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

Journal Menu

Journal Browser

Machine Learning and Bioinformatics in Human Health and Disease

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of International Journal of Molecular Sciences (ISSN 1422-0067). This special issue belongs to the section "Molecular Informatics".

Deadline for manuscript submissions: 30 June 2024 | Viewed by 9109

Share This Special Issue

Special Issue Editors

Dr. Ramin Ranjbarzadeh

E-Mail Website
Guest Editor

School of Computing, Faculty of Engineering and Computing, Dublin City University, Dublin, Ireland
Interests: image processing; signal processing; deep learning; text recognition; face detection; brain tumor segmentation; breast tumor segmentation; medical images; convolutional neural network; data mining; feature selection; optimizer; feature extraction
Special Issues, Collections and Topics in MDPI journals

Dr. Andreas Leiherer

E-Mail Website
Guest Editor

Vorarlberg Institute for Vascular Investigation and Treatment (VIVIT), Feldkirch, Austria
Interests: cardiology; epidemiology; virology; adipose tissue; metabolism; nutrition; data science; diabetes; renal disease; biomarker

Special Issue Information

Dear Colleagues,

Machine learning and bioinformatics have emerged as powerful tools for analyzing complex biological data and driving advances in human health and disease research. These fields offer a range of techniques for learning from and making predictions based on biological data, including genetic sequencing data, protein structure data, and medical imaging data.

In the context of human health and disease, machine learning and bioinformatics can be used to identify biomarkers for diseases, predict treatment outcomes, and develop new therapies. For example, machine learning algorithms can be used to analyze large datasets of patient information and identify patterns and correlations that might be missed by human experts. Bioinformatics techniques can be utilized to analyze genomic data and identify genetic variations that may contribute to disease.

Machine learning and bioinformatics techniques can also be used to analyze medical images, such as MRIs and CT scans, to identify structural changes associated with disease or injury. This can enable earlier and more accurate diagnoses, as well as more personalized treatment plans tailored to the specific needs of each patient.

However, as is the case with any computational method, machine learning and bioinformatics techniques have their limitations and challenges. One challenge is the need for large amounts of high-quality data to train and validate the algorithms. Another challenge is the potential for overfitting, where the algorithms learn patterns specific to the training data that cannot be applied to new data.

Despite these challenges, the potential benefits of applying machine learning and bioinformatics techniques to human health and disease research are extensive. This Special Issue will provide a platform for researchers to share their latest findings, insights, and innovations in this rapidly evolving field.

Potential topics include, but are not limited to, the following:

Machine learning approaches for identifying genetic risk factors for common diseases;
Analysis of single-cell RNA sequencing data using bioinformatics and machine learning techniques;
Machine learning for predicting drug interactions and side effects;
Bioinformatics and machine learning for precision medicine in cancer treatment;
Machine learning-based diagnosis of neurodegenerative diseases using neuroimaging data;
Integrating multi-omics data using machine learning techniques for disease diagnosis and treatment;
Development of predictive models for infectious disease outbreaks using machine learning and epidemiological data;
Application of machine learning and deep learning techniques in medical image analysis for disease diagnosis and treatment planning;
Identifying disease biomarkers using bioinformatics, deep learning, and machine learning approaches;
Machine learning approaches for predicting patient outcomes and disease progression.

Dr. Ramin Ranjbarzadeh
Dr. Andreas Leiherer
Guest Editors

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. 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

machine learning
bioinformatics
deep learning
multi-omics approaches
genetic risk factors
drug interactions
precision medicine
neurodegenerative diseases
disease diagnosis
epidemic prediction

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

16 pages, 2771 KiB

Open AccessArticle

Machine Learning Gene Signature to Metastatic ccRCC Based on ceRNA Network

by Epitácio Farias, Patrick Terrematte and Beatriz Stransky

Int. J. Mol. Sci. 2024, 25(8), 4214; https://doi.org/10.3390/ijms25084214 - 11 Apr 2024

