application which is accessible at http://dfh3pi.covenantuniversity.edu.ng.

•A modified differential evolution (DE) method was designed to improve the selection of hyperparameter configurations.•The modified DE outperformed existing optimization algorithms, including genetic algorithms and evolutionary strategies.•The modified DE demonstrated competitive time and memory efficiency in multiple experiments.•The modified DE was used to optimize the deep forest model for predicting human-Plasmodium falciparum PPIs.•The optimized DF was validated on customer churn and MNIST datasets and was later developed into a tool for PPI prediction.

A modified differential evolution (DE) method was designed to improve the selection of hyperparameter configurations.

The modified DE outperformed existing optimization algorithms, including genetic algorithms and evolutionary strategies.

The modified DE demonstrated competitive time and memory efficiency in multiple experiments.

The modified DE was used to optimize the deep forest model for predicting human-Plasmodium falciparum PPIs.

The optimized DF was validated on customer churn and MNIST datasets and was later developed into a tool for PPI prediction.