Artificial intelligence for proteomics and biomarker discovery

NNSFMDA: Lightweight Transformer Model with Bounded Nuclear Norm Minimization for Microbe-Drug Association Prediction

Identifying potential connections between microbe-drug pairs play an important role in drug discovery and clinical treatment. Techniques like graph neural networks effectively derive accurate node representations from sparse topologies,however, they struggle with over-smoothing and over-compression, and their interpretability is relatively poor. Conversely, mathematical methods with low-rank approximations are interpretable but often get trapped in local optima. To address these issues, we propose a new prediction model named NNSFMDA, in which, the bounded nuclear norm minimization and the simplified transformer were combined to infer possible drug-microbe associations. In NNSFMDA, we first constructed a heterogeneous microbe-drug network by integrating multiple microbe and drug similarity metrics, according to which, we subsequently transformed the prediction problem to a matrix filling problem, and then, iteratively approximated the matrix by minimizing the number of bounded nuclear norm. Finally, based on the newly-filled matrix, we introduced a simplified transformer to estimate possible scores of microbe-drug pairs. Results showed that NNSFMDA could achieve reliable AUC value of 0.98, which outperformed existing state-of-the-art competitive methods. In the experimental section, ablation experiments and modular analyses further demonstrate the superiority of the model, and case studies of microbe-drug associations confirm the validity of the model. These tests have all highlighted the potential of the NNSFMDA to predict latent microbe-drug associations in the future.

Proteomics in decoding cancer: A review

Cancer remains the second leading cause of death worldwide, posing a significant global health challenge. Extensive research has revealed common biological characteristics across cancer cells, forming the foundation for developing innovative diagnostic and therapeutic strategies. To better understand these shared traits, advanced measurement technologies are critical. Proteomics, the large-scale study of proteins and their functions, has emerged as a transformative tool for uncovering the complexities of cancer biology. This approach provides an in-depth view of cellular activities and protein interactions, offering unprecedented insights into cancer progression and treatment. Unlike traditional methods that investigate specific pathways in isolation, proteomics enables simultaneous analysis of thousands of proteins, generating a comprehensive understanding of cancer biology. This review explores the mechanisms underlying proteomics, its application to understanding cancer hallmarks, and its potential to transform clinical approaches. By examining proteomics' role in metastasis, angiogenesis, proliferation, and resistance mechanisms, this study highlights its contributions to cancer diagnosis, treatment, and personalized medicine. Additionally, prospects in integrating proteomics with other -omics fields and advancements in computational analysis will be discussed. This work aims to illuminate the path toward more effective, precise, and individualized cancer care through proteomics innovations.

Natural products for anti-fibrotic therapy in idiopathic pulmonary fibrosis: marine and terrestrial insights

Idiopathic Pulmonary Fibrosis (IPF) is a chronic fibrotic interstitial lung disease (ILD) of unknown etiology, characterized by increasing incidence and intricate pathogenesis. Current FDA-approved drugs suffer from significant side effects and limited efficacy, highlighting the urgent need for innovative therapeutic agents for IPF. Natural products (NPs), with their multi-target and multifaceted properties, present promising candidates for new drug development. This review delineates the anti-fibrotic pathways and targets of various natural products based on the established pathological mechanisms of IPF. It encompasses over 20 compounds, including flavonoids, saponins, polyphenols, terpenoids, natural polysaccharides, cyclic peptides, deep-sea fungal alkaloids, and algal proteins, sourced from both terrestrial and marine environments. The review explores their potential roles in mitigating pulmonary fibrosis, such as inhibiting inflammatory responses, protecting against lipid peroxidation damage, suppressing mesenchymal cell activation and proliferation, inhibiting fibroblast migration, influencing the synthesis and secretion of pro-fibrotic factors, and regulating extracellular matrix (ECM) synthesis and degradation. Additionally, it covers various in vivo and in vitro disease models, methodologies for analyzing marker expression and signaling pathways, and identifies potential new therapeutic targets informed by the latest research on IPF pathogenesis, as well as challenges in bioavailability and clinical translation. This review aims to provide essential theoretical and technical insights for the advancement of novel anti-pulmonary fibrosis drugs.

Intimate partner violence and stress-related disorders: from epigenomics to resilience

Intimate Partner Violence (IPV) is a major public health problem to be addressed with innovative and interconnecting strategies for ensuring the psychophysical health of the surviving woman. According to the World Health Organization, 27% of women worldwide have experienced physical and sexual IPV in their lifetime. Most of the studies on gender-based violence focus on short-term effects, while long-term effects are often marginally included even though they represent the most serious and complex consequences. The molecular mechanisms underlying stress-related disorders in IPV victims are multiple and include dysregulation of the hypothalamic-pituitary-adrenal axis, inflammatory response, epigenetic modifications, neurotransmitter imbalances, structural changes in the brain, and oxidative stress. This review aims to explore the long-term health consequences of intimate partner violence (IPV), emphasizing the biological and psychological mechanisms underlying stress-related disorders and resilience. By integrating findings from epigenetics, microbiome research, and artificial intelligence (AI)-based data analysis, we highlight novel strategies for mitigating IPV-related trauma and improving recovery pathways. Genome-wide environment interaction studies, enhanced by AI-assisted data analysis, offer a promising public health approach for identifying factors that contribute to stress-related disorders and those that promote resilience, thus guiding more effective prevention and intervention strategies.

Advancement in early diagnosis of polycystic ovary syndrome: biomarker-driven innovative diagnostic sensor

Polycystic ovary syndrome (PCOS) is a heterogeneous multifactorial endocrine disorder that affects one in five women around the globe. The pathology suggests a strong polygenic and epigenetic correlation, along with hormonal and metabolic dysfunction, but the exact etiology is still a mystery. The current diagnosis is mostly based on Rotterdam criteria, which resulted in a delayed diagnosis in most of the cases, leading to unbearable lifestyle complications and infertility. PCOS is not new; thus, constant efforts are made in the field of biomarker discovery and advanced diagnostic techniques. A plethora of research has enabled the identification of promising PCOS diagnostic biomarkers across hormonal, metabolic, genetic, and epigenetic domains. Not only biomarker identification, but the utilization of biosensing platforms also renders effective point-of-care diagnostic devices. Artificial intelligence also shows its power in modifying existing image-based analysis, even developing symptom-based prediction systems for the early diagnosis of this multifaceted disorder. This approach could affect the future management and treatment direction of PCOS, decreasing its severity and improving the reproductive life of women. The rationale of the current review is to identify the advancements in understanding the pathophysiology through biomarker discovery and the implementation of modern analytical techniques for the early diagnosis of PCOS.

Advancements in Biomarkers for Early Detection and Risk Stratification of Cardiovascular Diseases-A Literature Review

Introduction

CVDs is a leading cause of morbidity, mortality, and healthcare expenditure worldwide. Identifying individuals at risk or in the incipient stages of disease is instrumental in enabling timely interventions, preventive measures, and tailored treatment regimens. The landscape of CVDs is complicated by their heterogeneity, encompassing a spectrum of conditions such as coronary artery disease, heart failure, arrhythmias, and valvular disorders. In recent years, the integration of biomarkers into cardiovascular medicine has emerged as a paradigm-shifting approach with the potential to revolutionize early detection and risk stratification. By synthesizing a multitude of studies, we aim to provide a comprehensive resource that illuminates the transformative potential of biomarkers in ushering in a new era of precision cardiovascular medicine.

Aim

To identify the biomarkers for the detection and diagnosis of CVDs.

Materials and Methods

This review examines key studies from 2015 to the present that investigate the impact of cardiac biomarkers on cardiovascular outcomes. Data were gathered from PubMed, Cochrane Library, and Embase to ensure a comprehensive analysis. The review focuses on various cardiac biomarkers, assessing their levels and changes in relation to cardiovascular health, with special emphasis on advanced biomarkers such as proteomic and metabolomic markers in cardiovascular disease (CVD) diagnosis. Peer-reviewed studies published in English that evaluated the diagnostic, prognostic, or therapeutic role of cardiac biomarkers were included, with priority given to clinical trials, cohort studies, systematic reviews, and meta-analyses providing quantitative biomarker data. Studies unrelated to cardiac biomarkers, case reports, editorials, conference abstracts, and those with small sample sizes or insufficient methodological rigor were excluded. The review also accounts for potential confounding factors and research limitations, ensuring a balanced assessment of the literature. By synthesizing data from academic papers, clinical reports, and research articles, this study provides a comprehensive evaluation of the evolving role of cardiac biomarkers in CVD diagnosis and risk stratification.