Viewed by 435

Abstract

Clear-cell renal-cell carcinoma (ccRCC) is a silent-development pathology with a high rate of metastasis in patients. The activity of coding genes in metastatic progression is well known. New studies evaluate the association with non-coding genes, such as competitive endogenous RNA (ceRNA). This study aims to build a ceRNA network and a gene signature for ccRCC associated with metastatic development and analyze their biological functions. Using data from The Cancer Genome Atlas (TCGA), we constructed the ceRNA network with differentially expressed genes, assembled nine preliminary gene signatures from eight feature selection techniques, and evaluated the classification metrics to choose a final signature. After that, we performed a genomic analysis, a risk analysis, and a functional annotation analysis. We present an 11-gene signature: SNHG15, AF117829.1, hsa-miR-130a-3p, hsa-mir-381-3p, BTBD11, INSR, HECW2, RFLNB, PTTG1, HMMR, and RASD1. It was possible to assess the generalization of the signature using an external dataset from the International Cancer Genome Consortium (ICGC-RECA), which showed an Area Under the Curve of 81.5%. The genomic analysis identified the signature participants on chromosomes with highly mutated regions. The hsa-miR-130a-3p, AF117829.1, hsa-miR-381-3p, and PTTG1 were significantly related to the patient’s survival and metastatic development. Additionally, functional annotation resulted in relevant pathways for tumor development and cell cycle control, such as RNA polymerase II transcription regulation and cell control. The gene signature analysis within the ceRNA network, with literature evidence, suggests that the lncRNAs act as “sponges” upon the microRNAs (miRNAs). Therefore, this gene signature presents coding and non-coding genes and could act as potential biomarkers for a better understanding of ccRCC. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

21 pages, 4550 KiB

Open AccessArticle

Aflibercept Off-Target Effects in Diabetic Macular Edema: An In Silico Modeling Approach

by Morgane Blanot, Ricardo Pedro Casaroli-Marano, Jordi Mondéjar-Medrano, Thaïs Sallén, Esther Ramírez, Cristina Segú-Vergés and Laura Artigas

Int. J. Mol. Sci. 2024, 25(7), 3621; https://doi.org/10.3390/ijms25073621 - 23 Mar 2024

Viewed by 741

Abstract

Intravitreal aflibercept injection (IAI) is a treatment for diabetic macular edema (DME), but its mechanism of action (MoA) has not been completely elucidated. Here, we aimed to explore IAI’s MoA and its multi-target nature in DME pathophysiology with an in silico (computer simulation) disease model. We used the Therapeutic Performance Mapping System (Anaxomics Biotech property) to generate mathematical models based on the available scientific knowledge at the time of the study, describing the relationship between the modulation of vascular endothelial growth factor receptors (VEGFRs) by IAI and DME pathophysiological processes. We also undertook an enrichment analysis to explore the processes modulated by IAI, visualized the effectors’ predicted protein activity, and specifically evaluated the role of VEGFR1 pathway inhibition on DME treatment. The models simulated the potential pathophysiology of DME and the likely IAI’s MoA by inhibiting VEGFR1 and VEGFR2 signaling. The action of IAI through both signaling pathways modulated the identified pathophysiological processes associated with DME, with the strongest effects in angiogenesis, blood–retinal barrier alteration and permeability, and inflammation. VEGFR1 inhibition was essential to modulate inflammatory protein effectors. Given the role of VEGFR1 signaling on the modulation of inflammatory-related pathways, IAI may offer therapeutic advantages for DME through sustained VEGFR1 pathway inhibition. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

24 pages, 4471 KiB

Open AccessArticle

Comparison of the Capacity of Several Machine Learning Tools to Assist Immunofluorescence-Based Detection of Anti-Neutrophil Cytoplasmic Antibodies

by Daniel Bertin, Pierre Bongrand and Nathalie Bardin

Int. J. Mol. Sci. 2024, 25(6), 3270; https://doi.org/10.3390/ijms25063270 - 13 Mar 2024

