Search

Simple Summary: Recent high-throughput technologies such as transcriptomics, proteomics, and metabolomics have allowed progress in understanding biological systems at different levels of detail. Even so, it is necessary to integrate multiple omics data sets to achieve a comprehensive understanding of the subject under study. In this article, we review the methods used for integrating transcriptomics, proteomics, and metabolomics data and summarize them in three approaches: combined omics integration, correlation-based integration strategies, and machine learning integrative approaches. Our goal is to showcase the uses and limitations of each approach, allowing researchers to choose the more appropriate tool for each scenario to extract a comprehensive view of a biological system. With the advent of high-throughput technologies, the field of omics has made significant strides in characterizing biological systems at various levels of complexity. Transcriptomics, proteomics, and metabolomics are the three most widely used omics technologies, each providing unique insights into different layers of a biological system. However, analyzing each omics data set separately may not provide a comprehensive understanding of the subject under study. Therefore, integrating multi-omics data has become increasingly important in bioinformatics research. In this article, we review strategies for integrating transcriptomics, proteomics, and metabolomics data, including co-expression analysis, metabolite–gene networks, constraint-based models, pathway enrichment analysis, and interactome analysis. We discuss combined omics integration approaches, correlation-based strategies, and machine learning techniques that utilize one or more types of omics data. By presenting these methods, we aim to provide researchers with a better understanding of how to integrate omics data to gain a more comprehensive view of a biological system, facilitating the identification of complex patterns and interactions that might be missed by single-omics analyses. [ABSTRACT FROM AUTHOR]

Gene expression varies stochastically across genders, racial groups, and health statuses. Deciphering these patterns is crucial for identifying informative genes, classifying samples, and understanding diseases like cancer. This study analyzes 11,252 bulk RNA-seq samples to explore expression patterns of 19,156 genes, including 10,512 cancer tissue samples and 740 normal samples. Additionally, 4,884 single-cell RNA-seq samples are examined. Statistical analysis using 16 probability distributions shows that normal samples display a wider range of distributions compared to cancer samples. Cancer samples tend to favor asymmetric distributions such as generalized extreme value, logarithmic normal, and Gaussian mixture distributions. In contrast, certain genes in normal samples exhibit symmetric distributions. Remarkably, more than 95.5% of genes exhibit non-normal distributions, which challenges traditional assumptions. Furthermore, distributions differ significantly between bulk and single-cell RNA-seq data. Many cancer driver genes exhibit distinct distribution patterns across sample types, suggesting potential for gene selection and classification based on distribution characteristics. A novel skewness-based metric is proposed to quantify distribution variation across datasets, showing genes with significant skewness differences have biological relevance. Finally, an improved naïve Bayes method incorporating gene-specific distributions demonstrates superior performance in simulations over traditional methods. This work enhances understanding of gene expression and its application in omics-based gene selection and sample classification. [ABSTRACT FROM AUTHOR]

High-throughput technologies and machine learning (ML), when applied to a huge pool of medical data such as omics data, result in efficient analysis. Recent research aims to apply and develop ML models to predict a disease well in time using available omics datasets. The present work proposed a framework, 'OmicPredict', deploying a hybrid feature selection method and deep neural network (DNN) model to predict multiple diseases using omics data. The hybrid feature selection method is developed using the Analysis of Variance (ANOVA) technique and firefly algorithm. The OmicPredict framework is applied to three case studies, Alzheimer's disease, Breast cancer, and Coronavirus disease 2019 (COVID-19). In the case study of Alzheimer's disease, the framework predicts patients using GSE33000 and GSE44770 dataset. In the case study of Breast cancer, the framework predicts human epidermal growth factor receptor 2 (HER2) subtype status using Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset. In the case study of COVID-19, the framework performs patients' classification using GSE157103 dataset. The experimental results show that DNN model achieved an Area Under Curve (AUC) score of 0.949 for the Alzheimer's (GSE33000 and GSE44770) dataset. Furthermore, it achieved an AUC score of 0.987 and 0.989 for breast cancer (METABRIC) and COVID-19 (GSE157103) datasets, respectively, outperforming Random Forest, Naïve Bayes models, and the existing research. [ABSTRACT FROM AUTHOR]

Recent advancements in Natural Language Processing (NLP) have been significantly driven by the development of Large Language Models (LLMs), representing a substantial leap in language-based technology capabilities. These models, built on sophisticated deep learning architectures, typically transformers, are characterized by billions of parameters and extensive training data, enabling them to achieve high accuracy across various tasks. The transformer architecture of LLMs allows them to effectively handle context and sequential information, which is crucial for understanding and generating human language. Beyond traditional NLP applications, LLMs have shown significant promise in bioinformatics, transforming the field by addressing challenges associated with large and complex biological datasets. In genomics, proteomics, and personalized medicine, LLMs facilitate identifying patterns, predicting protein structures, or understanding genetic variations. This capability is crucial, e.g., for advancing drug discovery, where accurate prediction of molecular interactions is essential. This review discusses the current trends in LLMs research and their potential to revolutionize the field of bioinformatics and accelerate novel discoveries in the life sciences.

ObjectiveThis study analyzes the omics data resources in human-infecting coronavirus animal models collected from various public databases, focusing on data distribution, dataset quantity, data types, species, strains, and research content. It aims to enhance our understanding of biological characteristics and pathogenic mechanisms of coronaviruses, thereby providing a solid foundation for devising effective therapeutic strategies and preventive measures.Methods Query strategies, including specific virus names, time ranges, and inclusion and exclusion criteria, were defined to retrieve data from major public omics databases such as GEO and ArrayExpress. Secondary filtering was performed based on different field types to obtain a more accurate data list. An omics data text database was established for bibliometric analysis. Co-occurrence networks were constructed for the analysis of the correlation strengths between different research themes, technical methods, and involved species. The cell types, organs, and biological pathways involved in studies were examined to further elucidate the pathogenic interplay between pathogens and hosts. Results About twenty public databases containing coronavirus-related omics data were identified, with a primary focus on novel coronavirus infection. Commonly used species include humans, mice, hamsters, and monkeys, while the commonly used virus strains are Wuhan-Hu-1 and USA-WA1/2020. Lung tissues are primarily used in animal models such as mice, macaques, and ferrets, while airway epithelial cells and Calu-3 cells are predominantly employed in human-related studies. Expression profiling data indicate that gene pathways involved in inflammation, cytokine response, complement pathway, cell damage, proliferation, and differentiation are significantly upregulated after infection. Proteomics studies reveal significant changes in phosphoproteome, ubiquitinome, and total proteome of patient samples at different infection stages. Specific protein categories, including viral receptors and proteases, transcription factors, cytokines, proteins associated with coagulation system, angiogenesis-related proteins, and fibrosis markers, show alterations after coronavirus infection. In addition, metabolomics data suggest that phosphocholine, phosphoethanolamine, arachidonic acid, and oleic acid could serve as potential metabolic markers. Epigenomics research indicates m6A methylation plays a role in SARS-CoV-2 replication, infection, and transmission, affecting host cell-virus interactions. Among these, N, S, and non-structural proteins 2 and 3 exhibit the most significant ubiquitination. Trends in microbiomics research suggest that microbial communities in the gut and wastewater are emerging as new research focuses. Conclusion The data types of coronavirus omics are diverse, with a wide variety of models and cell types used. The selection of species and technical methods for modelling varies based on the characteristics of different viruses. Multi-omics data from animal models of coronavirus infection can reveal key interactions between hosts and pathogens, identifying biomarkers and potential therapeutic targets, and provide valuable information for a deeper understanding of biological characteristics and infection mechanisms of coronaviruses.

