IntelliGenes: Interactive and user-friendly multimodal AI/ML application for biomarker discovery and predictive medicine.

Artificial intelligence (AI) and machine learning (ML) have advanced in several areas and fields of life; however, its progress in the field of multi-omics is not matching the levels others have attained. Challenges include but are not limited to the handling and analysis of high volumes of complex multi-omics data, and the expertise needed to implement and execute AI/ML approaches. In this article, we present IntelliGenes, an interactive, customizable, cross-platform, and user-friendly AI/ML application for multi-omics data exploration to discover novel biomarkers and predict rare, common, and complex diseases. The implemented methodology is based on a nexus of conventional statistical techniques and cutting-edge ML algorithms, which outperforms single algorithms and result in enhanced accuracy. The interactive and cross-platform graphical user interface of IntelliGenes is divided into three main sections: (i) Data Manager, (ii) AI/ML Analysis, and (iii) Visualization. Data Manager supports the user in loading and customizing the input data and list of existing biomarkers. AI/ML Analysis allows the user to apply default combinations of statistical and ML algorithms, as well as customize and create new AI/ML pipelines. Visualization provides options to interpret a diverse set of produced results, including performance metrics, disease predictions, and various charts. The performance of IntelliGenes has been successfully tested at variable in-house and peer-reviewed studies, and was able to correctly classify individuals as patients and predict disease with high accuracy. It stands apart primarily in its simplicity in use for nontechnical users and its emphasis on generating interpretable visualizations. We have designed and implemented IntelliGenes in a way that a user with or without computational background can apply AI/ML approaches to discover novel biomarkers and predict diseases.

GWAS advancements to investigate disease associations and biological mechanisms.

Genome-wide association studies (GWAS) have been instrumental in elucidating the genetic architecture of various traits and diseases. Despite the success of GWAS, inherent limitations such as identifying rare and ultra-rare variants, the potential for spurious associations, and in pinpointing causative agents can undermine diagnostic capabilities. This review provides an overview of GWAS and highlights recent advances in genetics that employ a range of methodologies, including Whole Genome Sequencing (WGS), Mendelian Randomization (MR), the Pangenome's high-quality T2T-CHM13 panel, and the Human BioMolecular Atlas Program (HuBMAP), as potential enablers of current and future GWAS research. State of the literature demonstrate the capabilities of these techniques in enhancing the statistical power of GWAS. WGS, with its comprehensive approach, captures the entire genome, surpassing the capabilities of the traditional GWAS technique focused on predefined Single Nucleotide Polymorphism (SNP) sites. The Pangenome's T2T-CHM13 panel, with its holistic approach, aids in the analysis of regions with high sequence identity, such as segmental duplications (SDs). Mendelian Randomization has advanced causative inference, improving clinical diagnostics and facilitating definitive conclusions. Furthermore, spatial biology techniques like HuBMAP, enable 3D molecular mapping of tissues at single-cell resolution, offering insights into pathology of complex traits. This study aims to elucidate and advocate for the increased application of these technologies, highlighting their potential to shape the future of GWAS research.

Deciphering genomic signatures associating human dental oral craniofacial diseases with cardiovascular diseases using machine learning approaches.

OBJECTIVES: Periodontal diseases are chronic, inflammatory disorders that involve the destruction of supporting tissues surrounding the teeth which leads to permanent damage and substantially heightens systemic exposure. If left untreated, dental, oral, and craniofacial diseases (DOCs), especially periodontitis, can increase an individual's risk in developing complex traits including cardiovascular diseases (CVDs). In this study, we are focused on systematically investigating causality between periodontitis with CVDs with the application of artificial intelligence (AI), machine learning (ML) algorithms, and state-of-the-art bioinformatics approaches using RNA-seq-driven gene expression data of CVD patients. MATERIALS AND METHODS: In this study, we built a cohort of CVD patients, collected their blood samples, and performed RNA-seq and gene expression analysis to generate transcriptomic profiles. We proposed a nexus of AI/ML approaches for the identification of significant biomarkers, and predictive analysis. We implemented recursive feature elimination, Pearson correlation, chi-square, and analysis of variance to detect significant biomarkers, and utilized random forest and support vector machines for predictive analysis. RESULTS: Our AI/ML analyses have led us to the preliminary conclusion that GAS5, GPX1, HLA-B, and SNHG6 are the potential gene markers that can be used to explain the causal relationship between periodontitis and CVDs. CONCLUSIONS: CVDs are relatively common in patients with periodontal disease, and an increased risk of CVD is associated with periodontal disease independent of gender. Genetic susceptibility contributing to periodontitis and CVDs have been suggested to some extent, based on the similar degree of heritability shared between both complex diseases.

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.

