IntelliGenes: a novel machine learning pipeline for biomarker discovery and predictive analysis using multi-genomic profiles

Machine Learning Approach and Bioinformatics Analysis Discovered Key Genomic Signatures for Hepatitis B Virus-Associated Hepatocyte Remodeling and Hepatocellular Carcinoma

Hepatitis B virus (HBV) causes liver cancer, which is the third most common cause of cancer-related death worldwide. Chronic inflammation via HBV in the host hepatocytes causes hepatocyte remodeling (hepatocyte transformation and immortalization) and hepatocellular carcinoma (HCC). Recognizing cancer stages accurately to optimize early screening and diagnosis is a primary concern in the outlook of HBV-induced hepatocyte remodeling and liver cancer. Genomic signatures play important roles in addressing this issue. Recently, machine learning (ML) models and bioinformatics analysis have become very important in discovering novel genomic signatures for the early diagnosis, treatment, and prognosis of HBV-induced hepatic cell remodeling and HCC. We discuss the recent literature on the ML approach and bioinformatics analysis revealed novel genomic signatures for diagnosing and forecasting HBV-associated hepatocyte remodeling and HCC. Various genomic signatures, including various microRNAs and their associated genes, long noncoding RNAs (lncRNAs), and small nucleolar RNAs (snoRNAs), have been discovered to be involved in the upregulation and downregulation of HBV-HCC. Moreover, these genetic biomarkers also affect different biological processes, such as proliferation, migration, circulation, assault, dissemination, antiapoptosis, mitogenesis, transformation, and angiogenesis in HBV-infected hepatocytes.

Artificial intelligence in the management of metabolic disorders: a comprehensive review

This review explores the significant role of artificial intelligence (AI) in managing metabolic disorders like diabetes, obesity, metabolic dysfunction-associated fatty liver disease (MAFLD), and thyroid dysfunction. AI applications in this context encompass early diagnosis, personalized treatment plans, risk assessment, prevention, and biomarker discovery for early and accurate disease management. This review also delves into techniques involving machine learning (ML), deep learning (DL), natural language processing (NLP), computer vision, and reinforcement learning associated with AI and their application in metabolic disorders. The following study also enlightens the challenges and ethical considerations associated with AI implementation, such as data privacy, model interpretability, and bias mitigation. We have reviewed various AI-based tools utilized for the diagnosis and management of metabolic disorders, such as Idx, Guardian Connect system, and DreaMed for diabetes. Further, the paper emphasizes the potential of AI to revolutionize the management of metabolic disorders through collaborations among clinicians and AI experts, the integration of AI into clinical practice, and the necessity for long-term validation studies. The references provided in the paper cover a range of studies related to AI, ML, personalized medicine, metabolic disorders, and diagnostic tools in healthcare, including research on disease diagnostics, personalized therapy, chronic disease management, and the application of AI in diabetes care and nutrition.

Crosstalk of SPINK4 Expression With Patient Mortality, Immunotherapy and Metastasis in Pan-Cancer Based on Integrated Multi-Omics Analyses

Background

Cancer remains a major global health challenge, with early detection and prompt treatment being crucial for reducing mortality rates. The SPINK4 has been linked to the development of several tumors, and there is growing evidence of its involvement. However, its specific functions and effects in different cancer types remain unclear.

Methods

The association between SPINK4 expression levels and tumor progression was investigated and confirmed using the TCGA dataset. Kaplan-Meier curves were utilized to examine the correlation between SPINK4 expression with survival outcomes in pan-cancer patients. The Pearson method was employed to investigate the association of SPINK4 expression with the tumor microenvironment, stemness score, immunoinfiltrating subtype, and chemotherapy sensitivity in human different cancer types. Wound healing and Transwell assays were performed to confirm the roles of the model gene in colon adenocarcinoma cells.

Results

The expression of SPINK4 shows heterogeneity across pan-cancer tissues, and is closely associated with poor prognosis, immune cell invasion, tumor cell resistance, and tumor metastasis in a various human cancer. Mutation of SPINK4 hold significant predictive value for poor prognosis of pan-cancer patients. In addition, SPINK4 expression was significantly correlated with the tumor microenvironment (stromal cells and immune cells) and stemness score (DNAss and RNAss) in human pan-cancer tissues, particularly in BLCA and COAD. Single-cell sequencing analysis showed that SPINK4 is mainly expressed in endothelial cells in BLCA and in malignant cells in COAD. Drug resistance analysis showed a significant association between SPINK4 expression and sensitivity to several cancer chemotherapy drugs. Importantly, overexpression of SPINK4 promoted the metastasis of colon cancer cell lines (HCT116 and RKO), whereas SPINK4 knockout markedly inhibited their metastasis.