Results

Biomarkers play a pivotal role in cardiovascular disease risk prediction, diagnosis, and treatment by providing dynamic biological insights. High-sensitivity cardiac troponins (hs-cTn) enhance myocardial injury detection, while circulating microRNAs (miR-208, miR-499) serve as early indicators of myocardial infarction and heart failure. Lipoprotein(a) [Lp(a)] predicts long-term cardiovascular risk, and inflammatory biomarkers such as C-reactive protein (CRP) and interleukin-6 (IL-6) are linked to adverse outcomes. Multi-biomarker panels, such as hs-cTn with B-type natriuretic peptide (BNP), improve heart failure prognosis, while metabolomic profiling enables precision medicine. Additionally, biomarkers like BNP and NT-proBNP facilitate real-time therapeutic monitoring. These findings underscore the critical role of biomarkers in refining risk stratification, improving diagnostic accuracy, and enabling personalized treatment strategies in cardiovascular medicine.

Conclusion

The advancement of cardiovascular biomarkers has significantly enhanced early detection, risk stratification, and personalized treatment. Emerging biomarkers, including genetic variants, metabolomics, microRNAs, and imaging-based markers, provide deeper insights into disease mechanisms. Integrating multi-omic approaches with artificial intelligence may further refine predictive accuracy and therapeutic decision-making. However, clinical translation requires rigorous validation through large-scale, multicenter studies to ensure reliability and applicability across diverse populations. Standardization, cost-effectiveness assessments, and the development of biomarker panels are essential for clinical adoption. Future research should focus on bridging discovery and implementation, advancing precision medicine to improve cardiovascular outcomes.

Mass Spectrometry-Based Proteomics for Next-Generation Precision Oncology

Cancer is the leading cause of death worldwide characterized by patient heterogeneity and complex tumor microenvironment. While the genomics-based testing has transformed modern medicine, the challenge of diverse clinical outcomes highlights unmet needs for precision oncology. As functional molecules regulating cellular processes, proteins hold great promise as biomarkers and drug targets. Mass spectrometry (MS)-based clinical proteomics has illuminated the molecular features of cancers and facilitated discovery of biomarkers or therapeutic targets, paving the way for innovative strategies that enhance the precision of personalized treatment. In this article, we introduced the tools and current achievements of MS-based proteomics, choice of discovery and targeted MS from discovery to validation phases, profiling sensitivity from bulk samples to single-cell level and tissue to liquid biopsy specimens, current regulatory landscape of MS-based protein laboratory-developed tests (LDTs). The challenges, success and future perspectives in translating research MS assay into clinical applications are also discussed. With well-designed validation studies to demonstrate clinical benefits and meet the regulatory requirements for both analytical and clinical performance, the future of MS-based assays is promising with numerous opportunities to improve cancer diagnosis, treatment, and monitoring.

Natural and induced immune responses in oral cavity and saliva

This review comprehensively explores the intricate immune responses within the oral cavity, emphasizing the pivotal role of saliva in maintaining both oral and systemic health. Saliva, a complex biofluid, functions as a dynamic barrier against pathogens, housing diverse cellular components including epithelial cells, neutrophils, monocytes, dendritic cells, and lymphocytes, which collectively contribute to robust innate and adaptive immune responses. It acts as a physical and immunological barrier, providing the first line of defense against pathogens. The multifaceted protective mechanisms of salivary proteins, cytokines, and immunoglobulins, particularly secretory IgA (SIgA), are elucidated. We explore the natural and induced immune responses in saliva, focusing on its cellular and molecular composition. In addition to saliva, we highlight the significance of a serum-like fluid, the gingival crevicular fluid (GCF), in periodontal health and disease, and its potential as a diagnostic tool. Additionally, the review delves into the impact of diseases such as periodontitis, oral cancer, type 2 diabetes, and lupus on salivary immune responses, highlighting the potential of saliva as a non-invasive diagnostic tool for both oral and systemic conditions. We describe how oral tissue and the biofluid responds to diseases, including considerations to periodontal tissue health and in disease periodontitis. By examining the interplay between oral and systemic health through the oral-systemic axis, this review underscores the significance of salivary immune mechanisms in overall well-being and disease pathogenesis, emphasizing the importance of salivary mechanisms across the body.

A retrospective study using machine learning to develop predictive model to identify rotavirus-associated acute gastroenteritis in children

Background

Rotavirus is the leading cause of severe dehydrating diarrhea in children under 5 years worldwide. Timely diagnosis is critical, but access to confirmatory testing is limited in hospital settings. Machine learning (ML) models have shown promising potential in supporting symptom-based diagnosis of several diseases in resource-limited settings.

Objectives

This study aims to develop a machine-learning predictive model integrated with multiple sources of clinical parameters specific to rotavirus infection without relying on laboratory tests.

Methods

A clinical dataset of 509 children was collected in collaboration with the Regional Institute of Medical Sciences, Imphal, India. The clinical symptoms included diarrhea and its duration, number of stool episodes per day, fever, vomiting and its duration, number of vomiting episodes per day, temperature and dehydration. Correlation analysis is performed to check the feature-feature and feature-outcome collinearity. Feature selection using ANOVA F test is carried out to find the feature importance values and finally obtain the reduced feature subset. Seven supervised learning models were tested and compared viz., support vector machine (SVM), K-nearest neighbor (KNN), naive Bayes (NB), logistic regression (Log_R) , random forest (RF), decision tree (DT), and XGBoost (XGB). A comparison of the performances of the seven models using the classification results obtained. The performance of the models was evaluated based on accuracy, precision, recall, specificity, F1 score, macro F1, F2, and receiver operator characteristic curve.

Results

The seven ML models were exhaustively experimented on our dataset and compared based on eight evaluation scores which are accuracy, precision, recall, specificity, F1 score, F2 score, macro F1 score, and AUC values computed. We observed that when the seven ML models were applied, RF performed the best with an accuracy of 81.4%, F1 score of 86.9%, macro F1-score of 77.3%, F2 score of 86.5% and area under the curve (AUC) of 89%.

Conclusions

The machine learning models can contribute to predicting symptom-based diagnosis of rotavirus-associated acute gastroenteritis in children, especially in resource-limited settings. Further validation of the models using a large dataset is needed for predicting pediatric diarrheic populations with optimum sensitivity and specificity.

Plasma proteome analysis of rheumatic patients reveals differences in fingerprints based on cardiovascular history: a pilot study

The risk of cardiovascular disease (CVD) in patients with rheumatoid arthritis (RA) is much higher than that in the general population. As its etiology is not fully understood, we performed a pilot study using a shotgun proteomic approach to investigate whether the plasma signature in RA patients with CVD might show an altered profile. Subjects with RA were compared to a group of RA patients with a previous cardiovascular event (CVE). The cohort consisted of an RA control group (n = 10) and a group (n = 10) of RA patients with a history of CVD. Samples were collected at least 6 months before the CVE and 3-6 months after the CVE. All subjects were matched to controls for age, sex, and medication use. Plasma depletion of the 14 most abundant proteins was followed by bottom-up shotgun proteomics analysis (LC‒MS/MS). Relative changes in protein/peptide abundance were investigated using classical statistical analyses with Perseus and XG-Boost machine learning to compare between groups and to determine the relative importance of identified proteins, respectively. Principal component analysis (PCA) revealed no difference in the global protein and peptide signatures between the control and CVE groups. A total of 150, 239 and 74 protein ID's showed in comparison between Post Event vs. controls, Event vs. no Event and Pre event vs. Post Event respectively a statistically difference in relative abundance (p < 0.05). Remarkedly a total of 236 proteins ID's showed a statistical significant difference in relative abundance in the PRE-Event group compared to the control group which could also be confirmed by XGboost machine learning. Here, we demonstrated potential differences in the plasma proteome signature of rheumatic patients with cardiovascular events. Interestingly, this signature may be present prior to CVE's. However the conclusions must be drawn with caution, since this is a pilot study and further investigation with larger cohorts is warranted to identify potential risk markers that may predict the relative risk of CVEs in rheumatic diseases.

