A machine learning heuristic to identify biologically relevant and minimal biomarker panels from omics data

Unleashing the power of generative AI in drug discovery

Artificial intelligence (AI) is revolutionizing drug discovery by enhancing precision, reducing timelines and costs, and enabling AI-driven computer-aided drug design. This review focuses on recent advancements in deep generative models (DGMs) for de novo drug design, exploring diverse algorithms and their profound impact. It critically analyses the challenges that are intricately interwoven into these technologies, proposing strategies to unlock their full potential. It features case studies of both successes and failures in advancing drugs to clinical trials with AI assistance. Last, it outlines a forward-looking plan for optimizing DGMs in de novo drug design, thereby fostering faster and more cost-effective drug development.

Blood-Based Biomarkers for Managing Workload in Athletes: Perspectives for Research on Emerging Biomarkers

At present, various blood-based biomarkers have found their applications in the field of sports medicine. This current opinion addresses biomarkers that warrant consideration in future research for monitoring the athlete training load. In this regard, we identified a variety of emerging load-sensitive biomarkers, e.g., cytokines (such as IL-6), chaperones (such as heat shock proteins) or enzymes (such as myeloperoxidase) that could improve future athlete load monitoring as they have shown meaningful increases in acute and chronic exercise settings. In some cases, they have even been linked to training status or performance characteristics. However, many of these markers have not been extensively studied and the cost and effort of measuring these parameters are still high, making them inconvenient for practitioners so far. We therefore outline strategies to improve knowledge of acute and chronic biomarker responses, including ideas for standardized study settings. In addition, we emphasize the need for methodological advances such as the development of minimally invasive point-of-care devices as well as statistical aspects related to the evaluation of these monitoring tools to make biomarkers suitable for regular load monitoring.

Artificial Intelligence and laboratory data in rheumatic diseases

Artificial intelligence (AI)-based medical technologies are rapidly evolving into actionable solutions for clinical practice. Machine learning (ML) algorithms can process increasing amounts of laboratory data such as gene expression immunophenotyping data and biomarkers. In recent years, the analysis of ML has become particularly useful for the study of complex chronic diseases, such as rheumatic diseases, heterogenous conditions with multiple triggers. Numerous studies have used ML to classify patients and improve diagnosis, to stratify the risk and determine disease subtypes, as well as to discover biomarkers and gene signatures. This review aims to provide examples of ML models for specific rheumatic diseases using laboratory data and some insights into relevant strengths and limitations. A better understanding and future application of these analytical strategies could facilitate the development of precision medicine for rheumatic patients.

The application of machine learning in early diagnosis of osteoarthritis: a narrative review

Osteoarthritis (OA) is the commonest musculoskeletal disease worldwide, with an increasing prevalence due to aging. It causes joint pain and disability, decreased quality of life, and a huge burden on healthcare services for society. However, the current main diagnostic methods are not suitable for early diagnosing patients of OA. The use of machine learning (ML) in OA diagnosis has increased dramatically in the past few years. Hence, in this review article, we describe the research progress in the application of ML in the early diagnosis of OA, discuss the current trends and limitations of ML approaches, and propose future research priorities to apply the tools in the field of OA. Accurate ML-based predictive models with imaging techniques that are sensitive to early changes in OA ahead of the emergence of clinical features are expected to address the current dilemma. The diagnostic ability of the fusion model that combines multidimensional information makes patient-specific early diagnosis and prognosis estimation of OA possible in the future.

Using AI-Based Evolutionary Algorithms to Elucidate Adult Brain Tumor (Glioma) Etiology Associated with IDH1 for Therapeutic Target Identification

Adult brain tumors (glioma) represent a cancer of unmet need where standard-of-care is non-curative; thus, new therapies are urgently needed. It is unclear whether isocitrate dehydrogenases (IDH1/2) when not mutated have any role in gliomagenesis or tumor growth. Nevertheless, IDH1 is overexpressed in glioblastoma (GBM), which could impact upon cellular metabolism and epigenetic reprogramming. This study characterizes IDH1 expression and associated genes and pathways. A novel biomarker discovery pipeline using artificial intelligence (evolutionary algorithms) was employed to analyze IDH-wildtype adult gliomas from the TCGA LGG-GBM cohort. Ninety genes whose expression correlated with IDH1 expression were identified from: (1) All gliomas, (2) primary GBM, and (3) recurrent GBM tumors. Genes were overrepresented in ubiquitin-mediated proteolysis, focal adhesion, mTOR signaling, and pyruvate metabolism pathways. Other non-enriched pathways included O-glycan biosynthesis, notch signaling, and signaling regulating stem cell pluripotency (PCGF3). Potential prognostic (TSPYL2, JAKMIP1, CIT, TMTC1) and two diagnostic (MINK1, PLEKHM3) biomarkers were downregulated in GBM. Their gene expression and methylation were negatively and positively correlated with IDH1 expression, respectively. Two diagnostic biomarkers (BZW1, RCF2) showed the opposite trend. Prognostic genes were not impacted by high frequencies of molecular alterations and only one (TMTC1) could be validated in another cohort. Genes with mechanistic links to IDH1 were involved in brain neuronal development, cell proliferation, cytokinesis, and O-mannosylation as well as tumor suppression and anaplerosis. Results highlight metabolic vulnerabilities and therapeutic targets for use in future clinical trials.