Viewed by 445

Abstract

The success of artificial intelligence and machine learning is an incentive to develop new algorithms to increase the rapidity and reliability of medical diagnosis. Here we compared different strategies aimed at processing microscope images used to detect anti-neutrophil cytoplasmic antibodies, an important vasculitis marker: (i) basic classifier methods (logistic regression, k-nearest neighbors and decision tree) were used to process custom-made indices derived from immunofluorescence images yielded by 137 sera. (ii) These methods were combined with dimensional reduction to analyze 1733 individual cell images. (iii) More complex models based on neural networks were used to analyze the same dataset. The efficiency of discriminating between positive and negative samples and different fluorescence patterns was quantified with Rand-type accuracy index, kappa index and ROC curve. It is concluded that basic models trained on a limited dataset allowed for positive/negative discrimination with an efficiency comparable to that obtained by conventional analysis performed by humans (0.84 kappa score). More extensive datasets and more sophisticated models may be required for efficient discrimination between fluorescence patterns generated by different auto-antibody species. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

15 pages, 2233 KiB

Open AccessArticle

Application of Machine Learning Techniques to Assess Alpha-Fetoprotein at Diagnosis of Hepatocellular Carcinoma

by Sergio Gil-Rojas, Miguel Suárez, Pablo Martínez-Blanco, Ana M. Torres, Natalia Martínez-García, Pilar Blasco, Miguel Torralba and Jorge Mateo

Int. J. Mol. Sci. 2024, 25(4), 1996; https://doi.org/10.3390/ijms25041996 - 07 Feb 2024

Cited by 1 | Viewed by 823

Abstract

Hepatocellular carcinoma (HCC) is the most common primary liver tumor and is associated with high mortality rates. Approximately 80% of cases occur in cirrhotic livers, posing a significant challenge for appropriate therapeutic management. Adequate screening programs in high-risk groups are essential for early-stage detection. The extent of extrahepatic tumor spread and hepatic functional reserve are recognized as two of the most influential prognostic factors. In this retrospective multicenter study, we utilized machine learning (ML) methods to analyze predictors of mortality at the time of diagnosis in a total of 208 patients. The eXtreme gradient boosting (XGB) method achieved the highest values in identifying key prognostic factors for HCC at diagnosis. The etiology of HCC was found to be the variable most strongly associated with a poorer prognosis. The widely used Barcelona Clinic Liver Cancer (BCLC) classification in our setting demonstrated superiority over the TNM classification. Although alpha-fetoprotein (AFP) remains the most commonly used biological marker, elevated levels did not correlate with reduced survival. Our findings suggest the need to explore new prognostic biomarkers for individualized management of these patients. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

16 pages, 1775 KiB

Open AccessArticle

TEMINET: A Co-Informative and Trustworthy Multi-Omics Integration Network for Diagnostic Prediction

by Haoran Luo, Hong Liang, Hongwei Liu, Zhoujie Fan, Yanhui Wei, Xiaohui Yao and Shan Cong

Int. J. Mol. Sci. 2024, 25(3), 1655; https://doi.org/10.3390/ijms25031655 - 29 Jan 2024

Viewed by 676

Abstract

Advancing the domain of biomedical investigation, integrated multi-omics data have shown exceptional performance in elucidating complex human diseases. However, as the variety of omics information expands, precisely perceiving the informativeness of intra- and inter-omics becomes challenging due to the intricate interrelations, thus presenting significant challenges in the integration of multi-omics data. To address this, we introduce a novel multi-omics integration approach, referred to as TEMINET. This approach enhances diagnostic prediction by leveraging an intra-omics co-informative representation module and a trustworthy learning strategy used to address inter-omics fusion. Considering the multifactorial nature of complex diseases, TEMINET utilizes intra-omics features to construct disease-specific networks; then, it applies graph attention networks and a multi-level framework to capture more collective informativeness than pairwise relations. To perceive the contribution of co-informative representations within intra-omics, we designed a trustworthy learning strategy to identify the reliability of each omics in integration. To integrate inter-omics information, a combined-beliefs fusion approach is deployed to harmonize the trustworthy representations of different omics types effectively. Our experiments across four different diseases using mRNA, methylation, and miRNA data demonstrate that TEMINET achieves advanced performance and robustness in classification tasks. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

20 pages, 4200 KiB

Open AccessArticle

Machine Learning-Based Classification of Transcriptome Signatures of Non-Ulcerative Bladder Pain Syndrome

by Akshay Akshay, Mustafa Besic, Annette Kuhn, Fiona C. Burkhard, Alex Bigger-Allen, Rosalyn M. Adam, Katia Monastyrskaya and Ali Hashemi Gheinani