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.

Unravelling disease complexity: integrative analysis of multi-omic data in clinical research

INTRODUCTION

A holistic view on biological systems is today a reality with the application of multi-omic technologies. These technologies allow the profiling of genome, epigenome, transcriptome, proteome, metabolome as well as newly emerging 'omes.' While the multiple layers of data accumulate, their integration and reconciliation in a single system map is a cumbersome exercise that faces many challenges. Application to human health and disease requires large sample sizes, robust methodologies and high-quality standards.

AREAS COVERED

We review the different methods used to integrate multi-omics, as recent ones including artificial intelligence. With proteomics as an anchor technology, we then present selected applications of its data combination with other omics layers in clinical research, mainly covering literature from the last five years in the Scopus and/or PubMed databases.

EXPERT OPINION

Multi-omics is powerful to comprehensively type molecular layers and link them to phenotype. Yet, technologies and data are very diverse and still strategies and methodologies to properly integrate these modalities are needed.

Omics approaches: Role in acute myeloid leukemia biomarker discovery and therapy

Acute myeloid leukemia (AML) is the most common acute leukemia in adults and has the highest fatality rate. Patients aged 65 and above exhibit the poorest prognosis, with a mere 30 % survival rate within one year. One important issue in optimizing outcomes for AML patients is their limited ability to predict responses to specific therapies, response duration, and likelihood of relapse. Despite rigorous therapeutic interventions, a significant proportion of patients experience relapse. Consequently, there is a pressing need to introduce new targets for therapy. Sequencing and biotechnology have come a long way in the last ten years. This has made it easier for many omics technologies, like genomics, transcriptomics, proteomics, and metabolomics, to study molecular mechanisms of AML. An integrative approach is necessary to understand a complex biological process fully and offers an important opportunity to understand the information underlying diseases. In this review, we studied papers published between 2010 and 2024 employing omics approaches encompassing diagnosis, prognosis, and risk stratification of AML. Finally, we discuss prospects and challenges in applying -omics technologies to the discovery of novel biomarkers and therapy targets. Our review may be helpful for omics researchers who want to study AML from different molecular aspects.

The Application of artificial intelligence in periprosthetic joint infection

Periprosthetic joint infection (PJI) represents one of the most devastating complications following total joint arthroplasty, often necessitating additional surgeries and antimicrobial therapy, and potentially leading to disability. This significantly increases the burden on both patients and the healthcare system. Given the considerable suffering caused by PJI, its prevention and treatment have long been focal points of concern. However, challenges remain in accurately assessing individual risk, preventing the infection, improving diagnostic methods, and enhancing treatment outcomes. The development and application of artificial intelligence (AI) technologies have introduced new, more efficient possibilities for the management of many diseases. In this article, we review the applications of AI in the prevention, diagnosis, and treatment of PJI, and explore how AI methodologies might achieve individualized risk prediction, improve diagnostic algorithms through biomarkers and pathology, and enhance the efficacy of antimicrobial and surgical treatments. We hope that through multimodal AI applications, intelligent management of PJI can be realized in the future.

Modified Decision Tree with Custom Splitting Logic Improves Generalization across Multiple Brains' Proteomic Data Sets of Alzheimer's Disease

Many factors negatively affect a generalization of the findings in discovery proteomics. They include differentiation between patient cohorts, a variety of experimental conditions, etc. We presented a machine-learning-based workflow for proteomics data analysis, aiming at improving generalizability across multiple data sets. In particular, we customized the decision tree model by introducing a new parameter, min_groups_leaf, which regulates the presence of the samples from each data set inside the model's leaves. Further, we analyzed a trend for the feature importance's curve as a function of the novel parameter for feature selection to a list of proteins with significantly improved generalization. The developed workflow was tested using five proteomic data sets obtained for post-mortem human brain samples of Alzheimer's disease. The data sets consisted of 535 LC-MS/MS acquisition files. The results were obtained for two different pipelines of data processing: (1) MS1-only processing based on DirectMS1 search engine and (2) a standard MS/MS-based one. Using the developed workflow, we found seven proteins with expression patterns that were unique for asymptomatic Alzheimer patients. Two of them, Serotransferrin TRFE and DNA repair nuclease APEX1, may be potentially important for explaining the lack of dementia in patients with the presence of neuritic plaques and neurofibrillary tangles.

Artificial intelligence in in-vitro fertilization (IVF): A new era of precision and personalization in fertility treatments

In-vitro fertilization (IVF) has been a transformative advancement in assisted reproductive technology. However, success rates remain suboptimal, with only about one-third of cycles resulting in pregnancy and fewer leading to live births. This narrative review explores the potential of artificial intelligence (AI), machine learning (ML), and deep learning (DL) to enhance various stages of the IVF process. Personalization of ovarian stimulation protocols, gamete selection, and embryo annotation and selection are critical areas where AI may benefit significantly. AI-driven tools can analyze vast datasets to predict optimal stimulation protocols, potentially improving oocyte quality and fertilization rates. In sperm and oocyte quality assessment, AI can offer precise, objective analyses, reducing subjectivity and standardizing evaluations. In embryo selection, AI can analyze time-lapse imaging and morphological data to support the prediction of embryo viability, potentially aiding implantation outcomes. However, the role of AI in improving clinical outcomes remains to be confirmed by large-scale, well-designed clinical trials. Additionally, AI has the potential to enhance quality control and workflow optimization within IVF laboratories by continuously monitoring key performance indicators (KPIs) and facilitating efficient resource utilization. Ethical considerations, including data privacy, algorithmic bias, and fairness, are paramount for the responsible implementation of AI in IVF. Future research should prioritize validating AI tools in diverse clinical settings, ensuring their applicability and reliability. Collaboration among AI experts, clinicians, and embryologists is essential to drive innovation and improve outcomes in assisted reproduction. AI's integration into IVF holds promise for advancing patient care, but its clinical potential requires careful evaluation and ongoing refinement.

Integrative analysis of RNA-Seq data and machine learning approaches to identify Biomarkers for Rhizoctonia solani resistance in sugar beet

Rhizoctonia solani is a significant pathogen that causes crown and root rot in sugar beet (Beta vulgaris), leading to considerable yield losses. To develop resilient cultivars, it is crucial to understand the molecular mechanisms underlying both resistance and susceptibility. In this study, we employed RNA-Seq analysis alongside machine learning techniques to identify key biomarkers associated with resistance to R. solani. We ranked differentially expressed genes (DEGs) using feature-weighting algorithms, such as Relief and kernel-based methods, to model expression patterns between sensitive and tolerant cultivars. Our integrative approach identified several candidate genes, including Bv5g001004 (encoding Ethylene-responsive transcription factor 1A), Bv8g000842 (encoding 5'-adenylylsulfate reductase 1), and Bv7g000949 (encoding Heavy metal-associated isoprenylated plant protein 5). These genes are involved in stress signal transduction, sulfur metabolism, and disease resistance pathways. Graphical visualizations of the Random Forest and Decision Tree models illustrated the decision-making processes and gene interactions, enhancing our understanding of the complex relationships between sensitive and tolerant genotypes. This study demonstrates the effectiveness of integrating RNA-Seq and machine learning techniques for biomarker discovery and highlights potential targets for developing R. solani-resistant sugar beet cultivars. The findings provide a robust framework for improving crop enhancement strategies and contribute to sustainable agricultural practices by increasing stress resilience in economically important crops.