Transcriptional and post-transcriptional regulation of checkpoint genes on the tumour side of the immunological synapse

Cancer is a disease of the genome, therefore, its development has a clear Mendelian component, demonstrated by well-studied genes such as BRCA1 and BRCA2 in breast cancer risk. However, it is known that a single genetic variant is not enough for cancer to develop leading to the theory of multistage carcinogenesis. In many cases, it is a sequence of events, acquired somatic mutations, or simply polygenic components with strong epigenetic effects, such as in the case of brain tumours. The expression of many genes is the product of the complex interplay between several factors, including the organism’s genotype (in most cases Mendelian-inherited), genetic instability, epigenetic factors (non-Mendelian-inherited) as well as the immune response of the host, to name just a few. In recent years the importance of the immune system has been elevated, especially in the light of the immune checkpoint genes discovery and the subsequent development of their inhibitors. As the expression of these genes normally suppresses self-immunoreactivity, their expression by tumour cells prevents the elimination of the tumour by the immune system. These discoveries led to the rapid growth of the field of immuno-oncology that offers new possibilities of long-lasting and effective treatment options. Here we discuss the recent advances in the understanding of the key mechanisms controlling the expression of immune checkpoint genes in tumour cells.

Upregulation of Cyclin B2 (CCNB2) in breast cancer contributes to the development of lymphovascular invasion

Lymphovascular invasion (LVI) is a key step in breast cancer (BC) metastasis. Targeting the molecular drivers of LVI can improve BC patients' management. However, the underlying molecular mechanisms of LVI are complex and interconnected with various carcinogenesis pathways. This study aimed to identify the key regulatory gene associated with LVI and to investigate its mechanisms of action and prognostic significance. Artificial neural network (ANN) was applied to two large transcriptomic datasets of BC with well-characterised LVI status. Cyclin B2 (CCNB2) was identified in the top genes associated with LVI positivity. In vitro functional assays were carried out to assess the role of CCNB2 in tumour cell behaviour and their interactions with endothelial cells using a panel of BC cell lines. Large annotated BC cohorts were used to assess the clinical and prognostic role of CCNB2 at the transcriptomic and protein levels. Knockdown (KD) of CCNB2 mRNA reduced BC cell migration, inhibited proliferation, blocked the G2/M transition during the cell cycle and increased the number of apoptotic cells. Importantly, KD of CCNB2 reduced BC cell lines adherence and transmigration across endothelial cell lines. High CCNB2 protein expression was independently associated with LVI positivity in addition to other features of aggressive behaviour, including larger tumour size, higher histological grade, hormonal receptor-negativity, and HER2-positivity, and with shorter survival. We conclude that CCNB2 plays a crucial role in LVI development in BC, implying that CCNB2 could confer a promising therapeutic target to inhibit LVI and reduce metastatic events.

Identification of CNGB1 as a Predictor of Response to Neoadjuvant Chemotherapy in Muscle-Invasive Bladder Cancer

Simple Summary

Chemotherapy is recommended prior to surgical removal of the bladder for muscle-invasive bladder cancer patients. Despite a survival benefit, some patients do not respond and experience substantial toxicity and delay in surgery. Therefore, the identification of chemotherapy responders before initiating therapy would be a helpful clinical asset. To date, there are no reliable biomarkers routinely used in clinical practice that identify patients most likely to benefit from chemotherapy and their identification is urgently required for more precise delivery of care. To address this issue, we compared gene expression profiles of biopsy materials from 30 chemotherapy-responder and -non-responder patients. This analysis revealed a novel signature gene set and CNGB1 as a simpler proxy as a promising biomarker to predict chemoresponsiveness of muscle-invasive bladder cancer patients. Our findings require further validation in larger patient cohorts and in a clinical trial setting.

