Submit to Special Issue Submit Abstract to Special Issue Review for IJMS Propose a Special Issue

Journal Menu

Journal Browser

AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease

Print Special Issue Flyer
Editor
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A Special Issue of International Journal of Molecular Sciences (ISSN 1422-0067) belonging to the section "Molecular Informatics".

Deadline for manuscript submissions: 30 November 2026 | Viewed by 6238

Share This Special Issue

Editor

Dr. Santosh Anand

E-Mail Website
Guest Editor

Division of Biological Sciences, University of Missouri, Columbia, MO 65211, USA
Interests: bioinformatics; data science; machine learning; artificial intelligence; cancer; clinical trials; drug discovery; biomarkers
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI), machine learning (ML), and bioinformatics are revolutionizing our understanding of molecular mechanisms underlying human health and disease. These computational approaches are enabling the integration and analysis of large-scale biological data, leading to new insights into disease etiology, diagnosis, and therapeutic strategies. This Special Issue, “Artificial Intelligence, Machine Learning, and Bioinformatics in Molecular Mechanisms of Human Health and Disease,” aims to highlight cutting-edge research that leverages AI/ML and bioinformatics to uncover the molecular basis of health and disease.

We welcome original research papers, short communications, and review articles that cover topics including, but not limited to, the following:

Development and application of AI and machine learning algorithms in bioinformatics for disease prediction, diagnosis, and treatment;
Integration of multi-omics data (genomics, transcriptomics, proteomics, and metabolomics) to elucidate molecular mechanisms in health and disease;
Computational modelling of molecular networks and pathways relevant to human diseases;
Novel bioinformatics tools and databases for analyzing large-scale biological datasets;
Applications of AI and bioinformatics in personalized medicine and precision health;
Case studies demonstrating the impact of AI and bioinformatics on understanding complex diseases;
Study of molecular processes linked to healthy aging, resilience, and adaptation using AI/ML and bioinformatics;
Discovery of protective genetic factors and health-promoting molecular signatures using population genomics and AI/ML.

We look forward to receiving your contributions and advancing the interdisciplinary field of AI/ML and bioinformatics in molecular sciences.

Dr. Santosh Anand
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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Molecular Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. There is an Article Processing Charge (APC) for publication in this open access journal. For details about the APC please see here. 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.

Keywords

artificial intelligence
machine learning
bioinformatics
molecular mechanisms
human health
human disease
multi-omics data
molecular pathways
personalized medicine
disease biomarkers

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (8 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

18 pages, 3338 KB

Open AccessArticle

Multi-Omics Profiling Reveals Neutrophil Extracellular Trap Dysregulation in Diabetic Foot Ulcer Healing Impairment

by Dazhi Li, Haoyu Gu, Shibo Xia, Liangxi Yuan, Junmin Bao and Qingsheng Lu

Int. J. Mol. Sci. 2026, 27(15), 6701; https://doi.org/10.3390/ijms27156701 - 27 Jul 2026

Viewed by 562

Abstract

Diabetic foot ulcer (DFU) affects approximately 25% of diabetic patients and represents the leading cause of non-traumatic lower extremity amputation. Neutrophil extracellular traps (NETs) contribute to chronic inflammation; however, their mechanistic role in DFU healing failure remains incompletely characterized. This study integrated bulk RNA sequencing (GSE143735, n = 9) and single-cell RNA sequencing (scRNA-seq; GSE165816, n = 11) datasets to investigate NET-related transcriptional programs. Differential expression analysis identified 96 differentially expressed genes, with significant NET pathway enrichment in non-healers (normalized enrichment score = 4.35, false discovery rate q < 0.001). Analysis of 33,654 single cells revealed elevated NET activity scores in neutrophils from non-healing wounds (p = 4.73 × 10⁻¹⁵⁹). Four neutrophil subpopulations were identified, with the NETs-high subset expanded in non-healers (43.1% versus 15.4%). Cell–cell communication analysis demonstrated enhanced S100A8/A9–RAGE and IL1B–IL1R signaling in the non-healing state. A six-gene signature (S100A8, S100A9, MPO, ELANE, NCF1, HMGB1) achieved an area under the receiver operating characteristic curve of 0.750 for healing prediction under leave-one-out cross-validation. These findings implicate NET pathway activation as a potential driver of DFU healing impairment and identify candidate prognostic biomarkers warranting prospective validation. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Figure 1