Diabetic nephropathy (DN) is a common and serious complication of diabetes, contributing significantly to patient mortality. Complication of DN (CDN) ranks as the second leading cause of end-stage renal disease globally. To address this, understanding the genetic regulation underlying DN is crucial for personalized treatment strategies. In this study, we identified genes and lncRNAs associated with diabetes and diabetic nephropathy constructing a DN-related lncRNA–mRNA network (DNLMN). This network, characterized by scale-free biomolecular properties, generated through the study of topological properties, elucidates key regulatory interactions. Enrichment analysis of important network modules revealed critical biological processes and pathways involved in DN pathogenesis. In the second step, we investigated the differential expression and co-expression of hub nodes in diseased and normal individuals, identifying lncRNA-mRNA relationships implicated in disease regulation. Finally, we gathered DN-related single nucleotide polymorphisms (SNPs) and lncRNAs from the LincSNP 3.0 database. The DNLMN encompasses SNP-associated lncRNAs, and transcription factors (TFs) linked to differentially expressed lncRNAs between diseased and normal samples. These results underscore the significance of biomolecular networks in disease progression and highlighting the role of biomolecular variability contributes to personalized disease phenotyping and treatment.

Transcriptional regulatory networks (TRNs) associated with recombinant protein (rProt) synthesis in Yarrowia lipolytica are still under-described. Yet, it is foreseen that skillful manipulation with TRNs would enable global fine-tuning of the host strain's metabolism towards a high-level-producing phenotype. Our previous studies investigated the transcriptomes of Y. lipolytica strains overproducing biochemically different rProts and the functional impact of transcription factors (TFs) overexpression (OE) on rProt synthesis capacity in this species. Hence, much knowledge has been accumulated and deposited in public repositories. In this study, we combined both biological datasets and enriched them with further experimental data to investigate an interplay between TFs and rProts synthesis in Y. lipolytica at transcriptional and functional levels. Technically, the RNAseq datasets were extracted and re-analyzed for the TFs' expression profiles. Of the 140 TFs in Y. lipolytica, 87 TF-encoding genes were significantly deregulated in at least one of the strains. The expression profiles were juxtaposed against the rProt amounts from 125 strains co-overexpressing TF and rProt. In addition, several strains bearing knock-outs (KOs) in the TF loci were analyzed to get more insight into their actual involvement in rProt synthesis. Different profiles of the TFs' transcriptional deregulation and the impact of their OE or KO on rProts synthesis were observed, and new engineering targets were pointed. [ABSTRACT FROM AUTHOR]

Objective This study analyzes the omics data resources in human-infecting coronavirus animal models collected from various public databases, focusing on data distribution, dataset quantity, data types, species, strains, and research content. It aims to enhance our understanding of biological characteristics and pathogenic mechanisms of coronaviruses, thereby providing a solid foundation for devising effective therapeutic strategies and preventive measures. Methods Query strategies, including specific virus names, time ranges, and inclusion and exclusion criteria, were defined to retrieve data from major public omics databases such as GEO and ArrayExpress. Secondary filtering was performed based on different field types to obtain a more accurate data list. An omics data text database was established for bibliometric analysis. Co-occurrence networks were constructed for the analysis of the correlation strengths between different research themes, technical methods, and involved species. The cell types, organs, and biological pathways involved in studies were examined to further elucidate the pathogenic interplay between pathogens and hosts. Results About twenty public databases containing coronavirus-related omics data were identified, with a primary focus on novel coronavirus infection. Commonly used species include humans, mice, hamsters, and monkeys, while the commonly used virus strains are WuhanHu-1 and USA-WA1/2020. Lung tissues are primarily used in animal models such as mice, macaques, and ferrets, while airway epithelial cells and Calu-3 cells are predominantly employed in human-related studies. Expression profiling data indicate that gene pathways involved in inflammation, cytokine response, complement pathway, cell damage, proliferation, and differentiation are significantly upregulated after infection. Proteomics studies reveal significant changes in phosphoproteome, ubiquitinome, and total proteome of patient samples at different infection stages. Specific protein categories, including viral receptors and proteases, transcription factors, cytokines, proteins associated with coagulation system, angiogenesis-related proteins, and fibrosis markers, show alterations after coronavirus infection. In addition, metabolomics data suggest that phosphocholine, phosphoethanolamine, arachidonic acid, and oleic acid could serve as potential metabolic markers. Epigenomics research indicates m6A methylation plays a role in SARS-CoV-2 replication, infection, and transmission, affecting host cell-virus interactions. Among these, N, S, and non-structural proteins 2 and 3 exhibit the most significant ubiquitination. Trends in microbiomics research suggest that microbial communities in the gut and wastewater are emerging as new research focuses. Conclusion The data types of coronavirus omics are diverse, with a wide variety of models and cell types used. The selection of species and technical methods for modelling varies based on the characteristics of different viruses. Multi-omics data from animal models of coronavirus infection can reveal key interactions between hosts and pathogens, identifying biomarkers and potential therapeutic targets, and provide valuable information for a deeper understanding of biological characteristics and infection mechanisms of coronaviruses. [ABSTRACT FROM AUTHOR]

