Data Mining and Machine Learning Technologies

Dear Colleagues,

This Special Issue focuses on the application of data mining and machine learning techniques in protein engineering and design. We examine the transformative impact of modern computational methods on understanding, predicting, and redesigning protein structures. Particular attention is given to how artificial intelligence and deep learning models address the fundamental challenges in protein engineering: stability prediction, energy calculations, mutation analysis, and de novo protein design.

Scope:

This Special Issue encompasses the following topics:

• Machine learning models for predicting protein stability and mutation effects;
• Diffusion models and generative AI approaches for de novo protein design;
• Deep learning techniques for modeling protein–protein interactions;
• Innovative algorithms for protein energy calculations and conformational sampling;
• Data mining methods enabling efficient analysis of large protein databases;
• High-throughput computational screening platforms developed for protein engineering;
• Integration of physics-based and data-driven approaches in protein design;
• Machine learning approaches supporting enzyme optimization and function prediction;
• Industrial and biomedical applications of AI-assisted protein design systems;
• Novel computational tools addressing challenges in the protein engineering field;
• Structure-based protein design with deep learning frameworks;
• Sequence-to-structure-to-function prediction models;
• Rational design of protein binding interfaces using computational approaches;
• Neural network architectures specialized for protein structure prediction;

Purpose:

The purpose of this Special Issue is to consolidate the latest advancements in data mining and machine learning in protein engineering and design, foster knowledge sharing in this interdisciplinary field, and highlight innovative research that bridges electronics, computation, and bioengineering disciplines. Additionally, we aim to demonstrate the advantages that AI-assisted approaches offer compared to traditional methods in protein design and to identify future directions in this rapidly evolving field.

How the Issue Will Usefully Supplement Existing Literature:

This Special Issue will contribute to the existing literature in the following ways:

1. Interdisciplinary Integration: By bringing together electronic engineering, computer science, and biomedical engineering in the context of protein engineering, this Special Issue will establish bridges between disciplines that are often treated separately. This integration is particularly valuable as the boundaries between traditional academic fields continue to blur in the era of computational biology.
2. Methodological Advancements: While most protein engineering research published in biomolecular journals focuses on biological outcomes, this Special Issue will place special emphasis on computational methodology and algorithm development. This focus will provide a deeper understanding of the mathematical and computational foundations underlying modern protein engineering approaches.
3. Technology Transfer: This Special Issue will facilitate the transfer of cutting-edge technologies developed in electronics and computer science to the field of protein engineering, thereby accelerating the adoption of new tools and techniques in biomolecular design. This cross-pollination of ideas is essential for advancing the frontier of protein engineering capabilities.
4. New Paradigms: Traditional protein engineering often relies on laboratory-based trial-and-error methods, whereas this Special Issue will demonstrate how computation-centric and data-driven approaches can be more efficient and effective. These new paradigms have the potential to revolutionize how proteins are engineered, moving from labor-intensive experimental approaches to more predictive computational strategies.
5. Current Challenges: The recent literature has highlighted unresolved challenges in applying machine learning models to protein engineering. This Special Issue will address these gaps by presenting new solutions and methodologies that overcome existing limitations. By directly addressing current technical hurdles, we aim to propel the field forward.
6. Emerging Trends: The impressive success of recent AI models like AlphaFold and RoseTTAFold in protein structure prediction is transforming the field of protein engineering. This Special Issue will document the latest trends and advancements in this evolving area, providing researchers with a comprehensive overview of the state-of-the-art.
7. Application-Oriented Research: By combining theoretical research in protein engineering with practical applications in electronics and computer science, this Special Issue will lay the groundwork for more application-oriented studies. This emphasis on practical implementations will help bridge the gap between academic research and industrial applications.
8. Comprehensive Review of Computational Tools: While numerous computational tools have been developed for protein engineering, comprehensive reviews and comparisons of these tools are lacking in the current literature. This Special Issue will provide critical analyses of existing tools, helping researchers select the most appropriate methods for their specific protein engineering challenges.
9. Exploration of Novel AI Architectures: The Special Issue will examine how specialized neural network architectures can be designed specifically for protein-related tasks, going beyond the application of general-purpose machine learning models to address the unique challenges of protein engineering.
10. Integration of Multiple Data Modalities: The current literature often focuses on single-modal approaches to protein design. This Special Issue will explore how multiple data modalities (sequence, structure, function, and evolutionary information) can be integrated within unified computational frameworks to enhance protein design capabilities.

This Special Issue, by focusing on the computational aspects of protein engineering and design, will both expand the focus area of the Electronics journal and provide a valuable resource to the protein science and engineering community. It will serve as a vital reference for researchers at the intersection of electronics, computation, and protein engineering, documenting the latest methodological innovations and practical applications in this rapidly evolving field.

Prof. Dr. Ecir Uğur Küçüksille
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• artificial intelligence
• deep learning
• protein engineering
• de novo protein design
• computational biology
• data mining
• structure prediction
• energy calculations
• protein stability
• mutation analysis
• generative AI
• diffusion models
• molecular design
• bioinformatics