20 pages, 2739 KB

Open AccessArticle

Integrating Mutation-Derived and Expression Features from Single-Cell RNA Sequencing: Pitfalls of Standard Cross-Validation in Small-Cohort Settings

by Aidyn Kunikeyev, Amankeldi A. Salybekov, Aigerim Yerimbetova and Batyrkhan Omarov

Int. J. Mol. Sci. 2026, 27(14), 6429; https://doi.org/10.3390/ijms27146429 - 20 Jul 2026

Viewed by 338

Abstract

Single-cell RNA sequencing (scRNA-seq) studies increasingly combine expression-based and mutation-derived signals, but small-cohort designs with repeated runs from the same biological unit can make standard cross-validation overly optimistic. We reanalyzed PRJNA736095 (14 SRR runs from 7 GSM/donor proxies) using a GATK-centered RNA-seq variant-calling and gene-burden workflow, then evaluated mutation-derived, expression-only, and combined feature sets with leakage-safe preprocessing inside each validation fold. Run-level repeated stratified cross-validation showed high within-dataset separability for GATK gene-burden features (balanced accuracy 0.973 +/− 0.113), but GSM-grouped leave-one-GSM-out validation reduced balanced accuracy to 0.708 and exact GSM-level permutation testing was not significant (p = 0.257). Expression-only and combined feature sets did not improve GSM-grouped balanced accuracy over the variant-only branch. Expression–mutation marker overlap was not significant after FDR correction, and public external datasets were used only to define feasibility or processed biological context rather than as strong external classifier validation. These findings position the workflow as an auditable, hypothesis-generating framework and highlight pitfalls of standard cross-validation in small-cohort scRNA-seq machine-learning analyses. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Figure 1

16 pages, 4612 KB

Open AccessArticle

Discovery-Driven Plasma Proteomics Identifies a Multi-Protein Signature for Amyloid PET Positivity: A Machine Learning Analysis of the Bio-Hermes Cohort

by Stelios Lamprou, Kalliopi Mavromati, Frank J. Gunn-Moore and Terry J. Quinn

Int. J. Mol. Sci. 2026, 27(12), 5533; https://doi.org/10.3390/ijms27125533 - 18 Jun 2026

Viewed by 546

Abstract

Alzheimer’s disease is a progressive neurodegenerative disorder in which early detection remains limited by the cost and invasiveness of positron emission tomography and cerebrospinal fluid testing. We evaluated whether plasma proteomic profiles could distinguish amyloid PET-positive from amyloid PET-negative individuals using the Bio-Hermes cohort. After quality control and missing-data filtering, 988 participants and 295 proteins were analysed; 31 proteins showing group differences were used for supervised classification. Random Forest, Gradient Boosting, and Neural Network models were trained across four train/test splits with repeated cross-validation and class downsampling. Amyloid-positive and amyloid-negative groups differed across a subset of proteins, with five remaining significant after false discovery rate correction. Tree-based models performed most consistently, with Random Forest and Gradient Boosting achieving AUC values of 0.79–0.81 and balanced accuracy of 0.68–0.73. Eight proteins (SERPINA1, C3, CRP, APOE4, CFH, VTN, C1QTNF5, and PON1) emerged as recurring high-importance features. These findings indicate that discovery-driven plasma proteomics can identify multi-protein signatures associated with amyloid status and can complement established single-analyte blood biomarkers by adding pathway-level information. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Figure 1

27 pages, 4382 KB

Open AccessArticle

B.R.E.A.S.T. Breast canceR Enhanced AI-Supported Therapy: A New Interpretable Proteomics-Driven Machine Learning Framework for Therapy Response Prediction in Breast Cancer

by Alessia Bono, Gabriele La Monica, Federica Alamia, Dennis Tocco, Antonino Lauria and Annamaria Martorana

Int. J. Mol. Sci. 2026, 27(12), 5163; https://doi.org/10.3390/ijms27125163 - 6 Jun 2026