This review focuses on the intersection of artificial intelligence and genomic data in cancer research. It explores the types of genomic data used in the literature, the methodologies of machine learning and deep learning, recent applications, and the challenges associated with this field. Through an analysis of 47,586 articles and addressing seven research questions, the study reveals significant growth in this area over the past years. While there has been remarkable progress, ongoing attention is needed to address ethical considerations, interpretability of algorithms, and potential data biases, to ensure the reliable and responsible use of these advanced technologies. Overall, this paper provides a comprehensive overview of the current research landscape, offering insights into both the potential and challenges of AI in genomic data research. [ABSTRACT FROM AUTHOR]

The statistical analysis of omics data poses a great computational challenge given their ultra–high-dimensional nature and frequent between-features correlation. In this work, we extended the iterative sure independence screening (ISIS) algorithm by pairing ISIS with elastic-net (Enet) and 2 versions of adaptive elastic-net (adaptive elastic-net (AEnet) and multistep adaptive elastic-net (MSAEnet)) to efficiently improve feature selection and effect estimation in omics research. We subsequently used genome-wide human blood DNA methylation data from American Indian participants in the Strong Heart Study (n  = 2235 participants; measured in 1989-1991) to compare the performance (predictive accuracy, coefficient estimation, and computational efficiency) of ISIS-paired regularization methods with that of a bayesian shrinkage and traditional linear regression to identify an epigenomic multimarker of body mass index (BMI). ISIS-AEnet outperformed the other methods in prediction. In biological pathway enrichment analysis of genes annotated to BMI-related differentially methylated positions, ISIS-AEnet captured most of the enriched pathways in common for at least 2 of all the evaluated methods. ISIS-AEnet can favor biological discovery because it identifies the most robust biological pathways while achieving an optimal balance between bias and efficient feature selection. In the extended SIS R package, we also implemented ISIS paired with Cox and logistic regression for time-to-event and binary endpoints, respectively, and a bootstrap approach for the estimation of regression coefficients. [ABSTRACT FROM AUTHOR]

Massive multi-omics data are being used to research cancer pathogenesis at the molecular level as high-throughput sequencing technology advances. Many present approaches frequently fail to detect strongly coupled modules that are intimately associated with cancer. By combining two forms of omics data, a technique to active bio-module identification known as IdeMod is proposed, which employs gene expression and protein-protein interaction networks. IdeMod is a p-step random walk kernel regression model-based gene activity score algorithm that uses the Pareto optimum consensus (POC) method's dominance connections to generate a prioritised list of genes. IdeMod uses the SA GPROX simulated annealing technique to identify the PPI network's most linked and high-priority bio-modules. The techniques RegMod, LEAN, SigMod, ModFinder, and IdeMod were experimentally tested on real-world cervical and BRCA datasets. These findings show that the IdeMod algorithm may identify a densely linked module containing multiple genes that either promote or hinder tumour growth. The BRCA1 gene increases the likelihood of developing hereditary breast cancer associated with BRCA mutations. As a result, the IdeMod technique can be used in conjunction with other tools to detect bio-modules.

Proteins play a pivotal role in coordinating the functions of organisms, essentially governing their traits, as the dynamic arrangement of diverse amino acids leads to a multitude of folded configurations within peptide chains. Despite dynamic changes in amino acid composition of an individual protein (referred to as AAP) and great variance in protein expression levels under different conditions, our study, utilizing transcriptomics data from four model organisms uncovers surprising stability in the overall amino acid composition of the total cellular proteins (referred to as AACell). Although this value may vary between different species, we observed no significant differences among distinct strains of the same species. This indicates that organisms enforce system-level constraints to maintain a consistent AACell, even amid fluctuations in AAP and protein expression. Further exploration of this phenomenon promises insights into the intricate mechanisms orchestrating cellular protein expression and adaptation to varying environmental challenges.

Abstract Background Major advances in sequencing technologies and the sharing of data and metadata in science have resulted in a wealth of publicly available datasets. However, working with and especially curating public omics datasets remains challenging despite these efforts. While a growing number of initiatives aim to re-use previous results, these present limitations that often lead to the need for further in-house curation and processing. Results Here, we present the Omics Dataset Curation Toolkit (OMD Curation Toolkit), a python3 package designed to accompany and guide the researcher during the curation process of metadata and fastq files of public omics datasets. This workflow provides a standardized framework with multiple capabilities (collection, control check, treatment and integration) to facilitate the arduous task of curating public sequencing data projects. While centered on the European Nucleotide Archive (ENA), the majority of the provided tools are generic and can be used to curate datasets from different sources. Conclusions Thus, it offers valuable tools for the in-house curation previously needed to re-use public omics data. Due to its workflow structure and capabilities, it can be easily used and benefit investigators in developing novel omics meta-analyses based on sequencing data.

Biological networks are often used to represent complex biological systems, which can contain several types of entities. Analysis and visualization of such networks is supported by the Cytoscape software tool and its many apps. While earlier versions of stringApp focused on providing intraspecies protein-protein interactions from the STRING database, the new stringApp 2.0 greatly improves the support for heterogeneous networks. Here, we highlight new functionality that makes it possible to create networks that contain proteins and interactions from STRING as well as other biological entities and associations from other sources. We exemplify this by complementing a published SARS-CoV-2 interactome with interactions from STRING. We have also extended stringApp with new data and query functionality for protein-protein interactions between eukaryotic parasites and their hosts. We show how this can be used to retrieve and visualize a cross-species network for a malaria parasite, its host, and its vector. Finally, the latest stringApp version has an improved user interface, allows retrieval of both functional associations and physical interactions, and supports group-wise enrichment analysis of different parts of a network to aid biological interpretation. stringApp is freely available at https://apps.cytoscape.org/apps/stringapp.