Abstract

Cisplatin-based neoadjuvant chemotherapy (NAC) is recommended prior to radical cystectomy for muscle-invasive bladder cancer (MIBC) patients. Despite a 5–10% survival benefit, some patients do not respond and experience substantial toxicity and delay in surgery. To date, there are no clinically approved biomarkers predictive of response to NAC and their identification is urgently required for more precise delivery of care. To address this issue, a multi-methods analysis approach of machine learning and differential gene expression analysis was undertaken on a cohort of 30 MIBC cases highly selected for an exquisitely strong response to NAC or marked resistance and/or progression (discovery cohort). RGIFE (ranked guided iterative feature elimination) machine learning algorithm, previously demonstrated to have the ability to select biomarkers with high predictive power, identified a 9-gene signature (CNGB1, GGH, HIST1H4F, IDO1, KIF5A, MRPL4, NCDN, PRRT3, SLC35B3) able to select responders from non-responders with 100% predictive accuracy. This novel signature correlated with overall survival in meta-analysis performed using published NAC treated-MIBC microarray data (validation cohort 1, n = 26, Log rank test, p = 0.02). Corroboration with differential gene expression analysis revealed cyclic nucleotide-gated channel, CNGB1, as the top ranked upregulated gene in non-responders to NAC. A higher CNGB1 immunostaining score was seen in non-responders in tissue microarray analysis of the discovery cohort (n = 30, p = 0.02). Kaplan-Meier analysis of a further cohort of MIBC patients (validation cohort 2, n = 99) demonstrated that a high level of CNGB1 expression associated with shorter cancer specific survival (p < 0.001). Finally, in vitro studies showed siRNA-mediated CNGB1 knockdown enhanced cisplatin sensitivity of MIBC cell lines, J82 and 253JB-V. Overall, these data reveal a novel signature gene set and CNGB1 as a simpler proxy as a promising biomarker to predict chemoresponsiveness of MIBC patients.

A review of risk prediction models in cardiovascular disease: conventional approach vs. artificial intelligent approach

Cardiovascular disease (CVD) is the leading cause of death worldwide and is a global health issue. Traditionally, statistical models are used commonly in the risk prediction and assessment of CVD. However, the adoption of artificial intelligent (AI) approach is rapidly taking hold in the current era of technology to evaluate patient risks and predict the outcome of CVD. In this review, we outline various conventional risk scores and prediction models and do a comparison with the AI approach. The strengths and limitations of both conventional and AI approaches are discussed. Besides that, biomarker discovery related to CVD are also elucidated as the biomarkers can be used in the risk stratification as well as early detection of the disease. Moreover, problems and challenges involved in current CVD studies are explored. Lastly, future prospects of CVD risk prediction and assessment in the multi-modality of big data integrative approaches are proposed.

Computational Strategies for the Identification of a Transcriptional Biomarker Panel to Sense Cellular Growth States in Bacillus subtilis

A goal of the biotechnology industry is to be able to recognise detrimental cellular states that may lead to suboptimal or anomalous growth in a bacterial population. Our current knowledge of how different environmental treatments modulate gene regulation and bring about physiology adaptations is limited, and hence it is difficult to determine the mechanisms that lead to their effects. Patterns of gene expression, revealed using technologies such as microarrays or RNA-seq, can provide useful biomarkers of different gene regulatory states indicative of a bacterium's physiological status. It is desirable to have only a few key genes as the biomarkers to reduce the costs of determining the transcriptional state by opening the way for methods such as quantitative RT-PCR and amplicon panels. In this paper, we used unsupervised machine learning to construct a transcriptional landscape model from condition-dependent transcriptome data, from which we have identified 10 clusters of samples with differentiated gene expression profiles and linked to different cellular growth states. Using an iterative feature elimination strategy, we identified a minimal panel of 10 biomarker genes that achieved 100% cross-validation accuracy in predicting the cluster assignment. Moreover, we designed and evaluated a variety of data processing strategies to ensure our methods were able to generate meaningful transcriptional landscape models, capturing relevant biological processes. Overall, the computational strategies introduced in this study facilitate the identification of a detailed set of relevant cellular growth states, and how to sense them using a reduced biomarker panel.