Conclusion

These findings reveal the crucial role of SPINK4 in the pan-cancer process and may have significant implications for the diagnosis and treatment of cancer in the future.

Applying AI/ML for Analyzing Gene Expression Patterns

Artificial intelligence (AI) and machine learning (ML) have advanced in several areas and fields of life; however, its progress in the field of genomics is not matching the levels others have achieved. Challenges include but are not limited to the handling and analysis of high volumes of complex genomic data, and the expertise needed to implement and execute AI/ML approaches. In this chapter, we highlight the importance of transcriptomics, and RNA-seq driven gene expression data exploration to discover novel biomarkers and predict rare, common, and complex diseases. We discuss relevant high volume sequence data generated in the recent past and its availability through various channels, development of orthodox bioinformatics tools and technologies to investigate significantly expressed and abundantly enriched genes, and the implementation of cutting-edge AI/ML approaches to observe disease specific patterns. Current challenges include but are not limited to the acceptance of AI/ML in the scientific research and clinical environments, especially in providing personalized diagnoses and treatments. Reasons include unavailability of user-friendly AI/ML applications and reproducible results. Addressing these issues, we discuss our recently developed Findable, Accessible, Intelligent, and Reproducible (FAIR) solutions, designed for the users with and without computational background to discover biomarkers and predict diseases with high accuracy. We strongly believe that the rightful application of AI/ML techniques has the potential to open avenues for broader research, ultimately leading to personalized interventions and novel treatment targets. Its widespread application will contribute to the public health at large in the United States and around the globe.

VAREANT: a bioinformatics application for gene variant reduction and annotation

Motivation

The analysis of high-quality genomic variant data may offer a more complete understanding of the human genome, enabling researchers to identify novel biomarkers, stratify patients based on disease risk factors, and decipher underlying biological pathways. Although the availability of genomic data has sharply increased in recent years, the accessibility of bioinformatic tools to aid in its preparation is still lacking. Limitations with processing genomic data primarily include its large volume, associated computational and storage costs, and difficulty in identifying targeted and relevant information.

Results

We present VAREANT, an accessible and configurable bioinformatic application to support the preparation of variant data into a usable analysis-ready format. VAREANT is comprised of three standalone modules: (i) Pre-processing, (ii) Variant Annotation, (iii) AI/ML Data Preparation. Pre-processing supports the fine-grained filtering of complex variant datasets to eliminate extraneous data. Variant Annotation allows for the addition of variant metadata from the latest public annotation databases for subsequent analysis and interpretation. AI/ML Data Preparation supports the user in creating AI/ML-ready datasets suitable for immediate analysis with minimal pre-processing required. We have successfully tested and validated our tool on numerous variable-sized datasets and implemented VAREANT in two case studies involving patients with cardiovascular diseases.

Availability and implementation

The open-source code of VAREANT is available at GitHub: https://github.com/drzeeshanahmed/Gene_VAREANT.

GFPrint™: A machine learning tool for transforming genetic data into clinical insights

The increasing availability of massive genetic sequencing data in the clinical setting has triggered the need for appropriate tools to help fully exploit the wealth of information these data possess. GFPrint™ is a proprietary streaming algorithm designed to meet that need. By extracting the most relevant functional features, GFPrint™ transforms high-dimensional, noisy genetic sequencing data into an embedded representation, allowing unsupervised models to create data clusters that can be re-mapped to the original clinical information. Ultimately, this allows the identification of genes and pathways relevant to disease onset and progression. GFPrint™ has been tested and validated using two cancer genomic datasets publicly available. Analysis of the TCGA dataset has identified panels of genes whose mutations appear to negatively influence survival in non-metastatic colorectal cancer (15 genes), epidermoid non-small cell lung cancer (167 genes) and pheochromocytoma (313 genes) patients. Likewise, analysis of the Broad Institute dataset has identified 75 genes involved in pathways related to extracellular matrix reorganization whose mutations appear to dictate a worse prognosis for breast cancer patients. GFPrint™ is accessible through a secure web portal and can be used in any therapeutic area where the genetic profile of patients influences disease evolution.