Since gene regulation is a complex process in which multiple genes act simultaneously, accurately inferring gene regulatory networks (GRNs) is a long-standing challenge in systems biology. Although graph neural networks can formally describe intricate gene expression mechanisms, current GRN inference methods based on graph learning regard only transcription factor (TF)–target gene interactions as pairwise relationships, and cannot model the many-to-many high-order regulatory patterns that prevail among genes. Moreover, these methods often rely on limited prior regulatory knowledge, ignoring the structural information of GRNs in gene expression profiles. Therefore, we propose a multi-view hierarchical hypergraphs GRN (MHHGRN) inference model. Specifically, multiple heterogeneous biological information is integrated to construct multi-view hierarchical hypergraphs of TFs and target genes, using hypergraph convolution networks to model higher order complex regulatory relationships. Meanwhile, the coupled information diffusion mechanism and the cross-domain messaging mechanism facilitate the information sharing between genes to optimise gene embedding representations. Finally, a unique channel attention mechanism is used to adaptively learn feature representations from multiple views for GRN inference. Experimental results show that MHHGRN achieves better results than the baseline methods on the E. coli and S. cerevisiae benchmark datasets of the DREAM5 challenge, and it has excellent cross-species generalization, achieving comparable or better performance on scRNA-seq datasets from five mouse and two human cell lines. [ABSTRACT FROM AUTHOR]

We present several algorithms designed to learn a pattern of correspondence between 2 data sets in situations where it is desirable to match elements that exhibit a relationship belonging to a known parametric model. In the motivating case study, the challenge is to better understand micro-RNA regulation in the striatum of Huntington's disease model mice. The algorithms unfold in 2 stages. First, an optimal transport plan P and an optimal affine transformation are learned, using the Sinkhorn–Knopp algorithm and a mini-batch gradient descent. Second, P is exploited to derive either several co-clusters or several sets of matched elements. A simulation study illustrates how the algorithms work and perform. The real data application further illustrates their applicability and interest. [ABSTRACT FROM AUTHOR]

Recent technical advancements enable omics-based biological study of molecules with very high throughput and low cost, such as genomic, proteomic, and microbionics’. To overcome this drawback, Omics Data Classification using Constitutive Artificial Neural Network Optimized with Single Candidate Optimizer (ODC-ZOA-CANN-SCO) is proposed in this manuscript. The input data is pre-processing by using Adaptive variational Bayesian filtering (AVBF) to replace missing values. The pre-processing data is fed to Zebra Optimization Algorithm (ZOA) for dimensionality reduction. Then, the Constitutive Artificial Neural Network (CANN) is employed to classify omics data. The weight parameter is optimized by Single Candidate Optimizer (SCO). The proposed ODC-ZOA-CANN-SCO method attains 25.36%, 21.04%, 22.18%, 26.90%, and 28.12% higher accuracy when analysed to the existing methods like multi-omics data integration utilizing adaptive graph learning and attention mode for patient categorization with biomarker identification (MOD-AGL-AM-PABI), deep learning method depending upon multi-omics data integration to create risk stratification prediction mode for skin cutaneous melanoma (DL-MODI-RSP-SCM), Deep belief network-base model for identifying Alzheimer’s disease utilizing multi-omics data (DDN-DAD-MOD), hybrid cancer prediction depending upon multi-omics data and reinforcement learning state action reward state action (HCP-MOD-RL-SARSA), machine learning basis method under omics data including biological knowledge database for cancer clinical endpoint prediction (ML-ODBKD-CCEP) methods, respectively. [ABSTRACT FROM AUTHOR]

Background: Major advances in sequencing technologies and the sharing of data and metadata in science have resulted in a wealth of publicly available datasets. However, working with and especially curating public omics datasets remains challenging despite these efforts. While a growing number of initiatives aim to re-use previous results, these present limitations that often lead to the need for further in-house curation and processing. Results: Here, we present the Omics Dataset Curation Toolkit (OMD Curation Toolkit), a python3 package designed to accompany and guide the researcher during the curation process of metadata and fastq files of public omics datasets. This workflow provides a standardized framework with multiple capabilities (collection, control check, treatment and integration) to facilitate the arduous task of curating public sequencing data projects. While centered on the European Nucleotide Archive (ENA), the majority of the provided tools are generic and can be used to curate datasets from different sources. Conclusions: Thus, it offers valuable tools for the in-house curation previously needed to re-use public omics data. Due to its workflow structure and capabilities, it can be easily used and benefit investigators in developing novel omics meta-analyses based on sequencing data. [ABSTRACT FROM AUTHOR]

Enrichment analysis contextualizes biological features in pathways to facilitate a systematic understanding of high-dimensional data and is widely used in biomedical research. The emerging reporter score-based analysis (RSA) method shows more promising sensitivity, as it relies on P -values instead of raw values of features. However, RSA cannot be directly applied to multi-group and longitudinal experimental designs and is often misused due to the lack of a proper tool. Here, we propose the Generalized Reporter Score-based Analysis (GRSA) method for multi-group and longitudinal omics data. A comparison with other popular enrichment analysis methods demonstrated that GRSA had increased sensitivity across multiple benchmark datasets. We applied GRSA to microbiome, transcriptome and metabolome data and discovered new biological insights in omics studies. Finally, we demonstrated the application of GRSA beyond functional enrichment using a taxonomy database. We implemented GRSA in an R package, ReporterScore, integrating with a powerful visualization module and updatable pathway databases, which is available on the Comprehensive R Archive Network (https://cran.r-project.org/web/packages/ReporterScore). We believe that the ReporterScore package will be a valuable asset for broad biomedical research fields. [ABSTRACT FROM AUTHOR]

Tumor mutational burden (TMB) is a significant predictive biomarker for selecting patients that may benefit from immune checkpoint inhibitor therapy. Whole exome sequencing is a common method for measuring TMB; however, its clinical application is limited by the high cost and time-consuming wet-laboratory experiments and bioinformatics analysis. To address this challenge, we downloaded multimodal data of 326 gastric cancer patients from The Cancer Genome Atlas, including histopathological images, clinical data and various molecular data. Using these data, we conducted a comprehensive analysis to investigate the relationship between TMB, clinical factors, gene expression and image features extracted from hematoxylin and eosin images. We further explored the feasibility of predicting TMB levels, i.e. high and low TMB, by utilizing a residual network (Resnet)-based deep learning algorithm for histopathological image analysis. Moreover, we developed a multimodal fusion deep learning model that combines histopathological images with omics data to predict TMB levels. We evaluated the performance of our models against various state-of-the-art methods using different TMB thresholds and obtained promising results. Specifically, our histopathological image analysis model achieved an area under curve (AUC) of 0.749. Notably, the multimodal fusion model significantly outperformed the model that relied only on histopathological images, with the highest AUC of 0.971. Our findings suggest that histopathological images could be used with reasonable accuracy to predict TMB levels in gastric cancer patients, while multimodal deep learning could achieve even higher levels of accuracy. This study sheds new light on predicting TMB in gastric cancer patients. [ABSTRACT FROM AUTHOR]