Classification, Categorization, and Algorithms for Articular Cartilage Defects

There is a critical unmet need in the clinical implementation of valid preventative and therapeutic strategies for patients with articular cartilage pathology based on the significant gap in understanding of the relationships between diagnostic data, disease progression, patient-related variables, and symptoms. In this article, the current state of classification and categorization for articular cartilage pathology is discussed with particular focus on machine learning methods and the authors propose a bedside-bench-bedside approach with highly quantitative techniques as a solution to these hurdles. Leveraging computational learning with available data toward articular cartilage pathology patient phenotyping holds promise for clinical research and will likely be an important tool to identify translational solutions into evidence-based clinical applications to benefit patients. Recommendations for successful implementation of these approaches include using standardized definitions of articular cartilage, to include characterization of depth, size, location, and number; using measurements that minimize subjectivity or validated patient-reported outcome measures; considering not just the articular cartilage pathology but the whole joint, and the patient perception and perspective. Application of this approach through a multistep process by a multidisciplinary team of clinicians and scientists holds promise for validating disease mechanism-based phenotypes toward clinically relevant understanding of articular cartilage pathology for evidence-based application to orthopaedic practice.

Identification of the most important features of knee osteoarthritis structural progressors using machine learning methods

Objectives:

The aim was to identify the most important features of structural knee osteoarthritis (OA) progressors and classification using machine learning methods.

Methods:

Participants, features and outcomes were from the Osteoarthritis Initiative. Features were from baseline (1107), including articular knee tissues (135) assessed by quantitative magnetic resonance imaging (MRI). OA progressors were ascertained by four outcomes: cartilage volume loss in medial plateau at 48 and 96 months (Prop_CV_48M, 96M), Kellgren–Lawrence (KL) grade ⩾ 2 and medial joint space narrowing (JSN) ⩾ 1 at 48 months. Six feature selection models were used to identify the common features in each outcome. Six classification methods were applied to measure the accuracy of the selected features in classifying the subjects into progressors and non-progressors. Classification of the best features was done using an automatic machine learning interface and the area under the curve (AUC). To prioritize the top five features, sparse partial least square (sPLS) method was used.

Results:

For the classification of the best common features in each outcome, Multi-Layer Perceptron (MLP) achieved the highest AUC in Prop_CV_96M, KL and JSN (0.80, 0.88, 0.95), and Gradient Boosting Machine for Prop_CV_48M (0.70). sPLS showed the baseline top five features to predict knee OA progressors are the joint space width, mean cartilage thickness of the medial tibial plateau and sub-regions and JSN.

Conclusion:

In this comprehensive study using a large number of features (n = 1107) and MRI outcomes in addition to radiological outcomes, we identified the best features and classification methods for knee OA structural progressors. Data revealed baseline X-ray and MRI-based features could predict early OA knee progressors and that MLP is the best classification method.

Discovery of different metabotypes in overconditioned dairy cows by means of machine learning

Using data from targeted metabolomics in serum in combination with machine learning (ML) approaches, we aimed at (1) identifying divergent metabotypes in overconditioned cows and at (2) exploring how metabotypes are associated with lactation performance, blood metabolites, and hormones. In a previously established animal model, 38 pregnant multiparous Holstein cows were assigned to 2 groups that were fed differently to reach either high (HBCS) or normal (NBCS) body condition score (BCS) and backfat thickness (BFT) until dryoff at -49 d before calving [NBCS: BCS < 3.5 (3.02 ± 0.24) and BFT < 1.2 cm (0.92 ± 0.21), mean ± SD; HBCS: BCS > 3.75 (3.82 ± 0.33) and BFT > 1.4 cm (2.36 ± 0.35)]. Cows were then fed the same diets during the dry period and the subsequent lactation, and maintained the differences in BFT and BCS throughout the study. Blood samples were collected weekly from 7 wk antepartum (ap) to 12 wk postpartum (pp) to assess serum concentrations of metabolites (by targeted metabolomics and by classical analyses) and metabolic hormones. Metabolic clustering by applying 4 supervised ML-based classifiers [sequential minimal optimization (SMO), random forest (RF), alternating decision tree (ADTree), and naïve Bayes-updatable (NB)] on the changes (d 21 pp minus d 49 ap) in concentrations of 170 serum metabolites resulted in 4 distinct metabolic clusters: HBCS predicted HBCS (HBCS-PH, n = 13), HBCS predicted NBCS (HBCS-PN, n = 6), NBCS predicted NBCS (NBCS-PN, n = 15), and NBCS predicted HBCS (NBCS-PH, n = 4). The accuracies of SMO, RF, ADTree, and NB classifiers were >70%. Because the number of NBCS-PH cows was low, we did not consider this group for further comparisons. Dry matter intake (kg/d and percentage of body weight) and energy intake were greater in HBCS-PN than in HBCS-PH in early lactation, and HBCS-PN also reached a positive energy balance earlier than did HBCS-PH. Milk yield was not different between groups, but milk protein percentage was greater in HBCS-PN than in HBCS-PH cows. The circulating concentrations of fatty acids (FA) increased during early lactation in both groups, but HBCS-PN cows had lower concentrations of β-hydroxybutyrate, indicating lower ketogenesis compared with HBCS-PH cows. The concentrations of insulin, insulin-like growth factor 1, leptin, adiponectin, haptoglobin, glucose, and revised quantitative insulin sensitivity check index did not differ between the groups, whereas serum concentrations of glycerophospholipids were lower before calving in HBCS-PH than in HBCS-PN cows. Glycine was the only amino acid that had higher concentration after calving in HBCS-PH than in HBCS-PN cows. The circulating concentrations of some short- (C2, C3, and C4) and long-chain (C12, C16:0, C18:0, and C18:1) acylcarnitines on d 21 pp were greater in HBCS-PH than in HBCS-PN cows, indicating incomplete FA oxidation. In conclusion, the use of ML approaches involving data from targeted metabolomics in serum is a promising method for differentiating divergent metabotypes from apparently similar BCS phenotypes. Further investigations, using larger numbers of cows and farms, are warranted for confirmation of this finding.