Exploring AI-Driven Machine Learning Approaches for Optimal Classification of Peri-Implantitis Based on Oral Microbiome Data: A Feasibility Study

Background: Machine learning (ML) techniques have been recently proposed as a solution for aiding in the prevention and diagnosis of microbiome-related diseases. Here, we applied auto-ML approaches on real-case metagenomic datasets from saliva and subgingival peri-implant biofilm microbiomes to explore a wide range of ML algorithms to benchmark best-performing algorithms for predicting peri-implantitis (PI). Methods: A total of 100 metagenomes from the NCBI SRA database (PRJNA1163384) were used in this study to construct biofilm and saliva metagenomes datasets. Two AI-driven auto-ML approaches were used on constructed datasets to generate 100 ML-based models for the prediction of PI. These were compared with statistically significant single-microorganism-based models. Results: Several ML algorithms were pinpointed as suitable bespoke predictive approaches to apply to metagenomic data, outperforming the single-microorganism-based classification. Auto-ML approaches rendered high-performing models with Receiver Operating Characteristic-Area Under the Curve, sensitivities and specificities between 80% and 100%. Among these, classifiers based on ML-driven scoring of combinations of 2-4 microorganisms presented top-ranked performances and can be suitable for clinical application. Moreover, models generated based on the saliva microbiome showed higher predictive performance than those from the biofilm microbiome. Conclusions: This feasibility study bridges complex AI research with practical dental applications by benchmarking ML algorithms and exploring oral microbiomes as foundations for developing intuitive, cost-effective, and clinically relevant diagnostic platforms.

Integrated View of Baseline Protein Expression in Human Tissues Using Public Data Independent Acquisition Data Sets

The PRIDE database is the largest public data repository of mass spectrometry-based proteomics data and currently stores more than 40,000 data sets covering a wide range of organisms, experimental techniques, and biological conditions. During the past few years, PRIDE has seen a significant increase in the amount of submitted data-independent acquisition (DIA) proteomics data sets. This provides an excellent opportunity for large-scale data reanalysis and reuse. We have reanalyzed 15 public label-free DIA data sets across various healthy human tissues to provide a state-of-the-art view of the human proteome in baseline conditions (without any perturbations). We computed baseline protein abundances and compared them across various tissues, samples, and data sets. Our second aim was to compare protein abundances obtained here from the results of previous analyses using human baseline data-dependent acquisition (DDA) data sets. We observed a good correlation across some tissues, especially in the liver and colon, but weak correlations were found in others, such as the lung and pancreas. The reanalyzed results including protein abundance values and curated metadata are made available to view and download from the resource Expression Atlas.

Serum Biomarkers in Transthyretin Amyloidosis: An Overview of Neurofilaments, Cardiac, Renal, and Gastrointestinal Involvement

Hereditary transthyretin amyloidosis (ATTRv, v for variant) is a genetic disorder characterized by the deposition of misfolded transthyretin (TTR) protein in tissues, resulting in progressive dysfunction of multiple organs, including the nervous system, heart, kidneys, and gastrointestinal (GI) tract. Noninvasive serum biomarkers have become key tools for diagnosing and monitoring ATTRv. This review examines the role of available biomarkers for neurological, cardiac, renal, gastrointestinal, and multisystemic involvement in ATTRv. A thorough understanding of these biomarkers is essential for effective disease management and therapeutic monitoring.

Machine learning discovery of novel antihypertensive peptides from highland barley protein inhibiting angiotensin I-converting enzyme (ACE)

Hypertension is a major global health concern, and there is a need for new antihypertensive agents derived from natural sources. This study aims to identify novel angiotensin I-converting enzyme (ACE) inhibitors from bioactive peptides derived from food sources, particularly highland barley proteins, addressing the gap in effective natural ACE inhibitors. This research employs a machine learning-based pipeline combined with peptidomics to screen for ACE-inhibitory peptides, Gradient Boosted Decision Trees (GBDT) with the best performance among four tested models was used to predict the ACE-inhibitory capacity of peptides derived from papain-hydrolyzed highland barley protein. The selected peptides were validated through computer simulations and in vitro experiments, with FPRPFL identified as the most potent ACE-inhibitor (IC50 = 1.18 μM). Enzyme inhibition kinetics and digestion stability simulations were used to investigate its inhibition mode and stability. The binding mode and mechanism of action of FPRPFL with ACE were further analyzed using circular dichroism, molecular docking and molecular dynamics simulations. Network pharmacology revealed its multi-target and multi-pathway antihypertensive properties. The integration of machine learning and in vitro experiments enables accurate bioactive peptides identification and comprehensive their functionality analysis, establishing a valuable pipeline for elucidating peptide mechanisms and laying a solid foundation for industrial-scale production of natural ACE-inhibitors.

Exploring omics signature in the cardiovascular response to semaglutide: Mechanistic insights and clinical implications

BACKGROUND

Semaglutide, a glucagon-like peptide-1 (GLP-1) receptor agonist, is a widely used drug for the treatment of type 2 diabetes that offers significant cardiovascular benefits.

RESULTS

This review systematically examines the proteomic and metabolomic indicators associated with the cardiovascular effects of semaglutide. A comprehensive literature search was conducted to identify relevant studies. The review utilizes advanced analytical technologies such as mass spectrometry and nuclear magnetic resonance (NMR) to investigate the molecular mechanisms underlying the effects of semaglutide on insulin secretion, weight control, anti-inflammatory activities and lipid metabolism. These "omics" approaches offer critical insights into metabolic changes associated with cardiovascular health. However, challenges remain such as individual variability in expression, the need for comprehensive validation and the integration of these data with clinical parameters. These issues need to be addressed through further research to refine these indicators and increase their clinical utility.

CONCLUSION

Future integration of proteomic and metabolomic data with artificial intelligence (AI) promises to improve prediction and monitoring of cardiovascular outcomes and may enable more accurate and effective management of cardiovascular health in patients with type 2 diabetes. This review highlights the transformative potential of integrating proteomics, metabolomics and AI to advance cardiovascular medicine and improve patient outcomes.

Mass-spectrometry-based proteomics: from single cells to clinical applications

Mass-spectrometry (MS)-based proteomics has evolved into a powerful tool for comprehensively analysing biological systems. Recent technological advances have markedly increased sensitivity, enabling single-cell proteomics and spatial profiling of tissues. Simultaneously, improvements in throughput and robustness are facilitating clinical applications. In this Review, we present the latest developments in proteomics technology, including novel sample-preparation methods, advanced instrumentation and innovative data-acquisition strategies. We explore how these advances drive progress in key areas such as protein-protein interactions, post-translational modifications and structural proteomics. Integrating artificial intelligence into the proteomics workflow accelerates data analysis and biological interpretation. We discuss the application of proteomics to single-cell analysis and spatial profiling, which can provide unprecedented insights into cellular heterogeneity and tissue architecture. Finally, we examine the transition of proteomics from basic research to clinical practice, including biomarker discovery in body fluids and the promise and challenges of implementing proteomics-based diagnostics. This Review provides a broad and high-level overview of the current state of proteomics and its potential to revolutionize our understanding of biology and transform medical practice.

Aerobic capacity and muscle proteome: Insights from a mouse model

We explored the association between aerobic capacity (AC) and the skeletal muscle proteome of McArdle (n = 10) and wild-type (n = 8) mice, as models of intrinsically 'low' and 'normal' AC, respectively. AC was determined as total distance achieved in treadmill running until exhaustion. The quadriceps muscle proteome was studied using liquid chromatography with tandem mass spectrometry, with the Search Tool for the Retrieval of Interacting Genes/Proteins database used to generate protein-protein interaction (PPI) networks and enrichment analyses. AC was significantly associated (P-values ranging from 0.0002 to 0.049) with 73 (McArdle) and 61 (wild-type) proteins (r-values from -0.90 to 0.94). These proteins were connected in PPI networks that enriched biological processes involved in skeletal muscle structure/function in both groups (false discovery rate <0.05). In McArdle mice, the proteins associated with AC were involved in skeletal muscle fibre differentiation/development, lipid oxidation, mitochondrial function and calcium homeostasis, whereas in wild-type animals AC-associated proteins were related to cytoskeleton structure (intermediate filaments), cell cycle regulation and endocytic trafficking. Two proteins (WEE2, THYG) were associated with AC (negatively and positively, respectively) in both groups. Only 14 of the 132 proteins (∼11%) associated with AC in McArdle or wild-type mice were also associated with those previously reported to be modified by aerobic training in these mice, providing preliminary evidence for a large divergence in the muscle proteome signature linked to aerobic training or AC, irrespective of AC (intrinsically low or normal) levels. Our findings might help to gain insight into the molecular mechanisms underlying AC at the muscle tissue level.