Lung cancer has been the most common and the leading cause of cancer deaths globally. Besides clinicopathological observations and traditional molecular tests, the advent of robust and scalable techniques for nucleic acid analysis has revolutionized biological research and medicinal practice in lung cancer treatment. In response to the demands for minimally invasive procedures and technology development over the past decade, many types of multi-omics data at various genome levels have been generated. As omics data grow, artificial intelligence models, particularly deep learning, are prominent in developing more rapid and effective methods to potentially improve lung cancer patient diagnosis, prognosis and treatment strategy. This decade has seen genome-based deep learning models thriving in various lung cancer tasks, including cancer prediction, subtype classification, prognosis estimation, cancer molecular signatures identification, treatment response prediction and biomarker development. In this study, we summarized available data sources for deep-learning-based lung cancer mining and provided an update on recent deep learning models in lung cancer genomics. Subsequently, we reviewed the current issues and discussed future research directions of deep-learning-based lung cancer genomics research. [ABSTRACT FROM AUTHOR]

Heatmaps are preferred visualization modes for biologists to display high-dimensional information from high-throughput omics data. Many software including website services and R packages are available to generate various types of customized heatmaps. Here, we describe oppHeatmap (omics pilot platform of heatmap), a new tool constructed to render different kinds of heatmaps through MATLAB. oppHeatmap is available for plotting ordinary heatmaps, hierarchical clustering, TreeMaps, microplates graph, sample correlation (full heatmap and upper and lower triangle parts), gene correlation (between columns or tables), and polar heatmaps. oppHeatmap can support the modification of borders, fonts, and colors to customize the final plots. oppHeatmap can not only read data from Microsoft Excel to generate specific heatmaps but also make Excel heatmaps by coloring each cell in Excel. The graphs can be stored in SVG (supported vector graph) format and modified by other SVG recognition software. oppHeatmap is designed by MATLAB AppDesigner with GUI (graphical user interface) operation. The program for oppHeatmap was available at https://github.com/HangZhouSheep/oppHeatmap.are diagramed by All kinds of heatmaps oppHeatmap. The main function of oppHeatmap is to enable visualization of two types of heatmaps and a total of 11 graphs. The first type is a heatmap with a polar or rectangular coordinate system, including ordinary heatmap, microplates graph, polar heatmap, and Excel heatmap. The last one involves writing the heatmap in Excel and others in MATLAB. The second type is with rearranged rows and columns, which includes hierarchical clustering, TreeMaps, and sample/gene correlation between columns or rows. All plots support row standardization for better color contrast. Eleven base functions implement heatmap plotting in the command line environment of MATLAB. GUI designed by AppDesigner supports the interactive construction of heatmaps. [ABSTRACT FROM AUTHOR]

With the advent of high-throughput technologies, the field of omics has made significant strides in characterizing biological systems at various levels of complexity. Transcriptomics, proteomics, and metabolomics are the three most widely used omics technologies, each providing unique insights into different layers of a biological system. However, analyzing each omics data set separately may not provide a comprehensive understanding of the subject under study. Therefore, integrating multi-omics data has become increasingly important in bioinformatics research. In this article, we review strategies for integrating transcriptomics, proteomics, and metabolomics data, including co-expression analysis, metabolite–gene networks, constraint-based models, pathway enrichment analysis, and interactome analysis. We discuss combined omics integration approaches, correlation-based strategies, and machine learning techniques that utilize one or more types of omics data. By presenting these methods, we aim to provide researchers with a better understanding of how to integrate omics data to gain a more comprehensive view of a biological system, facilitating the identification of complex patterns and interactions that might be missed by single-omics analyses.

The article is a response to a letter discussing the effectiveness of a web application called MyPROSLE in classifying patients with lupus nephritis. The authors clarify that MyPROSLE is meant to provide additional information for clinical decisions, not replace standard diagnostic procedures. They address concerns raised in the letter and provide detailed explanations and analysis of MyPROSLE's performance. The authors also discuss the impact of incorporating healthy samples in the analysis and highlight the need for considering multiple performance metrics. They emphasize that MyPROSLE should only be used for research purposes and provide data availability and funding information. [Extracted from the article]

The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large‐scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields—Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence‐aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy—are discussed. [ABSTRACT FROM AUTHOR]

Abstract Modern omics technologies can generate massive amounts of biomedical data, providing unprecedented opportunities for individualized precision medicine. However, traditional statistical methods cannot effectively process and utilize such big data. To meet this new challenge, machine learning algorithms have been developed and applied rapidly in recent years, which are capable of reducing dimensionality, extracting features, organizing data and forming automatable data-driven clinical decision systems. Data-driven clinical decision-making have promising applications in precision medicine and has been studied in digestive diseases, including early diagnosis and screening, molecular typing, staging and stratification of digestive malignancies, as well as precise diagnosis of Crohn's disease, auxiliary diagnosis of imaging and endoscopy, differential diagnosis of cystic lesions, etiology discrimination of acute abdominal pain, stratification of upper gastrointestinal bleeding (UGIB), and real-time diagnosis of esophageal motility function, showing good application prospects. Herein, we reviewed the recent progress of data-driven clinical decision making in precision diagnosis of digestive diseases and discussed the limitations of data-driven decision making after a brief introduction of methods for data-driven decision making.

Abstract Background Cancer subtype identification is important for the early diagnosis of cancer and the provision of adequate treatment. Prior to identifying the subtype of cancer in a patient, feature selection is also crucial for reducing the dimensionality of the data by detecting genes that contain important information about the cancer subtype. Numerous cancer subtyping methods have been developed, and their performance has been compared. However, combinations of feature selection and subtype identification methods have rarely been considered. This study aimed to identify the best combination of variable selection and subtype identification methods in single omics data analysis. Results Combinations of six filter-based methods and six unsupervised subtype identification methods were investigated using The Cancer Genome Atlas (TCGA) datasets for four cancers. The number of features selected varied, and several evaluation metrics were used. Although no single combination was found to have a distinctively good performance, Consensus Clustering (CC) and Neighborhood-Based Multi-omics Clustering (NEMO) used with variance-based feature selection had a tendency to show lower p-values, and nonnegative matrix factorization (NMF) stably showed good performance in many cases unless the Dip test was used for feature selection. In terms of accuracy, the combination of NMF and similarity network fusion (SNF) with Monte Carlo Feature Selection (MCFS) and Minimum-Redundancy Maximum Relevance (mRMR) showed good overall performance. NMF always showed among the worst performances without feature selection in all datasets, but performed much better when used with various feature selection methods. iClusterBayes (ICB) had decent performance when used without feature selection. Conclusions Rather than a single method clearly emerging as optimal, the best methodology was different depending on the data used, the number of features selected, and the evaluation method. A guideline for choosing the best combination method under various situations is provided.

