Transparent Exploration of Machine Learning for Biomarker Discovery from Proteomics and Omics Data

Mass Spectrometry Advancements and Applications for Biomarker Discovery, Diagnostic Innovations, and Personalized Medicine

Mass spectrometry (MS) has revolutionized clinical chemistry, offering unparalleled capabilities for biomolecule analysis. This review explores the growing significance of mass spectrometry (MS), particularly when coupled with liquid chromatography (LC), in identifying disease biomarkers and quantifying biomolecules for diagnostic and prognostic purposes. The unique advantages of MS in accurately identifying and quantifying diverse molecules have positioned it as a cornerstone in personalized-medicine advancement. MS-based technologies have transformed precision medicine, enabling a comprehensive understanding of disease mechanisms and patient-specific treatment responses. LC-MS has shown exceptional utility in analyzing complex biological matrices, while high-resolution MS has expanded analytical capabilities, allowing the detection of low-abundance molecules and the elucidation of complex biological pathways. The integration of MS with other techniques, such as ion mobility spectrometry, has opened new avenues for biomarker discovery and validation. As we progress toward precision medicine, MS-based technologies will be crucial in addressing the challenges of individualized patient care, driving innovations in disease diagnosis, prognosis, and treatment strategies.

Single-cell transcriptome analysis revealed heterogeneity in glycolysis and identified IGF2 as a therapeutic target for ovarian cancer subtypes

BACKGROUND

As the most malignant tumor of the female reproductive system, ovarian cancer (OC) has garnered increasing attention. The Warburg effect, driven by glycolysis, accounts for tumor cell proliferation under aerobic conditions. However, the metabolic heterogeneity linked to glycolysis in OC remains elusive.

METHODS

We integrated single-cell data with OC to score glycolysis level in tumor cell subclusters. This led to the identification of a subcluster predominantly characterized by glycolysis, with a strong correlation to patient prognosis. Core transcription factors were pinpointed using hdWGCNA and metaVIPER. A specific transcription factor regulatory network was then constructed. A glycolysis-related prognostic model was developed and tested for estimating OC prognosis with a total of 85 machine-learning combinations, focusing on specific upregulated genes of two subtypes. We identified IGF2 as a key within the prognostic model and investigated its impact on OC progression and drug resistance through in vitro experiments, including the transwell assay, lactate production detection, and the CCK-8 assay.

RESULTS

Analysis showed that the Malignant 7 subcluster was primarily related to glycolysis. Two OC molecular subtypes, CS1 and CS2, were identified with distinct clinical, biological, and microenvironmental traits. A prognostic model was built, and IGF2 emerged as a key gene linked to prognosis. Experiments have proven that IGF2 can promote the glycolysis pathway and the malignant biological progression of OC cells.

CONCLUSIONS

We developed two novel OC subtypes based on glycolysis score, established a stable prognostic model, and identified IGF2 as the marker gene. These insights provided a new avenue for exploring OC's molecular mechanisms and personalized treatment approaches.

Frontiers in plasma proteome profiling platforms: innovations and applications

Biomarkers play a crucial role in advancing precision medicine by enabling more targeted and individualized approaches to diagnosis and treatment. Various biofluids, including serum, plasma, cerebrospinal fluid (CSF), saliva, tears, pancreatic cyst fluids, and urine, have been identified as rich sources of potential for the early detection of disease biomarkers in conditions such as cancer, cardiovascular diseases, and neurodegenerative disorders. The analysis of plasma and serum in proteomics research encounters challenges due to their high complexity and the wide dynamic range of protein abundance. These factors impede the sensitivity, coverage, and precision of protein detection when employing mass spectrometry, a widely utilized technology in discovery proteomics. Conventional approaches such as Neat Plasma workflow are inefficient in accurately quantifying low-abundant proteins, including those associated with tissue leakage, immune response molecules, interleukins, cytokines, and interferons. Moreover, the manual nature of the workflow poses a significant hurdle in conducting large cohort studies. In this study, our focus is on comparing workflows for plasma proteomic profiling to establish a methodology that is not only sensitive and reproducible but also applicable for large cohort studies in biomarker discovery. Our investigation revealed that the Proteograph XT workflow outperforms other workflows in terms of plasma proteome depth, quantitative accuracy, and reproducibility while offering complete automation of sample preparation. Notably, Proteograph XT demonstrates versatility by applying it to various types of biofluids. Additionally, the proteins quantified widely cover secretory proteins in peripheral blood, and the pathway analysis enriched with relevant components such as interleukins, tissue necrosis factors, chemokines, and B and T cell receptors provides valuable insights. These proteins, often challenging to quantify in complex biological samples, hold potential as early detection markers for various diseases, thereby contributing to the improvement of patient care quality.