Computational approaches to investigate the relationship between periodontitis and cardiovascular diseases for precision medicine

Periodontitis is a highly prevalent inflammatory illness that leads to the destruction of tooth supporting tissue structures and has been associated with an increased risk of cardiovascular disease (CVD). Precision medicine, an emerging branch of medical treatment, aims can further improve current traditional treatment by personalizing care based on one's environment, genetic makeup, and lifestyle. Genomic databases have paved the way for precision medicine by elucidating the pathophysiology of complex, heritable diseases. Therefore, the investigation of novel periodontitis-linked genes associated with CVD will enhance our understanding of their linkage and related biochemical pathways for targeted therapies. In this article, we highlight possible mechanisms of actions connecting PD and CVD. Furthermore, we delve deeper into certain heritable inflammatory-associated pathways linking the two. The goal is to gather, compare, and assess high-quality scientific literature alongside genomic datasets that seek to establish a link between periodontitis and CVD. The scope is focused on the most up to date and authentic literature published within the last 10 years, indexed and available from PubMed Central, that analyzes periodontitis-associated genes linked to CVD. Based on the comparative analysis criteria, fifty-one genes associated with both periodontitis and CVD were identified and reported. The prevalence of genes associated with both CVD and periodontitis warrants investigation to assess the validity of a potential linkage between the pathophysiology of both diseases.

Emerging Strategies in Drug Development and Clinical Care in the Era of Personalized and Precision Medicine

In the ever-changing landscape of modern medicine, we face an important moment where the interplay of disease, drugs, and patients defines a new paradigm [...].

Biomarker discovery with quantum neural networks: a case-study in CTLA4-activation pathways

BACKGROUND

Biomarker discovery is a challenging task due to the massive search space. Quantum computing and quantum Artificial Intelligence (quantum AI) can be used to address the computational problem of biomarker discovery from genetic data.

METHOD

We propose a Quantum Neural Networks architecture to discover genetic biomarkers for input activation pathways. The Maximum Relevance-Minimum Redundancy criteria score biomarker candidate sets. Our proposed model is economical since the neural solution can be delivered on constrained hardware.

RESULTS

We demonstrate the proof of concept on four activation pathways associated with CTLA4, including (1) CTLA4-activation stand-alone, (2) CTLA4-CD8A-CD8B co-activation, (3) CTLA4-CD2 co-activation, and (4) CTLA4-CD2-CD48-CD53-CD58-CD84 co-activation.

CONCLUSION

The model indicates new genetic biomarkers associated with the mutational activation of CLTA4-associated pathways, including 20 genes: CLIC4, CPE, ETS2, FAM107A, GPR116, HYOU1, LCN2, MACF1, MT1G, NAPA, NDUFS5, PAK1, PFN1, PGAP3, PPM1G, PSMD8, RNF213, SLC25A3, UBA1, and WLS. We open source the implementation at: https://github.com/namnguyen0510/Biomarker-Discovery-with-Quantum-Neural-Networks .

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

Personalized interventions are deemed vital given the intricate characteristics, advancement, inherent genetic composition, and diversity of cardiovascular diseases (CVDs). The appropriate utilization of artificial intelligence (AI) and machine learning (ML) methodologies can yield novel understandings of CVDs, enabling improved personalized treatments through predictive analysis and deep phenotyping. In this study, we proposed and employed a novel approach combining traditional statistics and a nexus of cutting-edge AI/ML techniques to identify significant biomarkers for our predictive engine by analyzing the complete transcriptome of CVD patients. After robust gene expression data pre-processing, we utilized three statistical tests (Pearson correlation, Chi-square test, and ANOVA) to assess the differences in transcriptomic expression and clinical characteristics between healthy individuals and CVD patients. Next, the recursive feature elimination classifier assigned rankings to transcriptomic features based on their relation to the case-control variable. The top ten percent of commonly observed significant biomarkers were evaluated using four unique ML classifiers (Random Forest, Support Vector Machine, Xtreme Gradient Boosting Decision Trees, and k-Nearest Neighbors). After optimizing hyperparameters, the ensembled models, which were implemented using a soft voting classifier, accurately differentiated between patients and healthy individuals. We have uncovered 18 transcriptomic biomarkers that are highly significant in the CVD population that were used to predict disease with up to 96% accuracy. Additionally, we cross-validated our results with clinical records collected from patients in our cohort. The identified biomarkers served as potential indicators for early detection of CVDs. With its successful implementation, our newly developed predictive engine provides a valuable framework for identifying patients with CVDs based on their biomarker profiles.