Unlocking the secrets of the immunopeptidome: MHC molecules, ncRNA peptides, and vesicles in immune response

The immunopeptidome, a diverse set of peptides presented by Major Histocompatibility Complex (MHC) molecules, is a critical component of immune recognition and response. This review article delves into the mechanisms of peptide presentation by MHC molecules, particularly emphasizing the roles of ncRNA-derived peptides and extracellular vesicles (EVs) in shaping the immunopeptidome landscape. We explore established and emerging insights into MHC molecule interactions with peptides, including the dynamics of peptide loading, transport, and the influence of cellular and genetic variations. The article highlights novel research on non-coding RNA (ncRNA)-derived peptides, which challenge conventional views of antigen processing and presentation and the role of EVs in transporting these peptides, thereby modulating immune responses at remote body sites. This novel research not only challenges conventional views but also opens up new avenues for understanding immune responses. Furthermore, we discuss the implications of these mechanisms in developing therapeutic strategies, particularly for cancer immunotherapy. By conducting a comprehensive analysis of current literature and advanced methodologies in immunopeptidomics, this review aims to deepen the understanding of the complex interplay between MHC peptide presentation and the immune system, offering new perspectives on potential diagnostic and therapeutic applications. Additionally, the interactions between ncRNA-derived peptides and EVs provide a mechanism for the enhanced surface presentation of these peptides and highlight a novel pathway for their systemic distribution, potentially altering immune surveillance and therapeutic landscapes.

Developing and validating a drug recommendation system based on tumor microenvironment and drug fingerprint

Introduction

Tumor heterogeneity significantly complicates the selection of effective cancer treatments, as patient responses to drugs can vary widely. Personalized cancer therapy has emerged as a promising strategy to enhance treatment effectiveness and precision. This study aimed to develop a personalized drug recommendation model leveraging genomic profiles to optimize therapeutic outcomes.

Methods

A content-based filtering algorithm was implemented to predict drug sensitivity. Patient features were characterized by the tumor microenvironment (TME), and drug features were represented by drug fingerprints. The model was trained and validated using the Genomics of Drug Sensitivity in Cancer (GDSC) database, followed by independent validation with the Cancer Cell Line Encyclopedia (CCLE) dataset. Clinical application was assessed using The Cancer Genome Atlas (TCGA) dataset, with Best Overall Response (BOR) serving as the clinical efficacy measure. Two multilayer perceptron (MLP) models were built to predict IC50 values for 542 tumor cell lines across 18 drugs.

Results

The model exhibited high predictive accuracy, with correlation coefficients (R) of 0.914 in the training set and 0.902 in the test set. Predictions for cytotoxic drugs, including Docetaxel (R = 0.72) and Cisplatin (R = 0.71), were particularly robust, whereas predictions for targeted therapies were less accurate (R < 0.3). Validation with CCLE (MFI as the endpoint) showed strong correlations (R = 0.67). Application to TCGA data successfully predicted clinical outcomes, including a significant association with 6-month progression-free survival (PFS, P = 0.007, AUC = 0.793).

Discussion

The model demonstrates strong performance across preclinical datasets, showing its potential for real-world application in personalized cancer therapy. By bridging preclinical IC50 and clinical BOR endpoints, this approach provides a promising tool for optimizing patient-specific treatments.

Challenges and Insights in Absolute Quantification of Recombinant Therapeutic Antibodies by Mass Spectrometry: An Introductory Review

This review describes mass spectrometry (MS)-based approaches for the absolute quantification of therapeutic monoclonal antibodies (mAbs), focusing on technical challenges in sample treatment and calibration. Therapeutic mAbs are crucial for treating cancer and inflammatory, infectious, and autoimmune diseases. We trace their development from hybridoma technology and the first murine mAbs in 1975 to today's chimeric and fully human mAbs. With increasing commercial relevance, the absolute quantification of mAbs, traceable to an international standard system of units (SI units), has attracted attention from science, industry, and national metrology institutes (NMIs). Quantification of proteotypic peptides after enzymatic digestion using high-performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS) has emerged as the most viable strategy, though methods targeting intact mAbs are still being explored. We review peptide-based quantification, focusing on critical experimental steps like denaturation, reduction, alkylation, choice of digestion enzyme, and selection of signature peptides. Challenges in amino acid analysis (AAA) for quantifying pure mAbs and peptide calibrators, along with software tools for targeted MS data analysis, are also discussed. Short explanations within each chapter provide newcomers with an overview of the field's challenges. We conclude that, despite recent progress, further efforts are needed to overcome the many technical hurdles along the quantification workflow and discuss the prospects of developing standardized protocols and certified reference materials (CRMs) for this goal. We also suggest future applications of newer technologies for absolute mAb quantification.

The PRIDE database at 20 years: 2025 update

The PRoteomics IDEntifications (PRIDE) database (https://www.ebi.ac.uk/pride/) is the world's leading mass spectrometry (MS)-based proteomics data repository and one of the founding members of the ProteomeXchange consortium. This manuscript summarizes the developments in PRIDE resources and related tools for the last three years. The number of submitted datasets to PRIDE Archive (the archival component of PRIDE) has reached on average around 534 datasets per month. This has been possible thanks to continuous improvements in infrastructure such as a new file transfer protocol for very large datasets (Globus), a new data resubmission pipeline and an automatic dataset validation process. Additionally, we will highlight novel activities such as the availability of the PRIDE chatbot (based on the use of open-source Large Language Models), and our work to improve support for MS crosslinking datasets. Furthermore, we will describe how we have increased our efforts to reuse, reanalyze and disseminate high-quality proteomics data into added-value resources such as UniProt, Ensembl and Expression Atlas.

Biomarkers in lung cancer diagnosis and bronchoscopy: Current landscape and future directions

Lung cancer is the leading cause of cancer death world-wide. Along the entire timeline of lung cancer identification, diagnosis and treatment, clinicians and patients face challenges in clinical decision-making that could be aided by useful biomarkers. In this review, we discuss the development of biomarkers and qualities that are ideal in a biomarker candidate, types of biospecimens that can be utilized for biomarker development in lung cancer, and how biomarkers could be clinically useful at various points along lung cancer timeline. We then review biomarkers that have been validated and are clinically available to assist with the management of lung nodules and diagnosis of lung cancer, which includes blood-based biomarkers to assist with decision-making prior to an invasive diagnostic procedure, as well as specimens obtained during a bronchoscopy and applied in cases of an inconclusive biopsy result. Finally, we discuss challenges in biomarker application and recent publications relevant to future lung cancer biomarker development.

Microfluidic Nanoparticle Separation for Precision Medicine

A deeper understanding of disease heterogeneity highlights the urgent need for precision medicine. Microfluidics, with its unique advantages, such as high adjustability, diverse material selection, low cost, high processing efficiency, and minimal sample requirements, presents an ideal platform for precision medicine applications. As nanoparticles, both of biological origin and for therapeutic purposes, become increasingly important in precision medicine, microfluidic nanoparticle separation proves particularly advantageous for handling valuable samples in personalized medicine. This technology not only enhances detection, diagnosis, monitoring, and treatment accuracy, but also reduces invasiveness in medical procedures. This review summarizes the fundamentals of microfluidic nanoparticle separation techniques for precision medicine, starting with an examination of nanoparticle properties essential for separation and the core principles that guide various microfluidic methods. It then explores passive, active, and hybrid separation techniques, detailing their principles, structures, and applications. Furthermore, the review highlights their contributions to advancements in liquid biopsy and nanomedicine. Finally, it addresses existing challenges and envisions future development spurred by emerging technologies such as advanced materials science, 3D printing, and artificial intelligence. These interdisciplinary collaborations are anticipated to propel the platformization of microfluidic separation techniques, significantly expanding their potential in precision medicine.