Abstract The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large‐scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields—Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence‐aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy—are discussed.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Metabolic pathway prediction and reconstruction play crucial roles in solving fundamental and applied biomedical problems. In the case of fundamental research, annotation of metabolic pathways allows one to study human health in normal, stressed, and diseased conditions. In applied research, it allows one to identify novel drugs and drug targets and to design mimetics (biomolecules with tailored properties), as well as contributes to the development of such disciplines as toxicology and nutrigenomics. It is important to understand the role of a metabolite as a substrate (the product or intermediate participant of an enzymatic reaction) in cellular signaling and phenotype implementation according to the pivotal paradigm of biology: "one gene–one protein–one function (one trait)". Due to the development of omics technologies, a vast body of data on the metabolome composition of living organisms has been accumulated over the past two decades. Systematization of the information on the roles played by metabolites in implementation of cellular signaling, as well as metabolic pathway reconstruction and refinement, have necessitated the development of bioinformatic tools for performing large-scale omics data mining. This paper reviews web-accessible databases relevant to metabolic pathways and considers the applications of the three types of bioinformatics methods for constructing metabolic networks (graphs for substrate–enzyme–product transformation; stoichiometric analysis of substrate–product transformation; and product retrosynthesis). It describes, step by step, a generalized algorithm for constructing biological pathway maps which explains to the researcher the workflow implemented in available bioinformatics tools and can be used to create new tools in projects requiring pathway reconstruction. [ABSTRACT FROM AUTHOR]

The ability to determine cell states is essential for understanding cell fate decisions. Recent methods, such as pseudotime and RNA velocity, allow mapping cell transcriptome states, yet thorough understanding and purposeful manipulation of cell state transitions and fate decisions are lacking. A cell state transition assessment and regulation (cSTAR) approach determines a core regulatory network that controls cell-wide network and 'computes' cell fate decision. Perturbation data are crucial to infer causal connections of core networks. Based on precise reconstruction of core networks, cSTAR can steer cell fate decisions that can help to reverse pathological cell states. Acquisition of omics data advances at a formidable pace. Yet, our ability to utilize these data to control cell phenotypes and design interventions that reverse pathological states lags behind. Here, we posit that cell states are determined by core networks that control cell-wide networks. To steer cell fate decisions, core networks connecting genotype to phenotype must be reconstructed and understood. A recent method, cell state transition assessment and regulation (cSTAR), applies perturbation biology to quantify causal connections and mechanistically models how core networks influence cell phenotypes. cSTAR models are akin to digital cell twins enabling us to purposefully convert pathological states back to physiologically normal states. While this capability has a range of applications, here we discuss reverting oncogenic transformation. [ABSTRACT FROM AUTHOR]

Emerging in the realm of bioinformatics, plant bioinformatics integrates computational and statistical methods to study plant genomes, transcriptomes, and proteomes. With the introduction of high-throughput sequencing technologies and other omics data, the demand for automated methods to analyze and interpret these data has increased. We propose a novel explainable gradient-based approach EG-CNN model for both omics data and hyperspectral images to predict the type of attack on plants in this study. We gathered gene expression, metabolite, and hyperspectral image data from plants afflicted with four prevalent diseases: powdery mildew, rust, leaf spot, and blight. Our proposed EG-CNN model employs a combination of these omics data to learn crucial plant disease detection characteristics. We trained our model with multiple hyperparameters, such as the learning rate, number of hidden layers, and dropout rate, and attained a test set accuracy of 95.5%. We also conducted a sensitivity analysis to determine the model’s resistance to hyperparameter variations. Our analysis revealed that our model exhibited a notable degree of resilience in the face of these variations, resulting in only marginal changes in performance. Furthermore, we conducted a comparative examination of the time efficiency of our EG-CNN model in relation to baseline models, including SVM, Random Forest, and Logistic Regression. Although our model necessitates additional time for training and validation due to its intricate architecture, it demonstrates a faster testing time per sample, offering potential advantages in real-world scenarios where speed is paramount. To gain insights into the internal representations of our EG-CNN model, we employed saliency maps for a qualitative analysis. This visualization approach allowed us to ascertain that our model effectively captures crucial aspects of plant disease, encompassing alterations in gene expression, metabolite levels, and spectral discrepancies within plant tissues. Leveraging omics data and hyperspectral images, this study underscores the potential of deep learning methods in the realm of plant disease detection. The proposed EG-CNN model exhibited impressive accuracy and displayed a remarkable degree of insensitivity to hyperparameter variations, which holds promise for future plant bioinformatics applications. [ABSTRACT FROM AUTHOR]

The joint estimation of multiple graphical models from high-dimensional data has been studied in the statistics and machine learning literature, owing to its importance in diverse fields including molecular biology, neuroscience, and the social sciences. We propose a Bayesian approach that decomposes the model parameters across multiple graphical models into shared components across subsets of models and edges, and idiosyncratic components. This approach leverages a novel multivariate prior distribution, coupled with a jointly convex regression-based pseudo-likelihood that enables fast computation using a robust and efficient Gibbs sampling scheme. We establish strong posterior consistency for model selection under high-dimensional scaling, with the number of variables growing exponentially as a function of the sample size. Lastly, we demonstrate the efficiency of the proposed approach in borrowing strength across models to identify shared edges using both synthetic and real data. [ABSTRACT FROM AUTHOR]