Robust and consistent biomarker candidates identification by a machine learning approach applied to pancreatic ductal adenocarcinoma metastasis

BACKGROUND

Machine Learning (ML) plays a crucial role in biomedical research. Nevertheless, it still has limitations in data integration and irreproducibility. To address these challenges, robust methods are needed. Pancreatic ductal adenocarcinoma (PDAC), a highly aggressive cancer with low early detection rates and survival rates, is used as a case study. PDAC lacks reliable diagnostic biomarkers, especially metastatic biomarkers, which remains an unmet need. In this study, we propose an ML-based approach for discovering disease biomarkers, apply it to the identification of a PDAC metastatic composite biomarker candidate, and demonstrate the advantages of harnessing data resources.

METHODS

We utilised primary tumour RNAseq data from five public repositories, pooling samples to maximise statistical power and integrating data by correcting for technical variance. Data were split into train and validation sets. The train dataset underwent variable selection via a 10-fold cross-validation process that combined three algorithms in 100 models per fold. Genes found in at least 80% of models and five folds were considered robust to build a consensus multivariate model. A random forest model was constructed using selected genes from the train dataset and tested in the validation set. We also assessed the goodness of prediction by recalibrating a model using only the validation data. The biological context and relevance of signals was explored through enrichment and pathway analyses using QIAGEN Ingenuity Pathway Analysis and GeneMANIA.

RESULTS

We developed a pipeline that can detect robust signatures to build composite biomarkers. We tested the pipeline in PDAC, exploiting transcriptomics data from different sources, proposing a composite biomarker candidate comprised of fifteen genes consistently selected that showed very promising predictive capability. Biological contextualisation revealed links with cancer progression and metastasis, underscoring their potential relevance. All code is available in GitHub.

CONCLUSION

This study establishes a robust framework for identifying composite biomarkers across various disease contexts. We demonstrate its potential by proposing a plausible composite biomarker candidate for PDAC metastasis. By reusing data from public repositories, we highlight the sustainability of our research and the wider applications of our pipeline. The preliminary findings shed light on a promising validation and application path.

AM-DMF-SCP: Integrated Single-Cell Proteomics Analysis on an Active Matrix Digital Microfluidic Chip

Single-cell proteomics offers unparalleled insights into cellular diversity and molecular mechanisms, enabling a deeper understanding of complex biological processes at the individual cell level. Here, we develop an integrated sample processing on an active-matrix digital microfluidic chip for single-cell proteomics (AM-DMF-SCP). Employing the AM-DMF-SCP approach and data-independent acquisition (DIA), we identify an average of 2258 protein groups in single HeLa cells within 15 min of the liquid chromatography gradient. We performed comparative analyses of three tumor cell lines: HeLa, A549, and HepG2, and machine learning was utilized to identify the unique features of these cell lines. Applying the AM-DMF-SCP to characterize the proteomes of a third-generation EGFR inhibitor, ASK120067-resistant cells (67R) and their parental NCI-H1975 cells, we observed a potential correlation between elevated VIM expression and 67R resistance, which is consistent with the findings from bulk sample analyses. These results suggest that AM-DMF-SCP is an automated, robust, and sensitive platform for single-cell proteomics and demonstrate the potential for providing valuable insights into cellular mechanisms.

Aqueous humor proteomics analyzed by bioinformatics and machine learning in PDR cases versus controls

BACKGROUND

To comprehend the complexities of pathophysiological mechanisms and molecular events that contribute to proliferative diabetic retinopathy (PDR) and evaluate the diagnostic value of aqueous humor (AH) in monitoring the onset of PDR.

METHODS

A cohort containing 16 PDR and 10 cataract patients and another validation cohort containing 8 PDR and 4 cataract patients were studied. AH was collected and subjected to proteomics analyses. Bioinformatics analysis and a machine learning-based pipeline called inference of biomolecular combinations with minimal bias were used to explore the functional relevance, hub proteins, and biomarkers.

RESULTS

Deep profiling of AH proteomes revealed several insights. First, the combination of SIAE, SEMA7A, GNS, and IGKV3D-15 and the combination of ATP6AP1, SPARCL1, and SERPINA7 could serve as surrogate protein biomarkers for monitoring PDR progression. Second, ALB, FN1, ACTB, SERPINA1, C3, and VTN acted as hub proteins in the profiling of AH proteomes. SERPINA1 was the protein with the highest correlation coefficient not only for BCVA but also for the duration of diabetes. Third, "Complement and coagulation cascades" was an important pathway for PDR development.

CONCLUSIONS

AH proteomics provides stable and accurate biomarkers for early warning and diagnosis of PDR. This study provides a deep understanding of the molecular mechanisms of PDR and a rich resource for optimizing PDR management.

Mass Spectrometry-Based Proteomics of Poly(methylmethacrylate)-Embedded Bone

Liquid chromatography-tandem mass spectrometry (LC-MS/MS) is a widely employed technique in proteomics research for studying the proteome biology of various clinical samples. Hard tissues, such as bone and teeth, are routinely preserved using synthetic poly(methyl methacrylate) (PMMA) embedding resins that enable histological, immunohistochemical, and morphological examination. However, the suitability of PMMA-embedded hard tissues for large-scale proteomic analysis remained unexplored. This study is the first to report on the feasibility of PMMA-embedded bone samples for LC-MS/MS analysis. Conventional workflows yielded merely limited coverage of the bone proteome. Using advanced strategies of prefractionation by high-pH reversed-phase liquid chromatography in combination with isobaric tandem mass tag labeling resulted in proteome coverage exceeding 1000 protein identifications. The quantitative comparison with cryopreserved samples revealed that each sample preparation workflow had a distinct impact on the proteomic profile. However, workflow replicates exhibited a high reproducibility for PMMA-embedded samples. Our findings further demonstrate that decalcification prior to protein extraction, along with the analysis of solubilization fractions, is not preferred for PMMA-embedded bone. The biological applicability of the proposed workflow was demonstrated using samples of human PMMA-embedded alveolar bone and the iliac crest, which revealed anatomical site-specific proteomic profiles. Overall, these results establish a crucial foundation for large-scale proteomics studies contributing to our knowledge of bone biology.

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

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

AlphaPept: a modern and open framework for MS-based proteomics

In common with other omics technologies, mass spectrometry (MS)-based proteomics produces ever-increasing amounts of raw data, making efficient analysis a principal challenge. A plethora of different computational tools can process the MS data to derive peptide and protein identification and quantification. However, during the last years there has been dramatic progress in computer science, including collaboration tools that have transformed research and industry. To leverage these advances, we develop AlphaPept, a Python-based open-source framework for efficient processing of large high-resolution MS data sets. Numba for just-in-time compilation on CPU and GPU achieves hundred-fold speed improvements. AlphaPept uses the Python scientific stack of highly optimized packages, reducing the code base to domain-specific tasks while accessing the latest advances. We provide an easy on-ramp for community contributions through the concept of literate programming, implemented in Jupyter Notebooks. Large datasets can rapidly be processed as shown by the analysis of hundreds of proteomes in minutes per file, many-fold faster than acquisition. AlphaPept can be used to build automated processing pipelines with web-serving functionality and compatibility with downstream analysis tools. It provides easy access via one-click installation, a modular Python library for advanced users, and via an open GitHub repository for developers.

Proteomic insights into the pathophysiology of hypertension-associated albuminuria: Pilot study in a South African cohort

BACKGROUND

Hypertension is an important public health priority with a high prevalence in Africa. It is also an independent risk factor for kidney outcomes. We aimed to identify potential proteins and pathways involved in hypertension-associated albuminuria by assessing urinary proteomic profiles in black South African participants with combined hypertension and albuminuria compared to those who have neither condition.

METHODS

The study included 24 South African cases with both hypertension and albuminuria and 49 control participants who had neither condition. Protein was extracted from urine samples and analysed using ultra-high-performance liquid chromatography coupled with mass spectrometry. Data were generated using data-independent acquisition (DIA) and processed using Spectronaut™ 15. Statistical and functional data annotation were performed on Perseus and Cytoscape to identify and annotate differentially abundant proteins. Machine learning was applied to the dataset using the OmicLearn platform.

RESULTS

Overall, a mean of 1,225 and 915 proteins were quantified in the control and case groups, respectively. Three hundred and thirty-two differentially abundant proteins were constructed into a network. Pathways associated with these differentially abundant proteins included the immune system (q-value [false discovery rate] = 1.4 × 10- 45), innate immune system (q = 1.1 × 10- 32), extracellular matrix (ECM) organisation (q = 0.03) and activation of matrix metalloproteinases (q = 0.04). Proteins with high disease scores (76-100% confidence) for both hypertension and chronic kidney disease included angiotensinogen (AGT), albumin (ALB), apolipoprotein L1 (APOL1), and uromodulin (UMOD). A machine learning approach was able to identify a set of 20 proteins, differentiating between cases and controls.

CONCLUSIONS

The urinary proteomic data combined with the machine learning approach was able to classify disease status and identify proteins and pathways associated with hypertension-associated albuminuria.

How Can Proteomics Help to Elucidate the Pathophysiological Crosstalk in Muscular Dystrophy and Associated Multi-System Dysfunction?

This perspective article is concerned with the question of how proteomics, which is a core technique of systems biology that is deeply embedded in the multi-omics field of modern bioresearch, can help us better understand the molecular pathogenesis of complex diseases. As an illustrative example of a monogenetic disorder that primarily affects the neuromuscular system but is characterized by a plethora of multi-system pathophysiological alterations, the muscle-wasting disease Duchenne muscular dystrophy was examined. Recent achievements in the field of dystrophinopathy research are described with special reference to the proteome-wide complexity of neuromuscular changes and body-wide alterations/adaptations. Based on a description of the current applications of top-down versus bottom-up proteomic approaches and their technical challenges, future systems biological approaches are outlined. The envisaged holistic and integromic bioanalysis would encompass the integration of diverse omics-type studies including inter- and intra-proteomics as the core disciplines for systematic protein evaluations, with sophisticated biomolecular analyses, including physiology, molecular biology, biochemistry and histochemistry. Integrated proteomic findings promise to be instrumental in improving our detailed knowledge of pathogenic mechanisms and multi-system dysfunction, widening the available biomarker signature of dystrophinopathy for improved diagnostic/prognostic procedures, and advancing the identification of novel therapeutic targets to treat Duchenne muscular dystrophy.

The Potential of Meta-Proteomics and Artificial Intelligence to Establish the Next Generation of Probiotics for Personalized Healthcare

The symbiosis of probiotic bacteria with humans has rendered various health benefits while providing nutrition and a suitable environment for their survival. However, the probiotics must survive unfavorable gut conditions to exert beneficial effects. The intrinsic resistance of probiotics to survive harsh conditions results from a myriad of proteins. Interaction of microbial proteins with the host is indispensable for modulating the gut microbiome, such as interaction with cell receptors and protective action against pathogens. The complex interplay of proteins should be unraveled by utilizing metaproteomic strategies. The contribution of probiotics to health is now widely accepted. However, due to the inconsistency of generalized probiotics, contemporary research toward precision probiotics has gained momentum for customized treatment. This review explores the application of metaproteomics and AI/ML algorithms in resolving multiomics data analysis and in silico prediction of microbial features for screening specific beneficial probiotic organisms. Implementing these integrative strategies could augment the potential of precision probiotics for personalized healthcare.

Unlocking the potential of microRNAs: machine learning identifies key biomarkers for myocardial infarction diagnosis

BACKGROUND

MicroRNAs (miRNAs) play a crucial role in regulating adaptive and maladaptive responses in cardiovascular diseases, making them attractive targets for potential biomarkers. However, their potential as novel biomarkers for diagnosing cardiovascular diseases requires systematic evaluation.

METHODS

In this study, we aimed to identify a key set of miRNA biomarkers using integrated bioinformatics and machine learning analysis. We combined and analyzed three gene expression datasets from the Gene Expression Omnibus (GEO) database, which contains peripheral blood mononuclear cell (PBMC) samples from individuals with myocardial infarction (MI), stable coronary artery disease (CAD), and healthy individuals. Additionally, we selected a set of miRNAs based on their area under the receiver operating characteristic curve (AUC-ROC) for separating the CAD and MI samples. We designed a two-layer architecture for sample classification, in which the first layer isolates healthy samples from unhealthy samples, and the second layer classifies stable CAD and MI samples. We trained different machine learning models using both biomarker sets and evaluated their performance on a test set.

RESULTS

We identified hsa-miR-21-3p, hsa-miR-186-5p, and hsa-miR-32-3p as the differentially expressed miRNAs, and a set including hsa-miR-186-5p, hsa-miR-21-3p, hsa-miR-197-5p, hsa-miR-29a-5p, and hsa-miR-296-5p as the optimum set of miRNAs selected by their AUC-ROC. Both biomarker sets could distinguish healthy from not-healthy samples with complete accuracy. The best performance for the classification of CAD and MI was achieved with an SVM model trained using the biomarker set selected by AUC-ROC, with an AUC-ROC of 0.96 and an accuracy of 0.94 on the test data.

CONCLUSIONS

Our study demonstrated that miRNA signatures derived from PBMCs could serve as valuable novel biomarkers for cardiovascular diseases.

Interpreting biologically informed neural networks for enhanced proteomic biomarker discovery and pathway analysis

The incorporation of machine learning methods into proteomics workflows improves the identification of disease-relevant biomarkers and biological pathways. However, machine learning models, such as deep neural networks, typically suffer from lack of interpretability. Here, we present a deep learning approach to combine biological pathway analysis and biomarker identification to increase the interpretability of proteomics experiments. Our approach integrates a priori knowledge of the relationships between proteins and biological pathways and biological processes into sparse neural networks to create biologically informed neural networks. We employ these networks to differentiate between clinical subphenotypes of septic acute kidney injury and COVID-19, as well as acute respiratory distress syndrome of different aetiologies. To gain biological insight into the complex syndromes, we utilize feature attribution-methods to introspect the networks for the identification of proteins and pathways important for distinguishing between subtypes. The algorithms are implemented in a freely available open source Python-package ( https://github.com/InfectionMedicineProteomics/BINN ).