Post-translational modifications of proteins in cardiovascular diseases examined by proteomic approaches

Over 400 different types of post-translational modifications (PTMs) have been reported and over 200 various types of PTMs have been discovered using mass spectrometry (MS)-based proteomics. MS-based proteomics has proven to be a powerful method capable of global PTM mapping with the identification of modified proteins/peptides, the localization of PTM sites and PTM quantitation. PTMs play regulatory roles in protein functions, activities and interactions in various heart related diseases, such as ischemia/reperfusion injury, cardiomyopathy and heart failure. The recognition of PTMs that are specific to cardiovascular pathology and the clarification of the mechanisms underlying these PTMs at molecular levels are crucial for discovery of novel biomarkers and application in a clinical setting. With sensitive MS instrumentation and novel biostatistical methods for precise processing of the data, low-abundance PTMs can be successfully detected and the beneficial or unfavorable effects of specific PTMs on cardiac function can be determined. Moreover, computational proteomic strategies that can predict PTM sites based on MS data have gained an increasing interest and can contribute to characterization of PTM profiles in cardiovascular disorders. More recently, machine learning- and deep learning-based methods have been employed to predict the locations of PTMs and explore PTM crosstalk. In this review article, the types of PTMs are briefly overviewed, approaches for PTM identification/quantitation in MS-based proteomics are discussed and recently published proteomic studies on PTMs associated with cardiovascular diseases are included.

Pinpointing the integration of artificial intelligence in liver cancer immune microenvironment

Liver cancer remains one of the most formidable challenges in modern medicine, characterized by its high incidence and mortality rate. Emerging evidence underscores the critical roles of the immune microenvironment in tumor initiation, development, prognosis, and therapeutic responsiveness. However, the composition of the immune microenvironment of liver cancer (LC-IME) and its association with clinicopathological significance remain unelucidated. In this review, we present the recent developments related to the use of artificial intelligence (AI) for studying the immune microenvironment of liver cancer, focusing on the deciphering of complex high-throughput data. Additionally, we discussed the current challenges of data harmonization and algorithm interpretability for studying LC-IME.

Biobanks and biomarkers: Their current and future role in biomedical research

The importance and utility of biobanks has increased exponentially since their inception and creation. Initially used as part of translational research, they now contribute over 40% of data for all cancer research papers in the United States of America and play a crucial role in all aspects of healthcare. Multiple classification systems exist but a simplified approach is to either classify as population-based or disease-oriented entities. Whilst historically publicly funded institutions, there has been a significant increase in industry funded entities across the world which has changed the dynamic of biobanks offering new possibilities but also new challenges. Biobanks face legal questions over data sharing and intellectual property as well as ethical and sustainability questions particularly as the world attempts to move to a low-carbon economy. International collaboration is required to address some of these challenges but this in itself is fraught with complexity and difficulty. This review will examine the current utility of biobanks in the modern healthcare setting as well as the current and future challenges these vital institutions face.

Multiomics Profiling of Plasma Reveals Molecular Alterations Prior to a Diagnosis with Stroke Among Chinese Hypertension Patients

We aimed to investigate the correlation between plasma proteins and metabolites and the occurrence of future strokes using mass spectrometry and bioinformatics as well as to identify other biomarkers that could predict stroke risk in hypertensive patients. In a nested case-control study, baseline plasma samples were collected from 50 hypertensive subjects who developed stroke and 50 gender-, age- and body mass index-matched controls. Plasma untargeted metabolomics and data independent acquisition-based proteomics analysis were performed in hypertensive patients, and 19 metabolites and 111 proteins were found to be differentially expressed. Integrative analyses revealed that molecular changes in plasma indicated dysregulation of protein digestion and absorption, salivary secretion, and regulation of actin cytoskeleton, along with significant metabolic suppression. C4BPA, Caprolactam, Col15A1, and HBB were identified as predictors of stroke occurrence, and the Support Vector Machines (SVM) model was determined to be the optimal predictive model by integrating six machine-learning classification models. The SVM model showed strong performance in both the internal validation set (area under the curve [AUC]: 0.977, 95% confidence interval [CI]: 0.941-1.000) and the external independent validation set (AUC: 0.973, 95% CI: 0.921-0.999).

The Circulating Proteome─Technological Developments, Current Challenges, and Future Trends

Recent improvements in proteomics technologies have fundamentally altered our capacities to characterize human biology. There is an ever-growing interest in using these novel methods for studying the circulating proteome, as blood offers an accessible window into human health. However, every methodological innovation and analytical progress calls for reassessing our existing approaches and routines to ensure that the new data will add value to the greater biomedical research community and avoid previous errors. As representatives of HUPO's Human Plasma Proteome Project (HPPP), we present our 2024 survey of the current progress in our community, including the latest build of the Human Plasma Proteome PeptideAtlas that now comprises 4608 proteins detected in 113 data sets. We then discuss the updates of established proteomics methods, emerging technologies, and investigations of proteoforms, protein networks, extracellualr vesicles, circulating antibodies and microsamples. Finally, we provide a prospective view of using the current and emerging proteomics tools in studies of circulating proteins.

Proteome-scale recombinant standards and a robust high-speed search engine to advance cross-linking MS-based interactomics

Advancing data analysis tools for proteome-wide cross-linking mass spectrometry (XL-MS) requires ground-truth standards that mimic biological complexity. Here we develop well-controlled XL-MS standards comprising hundreds of recombinant proteins that are systematically mixed for cross-linking. We use one standard dataset to guide the development of Scout, a search engine for XL-MS with MS-cleavable cross-linkers. Using other, independent standard datasets and published datasets, we benchmark the performance of Scout and existing XL-MS software. We find that Scout offers an excellent combination of speed, sensitivity and false discovery rate control. The results illustrate how our large recombinant standard can support the development of XL-MS analysis tools and evaluation of XL-MS results.

Artificial intelligence powers regenerative medicine into predictive realm

The expanding regenerative medicine toolkit is reaching a record number of lives. There is a pressing need to enhance the precision, efficiency, and effectiveness of regenerative approaches and achieve reliable outcomes. While regenerative medicine has relied on an empiric paradigm, availability of big data along with advances in informatics and artificial intelligence offer the opportunity to inform the next generation of regenerative sciences along the discovery, translation, and application pathway. Artificial intelligence can streamline discovery and development of optimized biotherapeutics by aiding in the interpretation of readouts associated with optimal repair outcomes. In advanced biomanufacturing, artificial intelligence holds potential in ensuring quality control and assuring scalability through automated monitoring of process-critical variables mandatory for product consistency. In practice application, artificial intelligence can guide clinical trial design, patient selection, delivery strategies, and outcome assessment. As artificial intelligence transforms the regenerative horizon, caution is necessary to reduce bias, ensure generalizability, and mitigate ethical concerns with the goal of equitable access for patients and populations.

Exercise and tumor proteome: insights from a neuroblastoma model

The impact of exercise on pediatric tumor biology is essentially unknown. We explored the effects of regular exercise on tumor proteome profile (as assessed with liquid chromatography with tandem mass spectrometry) in a mouse model of one of the most aggressive childhood malignancies, high-risk neuroblastoma (HR-NB). Tumor samples of 14 male mice (aged 6-8 wk) that were randomly allocated into an exercise (5-wk combined aerobic and resistance training) or nonexercise control group (6 and 8 mice/group, respectively) were analyzed. The Search Tool for the Retrieval of Interacting Genes/Proteins database was used to generate a protein-protein interaction (PPI) network and enrichment analyses. The Systems Biology Triangle (SBT) algorithm was applied for analyses at the functional category level. Tumors of exercised mice showed a higher and lower abundance of 101 and 150 proteins, respectively, than controls [false discovery rate (FDR) < 0.05]. These proteins were enriched in metabolic pathways, amino acid metabolism, regulation of hormone levels, and peroxisome proliferator-activated receptor signaling (FDR < 0.05). The SBT algorithm indicated that 184 and 126 categories showed a lower and higher abundance, respectively, in the tumors of exercised mice (FDR < 0.01). Categories with lower abundance were involved in energy production, whereas those with higher abundance were related to transcription/translation, apoptosis, and tumor suppression. Regular exercise altered the abundance of hundreds of intratumoral proteins and molecular pathways, particularly those involved in energy metabolism, apoptosis, and tumor suppression. These findings provide preliminary evidence of the molecular mechanisms underlying the potential effects of exercise in HR-NB.NEW & NOTEWORTHY We used liquid chromatography with tandem mass spectrometry to explore the impact of a 5-wk exercise intervention on the tumor proteome profile in a mouse model of one of the most aggressive childhood malignancies, high-risk neuroblastoma. Exercise altered the abundance of hundreds of proteins and pathways, particularly those involved in energy metabolism and tumor suppression. These molecular changes could mediate, at least partly, the potential antitumorigenic effects of exercise.