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

SUMMARY: In this article, we present IntelliGenes, a novel machine learning (ML) pipeline for the multi-genomics exploration to discover biomarkers significant in disease prediction with high accuracy. IntelliGenes is based on a novel approach, which consists of nexus of conventional statistical techniques and cutting-edge ML algorithms using multi-genomic, clinical, and demographic data. IntelliGenes introduces a new metric, i.e. Intelligent Gene (I-Gene) score to measure the importance of individual biomarkers for prediction of complex traits. I-Gene scores can be utilized to generate I-Gene profiles of individuals to comprehend the intricacies of ML used in disease prediction. IntelliGenes is user-friendly, portable, and a cross-platform application, compatible with Microsoft Windows, macOS, and UNIX operating systems. IntelliGenes not only holds the potential for personalized early detection of common and rare diseases in individuals, but also opens avenues for broader research using novel ML methodologies, ultimately leading to personalized interventions and novel treatment targets. AVAILABILITY AND IMPLEMENTATION: The source code of IntelliGenes is available on GitHub (https://github.com/drzeeshanahmed/intelligenes) and Code Ocean (https://codeocean.com/capsule/8638596/tree/v1).

Functional mutation, splice, distribution, and divergence analysis of impactful genes associated with heart failure and other cardiovascular diseases.

Cardiovascular disease (CVD) is caused by a multitude of complex and largely heritable conditions. Identifying key genes and understanding their susceptibility to CVD in the human genome can assist in early diagnosis and personalized treatment of the relevant patients. Heart failure (HF) is among those CVD phenotypes that has a high rate of mortality. In this study, we investigated genes primarily associated with HF and other CVDs. Achieving the goals of this study, we built a cohort of thirty-five consented patients, and sequenced their serum-based samples. We have generated and processed whole genome sequence (WGS) data, and performed functional mutation, splice, variant distribution, and divergence analysis to understand the relationships between each mutation type and its impact. Our variant and prevalence analysis found FLNA, CST3, LGALS3, and HBA1 linked to many enrichment pathways. Functional mutation analysis uncovered ACE, MME, LGALS3, NR3C2, PIK3C2A, CALD1, TEK, and TRPV1 to be notable and potentially significant genes. We discovered intron, 5' Flank, 3' UTR, and 3' Flank mutations to be the most common among HF and other CVD genes. Missense mutations were less common among HF and other CVD genes but had more of a functional impact. We reported HBA1, FADD, NPPC, ADRB2, ADBR1, MYH6, and PLN to be consequential based on our divergence analysis.

Genomic approaches to identify and investigate genes associated with atrial fibrillation and heart failure susceptibility.

Atrial fibrillation (AF) and heart failure (HF) contribute to about 45% of all cardiovascular disease (CVD) deaths in the USA and around the globe. Due to the complex nature, progression, inherent genetic makeup, and heterogeneity of CVDs, personalized treatments are believed to be critical. To improve the deciphering of CVD mechanisms, we need to deeply investigate well-known and identify novel genes that are responsible for CVD development. With the advancements in sequencing technologies, genomic data have been generated at an unprecedented pace to foster translational research. Correct application of bioinformatics using genomic data holds the potential to reveal the genetic underpinnings of various health conditions. It can help in the identification of causal variants for AF, HF, and other CVDs by moving beyond the one-gene one-disease model through the integration of common and rare variant association, the expressed genome, and characterization of comorbidities and phenotypic traits derived from the clinical information. In this study, we examined and discussed variable genomic approaches investigating genes associated with AF, HF, and other CVDs. We collected, reviewed, and compared high-quality scientific literature published between 2009 and 2022 and accessible through PubMed/NCBI. While selecting relevant literature, we mainly focused on identifying genomic approaches involving the integration of genomic data; analysis of common and rare genetic variants; metadata and phenotypic details; and multi-ethnic studies including individuals from ethnic minorities, and European, Asian, and American ancestries. We found 190 genes associated with AF and 26 genes linked to HF. Seven genes had implications in both AF and HF, which are SYNPO2L, TTN, MTSS1, SCN5A, PITX2, KLHL3, and AGAP5. We listed our conclusion, which include detailed information about genes and SNPs associated with AF and HF.

Integrated ACMG-approved genes and ICD codes for the translational research and precision medicine.

A timely understanding of the biological secrets of complex diseases will ultimately benefit millions of individuals by reducing the high risks for mortality and improving the quality of life with personalized diagnoses and treatments. Due to the advancements in sequencing technologies and reduced cost, genomics data are developing at an unmatched pace and levels to foster translational research and precision medicine. Over 10 million genomics datasets have been produced and publicly shared in 2022. Diverse and high-volume genomics and clinical data have the potential to broaden the scope of biological discoveries and insights by extracting, analyzing and interpreting the hidden information. However, the current and still unresolved challenges include the integration of genomic profiles of the patients with their medical records. The definition of disease in genomics medicine is simplified, whereas in the clinical world, diseases are classified, identified and adopted with their International Classification of Diseases (ICD) codes, which are maintained by the World Health Organization. Several biological databases have been produced, which include information about human genes and related diseases. However, still, there is no database that exists, which can precisely link clinical codes with relevant genes and variants to support genomic and clinical data integration for clinical and translational medicine. In this project, we focused on the development of an annotated gene-disease-code database, which is accessible through an online, cross-platform and user-friendly application, i.e. PROMIS-APP-SUITE-Gene-Disease-Code. However, our scope is limited to the integration of ICD-9 and ICD-10 codes with the list of genes approved by the American College of Medical Genetics and Genomics. The results include over 17 000 diseases and 4000 ICD codes, and over 11 000 gene-disease-code combinations. Database URL https://promis.rutgers.edu/pas/.

Investigating genes associated with heart failure, atrial fibrillation, and other cardiovascular diseases, and predicting disease using machine learning techniques for translational research and precision medicine.

Cardiovascular disease (CVD) is the leading cause of mortality and loss of disability adjusted life years (DALYs) globally. CVDs like Heart Failure (HF) and Atrial Fibrillation (AF) are associated with physical effects on the heart muscles. As a result of the complex nature, progression, inherent genetic makeup, and heterogeneity of CVDs, personalized treatments are believed to be critical. Rightful application of artificial intelligence (AI) and machine learning (ML) approaches can lead to new insights into CVDs for providing better personalized treatments with predictive analysis and deep phenotyping. In this study we focused on implementing AI/ML techniques on RNA-seq driven gene-expression data to investigate genes associated with HF, AF, and other CVDs, and predict disease with high accuracy. The study involved generating RNA-seq data derived from the serum of consented CVD patients. Next, we processed the sequenced data using our RNA-seq pipeline and applied GVViZ for gene-disease data annotation and expression analysis. To achieve our research objectives, we developed a new Findable, Accessible, Intelligent, and Reproducible (FAIR) approach that includes a five-level biostatistical evaluation, primarily based on the Random Forest (RF) algorithm. During our AI/ML analysis, we have fitted, trained, and implemented our model to classify and distinguish high-risk CVD patients based on their age, gender, and race. With the successful execution of our model, we predicted the association of highly significant HF, AF, and other CVDs genes with demographic variables.

Artificial Intelligence, Healthcare, Clinical Genomics, and Pharmacogenomics Approaches in Precision Medicine.

Precision medicine has greatly aided in improving health outcomes using earlier diagnosis and better prognosis for chronic diseases. It makes use of clinical data associated with the patient as well as their multi-omics/genomic data to reach a conclusion regarding how a physician should proceed with a specific treatment. Compared to the symptom-driven approach in medicine, precision medicine considers the critical fact that all patients do not react to the same treatment or medication in the same way. When considering the intersection of traditionally distinct arenas of medicine, that is, artificial intelligence, healthcare, clinical genomics, and pharmacogenomics-what ties them together is their impact on the development of precision medicine as a field and how they each contribute to patient-specific, rather than symptom-specific patient outcomes. This study discusses the impact and integration of these different fields in the scope of precision medicine and how they can be used in preventing and predicting acute or chronic diseases. Additionally, this study also discusses the advantages as well as the current challenges associated with artificial intelligence, healthcare, clinical genomics, and pharmacogenomics.

Artificial intelligence and machine learning approaches using gene expression and variant data for personalized medicine.

Precision medicine uses genetic, environmental and lifestyle factors to more accurately diagnose and treat disease in specific groups of patients, and it is considered one of the most promising medical efforts of our time. The use of genetics is arguably the most data-rich and complex components of precision medicine. The grand challenge today is the successful assimilation of genetics into precision medicine that translates across different ancestries, diverse diseases and other distinct populations, which will require clever use of artificial intelligence (AI) and machine learning (ML) methods. Our goal here was to review and compare scientific objectives, methodologies, datasets, data sources, ethics and gaps of AI/ML approaches used in genomics and precision medicine. We selected high-quality literature published within the last 5 years that were indexed and available through PubMed Central. Our scope was narrowed to articles that reported application of AI/ML algorithms for statistical and predictive analyses using whole genome and/or whole exome sequencing for gene variants, and RNA-seq and microarrays for gene expression. We did not limit our search to specific diseases or data sources. Based on the scope of our review and comparative analysis criteria, we identified 32 different AI/ML approaches applied in variable genomics studies and report widely adapted AI/ML algorithms for predictive diagnostics across several diseases.