Viewed by 580

Abstract

Breast cancer is a heterogeneous disease characterized by substantial molecular diversity and variable treatment outcomes across patients. Despite advances in targeted and systemic therapies, anticipating individual benefit remains a major clinical challenge. In this context, Artificial Intelligence (AI) can support precision oncology by integrating high-dimensional molecular profiles with clinical and pharmacological information. Here, we present B.R.E.A.S.T. (Breast canceR Enhanced AI-Supported Therapy), an interpretable machine learning framework designed to predict therapy outcome from tumor proteomic profiles integrated with clinical and treatment annotations. Proteomic data from The Cancer Genome Atlas (TCGA) and The Cancer Proteome Atlas (TCPA) were harmonized with outcome and therapy information, and thirteen supervised classifiers were systematically evaluated using stratified 5-fold cross-validation. Therapeutic outcome labels were operationally defined by integrating available treatment response annotations with complementary clinical outcome information. Across both cohorts, ensemble-based models consistently achieved the most stable and highest discriminative performance, supported by learning-curve analyses and consistent behavior across independent datasets. To enhance interpretability, we implemented a two-step feature selection strategy combining model-specific importance measures with a global consensus ranking, enabling the identification of a compact set of robust proteomic biomarkers associated with therapeutic outcome. Top-ranked features mapped to molecular programs relevant to breast cancer progression and treatment sensitivity, including regulators of cell survival, DNA damage response, PI3K/AKT/mTOR signaling, and invasion-related processes. Re-evaluation using only the top 30 globally ranked features preserved high predictive performance across both independent breast cancer cohorts, indicating that a parsimonious proteomic signature captures core molecular determinants of outcome. Overall, B.R.E.A.S.T. provides a robust and generalizable proteomics-driven framework for modeling outcome-associated therapeutic response patterns and supporting biologically informed biomarker discovery in breast cancer. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Graphical abstract

26 pages, 22970 KB

Open AccessArticle

Network-Based Bioinformatics Reveal Microenvironment-Driven Cell-to-Cell Communication in the Progression of Multiple Myeloma

by Eleni Nicolaidou, Grigoris Georgiou, Anastasis Oulas and George M. Spyrou

Int. J. Mol. Sci. 2026, 27(11), 4986; https://doi.org/10.3390/ijms27114986 - 30 May 2026

Viewed by 713

Abstract

Single-cell RNA sequencing (scRNAseq) captures unique profiles of individual cells and uncovers cell-to-cell communication (CCC) through ligand–receptor (LR) interactions. Moreover, it reveals signalling mechanisms underlying cellular heterogeneity and complexity in downstream responses in healthy and disease states. In this work, we developed a composite computational pipeline to track CCC patterns in the tumour microenvironment (TME) during Multiple Myeloma (MM) progression as a case study. Three publicly available scRNAseq datasets were analysed using basic single-cell analytics and stage-specific CCC networks were reconstructed with CellChat, in a microenvironment-specific approach. Basic network analytics (CytoHubba) were performed to identify key cell nodes based on network topology metrics; differential network rewiring (DyNet) was performed to calculate rewired nodes. Follow-up analyses were conducted with NicheNet to investigate downstream responses and target genes influenced by CCC. Our network analyses highlighted dendritic cells (DCs), plasmacytoid DCs (pDCs), hematopoietic stem cells (HSCs), red pulp macrophages (RPMs), natural killer (NK) cells, and T and B cells as important cell nodes. Moreover, in neutrophils, the HLA-DRA–JUN–FOS was shown to play a key role in the progression of monoclonal gammopathies of uncertain significance (MGUS) to active MM by supporting cancer hallmarks and MM pathophysiology. To conclude, our work suggests an explanatory–computational pipeline that incorporates well-known frameworks in a hypothesis-driven scope, which leads to results relevant to the pathophysiology of MM. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Figure 1

23 pages, 34240 KB

Open AccessArticle

miRNA-Mediated Signaling Networks in Non-Small Cell Lung Cancer: Linking Tumor Progression to Sarcopenia

by Swati Goswami, Pooja Gulhane and Shailza Singh

Int. J. Mol. Sci. 2026, 27(11), 4703; https://doi.org/10.3390/ijms27114703 - 23 May 2026

Viewed by 957

Abstract

Non-small cell lung cancer (NSCLC) remains a major cause of cancer-related mortality, with poor survival outcomes despite advances in surgery, chemotherapy, targeted therapy, and immunotherapy. The tumor microenvironment (TME) plays a central role in sustaining tumor growth, immune evasion, and systemic metabolic dysfunction. In this study, we performed an integrative analysis of differentially expressed microRNAs (miRNAs) to uncover their contributions to dysregulated signaling networks in NSCLC. hsa-miR-486-5p was identified as a prominent differentially expressed candidate miRNA. Using mathematical modeling and regression-based reduction, we identified Forkhead Box O1 (FOXO1) and Unc-51 like Autophagy Activating Kinase 2 (ULK2) as critical regulatory nodes that integrate oncogenic signaling with cellular homeostasis. Aberrant expression of hsa-miR-486-5p was found to modulate pathways including PI3K/AKT/mTOR, NF-κB, and JAK-STAT3, thereby promoting tumor progression and secretion of inflammatory cytokines. These cytokines, viz., IL-6, TNF-α, and IL-1β, activate muscle-specific protein degradation pathways through E3 ubiquitin ligases TRIM63 and FBXO32, linking NSCLC progression to cancer-associated sarcopenia. Quasipotential landscape analysis further revealed dynamic phenotypic transitions between stable and unstable states, highlighting the adaptability of tumor–host interactions. Collectively, our findings demonstrate that miRNA-mediated regulatory networks not only drive NSCLC progression and inflammation but also contribute to systemic muscle wasting. These insights emphasize the need for novel therapeutic strategies, including RNA-based interventions, to overcome resistance, improve survival, and address the metabolic complications associated with NSCLC. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Graphical abstract