An Integrated Multi-Disciplinary Perspectivefor Addressing Challenges of the Human Gut Microbiome

Our understanding of the human gut microbiome has grown exponentially. Advances in genome sequencing technologies and metagenomics analysis have enabled researchers to study microbial communities and their potential function within the context of a range of human gut related diseases and disorders. However, up until recently, much of this research has focused on characterizing the gut microbiological community structure and understanding its potential through system wide (meta) genomic and transcriptomic-based studies. Thus far, the functional output of these microbiomes, in terms of protein and metabolite expression, and within the broader context of host-gut microbiome interactions, has been limited. Furthermore, these studies highlight our need to address the issues of individual variation, and of samples as proxies. Here we provide a perspective review of the recent literature that focuses on the challenges of exploring the human gut microbiome, with a strong focus on an integrated perspective applied to these themes. In doing so, we contextualize the experimental and technical challenges of undertaking such studies and provide a framework for capitalizing on the breadth of insight such approaches afford. An integrated perspective of the human gut microbiome and the linkages to human health will pave the way forward for delivering against the objectives of precision medicine, which is targeted to specific individuals and addresses the issues and mechanisms in situ.

Machine-learning-based patient-specific prediction models for knee osteoarthritis

Osteoarthritis (OA) is an extremely common musculoskeletal disease. However, current guidelines are not well suited for diagnosing patients in the early stages of disease and do not discriminate patients for whom the disease might progress rapidly. The most important hurdle in OA management is identifying and classifying patients who will benefit most from treatment. Further efforts are needed in patient subgrouping and developing prediction models. Conventional statistical modelling approaches exist; however, these models are limited in the amount of information they can adequately process. Comprehensive patient-specific prediction models need to be developed. Approaches such as data mining and machine learning should aid in the development of such models. Although a challenging task, technology is now available that should enable subgrouping of patients with OA and lead to improved clinical decision-making and precision medicine.

EULAR points to consider for the use of big data in rheumatic and musculoskeletal diseases

BACKGROUND

Tremendous opportunities for health research have been unlocked by the recent expansion of big data and artificial intelligence. However, this is an emergent area where recommendations for optimal use and implementation are needed. The objective of these European League Against Rheumatism (EULAR) points to consider is to guide the collection, analysis and use of big data in rheumatic and musculoskeletal disorders (RMDs).

METHODS

A multidisciplinary task force of 14 international experts was assembled with expertise from a range of disciplines including computer science and artificial intelligence. Based on a literature review of the current status of big data in RMDs and in other fields of medicine, points to consider were formulated. Levels of evidence and strengths of recommendations were allocated and mean levels of agreement of the task force members were calculated.

RESULTS

Three overarching principles and 10 points to consider were formulated. The overarching principles address ethical and general principles for dealing with big data in RMDs. The points to consider cover aspects of data sources and data collection, privacy by design, data platforms, data sharing and data analyses, in particular through artificial intelligence and machine learning. Furthermore, the points to consider state that big data is a moving field in need of adequate reporting of methods and benchmarking, careful data interpretation and implementation in clinical practice.

CONCLUSION

These EULAR points to consider discuss essential issues and provide a framework for the use of big data in RMDs.

Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data

The identification of biomarker signatures in omics molecular profiling is usually performed to predict outcomes in a precision medicine context, such as patient disease susceptibility, diagnosis, prognosis, and treatment response. To identify these signatures, we have developed a biomarker discovery tool, called BioDiscML. From a collection of samples and their associated characteristics, i.e., the biomarkers (e.g., gene expression, protein levels, clinico-pathological data), BioDiscML exploits various feature selection procedures to produce signatures associated to machine learning models that will predict efficiently a specified outcome. To this purpose, BioDiscML uses a large variety of machine learning algorithms to select the best combination of biomarkers for predicting categorical or continuous outcomes from highly unbalanced datasets. The software has been implemented to automate all machine learning steps, including data pre-processing, feature selection, model selection, and performance evaluation. BioDiscML is delivered as a stand-alone program and is available for download at https://github.com/mickaelleclercq/BioDiscML.

Artificial intelligence in drug development: present status and future prospects

Artificial intelligence (AI) uses personified knowledge and learns from the solutions it produces to address not only specific but also complex problems. Remarkable improvements in computational power coupled with advancements in AI technology could be utilised to revolutionise the drug development process. At present, the pharmaceutical industry is facing challenges in sustaining their drug development programmes because of increased R&D costs and reduced efficiency. In this review, we discuss the major causes of attrition rates in new drug approvals, the possible ways that AI can improve the efficiency of the drug development process and collaboration of pharmaceutical industry giants with AI-powered drug discovery firms.

Dissecting the Genetics of Osteoporosis using Systems Approaches

Osteoporosis is a condition characterized by low bone mineral density (BMD) and an increased risk of fracture. Traits contributing to osteoporotic fracture are highly heritable, indicating that a comprehensive understanding of bone requires a thorough understanding of the genetic basis of bone traits. Towards this goal, genome-wide association studies (GWASs) have identified over 500 loci associated with bone traits. However, few of the responsible genes have been identified, and little is known of how these genes work together to influence systems-level bone function. In this review, we describe how systems genetics approaches can be used to fill these knowledge gaps.

Glycomics meets artificial intelligence - Potential of glycan analysis for identification of seropositive and seronegative rheumatoid arthritis patients revealed

In this study, one hundred serum samples from healthy people and patients with rheumatoid arthritis (RA) were analyzed. Standard immunoassays for detection of 10 different RA markers and analysis of glycan markers on antibodies in 10 different assay formats with several lectins were applied for each serum sample. A dataset containing 2000 data points was data mined using artificial neural networks (ANN). We identified key RA markers, which can discriminate between healthy people and seropositive RA patients (serum containing autoantibodies) with accuracy of 83.3%. Combination of RA markers with glycan analysis provided much better discrimination accuracy of 92.5%. Immunoassays completely failed to identify seronegative RA patients (serum not containing autoantibodies), while glycan analysis correctly identified 43.8% of these patients. Further, we revealed other critical parameters for successful glycan analysis such as type of a sample, format of analysis and orientation of captured antibodies for glycan analysis.

An Artificial Neural Network Integrated Pipeline for Biomarker Discovery Using Alzheimer's Disease as a Case Study

The field of machine learning has allowed researchers to generate and analyse vast amounts of data using a wide variety of methodologies. Artificial Neural Networks (ANN) are some of the most commonly used statistical models and have been successful in biomarker discovery studies in multiple disease types. This review seeks to explore and evaluate an integrated ANN pipeline for biomarker discovery and validation in Alzheimer's disease, the most common form of dementia worldwide with no proven cause and no available cure. The proposed pipeline consists of analysing public data with a categorical and continuous stepwise algorithm and further examination through network inference to predict gene interactions. This methodology can reliably generate novel markers and further examine known ones and can be used to guide future research in Alzheimer's disease.

Biomarkers for predicting outcomes in chronic kidney disease

PURPOSE OF REVIEW

Current biomarkers for chronic kidney disease (CKD) are limited by lack of sensitivity and inability to prognosticate CKD progression. Significant recent research has better characterized novel biomarker candidates that are associated with CKD progression and cardiovascular mortality in CKD. This review discusses the most significant advances within the past year.

RECENT FINDINGS

We discuss biomarkers for outcomes in CKD under two categories: emerging (defined as having been validated in an independent cohort), which include serum cystatin C, serum β-trace protein, β2-microglobulin, soluble urokinase-type plasminogen activator receptor, soluble tumor necrosis factor receptors 1/2, urinary monocyte chemotactic protein-1, neutrophil gelatin-associated lipocalin, kidney injury molecule-1, and fibroblast growth factor-23; and novel (which have shown associations in smaller observational studies but have not been validated yet), which include indoxyl sulfate, p-cresyl sulfate, trimethylamine-N-oxide, IL-18, Klotho, markers of endothelial dysfunction, vimentin, and procollagen type III N-terminal propeptide. Further, we also discuss future directions for biomarker research including unbiased -omics approaches.