Abstract Background In high-dimensional data (HDD) settings, the number of variables associated with each observation is very large. Prominent examples of HDD in biomedical research include omics data with a large number of variables such as many measurements across the genome, proteome, or metabolome, as well as electronic health records data that have large numbers of variables recorded for each patient. The statistical analysis of such data requires knowledge and experience, sometimes of complex methods adapted to the respective research questions. Methods Advances in statistical methodology and machine learning methods offer new opportunities for innovative analyses of HDD, but at the same time require a deeper understanding of some fundamental statistical concepts. Topic group TG9 “High-dimensional data” of the STRATOS (STRengthening Analytical Thinking for Observational Studies) initiative provides guidance for the analysis of observational studies, addressing particular statistical challenges and opportunities for the analysis of studies involving HDD. In this overview, we discuss key aspects of HDD analysis to provide a gentle introduction for non-statisticians and for classically trained statisticians with little experience specific to HDD. Results The paper is organized with respect to subtopics that are most relevant for the analysis of HDD, in particular initial data analysis, exploratory data analysis, multiple testing, and prediction. For each subtopic, main analytical goals in HDD settings are outlined. For each of these goals, basic explanations for some commonly used analysis methods are provided. Situations are identified where traditional statistical methods cannot, or should not, be used in the HDD setting, or where adequate analytic tools are still lacking. Many key references are provided. Conclusions This review aims to provide a solid statistical foundation for researchers, including statisticians and non-statisticians, who are new to research with HDD or simply want to better evaluate and understand the results of HDD analyses.

Emerging in the realm of bioinformatics, plant bioinformatics integrates computational and statistical methods to study plant genomes, transcriptomes, and proteomes. With the introduction of high-throughput sequencing technologies and other omics data, the demand for automated methods to analyze and interpret these data has increased. We propose a novel explainable gradient-based approach EG-CNN model for both omics data and hyperspectral images to predict the type of attack on plants in this study. We gathered gene expression, metabolite, and hyperspectral image data from plants afflicted with four prevalent diseases: powdery mildew, rust, leaf spot, and blight. Our proposed EG-CNN model employs a combination of these omics data to learn crucial plant disease detection characteristics. We trained our model with multiple hyperparameters, such as the learning rate, number of hidden layers, and dropout rate, and attained a test set accuracy of 95.5%. We also conducted a sensitivity analysis to determine the model’s resistance to hyperparameter variations. Our analysis revealed that our model exhibited a notable degree of resilience in the face of these variations, resulting in only marginal changes in performance. Furthermore, we conducted a comparative examination of the time efficiency of our EG-CNN model in relation to baseline models, including SVM, Random Forest, and Logistic Regression. Although our model necessitates additional time for training and validation due to its intricate architecture, it demonstrates a faster testing time per sample, offering potential advantages in real-world scenarios where speed is paramount. To gain insights into the internal representations of our EG-CNN model, we employed saliency maps for a qualitative analysis. This visualization approach allowed us to ascertain that our model effectively captures crucial aspects of plant disease, encompassing alterations in gene expression, metabolite levels, and spectral discrepancies within plant tissues. Leveraging omics data and hyperspectral images, this study underscores the potential of deep learning methods in the realm of plant disease detection. The proposed EG-CNN model exhibited impressive accuracy and displayed a remarkable degree of insensitivity to hyperparameter variations, which holds promise for future plant bioinformatics applications.

Modern omics technologies can generate massive amounts of biomedical data, providing unprecedented opportunities for individualized precision medicine. However, traditional statistical methods cannot effectively process and utilize such big data. To meet this new challenge, machine learning algorithms have been developed and applied rapidly in recent years, which are capable of reducing dimensionality, extracting features, organizing data and forming automatable data-driven clinical decision systems. Data-driven clinical decision-making have promising applications in precision medicine and has been studied in digestive diseases, including early diagnosis and screening, molecular typing, staging and stratification of digestive malignancies, as well as precise diagnosis of Crohn's disease, auxiliary diagnosis of imaging and endoscopy, differential diagnosis of cystic lesions, etiology discrimination of acute abdominal pain, stratification of upper gastrointestinal bleeding (UGIB), and real-time diagnosis of esophageal motility function, showing good application prospects. Herein, we reviewed the recent progress of data-driven clinical decision making in precision diagnosis of digestive diseases and discussed the limitations of data-driven decision making after a brief introduction of methods for data-driven decision making. [ABSTRACT FROM AUTHOR]

Omics data from clinical samples are the predominant source of target discovery and drug development. Typically, hundreds or thousands of differentially expressed genes or proteins can be identified from omics data. This scale of possibilities is overwhelming for target discovery and validation using biochemical or cellular experiments. Most of these proteins and genes have no corresponding drugs or even active compounds. Moreover, a proportion of them may have been previously reported as being relevant to the disease of interest. To facilitate translational drug discovery from omics data, we have developed a new classification tool named O mics and T ext driven T ranslational M edicine (OTTM). This tool can markedly narrow the range of proteins or genes that merit further validation via drug availability assessment and literature mining. For the 4489 candidate proteins identified in our previous proteomics study, OTTM recommended 40 FDA-approved or clinical trial drugs. Of these, 15 are available commercially and were tested on hepatocellular carcinoma Hep-G2 cells. Two drugs—tafenoquine succinate (an FDA-approved antimalarial drug targeting CYC1) and branaplam (a Phase 3 clinical drug targeting SMN1 for the treatment of spinal muscular atrophy)—showed potent inhibitory activity against Hep-G2 cell viability, suggesting that CYC1 and SMN1 may be potential therapeutic target proteins for hepatocellular carcinoma. In summary, OTTM is an efficient classification tool that can accelerate the discovery of effective drugs and targets using thousands of candidate proteins identified from omics data. The online and local versions of OTTM are available at http://otter-simm.com/ottm.html. [ABSTRACT FROM AUTHOR]

The advancement of mass spectrometry technologies has revolutionised plant metabolomics research by enabling the acquisition of raw metabolomics data. However, the identification, analysis, and visualisation of these data require specialised tools. Existing solutions lack a dedicated plant-specific metabolite database and pose usability challenges. To address these limitations, we developed PlantMetSuite, a web-based tool for comprehensive metabolomics analysis and visualisation. PlantMetSuite encompasses interactive bioinformatics tools and databases specifically tailored to plant metabolomics data, facilitating upstream-to-downstream analysis in metabolomics and supporting integrative multi-omics investigations. PlantMetSuite can be accessed directly through a user's browser without the need for installation or programming skills. The tool is freely available and will undergo regular updates and expansions to incorporate additional libraries and newly published metabolomics analysis methods. The tool's significance lies in empowering researchers with an accessible and customisable platform for unlocking plant metabolomics insights. [ABSTRACT FROM AUTHOR]