Bridging the Gap From Proteomics Technology to Clinical Application: Highlights From the 68th Benzon Foundation Symposium

The 68th Benzon Foundation Symposium brought together leading experts to explore the integration of mass spectrometry-based proteomics and artificial intelligence to revolutionize personalized medicine. This report highlights key discussions on recent technological advances in mass spectrometry-based proteomics, including improvements in sensitivity, throughput, and data analysis. Particular emphasis was placed on plasma proteomics and its potential for biomarker discovery across various diseases. The symposium addressed critical challenges in translating proteomic discoveries to clinical practice, including standardization, regulatory considerations, and the need for robust "business cases" to motivate adoption. Promising applications were presented in areas such as cancer diagnostics, neurodegenerative diseases, and cardiovascular health. The integration of proteomics with other omics technologies and imaging methods was explored, showcasing the power of multimodal approaches in understanding complex biological systems. Artificial intelligence emerged as a crucial tool for the acquisition of large-scale proteomic datasets, extracting meaningful insights, and enhancing clinical decision-making. By fostering dialog between academic researchers, industry leaders in proteomics technology, and clinicians, the symposium illuminated potential pathways for proteomics to transform personalized medicine, advancing the cause of more precise diagnostics and targeted therapies.

π-HuB: the proteomic navigator of the human body

The human body contains trillions of cells, classified into specific cell types, with diverse morphologies and functions. In addition, cells of the same type can assume different states within an individual's body during their lifetime. Understanding the complexities of the proteome in the context of a human organism and its many potential states is a necessary requirement to understanding human biology, but these complexities can neither be predicted from the genome, nor have they been systematically measurable with available technologies. Recent advances in proteomic technology and computational sciences now provide opportunities to investigate the intricate biology of the human body at unprecedented resolution and scale. Here we introduce a big-science endeavour called π-HuB (proteomic navigator of the human body). The aim of the π-HuB project is to (1) generate and harness multimodality proteomic datasets to enhance our understanding of human biology; (2) facilitate disease risk assessment and diagnosis; (3) uncover new drug targets; (4) optimize appropriate therapeutic strategies; and (5) enable intelligent healthcare, thereby ushering in a new era of proteomics-driven phronesis medicine. This ambitious mission will be implemented by an international collaborative force of multidisciplinary research teams worldwide across academic, industrial and government sectors.

Toward molecular diagnosis of major depressive disorder by plasma peptides using a deep learning approach

Major depressive disorder (MDD) is a severe psychiatric disorder that currently lacks any objective diagnostic markers. Here, we develop a deep learning approach to discover the mass spectrometric features that can discriminate MDD patients from health controls. Using plasma peptides, the neural network, termed as CMS-Net, can perform diagnosis and prediction with an accuracy of 0.9441. The sensitivity and specificity reached 0.9352 and 0.9517 respectively, and the area under the curve was enhanced to 0.9634. Using the gradient-based feature importance method to interpret crucial features, we identify 28 differential peptide sequences from 14 precursor proteins (e.g. hemoglobin, immunoglobulin, albumin, etc.). This work highlights the possibility of molecular diagnosis of MDD with the aid of chemical and computer science.

Risk factors for surgical site infection after general surgery in HIV-infected patients: a retrospective study

BACKGROUND

As the number of HIV-infected patients increased, the number of patients requiring general surgery has subsequently increased. However, impairment of immune function due to HIV infection increases the risk of postoperative surgical-site infection and significant harm to patient health. This study aimed to examine the risk factors for surgical-site infection after general surgery.

METHODS

The patients' data were from Zunyi fourth hospital medical information system. Machine learning based Boruta algorithm were used for variable screening. Univariable and multivariable logistic regression and restricted cubic spline analysis were performed to examine the relationship between significant variables and surgical-site infection.

RESULTS

A total of 125 general surgery postoperative HIV-infected patients participated in the study. Surgical-site pathogen culture identified Escherichia coli, Klebsiella pneumoniae, and mixed bacteria as the three most common pathogens causing Surgical-site infection. Univariable and multivariable logistic regression analysis to adjust for risk factors identified type III surgical incision (OR = 9.92, 95% CI = 1.28-76.75) and elevated preoperative white blood cell (WBC) count (OR = 1.30, 95% CI = 1.12-1.51) as independent risk factors for postoperative surgical-site infection, whereas CD4 + T lymphocyte count greater than 400 cells/µL was identified as a protective factor (OR = 0.23, 95% CI = 0.09-0.60) while. The restricted cubic spline analysis results directly reflected the dose-response relationship between continuous variables and postoperative surgical-site infection.

CONCLUSIONS

Type III incision and an elevated WBC count pose a higher risk of postoperative surgical-site infection. A CD4 + T lymphocyte counts greater than 400 cells/µL provided a protective effect of lower risk of surgical site infection. Preoperative serum neutrophil percentage, albumin level, red blood cell count, and serum urea level within a specific range were beneficial in reducing the risk of incisional infections. Our research provides a theoretical basis for clinical practice.

MS2Lipid: A Lipid Subclass Prediction Program Using Machine Learning and Curated Tandem Mass Spectral Data

Background: Untargeted lipidomics using collision-induced dissociation-based tandem mass spectrometry (CID-MS/MS) is essential for biological and clinical applications. However, annotation confidence still relies on manual curation by analytical chemists, despite the development of various software tools for automatic spectral processing based on rule-based fragment annotations. Methods: In this study, we present a novel machine learning model, MS2Lipid, for the prediction of known lipid subclasses from MS/MS queries, providing an orthogonal approach to existing lipidomics software programs in determining the lipid subclass of ion features. We designed a new descriptor, MCH (mode of carbon and hydrogen), to increase the specificity of lipid subclass prediction in nominal mass resolution MS data. Results: The model, trained with 6760 and 6862 manually curated MS/MS spectra for the positive and negative ion modes, respectively, classified queries into one or several of 97 lipid subclasses, achieving an accuracy of 97.4% in the test set. The program was further validated using various datasets from different instruments and curators, with the average accuracy exceeding 87.2%. Using an integrated approach with molecular spectral networking, we demonstrated the utility of MS2Lipid by annotating microbiota-derived esterified bile acids, whose abundance was significantly increased in fecal samples of obese patients in a human cohort study. This suggests that the machine learning model provides an independent criterion for lipid subclass classification, enhancing the annotation of lipid metabolites within known lipid classes. Conclusions: MS2Lipid is a highly accurate machine learning model that enhances lipid subclass annotation from MS/MS data and provides an independent criterion.

Artificial intelligence with mass spectrometry-based multimodal molecular profiling methods for advancing therapeutic discovery of infectious diseases

Infectious diseases, driven by a diverse array of pathogens, can swiftly undermine public health systems. Accurate diagnosis and treatment of infectious diseases-centered around the identification of biomarkers and the elucidation of disease mechanisms-are in dire need of more versatile and practical analytical approaches. Mass spectrometry (MS)-based molecular profiling methods can deliver a wealth of information on a range of functional molecules, including nucleic acids, proteins, and metabolites. While MS-driven omics analyses can yield vast datasets, the sheer complexity and multi-dimensionality of MS data can significantly hinder the identification and characterization of functional molecules within specific biological processes and events. Artificial intelligence (AI) emerges as a potent complementary tool that can substantially enhance the processing and interpretation of MS data. AI applications in this context lead to the reduction of spurious signals, the improvement of precision, the creation of standardized analytical frameworks, and the increase of data integration efficiency. This critical review emphasizes the pivotal roles of MS based omics strategies in the discovery of biomarkers and the clarification of infectious diseases. Additionally, the review underscores the transformative ability of AI techniques to enhance the utility of MS-based molecular profiling in the field of infectious diseases by refining the quality and practicality of data produced from omics analyses. In conclusion, we advocate for a forward-looking strategy that integrates AI with MS-based molecular profiling. This integration aims to transform the analytical landscape and the performance of biological molecule characterization, potentially down to the single-cell level. Such advancements are anticipated to propel the development of AI-driven predictive models, thus improving the monitoring of diagnostics and therapeutic discovery for the ongoing challenge related to infectious diseases.

Automated multiplexed affinity-based enrichment of peptides for LC-MS/MS plasma proteomics

Plasma proteomics offers high potential for biomarker discovery, as plasma is collected through a minimally invasive procedure and constitutes the most complex human-derived proteome. However, the wide dynamic range poses a significant challenge. Here, we propose a semi-automated method based on the use of multiple single chain variable fragment antibodies, each enriching for peptides found in up to a few hundred proteins. This approach allows for the analysis of a complementary fraction compared to full proteome analysis. Proteins from pooled plasma were extracted and digested before testing the performance of 29 different antibodies with the aim of reproducibly maximizing peptide enrichment. Our results demonstrate the enrichment of 3662 peptides not detected in neat plasma or negative controls. Moreover, most antibodies were able to enrich for at least 155 peptides across different levels of abundance in plasma. To further reduce analysis time, a combination of antibodies was used in a multiplexed setting. Repeated sample analyses showed low coefficients of variation, and the method is flexible in terms of affinity binders. It does not impose drastic increases in instrument time, thus showing excellent potential for usage in large scale discovery projects.

Deep Learning and Single-Cell Sequencing Analyses Unveiling Key Molecular Features in the Progression of Carotid Atherosclerotic Plaque

Rupture of advanced carotid atherosclerotic plaques increases the risk of ischaemic stroke, which has significant global morbidity and mortality rates. However, the specific characteristics of immune cells with dysregulated function and proven biomarkers for the diagnosis of atherosclerotic plaque progression remain poorly characterised. Our study elucidated the role of immune cells and explored diagnostic biomarkers in advanced plaque progression using single-cell RNA sequencing and high-dimensional weighted gene co-expression network analysis. We identified a subcluster of monocytes with significantly increased infiltration in the advanced plaques. Based on the monocyte signature and machine-learning approaches, we accurately distinguished advanced plaques from early plaques, with an area under the curve (AUC) of 0.899 in independent external testing. Using microenvironment cell populations (MCP) counter and non-negative matrix factorisation, we determined the association between monocyte signatures and immune cell infiltration as well as the heterogeneity of the patient. Finally, we constructed a convolutional neural network deep learning model based on gene-immune correlation, which achieved an AUC of 0.933, a sensitivity of 92.3%, and a specificity of 87.5% in independent external testing for diagnosing advanced plaques. Our findings on unique subpopulations of monocytes that contribute to carotid plaque progression are crucial for the development of diagnostic tools for clinical diseases.

AI-driven innovations in Alzheimer's disease: Integrating early diagnosis, personalized treatment, and prognostic modelling

Alzheimer's disease (AD) presents a significant challenge in neurodegenerative research and clinical practice due to its complex etiology and progressive nature. The integration of artificial intelligence (AI) into the diagnosis, treatment, and prognostic modelling of AD holds promising potential to transform the landscape of dementia care. This review explores recent advancements in AI applications across various stages of AD management. In early diagnosis, AI-enhanced neuroimaging techniques, including MRI, PET, and CT scans, enable precise detection of AD biomarkers. Machine learning models analyze these images to identify patterns indicative of early cognitive decline. Additionally, AI algorithms are employed to detect genetic and proteomic biomarkers, facilitating early intervention. Cognitive and behavioral assessments have also benefited from AI, with tools that enhance the accuracy of neuropsychological tests and analyze speech and language patterns for early signs of dementia. Personalized treatment strategies have been revolutionized by AI-driven approaches. In drug discovery, virtual screening and drug repurposing, guided by predictive modelling, accelerate the identification of effective treatments. AI also aids in tailoring therapeutic interventions by predicting individual responses to treatments and monitoring patient progress, allowing for dynamic adjustment of care plans. Prognostic modelling, another critical area, utilizes AI to predict disease progression through longitudinal data analysis and risk prediction models. The integration of multi-modal data, combining clinical, genetic, and imaging information, enhances the accuracy of these predictions. Deep learning techniques are particularly effective in fusing diverse data types to uncover new insights into disease mechanisms and progression. Despite these advancements, challenges remain, including ethical considerations, data privacy, and the need for seamless integration of AI tools into clinical workflows. This review underscores the transformative potential of AI in AD management while highlighting areas for future research and development. By leveraging AI, the healthcare community can improve early diagnosis, personalize treatments, and predict disease outcomes more accurately, ultimately enhancing the quality of life for individuals with AD.

Unveiling Tumorigenesis Mechanisms and Drug Therapy in Neuroblastoma by Mass Spectrometry Based Proteomics

Neuroblastoma (NB) is the most common type of extracranial solid tumors in children. Despite the advancements in treatment strategies over the past years, the overall survival rate in patients within the high-risk NB group remains less than 50%. Therefore, new treatment options are urgently needed for this group of patients. Compared with genomic aberrations, proteomic alterations are more dynamic and complex, as well as more directly related to pathological phenotypes and external perturbations such as environmental changes and drug treatments. This review focuses on specific examples of proteomics application in various fundamental aspects of NB research, including tumorigenesis, drug treatment, drug resistance, and highlights potential protein signatures and related signaling pathways with translational values for clinical practice. Moreover, emerging cutting-edge proteomic techniques, such as single cell and spatial proteomics, as well as mass spectrometry imaging, are discussed for their potentials to probe intratumor heterogeneity of NB.

AI predictive modeling of survival outcomes for renal cancer patients undergoing targeted therapy

Renal clear cell cancer (RCC) is a complex disease that is challenging to predict patient outcomes. Despite improvements with targeted therapy, personalized treatment planning is still needed. Artificial intelligence (AI) can help address this challenge by developing predictive models that accurately forecast patient survival periods. With AI-powered decision support, clinicians can provide patients with tailored treatment plans, enhancing treatment efficacy and quality of life. The study analyzed 267 patients with renal clear cell carcinoma, focusing on 26 who received targeted drug therapy. The data was refined by excluding 8 patients without enhanced CT scans. The research team categorized patients into two groups based on their expected lifespan: Group 1 (over 3 years) and Group 2 (under 3 years). The UPerNet algorithm was used to extract features from CT tumor markers, validating their effectiveness. These features were then used to develop an AI-based predictive model trained on the dataset. The developed AI model demonstrated remarkable accuracy, achieving a rate of 93.66% in Group 1 and 94.14% in Group 2. In conclusion, our study demonstrates the potential of AI technology in predicting the survival time of RCC patients undergoing targeted drug therapy. The established prediction model exhibits high predictive accuracy and stability, serving as a valuable tool for clinicians to facilitate the development of more personalized treatment plans for patients. This study highlights the importance of integrating AI technology in clinical decision-making, enabling patients to receive more effective and targeted treatment plans that enhance their overall quality of life.

Advancement in Multi-omics approaches for Uterine Sarcoma

Uterine sarcoma (US) is a rare malignant tumor that has various pathological types and high heterogeneity in the female reproductive system. Its subtle early symptoms, frequent recurrence, and resistance to radiation and chemotherapy make the prognosis for US patients very poor. Therefore, understanding the molecular mechanisms underlying tumorigenesis and progression is essential for an accurate diagnosis and targeted therapy to improve patient outcomes. Recent advancements in high-throughput molecular sequencing have allowed for a deeper understanding of diseases through multi-omics technologies. In this review, the latest progress and future potential of multi-omics technologies in US research is examined, and their roles in biomarker discovery and their application in the precise diagnosis and treatment of US are highlighted.