Trader as a new optimization algorithm predicts drug-target interactions efficiently.

Area of Science:

• * Computational biology and bioinformatics.
• * Machine learning and artificial intelligence.
• * Drug discovery and development.

Background:

• * Existing machine learning methods for predicting drug benefits have limitations in accuracy.
• * Efficient prediction of drug-target interactions (DTIs) is crucial for identifying new drug applications.
• * Novel optimization algorithms are needed to enhance machine learning model performance.

Purpose of the Study:

• * To introduce a novel machine learning method based on the Trader optimization algorithm.
• * To evaluate the performance of the Trader algorithm against state-of-the-art optimization techniques.
• * To demonstrate the efficacy of the Trader-trained neural network in predicting drug-target interactions (DTIs).

Main Methods:

• * Development of a new optimization algorithm named Trader.
• * Comparison of Trader with ten other optimization algorithms using benchmark functions.
• * Design and training of a multi-layer artificial neural network using the Trader algorithm for DTI prediction.
• * Validation of the proposed method on DTI datasets and comparison with existing approaches.

Main Results:

• * The Trader algorithm demonstrated superior performance compared to ten other optimization algorithms.
• * The Trader-trained neural network achieved significant accuracy in predicting unknown drug-target interactions (DTIs).
• * The proposed method overcomes limitations of existing optimization algorithms, yielding improved outcomes.

Conclusions:

• * The novel Trader optimization algorithm enhances machine learning model performance for DTI prediction.
• * This approach offers a more accurate and efficient tool for drug discovery and repurposing.
• * The developed machine learning method shows significant potential for advancing pharmaceutical research.