SUMMARY

There are a number of promising biomarkers that can better prognosticate outcomes in and progression of CKD. Further research is warranted to examine whether these biomarkers validate independently as well, and if their incorporation improves clinical practice or trial enrollment.

Lipidomes of lung cancer and tumour-free lung tissues reveal distinct molecular signatures for cancer differentiation, age, inflammation, and pulmonary emphysema

Little is known about the human lung lipidome, its variability in different physiological states, its alterations during carcinogenesis and the development of pulmonary emphysema. We investigated how health status might be mirrored in the lung lipidome. Tissues were sampled for both lipidomic and histological analysis. Using a screening approach, we characterised lipidomes of lung cancer tissues and corresponding tumour-free alveolar tissues. We quantified 311 lipids from 11 classes in 43 tissue samples from 26 patients. Tumour tissues exhibited elevated levels of triacylglycerols and cholesteryl esters, as well as a significantly lower abundance of phosphatidylglycerols, which are typical lung surfactant components. Adenocarcinomas and squamous cell carcinomas were distinguished with high specificity based on lipid panels. Lipidomes of tumour biopsy samples showed clear changes depending on their histology and, in particular, their proportion of active tumour cells and stroma. Partial least squares regression showed correlations between lipid profiles of tumour-free alveolar tissues and the degree of emphysema, inflammation status, and the age of patients. Unsaturated long-chain phosphatidylserines and phosphatidylinositols showed a positive correlation with a worsened emphysema status and ageing. This work provides a resource for the human lung lipidome and a systematic data analysis strategy to link clinical characteristics and histology.

Metabolomics and Integrative Omics for the Development of Thai Traditional Medicine

In recent years, interest in studies of traditional medicine in Asian and African countries has gradually increased due to its potential to complement modern medicine. In this review, we provide an overview of Thai traditional medicine (TTM) current development, and ongoing research activities of TTM related to metabolomics. This review will also focus on three important elements of systems biology analysis of TTM including analytical techniques, statistical approaches and bioinformatics tools for handling and analyzing untargeted metabolomics data. The main objective of this data analysis is to gain a comprehensive understanding of the system wide effects that TTM has on individuals. Furthermore, potential applications of metabolomics and systems medicine in TTM will also be discussed.

RGIFE: a ranked guided iterative feature elimination heuristic for the identification of biomarkers

BACKGROUND

Current -omics technologies are able to sense the state of a biological sample in a very wide variety of ways. Given the high dimensionality that typically characterises these data, relevant knowledge is often hidden and hard to identify. Machine learning methods, and particularly feature selection algorithms, have proven very effective over the years at identifying small but relevant subsets of variables from a variety of application domains, including -omics data. Many methods exist with varying trade-off between the size of the identified variable subsets and the predictive power of such subsets. In this paper we focus on an heuristic for the identification of biomarkers called RGIFE: Rank Guided Iterative Feature Elimination. RGIFE is guided in its biomarker identification process by the information extracted from machine learning models and incorporates several mechanisms to ensure that it creates minimal and highly predictive features sets.

RESULTS

We compare RGIFE against five well-known feature selection algorithms using both synthetic and real (cancer-related transcriptomics) datasets. First, we assess the ability of the methods to identify relevant and highly predictive features. Then, using a prostate cancer dataset as a case study, we look at the biological relevance of the identified biomarkers.

CONCLUSIONS

We propose RGIFE, a heuristic for the inference of reduced panels of biomarkers that obtains similar predictive performance to widely adopted feature selection methods while selecting significantly fewer feature. Furthermore, focusing on the case study, we show the higher biological relevance of the biomarkers selected by our approach. The RGIFE source code is available at: http://ico2s.org/software/rgife.html .

Discriminating cognitive status in Parkinson's disease through functional connectomics and machine learning

There is growing interest in the potential of neuroimaging to help develop non-invasive biomarkers in neurodegenerative diseases. In this study, connection-wise patterns of functional connectivity were used to distinguish Parkinson’s disease patients according to cognitive status using machine learning. Two independent subject samples were assessed with resting-state fMRI. The first (training) sample comprised 38 healthy controls and 70 Parkinson’s disease patients (27 with mild cognitive impairment). The second (validation) sample included 25 patients (8 with mild cognitive impairment). The Brainnetome atlas was used to reconstruct the functional connectomes. Using a support vector machine trained on features selected through randomized logistic regression with leave-one-out cross-validation, a mean accuracy of 82.6% (p < 0.002) was achieved in separating patients with mild cognitive impairment from those without it in the training sample. The model trained on the whole training sample achieved an accuracy of 80.0% when used to classify the validation sample (p = 0.006). Correlation analyses showed that the connectivity level in the edges most consistently selected as features was associated with memory and executive function performance in the patient group. Our results demonstrate that connection-wise patterns of functional connectivity may be useful for discriminating Parkinson’s disease patients according to the presence of cognitive deficits.

