AI-Driven Advancements in Bioinformatics: Harnessing Explainable Deep Learning for Unraveling Complex Biological Insights

Dear Colleagues,

The explosion of biological data in the field of molecular biology over the past few decades has presented both opportunities and challenges. While traditional biophysical and biochemical techniques offer precise data, their scalability for processing large-scale omics data remains limited. As a consequence, the gap between the known and unknown aspects of biological data has been widening, necessitating the urgent implementation of high-throughput approaches to efficiently handle data generation, cleaning, analysis and sharing. In this context, bioinformatics technologies have emerged as a powerful and transformative solution, harnessing in silico methods such as molecular modeling, pattern recognition, machine learning and explainable deep learning to address the complexities and sheer volume of big data in both biology and medicinal drug design. The overarching goal of this Special Issue is to illuminate the cutting-edge high-throughput explainable artificial intelligence approaches that can effectively address the challenges presented by big data in the realm of bioinformatics. We invite contributions from the scientific community that delve into innovative and interdisciplinary methods, incorporating mathematical, statistical and intelligent techniques to tackle complex problems in various domains. The scope of this Issue spans a wide range of areas, including, but not limited to, systems biology, comparative proteomics, structural genomics, biomedical engineering and bio systems engineering. Original research articles and comprehensive review papers are welcome, with the intention of showcasing the state-of-the-art advancements in this rapidly evolving field. We encourage researchers and experts to present their novel findings, methodologies and insights to enrich our understanding of high-throughput bioinformatics. By exploring diverse approaches and methodologies, we seek to foster collaborations and knowledge exchange, thereby catalyzing advancements in biotechnology, healthcare and drug discovery. We extend a resolute invitation to researchers and innovators to contribute their visionary work, exploring a diverse array of topics, including, but not limited to, the following: explainable deep learning models for interpreting complex genomics data and identifying crucial disease-associated genetic markers; meta-learning approaches for optimizing and automating the selection of optimal bioinformatics pipelines for diverse omics datasets; AI-driven de novo drug design using generative models to discover novel compounds with a high binding affinity to specific drug targets; reinforcement learning algorithms for optimizing personalized treatment plans in precision medicine based on individual patient genomics and clinical data; graph neural networks for predicting protein-protein interactions and uncovering potential drug targets in complex biological networks; high-performance computing and parallel processing techniques to accelerate large-scale biological simulations and molecular dynamics studies; hybrid models combining deep learning and Bayesian networks for predicting disease risk and progression in population-scale studies; integrative analysis of multi-omics data using deep learning-based multi-view representation learning to unravel complex interactions in biological systems; federated learning approaches to preserve data privacy and security while collaborating across multiple institutions in large-scale bioinformatics research; deep generative models for generating synthetic biological data to augment limited datasets and improve the robustness and generalization of bioinformatics models; AI-powered identification of microbial biomarkers and signatures for diagnosing infectious diseases and monitoring microbiome dynamics; cloud-based federated learning platforms for collaborative bioinformatics research, allowing for researchers to share models and knowledge across institutions without sharing raw data; and integrating electronic health records (EHRs) and genomic data using advanced machine learning techniques for early disease prediction and personalized treatment recommendations.

Prof. Dr. Kelvin Wong
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. Life is an international peer-reviewed open access monthly 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 2600 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.

• artificial intelligence
• bioinformatics
• systems biology
• comparative proteomics
• structural genomics
• biomedical engineering
• bio systems engineering

Title: Efficacy of Mammographic Artificial Intelligence Computer-Aided Detection in Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy
Authors: Ga Eun Park; Bong Joo Kang; Sung Hun Kim; Han Song Mun
Affiliation: Department of Radiology, Seoul Saint Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul, Republic of Korea, Seoul, Republic of Korea
Abstract: This study evaluates the potential of an AI-based computer-aided detection (AI-CAD) system in digital mammography for predicting pathologic complete response (pCR) in breast cancer patients after neoadjuvant chemotherapy (NAC). A retrospective analysis of 132 patients who underwent NAC and surgery between January 2020 and December 2022 was performed. Pre- and post-NAC mammograms were analyzed using conventional CAD and AI-CAD systems, with negative exams defined by the absence of marked abnormalities. Two radiologists reviewed mammography, ultrasound, MRI, and diffusion-weighted imaging (DWI). Concordance rates between CAD and AI-CAD were calculated, and the diagnostic performance, including area under the receiver operating characteristics curve (AUC), was assessed. The pre-NAC concordance rates were 90.9% for CAD and 97% for AI-CAD, while post-NAC rates were 88.6% for CAD and 89.4% for AI-CAD. MRI had the highest diagnostic performance for pCR prediction, with AI-CAD performing comparably to other modalities. Univariate analysis identified significant predictors of pCR, including AI-CAD, mammography, ultrasound, MRI, histologic grade, ER, PR, HER2, and Ki-67. In multivariable analysis, negative MRI, histologic grade 3, and HER2 positivity remained significant predictors. In conclusion, this study demonstrates that AI-CAD in digital mammography shows potential in reflecting the pCR of breast cancer patients following NAC.