26 pages, 5224 KB

Open AccessArticle

Integrative Transcriptomic Analysis Identifies Shared Immune–Fibrotic Transcriptional Programs Across Crohn’s Disease and Idiopathic Pulmonary Fibrosis

by Renwei Luo, Qiong Zhang, Qinglu Fan, Qingyun Chen, Zhihao Nie, Lingxuan Dan, Fengling Luo, Yige Cao and Songping Xie

Int. J. Mol. Sci. 2026, 27(10), 4428; https://doi.org/10.3390/ijms27104428 - 15 May 2026

Viewed by 767

Abstract

Idiopathic pulmonary fibrosis (IPF) and Crohn’s disease (CD) share overlapping immune and fibrotic processes, yet their convergent molecular mechanisms remain poorly defined. Here, we performed an integrative transcriptomic analysis of nine public datasets to identify shared transcriptional signatures across IPF and CD. The main discovery and validation analyses were based on bulk transcriptomic datasets and combined differential expression profiling, weighted gene co-expression network analysis, and machine-learning–based feature prioritization. We identified 28 shared disease-associated module genes, from which three core genes—ZNF395, EEF2K, and BAHD1—were prioritized based on reproducibility and biological consistency. Functional enrichment analysis revealed their involvement in immune regulation, protein homeostasis, and stress-response pathways. Immune deconvolution and supportive single-cell RNA-sequencing further suggested associations between these genes and T-cell and myeloid cell populations, suggesting coordinated immune-fibrotic regulation. Experimental validation in a repetitive bleomycin challenge model and TGF-β1-stimulated fibroblasts showed consistent downregulation of these genes during fibrotic remodeling, supporting their association with fibrosis-related transcriptional states. Collectively, our study identifies conserved immune–fibrotic transcriptional programs shared across intestinal inflammation and pulmonary fibrosis, providing a hypothesis-generating molecular framework for understanding extraintestinal pulmonary involvement in Crohn’s disease and prioritizing candidate genes for future mechanistic investigation. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Figure 1

23 pages, 9416 KB

Open AccessArticle

Integrated Single-Cell and Bulk RNA Sequencing Identifies Macrophage Heterogeneity and Mitophagy-Related Biomarkers in Idiopathic Pulmonary Fibrosis

by Chen Shang and Gao Huang

Int. J. Mol. Sci. 2026, 27(10), 4201; https://doi.org/10.3390/ijms27104201 - 8 May 2026

Viewed by 873

Abstract

Mitophagy clears damaged mitochondria and maintains normal macrophage function. Clarifying the associations between idiopathic pulmonary fibrosis (IPF), macrophages, and mitophagy is crucial for early diagnosis and clinical management. Core macrophage subsets were identified as M2 macrophages via single-cell RNA sequencing and immune infiltration analysis. Differentially expressed genes related to this subset were obtained. Integrated differential expression analysis, weighted gene co-expression network analysis, machine learning, and expression verification were applied to screen biomarkers. CD163 and SPP1 were identified through biomarker screening, both showing significantly increased expression in IPF. Functional enrichment showed that these biomarkers are mainly involved in cell cycle checkpoints and ciliopathies. Immune microenvironment analysis identified 16 immune cell types with significant differences between IPF and control groups, among which T helper 2 cells were strongly positively correlated with CD163. A total of nine drugs were found to be associated with CD163 and SPP1. The expression of these biomarkers changed dynamically during M2 macrophage differentiation. This study integrates single-cell and bulk transcriptomics analysis to reveal the critical roles of CD163 and SPP1 in the IPF macrophage–mitochondrial autophagy axis, a novel framework for understanding the macrophage–mitophagy axis in IPF pathogenesis. Full article

(This article belongs to the Special Issue AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease)

► Show Figures

Journal Menu

Journal Browser

AI, ML and Bioinformatics in Molecular Mechanisms of Human Health and Disease

Share This Special Issue

Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI