Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data

Explainable Artificial Intelligence in Quantifying Breast Cancer Factors: Saudi Arabia Context

Breast cancer represents a significant health concern, particularly in Saudi Arabia, where it ranks as the most prevalent cancer type among women. This study focuses on leveraging eXplainable Artificial Intelligence (XAI) techniques to predict benign and malignant breast cancer cases using various clinical and pathological features specific to Saudi Arabian patients. Six distinct models were trained and evaluated based on common performance metrics such as accuracy, precision, recall, F1 score, and AUC-ROC score. To enhance interpretability, Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) were applied. The analysis identified the Random Forest model as the top performer, achieving an accuracy of 0.72, along with robust precision, recall, F1 score, and AUC-ROC score values. Conversely, the Support Vector Machine model exhibited the poorest performance metrics, indicating its limited predictive capability. Notably, the XAI approaches unveiled variations in the feature importance rankings across models, underscoring the need for further investigation. These findings offer valuable insights into breast cancer diagnosis and machine learning interpretation, aiding healthcare providers in understanding and potentially integrating such technologies into clinical practices.

Circulating tumor DNA- and cancer tissue-based next-generation sequencing reveals comparable consistency in targeted gene mutations for advanced or metastatic non-small cell lung cancer

BACKGROUND

Molecular subtyping is an essential complementarity after pathological analyses for targeted therapy. This study aimed to investigate the consistency of next-generation sequencing (NGS) results between circulating tumor DNA (ctDNA)-based and tissue-based in non-small cell lung cancer (NSCLC) and identify the patient characteristics that favor ctDNA testing.

METHODS

Patients who diagnosed with NSCLC and received both ctDNA- and cancer tissue-based NGS before surgery or systemic treatment in Lung Cancer Center, Sichuan University West China Hospital between December 2017 and August 2022 were enrolled. A 425-cancer panel with a HiSeq 4000 NGS platform was used for NGS. The unweighted Cohen's kappa coefficient was employed to discriminate the high-concordance group from the low-concordance group with a cutoff value of 0.6. Six machine learning models were used to identify patient characteristics that relate to high concordance between ctDNA-based and tissue-based NGS.

RESULTS

A total of 85 patients were enrolled, of which 22.4% (19/85) had stage III disease and 56.5% had stage IV disease. Forty-four patients (51.8%) showed consistent gene mutation types between ctDNA-based and tissue-based NGS, while one patient (1.2%) tested negative in both approaches. Advanced diseases and metastases to other organs would be fit for the ctDNA-based NGS, and the generalized linear model showed that T stage, M stage, and tumor mutation burden were the critical discriminators to predict the consistency of results between ctDNA-based and tissue-based NGS.

CONCLUSION

ctDNA-based NGS showed comparable detection performance in the targeted gene mutations compared with tissue-based NGS, and it could be considered in advanced or metastatic NSCLC.

From Data to Cure: A Comprehensive Exploration of Multi-omics Data Analysis for Targeted Therapies

In the dynamic landscape of targeted therapeutics, drug discovery has pivoted towards understanding underlying disease mechanisms, placing a strong emphasis on molecular perturbations and target identification. This paradigm shift, crucial for drug discovery, is underpinned by big data, a transformative force in the current era. Omics data, characterized by its heterogeneity and enormity, has ushered biological and biomedical research into the big data domain. Acknowledging the significance of integrating diverse omics data strata, known as multi-omics studies, researchers delve into the intricate interrelationships among various omics layers. This review navigates the expansive omics landscape, showcasing tailored assays for each molecular layer through genomes to metabolomes. The sheer volume of data generated necessitates sophisticated informatics techniques, with machine-learning (ML) algorithms emerging as robust tools. These datasets not only refine disease classification but also enhance diagnostics and foster the development of targeted therapeutic strategies. Through the integration of high-throughput data, the review focuses on targeting and modeling multiple disease-regulated networks, validating interactions with multiple targets, and enhancing therapeutic potential using network pharmacology approaches. Ultimately, this exploration aims to illuminate the transformative impact of multi-omics in the big data era, shaping the future of biological research.

Prediction of Clinical Remission with Adalimumab Therapy in Patients with Ulcerative Colitis by Fourier Transform-Infrared Spectroscopy Coupled with Machine Learning Algorithms

We aimed to develop prediction models for clinical remission associated with adalimumab treatment in patients with ulcerative colitis (UC) using Fourier transform-infrared (FT-IR) spectroscopy coupled with machine learning (ML) algorithms. This prospective, observational, multicenter study enrolled 62 UC patients and 30 healthy controls. The patients were treated with adalimumab for 56 weeks, and clinical remission was evaluated using the Mayo score. Baseline fecal samples were collected and analyzed using FT-IR spectroscopy. Various data preprocessing methods were applied, and prediction models were established by 10-fold cross-validation using various ML methods. Orthogonal partial least squares-discriminant analysis (OPLS-DA) showed a clear separation of healthy controls and UC patients, applying area normalization and Pareto scaling. OPLS-DA models predicting short- and long-term remission (8 and 56 weeks) yielded area-under-the-curve values of 0.76 and 0.75, respectively. Logistic regression and a nonlinear support vector machine were selected as the best prediction models for short- and long-term remission, respectively (accuracy of 0.99). In external validation, prediction models for short-term (logistic regression) and long-term (decision tree) remission performed well, with accuracy values of 0.73 and 0.82, respectively. This was the first study to develop prediction models for clinical remission associated with adalimumab treatment in UC patients by fecal analysis using FT-IR spectroscopy coupled with ML algorithms. Logistic regression, nonlinear support vector machines, and decision tree were suggested as the optimal prediction models for remission, and these were noninvasive, simple, inexpensive, and fast analyses that could be applied to personalized treatments.

Identification and Validation of PTGS2 Gene as an Oxidative Stress-Related Biomarker for Arteriovenous Fistula Failure

(1) Background: Arteriovenous fistulas (AVFs) are the preferred site for hemodialysis. Unfortunately, approximately 60% of patients suffer from AVF failure within one year. Oxidative stress plays an important role in the occurrence and development of AVF. However, the underlying mechanisms remain unclear. Therefore, specific oxidative stress-related biomarkers are urgently needed for the diagnosis and treatment of AVF failure. (2) Methods: Bioinformatics analysis was carried out on dataset GSE119296 to screen for PTGS2 as a candidate gene related to oxidative stress and to verify the expression level and diagnostic efficacy of PTGS2 in clinical patients. The effects of NS398, a PTGS2 inhibitor, on hemodynamics, smooth muscle cell proliferation, migration, and oxidative stress were evaluated in a mouse AVF model. (3) Results: Based on 83 oxidative stress-related differentially expressed genes, we identified the important pathways related to oxidative stress. PTGS2 may have diagnostic and therapeutic efficacy for AVF failure. We further confirmed this finding using clinical specimens and validation datasets. The animal experiments illustrated that NS398 administration could reduce neointimal area (average decrease: 49%) and improve peak velocity (average increase: 53%). (4) Conclusions: Our study identified PTGS2 as an important oxidative stress-related biomarker for AVF failure. Targeting PTGS2 reduced oxidative stress and improved hemodynamics in an AVF mouse model.

Multiomics insights on the onset, progression, and metastatic evolution of breast cancer

Breast cancer is the most common malignant neoplasm in women. Despite progress to date, 700,000 women worldwide died of this disease in 2020. Apparently, the prognostic markers currently used in the clinic are not sufficient to determine the most appropriate treatment. For this reason, great efforts have been made in recent years to identify new molecular biomarkers that will allow more precise and personalized therapeutic decisions in both primary and recurrent breast cancers. These molecular biomarkers include genetic and post-transcriptional alterations, changes in protein expression, as well as metabolic, immunological or microbial changes identified by multiple omics technologies (e.g., genomics, epigenomics, transcriptomics, proteomics, glycomics, metabolomics, lipidomics, immunomics and microbiomics). This review summarizes studies based on omics analysis that have identified new biomarkers for diagnosis, patient stratification, differentiation between stages of tumor development (initiation, progression, and metastasis/recurrence), and their relevance for treatment selection. Furthermore, this review highlights the importance of clinical trials based on multiomics studies and the need to advance in this direction in order to establish personalized therapies and prolong disease-free survival of these patients in the future.

Machine learning-guided REIMS pattern recognition of non-dairy cream, milk fat cream and whipping cream for fraudulence identification

The illegal adulteration of non-dairy cream in milk fat cream during the manufacturing process of baked goods has significantly hindered the robust growth of the dairy industry. In this study, a method based on rapid evaporative ionization mass spectrometry (REIMS) lipidomics pattern recognition integrated with machine learning algorithms was established. A total of 26 ions with importance were picked using multivariate statistical analysis as salient contributing features to distinguish between milk fat cream and non-dairy cream. Furthermore, employing discriminant analysis, decision trees, support vector machines, and neural network classifiers, machine learning models were utilized to classify non-dairy cream, milk fat cream, and minute quantities of non-dairy cream adulterated in milk fat cream. These approaches were enhanced through hyperparameter optimization and feature engineering, yielding accuracy rates at 98.4-99.6%. This artificial intelligent method of machine learning-guided REIMS pattern recognition can accurately identify adulteration of whipped cream and might help combat food fraud.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Deep learning analysis of UPLC-MS/MS-based metabolomics data to predict Alzheimer's disease

OBJECTIVE

Metabolic biomarkers can potentially inform disease progression in Alzheimer's disease (AD). The purpose of this study is to identify and describe a new set of diagnostic biomarkers for developing deep learning (DL) tools to predict AD using Ultra Performance Liquid Chromatography Mass Spectrometry (UPLC-MS/MS)-based metabolomics data.

METHODS

A total of 177 individuals, including 78 with AD and 99 with cognitive normal (CN), were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort along with 150 metabolomic biomarkers. We performed feature selection using the Least Absolute Shrinkage and Selection Operator (LASSO). The H2O DL function was used to build multilayer feedforward neural networks to predict AD.

RESULTS

The LASSO selected 21 metabolic biomarkers. To develop DL models, the 21 biomarkers identified by LASSO were imported into the H2O package. The data was split into 70% for training and 30% for validation. The best DL model with two layers and 18 neurons achieved an accuracy of 0.881, F1-score of 0.892, and AUC of 0.873. Several metabolomic biomarkers involved in glucose and lipid metabolism, in particular bile acid metabolites, were associated with APOE-ε4 allele and clinical biomarkers (Aβ42, tTau, pTau), cognitive assessments [the Alzheimer's Disease Assessment Scale-cognitive subscale 13 (ADAS13), the Mini-Mental State Examination (MMSE)], and hippocampus volume.

CONCLUSIONS

This study identified a new set of diagnostic metabolomic biomarkers for developing DL tools to predict AD. These biomarkers may help with early diagnosis, prognostic risk stratification, and/or early treatment interventions for patients at risk for AD.

Identification and validation of FPR1, FPR2, IL17RA and TLR7 as immunogenic cell death related genes in osteoarthritis

Immunogenic cell death (ICDs) has gained increasing attention for its significant clinical efficacy in various diseases. Similarly, more and more attention has been paid in the role of immune factors in the pathological process of osteoarthritis (OA). The objective of this study is to reveal the relationship between ICD-related genes and the process of OA at the gene level through bioinformatics analysis. In this study, Limma R package was applied to identify differentially expressed genes (DEG), and OA related module genes were determined by weighted gene co-expression network analysis. The ICD-related genes were extracted from a previous study. The module genes related to DEGs and ICD were overlapped. Then, hub genes were identified by a series of analyses using the Least absolute shrinkage and selection operator and random forest algorithm, the expression level and diagnostic value of hub genes were evaluated by Logistic regression. In addition, we used Spearman rank correlation analysis to clarify the relationship between hub genes and infiltrating immune cells and immune pathways. The expression levels of FPR1, FPR2, IL17RA, and TLR7 was verified in SD rat knee joint model of OA by immunohistochemistry. The expression levels of FPR1, FPR2, IL17RA, and TLR7 mRNA were detected in the IL-1β induced rat chondrocytes in qPCR experiment in vitro. Four hub genes (FPR1, FPR2, IL17RA, and TLR7) were ultimately identified as OA biomarkers associated with ICD. And knockdown of TLR7 reversed collagen II and ADAMTS-5 degradation in IL-1β-stimulated chondrocytes. This research may provide new immune related biomarkers for the diagnosis of OA and serve as a reference for disease treatment monitoring.

Precision oncology: Artificial intelligence, circulating cell-free DNA, and the minimally invasive detection of pancreatic cancer-A pilot study

BACKGROUND

Pancreatic cancer (PC) is among the most lethal cancers. The lack of effective tools for early detection results in late tumor detection and, consequently, high mortality rate. Precision oncology aims to develop targeted individual treatments based on advanced computational approaches of omics data. Biomarkers, such as global alteration of cytosine (CpG) methylation, can be pivotal for these objectives. In this study, we performed DNA methylation profiling of pancreatic cancer patients using circulating cell-free DNA (cfDNA) and artificial intelligence (AI) including Deep Learning (DL) for minimally invasive detection to elucidate the epigenetic pathogenesis of PC.

METHODS

The Illumina Infinium HD Assay was used for genome-wide DNA methylation profiling of cfDNA in treatment-naïve patients. Six AI algorithms were used to determine PC detection accuracy based on cytosine (CpG) methylation markers. Additional strategies for minimizing overfitting were employed. The molecular pathogenesis was interrogated using enrichment analysis.

RESULTS

In total, we identified 4556 significantly differentially methylated CpGs (q-value < 0.05; Bonferroni correction) in PC versus controls. Highly accurate PC detection was achieved with all 6 AI platforms (Area under the receiver operator characteristics curve [0.90-1.00]). For example, DL achieved AUC (95% CI): 1.00 (0.95-1.00), with a sensitivity and specificity of 100%. A separate modeling approach based on logistic regression-based yielded an AUC (95% CI) 1.0 (1.0-1.0) with a sensitivity and specificity of 100% for PC detection. The top four biological pathways that were epigenetically altered in PC and are known to be linked with cancer are discussed.

CONCLUSION

Using a minimally invasive approach, AI, and epigenetic analysis of circulating cfDNA, high predictive accuracy for PC was achieved. From a clinical perspective, our findings suggest that that early detection leading to improved overall survival may be achievable in the future.

An omics data analysis method based on feature linear relationship and graph convolutional network

Biological networks are known to be highly modular, and the dysfunction of network modules may cause diseases. Defining the key modules from the omics data and establishing the classification model is helpful in promoting the research of disease diagnosis and prognosis. However, for applying modules in downstream analysis such as disease states discrimination, most methods only utilize the node information, and ignore the node interactions or topological information, which may lead to false positives and limit the model performance. In this study, we propose an omics data analysis method based on feature linear relationship and graph convolutional network (LCNet). In LCNet, we adopt a way of applying the difference of feature linear relationships during disease development to characterize physiological and pathological changes and construct the differential linear relation network, which is simple and interpretable from the perspective of feature linear relationship. A greedy strategy is developed for searching the highly interactive modules with a strong discrimination ability. To fully utilize the information of the detected modules, the personalized sub-graphs for each sample based on the modules are defined, and the graph convolutional network (GCN) classifiers are trained to predict the sample labels. The experimental results on public datasets show the superiority of LCNet in classification performance. For Breast Cancer metabolic data, the identified metabolites by LCNet involve important pathways. Thus, LCNet can identify the module biomarkers by feature linear relationship and a greedy strategy, and label samples by personalized sub-graphs and GCN. It provides a new manner of utilizing node (molecule) information and topological information in the defined modules for better disease classification.

Predicting key gene related to immune infiltration and myofibroblast-like valve interstitial cells in patients with calcified aortic valve disease based on bioinformatics analysis

BACKGROUND

Calcified aortic valve disease (CAVD) is the most prevalent valvular disease that can be treated only through valve replacement. We aimed to explore potential biomarkers and the role of immune cell infiltration in CAVD progression through bioinformatics analysis.

METHODS

Differentially ex-pressed genes (DEGs) were screened out based on three microarray datasets: GSE12644, GSE51472 and GSE83453. Gene Ontology (GO) and Kyoto Encyclopaedia of Genes and Genomes (KEGG) pathway enrichment analysis were performed to evaluate gene expression differences. Machine learning algorithms and DEGs were used to screen key gene. We used CIBERSORT to evaluate the immune cell infiltration of CAVD and evaluated the correlation between the biomarkers and infiltrating immune cells. We also compared bioinformatics analysis results with the valve interstitial cells (VICs) gene expression in single-cell RNA sequencing.

RESULTS

Collagen triple helix repeat containing 1 (CTHRC1) was identified as the key gene of CAVD. We identified a cell subtype valve interstitial cells-fibroblast, which was closely associated with fibro-calcific progress of aortic valve. CTHRC1 highly expressed in the VIC subpopulation. Immune infiltration analysis demonstrated that mast cells, B cells, dendritic cells and eosinophils were involved in pathogenesis of CAVD. Correlation analysis demonstrated that CTHRC1 was correlated with mast cells mostly.

CONCLUSIONS

In summary, the study suggested that CTHRC1 was a key gene of CAVD and CTHRC1 might participate in the potential molecular pathways involved in the connection between infiltrating immune cells and myofibroblast phenotype VICs.

Integrating Omics Data in Genome-Scale Metabolic Modeling: A Methodological Perspective for Precision Medicine

Recent advancements in omics technologies have generated a wealth of biological data. Integrating these data within mathematical models is essential to fully leverage their potential. Genome-scale metabolic models (GEMs) provide a robust framework for studying complex biological systems. GEMs have significantly contributed to our understanding of human metabolism, including the intrinsic relationship between the gut microbiome and the host metabolism. In this review, we highlight the contributions of GEMs and discuss the critical challenges that must be overcome to ensure their reproducibility and enhance their prediction accuracy, particularly in the context of precision medicine. We also explore the role of machine learning in addressing these challenges within GEMs. The integration of omics data with GEMs has the potential to lead to new insights, and to advance our understanding of molecular mechanisms in human health and disease.

A comparison of different machine-learning techniques for the selection of a panel of metabolites allowing early detection of brain tumors

Metabolomics combined with machine learning methods (MLMs), is a powerful tool for searching novel diagnostic panels. This study was intended to use targeted plasma metabolomics and advanced MLMs to develop strategies for diagnosing brain tumors. Measurement of 188 metabolites was performed on plasma samples collected from 95 patients with gliomas (grade I-IV), 70 with meningioma, and 71 healthy individuals as a control group. Four predictive models to diagnose glioma were prepared using 10 MLMs and a conventional approach. Based on the cross-validation results of the created models, the F1-scores were calculated, then obtained values were compared. Subsequently, the best algorithm was applied to perform five comparisons involving gliomas, meningiomas, and controls. The best results were obtained using the newly developed hybrid evolutionary heterogeneous decision tree (EvoHDTree) algorithm, which was validated using Leave-One-Out Cross-Validation, resulting in an F1-score for all comparisons in the range of 0.476-0.948 and the area under the ROC curves ranging from 0.660 to 0.873. Brain tumor diagnostic panels were constructed with unique metabolites, which reduces the likelihood of misdiagnosis. This study proposes a novel interdisciplinary method for brain tumor diagnosis based on metabolomics and EvoHDTree, exhibiting significant predictive coefficients.

Epigenetic and Tumor Microenvironment for Prognosis of Patients with Gastric Cancer

BACKGROUND

Epigenetics studies heritable or inheritable mechanisms that regulate gene expression rather than altering the DNA sequence. However, no research has investigated the link between TME-related genes (TRGs) and epigenetic-related genes (ERGs) in GC.

METHODS

A complete review of genomic data was performed to investigate the relationship between the epigenesis tumor microenvironment (TME) and machine learning algorithms in GC.

RESULTS

Firstly, TME-related differential expression of genes (DEGs) performed non-negative matrix factorization (NMF) clustering analysis and determined two clusters (C1 and C2). Then, Kaplan-Meier curves for overall survival (OS) and progression-free survival (PFS) rates suggested that cluster C1 predicted a poorer prognosis. The Cox-LASSO regression analysis identified eight hub genes (SRMS, MET, OLFML2B, KIF24, CLDN9, RNF43, NETO2, and PRSS21) to build the TRG prognostic model and nine hub genes (TMPO, SLC25A15, SCRG1, ISL1, SOD3, GAD1, LOXL4, AKR1C2, and MAGEA3) to build the ERG prognostic model. Additionally, the signature's area under curve (AUC) values, survival rates, C-index scores, and mean squared error (RMS) curves were evaluated against those of previously published signatures, which revealed that the signature identified in this study performed comparably. Meanwhile, based on the IMvigor210 cohort, a statistically significant difference in OS between immunotherapy and risk scores was observed. It was followed by LASSO regression analysis which identified 17 key DEGs and a support vector machine (SVM) model identified 40 significant DEGs, and based on the Venn diagram, eight co-expression genes (ENPP6, VMP1, LY6E, SHISA6, TMEM158, SYT4, IL11, and KLK8) were discovered.

CONCLUSION

The study identified some hub genes that could be useful in predicting prognosis and management in GC.

Rapid discrimination of Brucellosis in sheep using serum Fourier transform infrared spectroscopy combined with PCA-LDA algorithm

Brucellosis in sheep is an infectious disease caused by Brucella melitensis in sheep. The current conventional serological methods for screening Brucella-infected sheep have the disadvantage of time consuming and low accuracy, so a simple, rapid and highly accurate screening method is needed. The aim of this study was to evaluate the feasibility of diagnosing Brucella-infected sheep by serum samples based on the Fourier transform infrared (FTIR) spectroscopy. In this study, FTIR spectroscopy of serum from Brucella-infected sheep (n=102) and healthy sheep (n=125) revealed abnormal protein and lipid metabolism in serum from Brucella-infected sheep compared to healthy sheep. Principal component analysis-Linear discriminant analysis (PCA-LDA) method was used to differentiate the FTIR spectra of serum from Brucella-infected sheep and healthy sheep in the protein band (3700-3090 cm^-1) and lipid band (3000-2800 cm^-1), and its overall diagnostic accuracy was 100% (sensitivity 100%, specificity 100%). In conclusion, our results suggest that serum FTIR spectroscopy combined with PCA-LDA algorithm has great potential for brucellosis in sheep screening.

Accurate Classification and Prediction of Acute Myocardial Infarction through an ARMD Procedure

The risk stratification of acute myocardial infarction (AMI) patients is of prime importance for clinical management and prognosis assessment. Thus, we propose an ensemble machine learning analysis procedure named ADASYN-RFECV-MDA-DNN (ARMD) to address sample-unbalanced problems and enable stratification and prediction of AMI outcomes. The ARMD analysis procedure was applied to the NMR data of sera from 534 AMI-related subjects in four categories with an extremely imbalanced sample proportion. Firstly, the adaptive synthetic sampling (ADASYN) algorithm was used to address the issue of the original sample imbalance. Secondly, the recursive feature elimination with cross-validation (RFECV) processing and random forest mean decrease accuracy (RF-MDA) algorithm was performed to identify the differential metabolites corresponding to each AMI outcome. Finally, the deep neural network (DNN) was employed to classify and predict AMI events, and its performance was evaluated by comparing the four traditional machine learning methods. Compared with the other four machine learning models, DNN presented consistent superiority in almost all of the model parameters including precision, f1-score, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and classification accuracy, highlighting the potential of deep learning in classification and stratification of clinical diseases. The ARMD analysis procedure was a practical analysis tool for supervised classification and regression modeling of clinical diseases.

Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction

This study investigated whether combining metabolomic and embryologic data with machine learning (ML) models improve the prediction of embryo implantation potential. In this prospective cohort study, infertile couples (n=56) undergoing day-5 single blastocyst transfer between February 2019 and August 2021 were included. After day-5 single blastocyst transfer, spent culture medium (SCM) was subjected to metabolite analysis using nuclear magnetic resonance (NMR) spectroscopy. Derived metabolite levels and embryologic parameters between successfully implanted and failed groups were incorporated into ML models to explore their predictive potential regarding embryo implantation. The SCM of blastocysts that resulted in successful embryo implantation had significantly lower pyruvate (p<0.05) and threonine (p<0.05) levels compared to medium control but not compared to SCM related to embryos that failed to implant. Notably, the prediction accuracy increased when classical ML algorithms were combined with metabolomic and embryologic data. Specifically, the custom artificial neural network (ANN) model with regularized parameters for metabolomic data provided 100% accuracy, indicating the efficiency in predicting implantation potential. Hence, combining ML models (specifically, custom ANN) with metabolomic and embryologic data improves the prediction of embryo implantation potential. The approach could potentially be used to derive clinical benefits for patients in real-time.

Integrated multiple microarray studies by robust rank aggregation to identify immune-associated biomarkers in Crohn's disease based on three machine learning methods

Crohn's disease (CD) is a complex autoimmune disorder presumed to be driven by complex interactions of genetic, immune, microbial and even environmental factors. Intrinsic molecular mechanisms in CD, however, remain poorly understood. The identification of novel biomarkers in CD cases based on larger samples through machine learning approaches may inform the diagnosis and treatment of diseases. A comprehensive analysis was conducted on all CD datasets of Gene Expression Omnibus (GEO); our team then used the robust rank aggregation (RRA) method to identify differentially expressed genes (DEGs) between controls and CD patients. PPI (protein‒protein interaction) network and functional enrichment analyses were performed to investigate the potential functions of the DEGs, with molecular complex detection (MCODE) identifying some important functional modules from the PPI network. Three machine learning algorithms, support vector machine-recursive feature elimination (SVM-RFE), random forest (RF), and least absolute shrinkage and selection operator (LASSO), were applied to determine characteristic genes, which were verified by ROC curve analysis and immunohistochemistry (IHC) using clinical samples. Univariable and multivariable logistic regression were used to establish a machine learning score for diagnosis. Single-sample GSEA (ssGSEA) was performed to examine the correlation between immune infiltration and biomarkers. In total, 5 datasets met the inclusion criteria: GSE75214, GSE95095, GSE126124, GSE179285, and GSE186582. Based on RRA integrated analysis, 203 significant DEGs were identified (120 upregulated genes and 83 downregulated genes), and MCODE revealed some important functional modules in the PPI network. Machine learning identified LCN2, REG1A, AQP9, CCL2, GIP, PROK2, DEFA5, CXCL9, and NAMPT; AQP9, PROK2, LCN2, and NAMPT were further verified by ROC curves and IHC in the external cohort. The final machine learning score was defined as [Expression level of AQP9 × (2.644)] + [Expression level of LCN2 × (0.958)] + [Expression level of NAMPT × (1.115)]. ssGSEA showed markedly elevated levels of dendritic cells and innate immune cells, such as macrophages and NK cells, in CD, consistent with the gene enrichment results that the DEGs are mainly involved in the IL-17 signaling pathway and humoral immune response. The selected biomarkers analyzed by the RRA method and machine learning are highly reliable. These findings improve our understanding of the molecular mechanisms of CD pathogenesis.

Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine

Cancer progression is linked to gene-environment interactions that alter cellular homeostasis. The use of biomarkers as early indicators of disease manifestation and progression can substantially improve diagnosis and treatment. Large omics datasets generated by high-throughput profiling technologies, such as microarrays, RNA sequencing, whole-genome shotgun sequencing, nuclear magnetic resonance, and mass spectrometry, have enabled data-driven biomarker discoveries. The identification of differentially expressed traits as molecular markers has traditionally relied on statistical techniques that are often limited to linear parametric modeling. The heterogeneity, epigenetic changes, and high degree of polymorphism observed in oncogenes demand biomarker-assisted personalized medication schemes. Deep learning (DL), a major subunit of machine learning (ML), has been increasingly utilized in recent years to investigate various diseases. The combination of ML/DL approaches for performance optimization across multi-omics datasets produces robust ensemble-learning prediction models, which are becoming useful in precision medicine. This review focuses on the recent development of ML/DL methods to provide integrative solutions in discovering cancer-related biomarkers, and their utilization in precision medicine.

Uncovering the molecular mechanisms between heart failure and end-stage renal disease via a bioinformatics study

Background: Heart failure (HF) is not only a common complication in patients with end-stage renal disease (ESRD) but also a major cause of death. Although clinical studies have shown that there is a close relationship between them, the mechanism of its occurrence is unclear. The aim of this study is to explore the molecular mechanisms between HF and ESRD through comprehensive bioinformatics analysis, providing a new perspective on the crosstalk between these two diseases. Methods: The HF and ESRD datasets were downloaded from the Gene Expression Omnibus (GEO) database; we identified and analyzed common differentially expressed genes (DEGs). First, Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and gene set variation analyses (GSVA) were applied to explore the potential biological functions and construct protein-protein interaction (PPI) networks. Also, four algorithms, namely, random forest (RF), Boruta algorithm, logical regression of the selection operator (LASSO), and support vector machine-recursive feature elimination (SVM-RFE), were used to identify the candidate genes. Subsequently, the diagnostic efficacy of hub genes for HF and ESRD was evaluated using eXtreme Gradient Boosting (XGBoost) algorithm. CIBERSORT was used to analyze the infiltration of immune cells. Thereafter, we predicted target microRNAs (miRNAs) using databases (miRTarBase, TarBase, and ENOCRI), and transcription factors (TFs) were identified using the ChEA3 database. Cytoscape software was applied to construct mRNA-miRNA-TF regulatory networks. Finally, the Drug Signatures Database (DSigDB) was used to identify potential drug candidates. Results: A total of 68 common DEGs were identified. The enrichment analysis results suggest that immune response and inflammatory factors may be common features of the pathophysiology of HF and ESRD. A total of four hub genes (BCL6, CCL5, CNN1, and PCNT) were validated using RF, LASSO, Boruta, and SVM-RFE algorithms. Their AUC values were all greater than 0.8. Immune infiltration analysis showed that immune cells such as macrophages, neutrophils, and NK cells were altered in HF myocardial tissue, while neutrophils were significantly correlated with all four hub genes. Finally, 11 target miRNAs and 10 TFs were obtained, and miRNA-mRNA-TF regulatory network construction was performed. In addition, 10 gene-targeted drugs were discovered. Conclusion: Our study revealed important crosstalk between HF and ESRD. These common pathways and pivotal genes may provide new ideas for further clinical treatment and experimental studies.

Combined metabolomics and machine learning algorithms to explore metabolic biomarkers for diagnosis of acute myocardial ischemia

Acute myocardial ischemia (AMI) remains the leading cause of death worldwide, and the post-mortem diagnosis of AMI represents a current challenge for both clinical and forensic pathologists. In the present study, the untargeted metabolomics based on ultra-performance liquid chromatography combined with high-resolution mass spectrometry was applied to analyze serum metabolic signatures from AMI in a rat model (n = 10 per group). A total of 28 endogenous metabolites in serum were significantly altered in AMI group relative to control and sham groups. A set of machine learning algorithms, namely gradient tree boosting (GTB), support vector machine (SVM), random forest (RF), logistic regression (LR), and multilayer perceptron (MLP) models, was used to screen the more valuable metabolites from 28 metabolites to optimize the biomarker panel. The results showed that classification accuracy and performance of MLP model were better than other algorithms when the metabolites consisting of L-threonic acid, N-acetyl-L-cysteine, CMPF, glycocholic acid, L-tyrosine, cholic acid, and glycoursodeoxycholic acid. Finally, 17 blood samples from autopsy cases were applied to validate the classification model's value in human samples. The MLP model constructed based on rat dataset achieved accuracy of 88.23%, and ROC of 0.89 for predicting AMI type II in autopsy cases of sudden cardiac death. The results demonstrated that MLP model based on 7 molecular biomarkers had a good diagnostic performance for both AMI rats and autopsy-based blood samples. Thus, the combination of metabolomics and machine learning algorithms provides a novel strategy for AMI diagnosis.

Identification and validation of immune and oxidative stress-related diagnostic markers for diabetic nephropathy by WGCNA and machine learning

Background

Diabetic nephropathy (DN) is the primary cause of end-stage renal disease, but existing therapeutics are limited. Therefore, novel molecular pathways that contribute to DN therapy and diagnostics are urgently needed.

Methods

Based on the Gene Expression Omnibus (GEO) database and Limma R package, we identified differentially expressed genes of DN and downloaded oxidative stress-related genes based on the Genecard database. Then, immune and oxidative stress-related hub genes were screened by combined WGCNA, machine learning, and protein-protein interaction (PPI) networks and validated by external validation sets. We conducted ROC analysis to assess the diagnostic efficacy of hub genes. The correlation of hub genes with clinical characteristics was analyzed by the Nephroseq v5 database. To understand the cellular clustering of hub genes in DN, we performed single nucleus RNA sequencing through the KIT database.

Results

Ultimately, we screened three hub genes, namely CD36, ITGB2, and SLC1A3, which were all up-regulated. According to ROC analysis, all three demonstrated excellent diagnostic efficacy. Correlation analysis revealed that the expression of hub genes was significantly correlated with the deterioration of renal function, and the results of single nucleus RNA sequencing showed that hub genes were mainly clustered in endothelial cells and leukocyte clusters.

Conclusion

By combining three machine learning algorithms with WGCNA analysis, this research identified three hub genes that could serve as novel targets for the diagnosis and therapy of DN.

Applications of machine learning in metabolomics: Disease modeling and classification

Metabolomics research has recently gained popularity because it enables the study of biological traits at the biochemical level and, as a result, can directly reveal what occurs in a cell or a tissue based on health or disease status, complementing other omics such as genomics and transcriptomics. Like other high-throughput biological experiments, metabolomics produces vast volumes of complex data. The application of machine learning (ML) to analyze data, recognize patterns, and build models is expanding across multiple fields. In the same way, ML methods are utilized for the classification, regression, or clustering of highly complex metabolomic data. This review discusses how disease modeling and diagnosis can be enhanced via deep and comprehensive metabolomic profiling using ML. We discuss the general layout of a metabolic workflow and the fundamental ML techniques used to analyze metabolomic data, including support vector machines (SVM), decision trees, random forests (RF), neural networks (NN), and deep learning (DL). Finally, we present the advantages and disadvantages of various ML methods and provide suggestions for different metabolic data analysis scenarios.

The Analysis of Relevant Gene Networks Based on Driver Genes in Breast Cancer

BACKGROUND

The occurrence and development of breast cancer has a strong correlation with a person's genetics. Therefore, it is important to analyze the genetic factors of breast cancer for future development of potential targeted therapies from the genetic level.

METHODS

In this study, we complete an analysis of the relevant protein-protein interaction network relating to breast cancer. This includes three steps, which are breast cancer-relevant genes selection using mutual information method, protein-protein interaction network reconstruction based on the STRING database, and vital genes calculating by nodes centrality analysis.

RESULTS

The 230 breast cancer-relevant genes were chosen in gene selection to reconstruct the protein-protein interaction network and some vital genes were calculated by node centrality analyses. Node centrality analyses conducted with the top 10 and top 20 values of each metric found 19 and 39 statistically vital genes, respectively. In order to prove the biological significance of these vital genes, we carried out the survival analysis and DNA methylation analysis, inquired about the prognosis in other cancer tissues and the RNA expression level in breast cancer. The results all proved the validity of the selected genes.

CONCLUSIONS

These genes could provide a valuable reference in clinical treatment among breast cancer patients.

Interpretable machine learning methods for predictions in systems biology from omics data

Machine learning has become a powerful tool for systems biologists, from diagnosing cancer to optimizing kinetic models and predicting the state, growth dynamics, or type of a cell. Potential predictions from complex biological data sets obtained by “omics” experiments seem endless, but are often not the main objective of biological research. Often we want to understand the molecular mechanisms of a disease to develop new therapies, or we need to justify a crucial decision that is derived from a prediction. In order to gain such knowledge from data, machine learning models need to be extended. A recent trend to achieve this is to design “interpretable” models. However, the notions around interpretability are sometimes ambiguous, and a universal recipe for building well-interpretable models is missing. With this work, we want to familiarize systems biologists with the concept of model interpretability in machine learning. We consider data sets, data preparation, machine learning methods, and software tools relevant to omics research in systems biology. Finally, we try to answer the question: “What is interpretability?” We introduce views from the interpretable machine learning community and propose a scheme for categorizing studies on omics data. We then apply these tools to review and categorize recent studies where predictive machine learning models have been constructed from non-sequential omics data.

Omics Data and Data Representations for Deep Learning-Based Predictive Modeling

Medical discoveries mainly depend on the capability to process and analyze biological datasets, which inundate the scientific community and are still expanding as the cost of next-generation sequencing technologies is decreasing. Deep learning (DL) is a viable method to exploit this massive data stream since it has advanced quickly with there being successive innovations. However, an obstacle to scientific progress emerges: the difficulty of applying DL to biology, and this because both fields are evolving at a breakneck pace, thus making it hard for an individual to occupy the front lines of both of them. This paper aims to bridge the gap and help computer scientists bring their valuable expertise into the life sciences. This work provides an overview of the most common types of biological data and data representations that are used to train DL models, with additional information on the models themselves and the various tasks that are being tackled. This is the essential information a DL expert with no background in biology needs in order to participate in DL-based research projects in biomedicine, biotechnology, and drug discovery. Alternatively, this study could be also useful to researchers in biology to understand and utilize the power of DL to gain better insights into and extract important information from the omics data.

Identification of HIBCH as a Fatty Acid Metabolism-Related Biomarker in Aortic Valve Calcification Using Bioinformatics

Objective. To identify fatty acid metabolism-related biomarkers of aortic valve calcification (AVC) using bioinformatics and to research the role of immune cell infiltration for AVC. Methods. The AVC dataset was retrieved from the Gene Expression Omnibus database. R package is used for differential expression genes analysis and weighted gene coexpression analysis. The differentially coexpressed genes were identified by the Venn diagram, followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses of differentially coexpressed genes. Functions closely related to AVC were identified by GO and KEGG enrichment analyses of differentially coexpressed genes. Genes related to fatty acid metabolism were retrieved from the Molecular Signatures Database (MSigDB) database. After removing duplicate genes, least absolute shrinkage and selection operator (LASSO) regression analysis, support vector machine recursive feature elimination (SVM-RFE), and random forest were applied to recognize biomarkers related to fatty acid metabolism in AVC. The CIBERSORT tool was used to analyze infiltration of immune cells in normal and AVC samples. Correlations between biomarkers and immune cells were calculated. Finally, HIBCH-related pathway was predicted by single-gene gene set enrichment analysis (GSEA). Results. 2416 differentially expressed genes and one coexpression module were identified. A total of 1473 differentially coexpressed genes were acquired. GO and KEGG enrichment analyses demonstrated that differentially coexpressed genes were closely related to fatty acid metabolism. LASSO regression analysis, SVM-REF, and random forest revealed that 3-hydroxyisobutyryl-CoA hydrolase (HIBCH) was a biomarker of fatty acid metabolism-related genes in AVC. Significant high levels of memory B cells were found in AVC than normal samples, while activated natural killer (NK) cells were significantly low in AVC than normal samples. A significantly positive relevance was observed between HIBCH and activated NK cells, regulatory T cells, monocytes, naïve B cells, activated dendritic cells, resting memory CD4 T cells, resting NK cells, and CD8 T cells. A significantly negative relevance was observed between HIBCH and activated memory CD4 T cells, memory B cells, neutrophils, gamma delta T cells, M0 macrophages, and plasma cells. The single-gene GSEA results suggest that HIBCH may work through the inhibition of multiple immune-related pathways. Conclusion. HIBCH is closely relevant to immune cell infiltration in AVC and could be applied as a diagnostic marker for AVC.

Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

Background

Presently, there is a wide variety of classification methods and deep neural network approaches in bioinformatics. Deep neural networks have proven their effectiveness for classification tasks, and have outperformed classical methods, but they suffer from a lack of interpretability. Therefore, these innovative methods are not appropriate for decision support systems in healthcare. Indeed, to allow clinicians to make informed and well thought out decisions, the algorithm should provide the main pieces of information used to compute the predicted diagnosis and/or prognosis, as well as a confidence score for this prediction.

Methods

Herein, we used a new supervised autoencoder (SAE) approach for classification of clinical metabolomic data. This new method has the advantage of providing a confidence score for each prediction thanks to a softmax classifier and a meaningful latent space visualization and to include a new efficient feature selection method, with a structured constraint, which allows for biologically interpretable results.

Results

Experimental results on three metabolomics datasets of clinical samples illustrate the effectiveness of our SAE and its confidence score. The supervised autoencoder provides an accurate localization of the patients in the latent space, and an efficient confidence score. Experiments show that the SAE outperforms classical methods (PLS-DA, Random Forests, SVM, and neural networks (NN)). Furthermore, the metabolites selected by the SAE were found to be biologically relevant.

Conclusion

In this paper, we describe a new efficient SAE method to support diagnostic or prognostic evaluation based on metabolomics analyses.

Complex metabolic interactions between ovary, plasma, urine, and hair in ovarian cancer

Ovarian cancer (OC) is the third most common malignant tumor of women accompanied by alteration of systemic metabolism, yet the underlying interactions between the local OC tissue and other system biofluids remain unclear. In this study, we recruited 17 OC patients, 16 benign ovarian tumor (BOT) patients, and 14 control patients to collect biological samples including ovary plasma, urine, and hair from the same patient. The metabolic features of samples were characterized using a global and targeted metabolic profiling strategy based on Gas chromatography-mass spectrometry (GC-MS). Principal component analysis (PCA) revealed that the metabolites display obvious differences in ovary tissue, plasma, and urine between OC and non-malignant groups but not in hair samples. The metabolic alterations in OC tissue included elevated glycolysis (lactic acid) and TCA cycle intermediates (malic acid, fumaric acid) were related to energy metabolism. Furthermore, the increased levels of glutathione and polyunsaturated fatty acids (linoleic acid) together with decreased levels of saturated fatty acid (palmitic acid) were observed, which might be associated with the anti-oxidative stress capability of cancer. Furthermore, how metabolite profile changes across differential biospecimens were compared in OC patients. Plasma and urine showed a lower concentration of amino acids (alanine, aspartic acid, glutamic acid, proline, leucine, and cysteine) than the malignant ovary. Plasma exhibited the highest concentrations of fatty acids (stearic acid, EPA, and arachidonic acid), while TCA cycle intermediates (succinic acid, citric acid, and malic acid) were most concentrated in the urine. In addition, five plasma metabolites and three urine metabolites showed the best specificity and sensitivity in differentiating the OC group from the control or BOT groups (AUC > 0.90) using machine learning modeling. Overall, this study provided further insight into different specimen metabolic characteristics between OC and non-malignant disease and identified the metabolic fluctuation across ovary and biofluids.

AI/ML-driven advances in untargeted metabolomics and exposomics for biomedical applications

Metabolomics describes a high-throughput approach for measuring a repertoire of metabolites and small molecules in biological samples. One utility of untargeted metabolomics, unbiased global analysis of the metabolome, is to detect key metabolites as contributors to, or readouts of, human health and disease. In this perspective, we discuss how artificial intelligence (AI) and machine learning (ML) have promoted major advances in untargeted metabolomics workflows and facilitated pivotal findings in the areas of disease screening and diagnosis. We contextualize applications of AI and ML to the emerging field of high-resolution mass spectrometry (HRMS) exposomics, which unbiasedly detects endogenous metabolites and exogenous chemicals in human tissue to characterize exposure linked with disease outcomes. We discuss the state of the science and suggest potential opportunities for using AI and ML to improve data quality, rigor, detection, and chemical identification in untargeted metabolomics and exposomics studies.

Metabolomics of Breast Cancer: A Review

Breast cancer is the most commonly diagnosed cancer in women worldwide. Major advances have been made towards breast cancer prevention and treatment. Unfortunately, the incidence of breast cancer is still increasing globally. Metabolomics is the field of science which studies all the metabolites in a cell, tissue, system, or organism. Metabolomics can provide information on dynamic changes occurring during cancer development and progression. The metabolites identified using cutting-edge metabolomics techniques will result in the identification of biomarkers for the early detection, diagnosis, and treatment of cancers. This review briefly introduces the metabolic changes in cancer with particular focus on breast cancer.