Integrating transcriptome and proteome profiling: Strategies and applications

Discovering the gene expression signature associated with a cellular state is one of the basic quests in majority of biological studies. For most of the clinical and cellular manifestations, these molecular differences may be exhibited across multiple layers of gene regulation like genomic variations, gene expression, protein translation and post-translational modifications. These system wide variations are dynamic in nature and their crosstalk is overwhelmingly complex, thus analyzing them separately may not be very informative. This necessitates the integrative analysis of such multiple layers of information to understand the interplay of the individual components of the biological system. Recent developments in high throughput RNA sequencing and mass spectrometric (MS) technologies to probe transcripts and proteins made these as preferred methods for understanding global gene regulation. Subsequently, improvements in "big-data" analysis techniques enable novel conclusions to be drawn from integrative transcriptomic-proteomic analysis. The unified analyses of both these data types have been rewarding for several biological objectives like improving genome annotation, predicting RNA-protein quantities, deciphering gene regulations, discovering disease markers and drug targets. There are different ways in which transcriptomics and proteomics data can be integrated; each aiming for different research objectives. Here, we review various studies, approaches and computational tools targeted for integrative analysis of these two high-throughput omics methods.

Review of biomarkers in systemic juvenile idiopathic arthritis: helpful tools or just playing tricks?

BACKGROUND

Diagnosing systemic juvenile idiopathic arthritis (SJIA) can be extremely challenging if typical arthritis is lacking. A variety of biomarkers have been described for the diagnosis and management of SJIA. However, very few markers have been well-validated. In addition, increasing numbers of biomarkers are identified by high throughput or multi-marker panels.

METHOD

We identified diagnostic or prognostic biomarkers by systematic literature review, evaluating each according to a predefined level of verification, validation or clinical utility. Diagnostic biomarkers were those identifying SJIA versus (1) non-SJIA conditions or healthy controls (HC) or (2) other non-systemic JIA subtypes. Prognostic biomarkers were those specifically tested for the prediction of (1) disease flare, (2) increased disease activity +/- discrimination of active versus inactive disease, or (3) macrophage activation syndrome (MAS).

RESULTS

Fifty-five studies fulfilled the inclusion criteria identifying 68 unique biomarkers, of which 50/68 (74 %) were investigated by only a single research group. Candidate marker verification and clinical utility was evaluated according to whether markers were readily and reliably measurable, investigated by independent study groups, discovered by more than one method (i.e. verified markers) and validated in independent cohorts. This evaluation revealed diagnostic biomarkers of high interest for further evaluation in the diagnostic approach to SJIA that included heme oxygenase-1, interleukin-6 (IL-6), IL-12, IL-18, osteoprotegerin, S100 calcium-binding protein A12 (S100A12) and S100A8/A9.

CONCLUSION

In summary, a number of biomarkers were identified, though most had limited evidence for their use. However, our findings combined with the identified studies could inform validation studies, whether in single or multi-marker assays, which are urgently needed.

Biomarkers of (osteo)arthritis

Arthritic diseases are a major cause of disability and morbidity, and cause an enormous burden for health and social care systems globally. Osteoarthritis (OA) is the most common form of arthritis. The key risk factors for the development of OA are age, obesity, joint trauma or instability. Metabolic and endocrine diseases can also contribute to the pathogenesis of OA. There is accumulating evidence to suggest that OA is a whole-organ disease that is influenced by systemic mediators, inflammaging, innate immunity and the low-grade inflammation induced by metabolic syndrome. Although all joint tissues are implicated in disease progression in OA, articular cartilage has received the most attention in the context of aging, injury and disease. There is increasing emphasis on the early detection of OA as it has the capacity to target and treat the disease more effectively. Indeed it has been suggested that this is the era of "personalized prevention" for OA. However, the development of strategies for the prevention of OA require new and sensitive biomarker tools that can detect the disease in its molecular and pre-radiographic stage, before structural and functional alterations in cartilage integrity have occurred. There is also evidence to support a role for biomarkers in OA drug discovery, specifically the development of disease modifying osteoarthritis drugs. This Special Issue of Biomarkers is dedicated to recent progress in the field of OA biomarkers. The papers in this Special Issue review the current state-of-the-art and discuss the utility of OA biomarkers as diagnostic and prognostic tools.