Historically, the chief focus of lymph node metastasis research has been molecular and clinical studies of a few essential pathways and genes. Recent years have seen a rapid accumulation of massive omics and imaging data catalyzed by the rapid development of advanced technologies. This rapid increase in data has driven improvements in the accuracy of diagnosis of lymph node metastasis, and its analysis further demands new methods and the opportunity to provide novel insights for basic research. In fact, the combination of omics data, imaging data, clinical medicine, and diagnostic methods has led to notable advances in our basic understanding and transformation of lymph node metastases in rectal cancer. Higher levels of integration will require a concerted effort among data scientists and clinicians. Herein, we review the current state and future challenges to advance the diagnosis of lymph node metastases in rectal cancer. [ABSTRACT FROM AUTHOR]

Background: Cancer subtype identification is important for the early diagnosis of cancer and the provision of adequate treatment. Prior to identifying the subtype of cancer in a patient, feature selection is also crucial for reducing the dimensionality of the data by detecting genes that contain important information about the cancer subtype. Numerous cancer subtyping methods have been developed, and their performance has been compared. However, combinations of feature selection and subtype identification methods have rarely been considered. This study aimed to identify the best combination of variable selection and subtype identification methods in single omics data analysis. Results: Combinations of six filter-based methods and six unsupervised subtype identification methods were investigated using The Cancer Genome Atlas (TCGA) datasets for four cancers. The number of features selected varied, and several evaluation metrics were used. Although no single combination was found to have a distinctively good performance, Consensus Clustering (CC) and Neighborhood-Based Multi-omics Clustering (NEMO) used with variance-based feature selection had a tendency to show lower p-values, and nonnegative matrix factorization (NMF) stably showed good performance in many cases unless the Dip test was used for feature selection. In terms of accuracy, the combination of NMF and similarity network fusion (SNF) with Monte Carlo Feature Selection (MCFS) and Minimum-Redundancy Maximum Relevance (mRMR) showed good overall performance. NMF always showed among the worst performances without feature selection in all datasets, but performed much better when used with various feature selection methods. iClusterBayes (ICB) had decent performance when used without feature selection. Conclusions: Rather than a single method clearly emerging as optimal, the best methodology was different depending on the data used, the number of features selected, and the evaluation method. A guideline for choosing the best combination method under various situations is provided. [ABSTRACT FROM AUTHOR]

Cytoscape is an open-source software used to analyze and visualize biological networks. In addition to being able to import networks from a variety of sources, Cytoscape allows users to import tabular node data and visualize it onto networks. Unfortunately, such data tables can only contain one row of data per node, whereas omics data often have multiple rows for the same gene or protein, representing different post-translational modification sites, peptides, splice isoforms, or conditions. Here, we present a new app, Omics Visualizer, that allows users to import data tables with several rows referring to the same node, connect them to one or more networks, and visualize the connected data onto networks. Omics Visualizer uses the Cytoscape enhancedGraphics app to show the data either in the nodes (pie visualization) or around the nodes (donut visualization), where the colors of the slices represent the imported values. If the user does not provide a network, the app can retrieve one from the STRING database using the Cytoscape stringApp. The Omics Visualizer app is freely available at https://apps.cytoscape.org/apps/omicsvisualizer.

The accurate prediction of phenotypes in microorganisms is a main challenge for systems biology. Genome-scale models (GEMs) are a widely used mathematical formalism for predicting metabolic fluxes using constraint-based modeling methods such as flux balance analysis (FBA). However, they require prior knowledge of the metabolic network of an organism and appropriate objective functions, often hampering the prediction of metabolic fluxes under different conditions. Moreover, the integration of omics data to improve the accuracy of phenotype predictions in different physiological states is still in its infancy. Here, we present a novel approach for predicting fluxes under various conditions. We explore the use of supervised machine learning (ML) models using transcriptomics and/or proteomics data and compare their performance against the standard parsimonious FBA (pFBA) approach using case studies of Escherichia coli organism as an example. Our results show that the proposed omics-based ML approach is promising to predict both internal and external metabolic fluxes with smaller prediction errors in comparison to the pFBA approach. The code, data, and detailed results are available at the project's repository [1].

Pulmonary fibrosing diseases are in the very epicenter of biomedical research both due to their increasing prevalence and their association with SARS-CoV-2 infections. Research of idiopathic pulmonary fibrosis, the most lethal among the interstitial lung diseases, is in need for new biomarkers and potential disease targets, a goal that could be accelerated using machine learning techniques. In this study, we have used Shapley values to explain the decisions made by an ensemble learning model trained to classify samples to an either pulmonary fibrosis or steady state based on the expression values of deregulated genes. This process resulted in a full and a laconic set of features capable of separating phenotypes to an at least equal degree as previously published marker sets. Indicatively, a maximum increase of 6% in specificity and 5% in Mathew’s correlation coefficient was achieved. Evaluation with an additional independent dataset showed our feature set having a greater generalization potential than the rest. Ultimately, the proposed gene lists are expected not only to serve as new sets of diagnostic marker elements, but also as a target pool for future research initiatives.

Penalized Cox regression can efficiently be used for the determination of biomarkers in high-dimensional genomic data related to disease prognosis. However, results of Penalized Cox regression is influenced by the heterogeneity of the samples who have different dependent structure between survival time and covariates from most individuals. These observations are called influential observations or outliers. A robust penalized Cox model (Reweighted Elastic Net-type maximum trimmed partial likelihood estimator, Rwt MTPL-EN) is proposed to improve the prediction accuracy and identify influential observations. A new algorithm AR-Cstep to solve Rwt MTPL-EN model is also proposed. This method has been validated by simulation study and application to glioma microarray expression data. When there were no outliers, the results of Rwt MTPL-EN were close to the Elastic Net (EN). When outliers existed, the results of EN were impacted by outliers. And whenever the censored rate was large or low, the robust Rwt MTPL-EN performed better than EN. and could resist the outliers in both predictors and response. In terms of outliers detection accuracy, Rwt MTPL-EN was much higher than EN. The outliers who "lived too long" made EN perform worse, but were accurately detected by Rwt MTPL-EN. Through the analysis of glioma gene expression data, most of the outliers identified by EN were those "failed too early", but most of them were not obvious outliers according to risk estimated from omics data or clinical variables. Most of the outliers identified by Rwt MTPL-EN were those who "lived too long", and most of them were obvious outliers according to risk estimated from omics data or clinical variables. Rwt MTPL-EN can be adopted to detect influential observations in high-dimensional survival data.