Int. J. Mol. Sci. 2024, 25(3), 1568; https://doi.org/10.3390/ijms25031568 - 26 Jan 2024

Viewed by 663

Abstract

Lower urinary tract dysfunction (LUTD) presents a global health challenge with symptoms impacting a substantial percentage of the population. The absence of reliable biomarkers complicates the accurate classification of LUTD subtypes with shared symptoms such as non-ulcerative Bladder Pain Syndrome (BPS) and overactive bladder caused by bladder outlet obstruction with Detrusor Overactivity (DO). This study introduces a machine learning (ML)-based approach for the identification of mRNA signatures specific to non-ulcerative BPS. Using next-generation sequencing (NGS) transcriptome data from bladder biopsies of patients with BPS, benign prostatic obstruction with DO, and controls, our statistical approach successfully identified 13 candidate genes capable of discerning BPS from control and DO patients. This set was validated using Quantitative Polymerase Chain Reaction (QPCR) in a larger patient cohort. To confirm our findings, we applied both supervised and unsupervised ML approaches to the QPCR dataset. A three-mRNA signature TPPP3, FAT1, and NCALD, emerged as a robust classifier for non-ulcerative BPS. The ML-based framework used to define BPS classifiers establishes a solid foundation for comprehending the gene expression changes in the bladder during BPS and serves as a valuable resource and methodology for advancing signature identification in other fields. The proposed ML pipeline demonstrates its efficacy in handling challenges associated with limited sample sizes, offering a promising avenue for applications in similar domains. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

26 pages, 7222 KiB

Open AccessArticle

Grid-Based Structural and Dimensional Skin Cancer Classification with Self-Featured Optimized Explainable Deep Convolutional Neural Networks

by Kavita Behara, Ernest Bhero and John Terhile Agee

Int. J. Mol. Sci. 2024, 25(3), 1546; https://doi.org/10.3390/ijms25031546 - 26 Jan 2024

Viewed by 803

Abstract

Skin cancer is a severe and potentially lethal disease, and early detection is critical for successful treatment. Traditional procedures for diagnosing skin cancer are expensive, time-intensive, and necessitate the expertise of a medical practitioner. In recent years, many researchers have developed artificial intelligence (AI) tools, including shallow and deep machine learning-based approaches, to diagnose skin cancer. However, AI-based skin cancer diagnosis faces challenges in complexity, low reproducibility, and explainability. To address these problems, we propose a novel Grid-Based Structural and Dimensional Explainable Deep Convolutional Neural Network for accurate and interpretable skin cancer classification. This model employs adaptive thresholding for extracting the region of interest (ROI), using its dynamic capabilities to enhance the accuracy of identifying cancerous regions. The VGG-16 architecture extracts the hierarchical characteristics of skin lesion images, leveraging its recognized capabilities for deep feature extraction. Our proposed model leverages a grid structure to capture spatial relationships within lesions, while the dimensional features extract relevant information from various image channels. An Adaptive Intelligent Coney Optimization (AICO) algorithm is employed for self-feature selected optimization and fine-tuning the hyperparameters, which dynamically adapts the model architecture to optimize feature extraction and classification. The model was trained and tested using the ISIC dataset of 10,015 dermascope images and the MNIST dataset of 2357 images of malignant and benign oncological diseases. The experimental results demonstrated that the model achieved accuracy and CSI values of 0.96 and 0.97 for TP 80 using the ISIC dataset, which is 17.70% and 16.49% more than lightweight CNN, 20.83% and 19.59% more than DenseNet, 18.75% and 17.53% more than CNN, 6.25% and 6.18% more than Efficient Net-B0, 5.21% and 5.15% over ECNN, 2.08% and 2.06% over COA-CAN, and 5.21% and 5.15% more than ARO-ECNN. Additionally, the AICO self-feature selected ECNN model exhibited minimal FPR and FNR of 0.03 and 0.02, respectively. The model attained a loss of 0.09 for ISIC and 0.18 for the MNIST dataset, indicating that the model proposed in this research outperforms existing techniques. The proposed model improves accuracy, interpretability, and robustness for skin cancer classification, ultimately aiding clinicians in early diagnosis and treatment. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Figure 1