Variational autoencoders learn transferrable representations of metabolomics data

Dimensionality reduction approaches are commonly used for the deconvolution of high-dimensional metabolomics datasets into underlying core metabolic processes. However, current state-of-the-art methods are widely incapable of detecting nonlinearities in metabolomics data. Variational Autoencoders (VAEs) are a deep learning method designed to learn nonlinear latent representations which generalize to unseen data. Here, we trained a VAE on a large-scale metabolomics population cohort of human blood samples consisting of over 4500 individuals. We analyzed the pathway composition of the latent space using a global feature importance score, which demonstrated that latent dimensions represent distinct cellular processes. To demonstrate model generalizability, we generated latent representations of unseen metabolomics datasets on type 2 diabetes, acute myeloid leukemia, and schizophrenia and found significant correlations with clinical patient groups. Notably, the VAE representations showed stronger effects than latent dimensions derived by linear and non-linear principal component analysis. Taken together, we demonstrate that the VAE is a powerful method that learns biologically meaningful, nonlinear, and transferrable latent representations of metabolomics data.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Artificial Intelligence and Circulating Cell-Free DNA Methylation Profiling: Mechanism and Detection of Alzheimer's Disease

Background: Despite extensive efforts, significant gaps remain in our understanding of Alzheimer’s disease (AD) pathophysiology. Novel approaches using circulating cell-free DNA (cfDNA) have the potential to revolutionize our understanding of neurodegenerative disorders. Methods: We performed DNA methylation profiling of cfDNA from AD patients and compared them to cognitively normal controls. Six Artificial Intelligence (AI) platforms were utilized for the diagnosis of AD while enrichment analysis was used to elucidate the pathogenesis of AD. Results: A total of 3684 CpGs were significantly (adj. p-value < 0.05) differentially methylated in AD versus controls. All six AI algorithms achieved high predictive accuracy (AUC = 0.949−0.998) in an independent test group. As an example, Deep Learning (DL) achieved an AUC (95% CI) = 0.99 (0.95−1.0), with 94.5% sensitivity and specificity. Conclusion: We describe numerous epigenetically altered genes which were previously reported to be differentially expressed in the brain of AD sufferers. Genes identified by AI to be the best predictors of AD were either known to be expressed in the brain or have been previously linked to AD. We highlight enrichment in the Calcium signaling pathway, Glutamatergic synapse, Hedgehog signaling pathway, Axon guidance and Olfactory transduction in AD sufferers. To the best of our knowledge, this is the first reported genome-wide DNA methylation study using cfDNA to detect AD.

Precision Oncology: Artificial Intelligence and DNA Methylation Analysis of Circulating Cell-Free DNA for Lung Cancer Detection

Background

Lung cancer (LC) is a leading cause of cancer-deaths globally. Its lethality is due in large part to the paucity of accurate screening markers. Precision Medicine includes the use of omics technology and novel analytic approaches for biomarker development. We combined Artificial Intelligence (AI) and DNA methylation analysis of circulating cell-free tumor DNA (ctDNA), to identify putative biomarkers for and to elucidate the pathogenesis of LC.

Methods

Illumina Infinium MethylationEPIC BeadChip array analysis was used to measure cytosine (CpG) methylation changes across the genome in LC. Six different AI platforms including support vector machine (SVM) and Deep Learning (DL) were used to identify CpG biomarkers and for LC detection. Training set and validation sets were generated, and 10-fold cross validation performed. Gene enrichment analysis using g:profiler and GREAT enrichment was used to elucidate the LC pathogenesis.

Results

Using a stringent GWAS significance threshold, p-value <5x10^-8, we identified 4389 CpGs (cytosine methylation loci) in coding genes and 1812 CpGs in non-protein coding DNA regions that were differentially methylated in LC. SVM and three other AI platforms achieved an AUC=1.00; 95% CI (0.90-1.00) for LC detection. DL achieved an AUC=1.00; 95% CI (0.95-1.00) and 100% sensitivity and specificity. High diagnostic accuracies were achieved with only intragenic or only intergenic CpG loci. Gene enrichment analysis found dysregulation of molecular pathways involved in the development of small cell and non-small cell LC.

Conclusion

Using AI and DNA methylation analysis of ctDNA, high LC detection rates were achieved. Further, many of the genes that were epigenetically altered are known to be involved in the biology of neoplasms in general and lung cancer in particular.

Feature Selection Pipelines with Classification for Non-targeted Metabolomics Combining the Neural Network and Genetic Algorithm

Non-targeted metabolomics via high-resolution mass spectrometry methods, such as direct infusion Fourier transform-ion cyclotron resonance mass spectrometry (DI-FT-ICR MS), produces data sets with thousands of features. By contrast, the number of samples is in general substantially lower. This disparity presents challenges when analyzing non-targeted metabolomics data sets and often requires custom methods to uncover information not always accessible via classical statistical techniques. In this work, we present a pipeline that combines a convolutional neural network with traditional statistical approaches and an adaptation of a genetic algorithm. The developed method was applied to a lifestyle intervention cohort data set, where subjects at risk of type 2 diabetes underwent an oral glucose tolerance test. Feature selection is the final result of the pipeline, achieved through classification of the data set via a neural network, with a precision-recall score of over 0.9 on the test set. The features most relevant for the described classification were then chosen via a genetic algorithm. The output of the developed pipeline encompasses approximately 200 features with high predictive scores, providing a fingerprint of the metabolic changes in the prediabetic class on the data set. Our framework presents a new approach which allows to apply complex modeling based on convolutional neural networks for the analysis of high-resolution mass spectrometric data.

Identification of DTL as Related Biomarker and Immune Infiltration Characteristics of Nasopharyngeal Carcinoma via Comprehensive Strategies

Purpose

Although considerable progress has been made in basic and clinical research on nasopharyngeal carcinoma (NPC), the biomarkers of the progression of NPC have not been fully studied and described. This study was designed to identify potential novel biomarkers for NPC using integrated analyses and explore the immune cell infiltration in this pathological process.

Methods

Five GEO data sets were downloaded from gene expression omnibus database (GEO) and analysed to identify differentially expressed genes (DEGs), followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. The four algorithms were adopted for screening of novel and key biomarkers for NPC, including random forest (RF) machine learning algorithm, least absolute shrinkage and selection operator (LASSO) logistic regression, support vector machine-recursive feature elimination (SVM-RFE), and weighted gene co-expression network analysis (WGCNA). Lastly, CIBERSORT was used to assess the infiltration of immune cells in NPC, and the correlation between diagnostic markers and infiltrating immune cells was analyzed.

Results

Herein, we identified 46 DEGs, and enrichment analysis results showed that DEGs and several kinds of signaling pathways might be closely associated with the occurrence and progression of NPC. DTL was recognized as NPC-related biomarker. DTL, also known as retinoic acid-regulated nuclear matrix-associated protein (RAMP), or DNA replication factor 2 (CDT2), is reported to be correlated with the cell proliferation, cell cycle arrest and cell invasion in hepatocellular carcinoma, breast cancer and gastric cancer. Immune infiltration analysis demonstrated that macrophages M0, macrophages M1 and T cells CD4 memory activated were linked to pathogenesis of NPC.

Conclusion

In summary, we adopted a comprehensive strategy to screen DTL as biomarkers related to NPC and explore the critical role of immune cell infiltration in NPC.

Navigating the pitfalls of applying machine learning in genomics

The scale of genetic, epigenomic, transcriptomic, cheminformatic and proteomic data available today, coupled with easy-to-use machine learning (ML) toolkits, has propelled the application of supervised learning in genomics research. However, the assumptions behind the statistical models and performance evaluations in ML software frequently are not met in biological systems. In this Review, we illustrate the impact of several common pitfalls encountered when applying supervised ML in genomics. We explore how the structure of genomics data can bias performance evaluations and predictions. To address the challenges associated with applying cutting-edge ML methods to genomics, we describe solutions and appropriate use cases where ML modelling shows great potential.

A Comprehensive Evaluation of Metabolomics Data Preprocessing Methods for Deep Learning

Machine learning has greatly advanced over the past decade, owing to advances in algorithmic innovations, hardware acceleration, and benchmark datasets to train on domains such as computer vision, natural-language processing, and more recently the life sciences. In particular, the subfield of machine learning known as deep learning has found applications in genomics, proteomics, and metabolomics. However, a thorough assessment of how the data preprocessing methods required for the analysis of life science data affect the performance of deep learning is lacking. This work contributes to filling that gap by assessing the impact of commonly used as well as newly developed methods employed in data preprocessing workflows for metabolomics that span from raw data to processed data. The results from these analyses are summarized into a set of best practices that can be used by researchers as a starting point for downstream classification and reconstruction tasks using deep learning.

Maternal plasma lipids are involved in the pathogenesis of preterm birth

BACKGROUND

Preterm birth is defined by the onset of labor at a gestational age shorter than 37 weeks, and it can lead to premature birth and impose a threat to newborns' health. The Puerto Rico PROTECT cohort is a well-characterized prospective birth cohort that was designed to investigate environmental and social contributors to preterm birth in Puerto Rico, where preterm birth rates have been elevated in recent decades. To elucidate possible relationships between metabolites and preterm birth in this cohort, we conducted a nested case-control study to conduct untargeted metabolomic characterization of maternal plasma of 31 women who experienced preterm birth and 69 controls who underwent full-term labor at 24-28 gestational weeks.

RESULTS

A total of 333 metabolites were identified and annotated with liquid chromatography/mass spectrometry. Subsequent weighted gene correlation network analysis shows that the fatty acid and carene-enriched module has a significant positive association (P = 8e-04, FDR = 0.006) with preterm birth. After controlling for potential clinical confounders, a total of 38 metabolites demonstrated significant changes uniquely associated with preterm birth, where 17 of them were preterm biomarkers. Among 7 machine-learning classifiers, the application of random forest achieved a highly accurate and specific prediction (AUC = 0.92) for preterm birth in testing data, demonstrating their strong potential as biomarkers for preterm births. The 17 preterm biomarkers are involved in cell signaling, lipid metabolism, and lipid peroxidation functions. Additional modeling using only the 19 spontaneous preterm births (sPTB) and controls identifies 16 sPTB markers, with an AUC of 0.89 in testing data. Half of the sPTB overlap with those markers for preterm births. Further causality analysis infers that suberic acid upregulates several fatty acids to promote preterm birth.

CONCLUSIONS

Altogether, this study demonstrates the involvement of lipids, particularly fatty acids, in the pathogenesis of preterm birth.

Multivariate analysis of NMR-based metabolomic data

Nuclear magnetic resonance (NMR) spectroscopy allows for simultaneous detection of a wide range of metabolites and lipids. As metabolites act together in complex metabolic networks, they are often highly correlated, and optimal biological insight is achieved when using methods that take the correlation into account. For this reason, latent-variable-based methods, such as principal component analysis and partial least-squares discriminant analysis, are widely used in metabolomic studies. However, with increasing availability of larger population cohorts, and a shift from analysis of spectral data to using quantified metabolite levels, both more traditional statistical approaches and alternative machine learning methods have become more widely used. This review aims at providing an overview of the current state-of-the-art multivariate methods for the analysis of NMR-based metabolomic data as well as alternative methods, highlighting their strengths and limitations.

Biomarker selection and a prospective metabolite-based machine learning diagnostic for lyme disease

We provide a pipeline for data preprocessing, biomarker selection, and classification of liquid chromatography–mass spectrometry (LCMS) serum samples to generate a prospective diagnostic test for Lyme disease. We utilize tools of machine learning (ML), e.g., sparse support vector machines (SSVM), iterative feature removal (IFR), and k-fold feature ranking to select several biomarkers and build a discriminant model for Lyme disease. We report a 98.13% test balanced success rate (BSR) of our model based on a sequestered test set of LCMS serum samples. The methodology employed is general and can be readily adapted to other LCMS, or metabolomics, data sets.

Development of computational models using omics data for the identification of effective cancer metabolic biomarkers

Identification of novel biomarkers has been an active area of study for the effective diagnosis, prognosis and treatment of cancers. Among various types of cancer biomarkers, metabolic biomarkers, including enzymes, metabolites and metabolic genes, deserve attention as they can serve as a reliable source for diagnosis, prognosis and treatment of cancers. In particular, efforts to identify novel biomarkers have been greatly facilitated by a rapid increase in the volume of multiple omics data generated for a range of cancer cells. These omics data in turn serve as ingredients for developing computational models that can help derive deeper insights into the biology of cancer cells, and identify metabolic biomarkers. In this review, we provide an overview of omics data generated for cancer cells, and discuss recent studies on computational models that were developed using omics data in order to identify effective cancer metabolic biomarkers.

Comprehensive Analysis of Serum Metabolites Profiles in Acute Radiation Enteritis Rats by Untargeted Metabolomics

Acute radiation enteritis is a common complication occurring in patients with pelvic and abdominal tumors who receive radiotherapy. Acute radiation enteritis seriously reduces the life quality, even threatens the lives of patients. Untargeted metabolomics is an emerging strategy to explore the novel biomarkers and uncover potential pathogenesis of acute radiation enteritis. Acute radiation enteritis rat model was established by single abdominal irradiation with a gamma-ray dose of 10 Gy. Serum from 15 acute radiation enteritis rats and 10 controls was extracted for metabolomics analysis by UHPLC-Q-TOF/MS. Clinical manifestations and morphological alterations of intestine confirmed the successful establishment of acute radiation enteritis. According to the metabolomics data, 6,044 positive peaks and 4,241 negative peaks were extracted from each specimen. OPLS-DA analysis and the heat map for cluster analysis showed satisfactory discriminatory power between acute radiation enteritis rats and controls. Subsequent analysis extracted 66 significantly differentially expressed metabolites, which might be potential biomarkers for acute radiation enteritis diagnosis. Moreover, Kyoto Encyclopedia of Genes and Genomes enrichment analyses uncovered the potential mechanisms through which differentially expressed metabolites participated in acute radiation enteritis pathogenesis. To sum up, we summarized several differentially expressed serum metabolites as potential biomarkers for diagnosis of acute radiation enteritis and provide latent clues for elucidating acute radiation enteritis pathology.

Navigating Multi-Scale Cancer Systems Biology Towards Model-Driven Clinical Oncology and Its Applications in Personalized Therapeutics

Rapid advancements in high-throughput omics technologies and experimental protocols have led to the generation of vast amounts of scale-specific biomolecular data on cancer that now populates several online databases and resources. Cancer systems biology models built using this data have the potential to provide specific insights into complex multifactorial aberrations underpinning tumor initiation, development, and metastasis. Furthermore, the annotation of these single- and multi-scale models with patient data can additionally assist in designing personalized therapeutic interventions as well as aid in clinical decision-making. Here, we have systematically reviewed the emergence and evolution of (i) repositories with scale-specific and multi-scale biomolecular cancer data, (ii) systems biology models developed using this data, (iii) associated simulation software for the development of personalized cancer therapeutics, and (iv) translational attempts to pipeline multi-scale panomics data for data-driven in silico clinical oncology. The review concludes that the absence of a generic, zero-code, panomics-based multi-scale modeling pipeline and associated software framework, impedes the development and seamless deployment of personalized in silico multi-scale models in clinical settings.

Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data

Deep learning (DL) is a distinct class of machine learning that has achieved first-class performance in many fields of study. For epigenomics, the application of DL to assist physicians and scientists in human disease-relevant prediction tasks has been relatively unexplored until very recently. In this article, we critically review published studies that employed DL models to predict disease detection, subtype classification, and treatment responses, using epigenomic data. A comprehensive search on PubMed, Scopus, Web of Science, Google Scholar, and arXiv.org was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Among 1140 initially identified publications, we included 22 articles in our review. DNA methylation and RNA-sequencing data are most frequently used to train the predictive models. The reviewed models achieved a high accuracy ranged from 88.3% to 100.0% for disease detection tasks, from 69.5% to 97.8% for subtype classification tasks, and from 80.0% to 93.0% for treatment response prediction tasks. We generated a workflow to develop a predictive model that encompasses all steps from first defining human disease-related tasks to finally evaluating model performance. DL holds promise for transforming epigenomic big data into valuable knowledge that will enhance the development of translational epigenomics.