16 pages, 3856 KiB

Open AccessArticle

Alzheimer’s Disease: Causal Effect between Obesity and APOE Gene Polymorphisms

by Tianyu Zhao, Tangsheng Zhong, Meishuang Zhang, Yang Xu, Ming Zhang and Li Chen

Int. J. Mol. Sci. 2023, 24(17), 13531; https://doi.org/10.3390/ijms241713531 - 31 Aug 2023

Cited by 1 | Viewed by 1269

Abstract

Currently studies on the correlation between obesity and Alzheimer’s disease (AD) are still unclear. In addition, few indicators have been used to evaluate obesity, which has failed to comprehen-sively study the correlations between body fat mass, body fat distribution, and AD. Thus, this study innovatively utilized bioinformatics and Mendelian randomization (MR) to explore the key targets of obesity-induced AD, and investigate the causal associations between different types of obesity and key targets. The common targets of obesity and AD were screened using the GeneCards database, and functional and pathway annotations were carried out, thereby revealing the key target. MR analysis was conducted between body anthropometric indexes of obesity and the key target using an IVW model. Bioinformatics analysis revealed Apolipoprotein E (APOE) as the key target of obesity-induced AD. MR results showed that body mass index (BMI) had a negative causal association with APOE2, while body fat percentage (BFP) and trunk fat percentage (TFP) had no significant causal association with APOE2; BMI, BFP, and TFP had a negative causal association with APOE3, and none had any significant causal association with APOE4. In conclusion, there is a correlation between obesity and AD, which is mainly due to the polymorphism of the APOE gene rather than adipose tissue distribution. APOE3 carriers may be more susceptible to obesity, while the risk of AD caused by APOE2 and APOE4 may not be induced by obesity. This study sheds new light on current disputes. At the same time, it is suggested to regulate the body fat mass of APOE3 carriers in the early stage, and to reduce the risk of AD. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Graphical abstract

20 pages, 12440 KiB

Open AccessArticle

by Wenbo Zhang, Zhe Cai, Dandan Liang, Jiaochan Han, Ping Wu, Jiayi Shan, Guangxun Meng and Huasong Zeng

Int. J. Mol. Sci. 2023, 24(13), 10619; https://doi.org/10.3390/ijms241310619 - 25 Jun 2023

Cited by 1 | Viewed by 1574

Abstract

Juvenile idiopathic arthritis (JIA) is the most common chronic rheumatic disease in children. The heterogeneity of the disease can be investigated via single-cell RNA sequencing (scRNA-seq) for its gap in the literature. Firstly, five types of immune cells (plasma cells, naive CD4 T cells, memory-activated CD4 T cells, eosinophils, and neutrophils) were significantly different between normal control (NC) and JIA samples. WGCNA was performed to identify genes that exhibited the highest correlation to differential immune cells. Then, 168 differentially expressed immune cell-related genes (DE-ICRGs) were identified by overlapping 13,706 genes identified by WGCNA and 286 differentially expressed genes (DEGs) between JIA and NC specimens. Next, four key genes, namely SOCS3, JUN, CLEC4C, and NFKBIA, were identified by a protein–protein interaction (PPI) network and three machine learning algorithms. The results of functional enrichment revealed that SOCS3, JUN, and NFKBIA were all associated with hallmark TNF-α signaling via NF-κB. In addition, cells in JIA samples were clustered into four groups (B cell, monocyte, NK cell, and T cell groups) by single-cell data analysis. CLEC4C and JUN exhibited the highest level of expression in B cells; NFKBIA and SOCS3 exhibited the highest level of expression in monocytes. Finally, real-time quantitative PCR (RT-qPCR) revealed that the expression of three key genes was consistent with that determined by differential analysis. Our study revealed four key genes with prognostic value for JIA. Our findings could have potential implications for JIA treatment and investigation. Full article

(This article belongs to the Special Issue Machine Learning and Bioinformatics in Human Health and Disease)

► Show Figures

Journal Menu

Journal Browser

Machine Learning and Bioinformatics in Human Health and Disease

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI