Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19.

Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929 patients. Segtnan™ is available as a mobile application entailing an AI-integrated personalized risk assessment approach with a novel data-driven equation for pooling of biological samples. The AI was selected from a comparison between 15 machine learning classifiers (highest accuracy = 80.14%) and a feed-forward neural network with an accuracy of 81.38% in predicting the rRT-PCR test results based on a designed survey with minimal clinical questions. Furthermore, we derived a novel pool-size equation from the pooling data of 54 published original studies. The results demonstrated testing capacity increase of 750%, 60%, and 5% at prevalence rates of 0.05%, 22%, and 50%, respectively. Compared to Dorfman's method, our novel equation saved more tests significantly at high prevalence, i.e., 28% (p = 0.006), 40% (p = 0.00001), and 66% (p = 0.02). Lastly, we illustrated the feasibility of the Segtnan™ usage in clinically complex settings like emergency and psychiatric departments.

Landscape analysis of available European data sources amenable for machine learning and recommendations on usability for rare diseases screening.

BACKGROUND: Patient registries and databases are essential tools for advancing clinical research in the area of rare diseases, as well as for enhancing patient care and healthcare planning. The primary aim of this study is a landscape analysis of available European data sources amenable to machine learning (ML) and their usability for Rare Diseases screening, in terms of findable, accessible, interoperable, reusable(FAIR), legal, and business considerations. Second, recommendations will be proposed to provide a better understanding of the health data ecosystem. METHODS: In the period of March 2022 to December 2022, a cross-sectional study using a semi-structured questionnaire was conducted among potential respondents, identified as main contact person of a health-related databases. The design of the self-completed questionnaire survey instrument was based on information drawn from relevant scientific publications, quantitative and qualitative research, and scoping review on challenges in mapping European rare disease (RD) databases. To determine database characteristics associated with the adherence to the FAIR principles, legal and business aspects of database management Bayesian models were fitted. RESULTS: In total, 330 unique replies were processed and analyzed, reflecting the same number of distinct databases (no duplicates included). In terms of geographical scope, we observed 24.2% (n = 80) national, 10.0% (n = 33) regional, 8.8% (n = 29) European, and 5.5% (n = 18) international registries coordinated in Europe. Over 80.0% (n = 269) of the databases were still active, with approximately 60.0% (n = 191) established after the year 2000 and 71.0% last collected new data in 2022. Regarding their geographical scope, European registries were associated with the highest overall FAIR adherence, while registries with regional and "other" geographical scope were ranked at the bottom of the list with the lowest proportion. Responders' willingness to share data as a contribution to the goals of the Screen4Care project was evaluated at the end of the survey. This question was completed by 108 respondents; however, only 18 of them (16.7%) expressed a direct willingness to contribute to the project by sharing their databases. Among them, an equal split between pro-bono and paid services was observed. CONCLUSIONS: The most important results of our study demonstrate not enough sufficient FAIR principles adherence and low willingness of the EU health databases to share patient information, combined with some legislation incapacities, resulting in barriers to the secondary use of data.

nanoBERT: a deep learning model for gene agnostic navigation of the nanobody mutational space.

Motivation: Nanobodies are a subclass of immunoglobulins, whose binding site consists of only one peptide chain, bestowing favorable biophysical properties. Recently, the first nanobody therapy was approved, paving the way for further clinical applications of this antibody format. Further development of nanobody-based therapeutics could be streamlined by computational methods. One of such methods is infilling-positional prediction of biologically feasible mutations in nanobodies. Being able to identify possible positional substitutions based on sequence context, facilitates functional design of such molecules. Results: Here we present nanoBERT, a nanobody-specific transformer to predict amino acids in a given position in a query sequence. We demonstrate the need to develop such machine-learning based protocol as opposed to gene-specific positional statistics since appropriate genetic reference is not available. We benchmark nanoBERT with respect to human-based language models and ESM-2, demonstrating the benefit for domain-specific language models. We also demonstrate the benefit of employing nanobody-specific predictions for fine-tuning on experimentally measured thermostability dataset. We hope that nanoBERT will help engineers in a range of predictive tasks for designing therapeutic nanobodies. Availability and implementation: https://huggingface.co/NaturalAntibody/.

Single-Cell Multi-Omics Map of Cell Type-Specific Mechanistic Drivers of Multiple Sclerosis Lesions.

BACKGROUND AND OBJECTIVES: In progressive multiple sclerosis (MS), compartmentalized inflammation plays a pivotal role in the complex pathology of tissue damage. The interplay between epigenetic regulation, transcriptional modifications, and location-specific alterations within white matter (WM) lesions at the single-cell level remains underexplored. METHODS: We examined intracellular and intercellular pathways in the MS brain WM using a novel dataset obtained by integrated single-cell multi-omics techniques from 3 active lesions, 3 chronic active lesions, 3 remyelinating lesions, and 3 control WM of 6 patients with progressive MS and 3 non-neurologic controls. Single-nucleus RNA-seq and ATAC-seq were combined and additionally enriched with newly conducted spatial transcriptomics from 1 chronic active lesion. Functional gene modules were then validated in our previously published bulk tissue transcriptome data obtained from 73 WM lesions of patients with progressive MS and 25 WM of non-neurologic disease controls. RESULTS: Our analysis uncovered an MS-specific oligodendrocyte genetic signature influenced by the KLF/SP gene family. This modulation has potential associations with the autocrine iron uptake signaling observed in transcripts of transferrin and its receptor LRP2. In addition, an inflammatory profile emerged within these oligodendrocytes. We observed unique cellular endophenotypes both at the periphery and within the chronic active lesion. These include a distinct metabolic astrocyte phenotype, the importance of FGF signaling among astrocytes and neurons, and a notable enrichment of mitochondrial genes at the lesion edge populated predominantly by astrocytes. Our study also identified B-cell coexpression networks indicating different functional B-cell subsets with differential location and specific tendencies toward certain lesion types. DISCUSSION: The use of single-cell multi-omics has offered a detailed perspective into the cellular dynamics and interactions in MS. These nuanced findings might pave the way for deeper insights into lesion pathogenesis in progressive MS.

Monitoring performance of clinical artificial intelligence: a scoping review protocol.

OBJECTIVE: The objective of this scoping review is to describe the scope and nature of research on the monitoring of clinical artificial intelligence (AI) systems. The review will identify the various methodologies used to monitor clinical AI, while also mapping the factors that influence the selection of monitoring approaches. INTRODUCTION: AI is being used in clinical decision-making at an increasing rate. While much attention has been directed toward the development and validation of AI for clinical applications, the practical implementation aspects, notably the establishment of rational monitoring/quality assurance systems, has received comparatively limited scientific interest. Given the scarcity of evidence and the heterogeneity of methodologies used in this domain, there is a compelling rationale for conducting a scoping review on this subject. INCLUSION CRITERIA: This scoping review will include any publications that describe systematic, continuous, or repeated initiatives that evaluate or predict clinical performance of AI models with direct implications for the management of patients in any segment of the health care system. METHODS: Publications will be identified through searches of the MEDLINE (Ovid), Embase (Ovid), and Scopus databases. Additionally, backward and forward citation searches, as well as a thorough investigation of gray literature, will be conducted. Title and abstract screening, full-text evaluation, and data extraction will be performed by 2 or more independent reviewers. Data will be extracted using a tool developed by the authors. The results will be presented graphically and narratively. REVIEW REGISTRATION: Open Science Framework https://osf.io/afkrn.

Analytical Performance Specifications for Input Variables: Investigation of the Model of End-Stage Liver Disease.

BACKGROUND: Artificial intelligence models constitute specific uses of analysis results and, therefore, necessitate evaluation of analytical performance specifications (APS) for this context specifically. The Model of End-stage Liver Disease (MELD) is a clinical prediction model based on measurements of bilirubin, creatinine, and the international normalized ratio (INR). This study evaluates the propagation of error through the MELD, to inform choice of APS for the MELD input variables. METHODS: A total of 6093 consecutive MELD scores and underlying analysis results were retrospectively collected. "Desirable analytical variation" based on biological variation as well as current local analytical variation was simulated onto the data set as well as onto a constructed data set, representing a worst-case scenario. Resulting changes in MELD score and risk classification were calculated. RESULTS: Biological variation-based APS in the worst-case scenario resulted in 3.26% of scores changing by ≥1 MELD point. In the patient-derived data set, the same variation resulted in 0.92% of samples changing by ≥1 MELD point, and 5.5% of samples changing risk category. Local analytical performance resulted in lower reclassification rates. CONCLUSIONS: Error propagation through MELD is complex and includes population-dependent mechanisms. Biological variation-derived APS were acceptable for all uses of the MELD score. Other combinations of APS can yield equally acceptable results. This analysis exemplifies how error propagation through artificial intelligence models can become highly complex. This complexity will necessitate that both model suppliers and clinical laboratories address analytical performance specifications for the specific use case, as these may differ from performance specifications for traditional use of the analyses.

Dynamics of inflammation-associated plasma proteins following faecal microbiota transplantation in patients with psoriatic arthritis and healthy controls: exploratory findings from the FLORA trial.

OBJECTIVES: The gut microbiota can mediate both pro and anti-inflammatory responses. In patients with psoriatic arthritis (PsA), we investigated the impact of faecal microbiota transplantation (FMT), relative to sham transplantation, on 92 inflammation-associated plasma proteins. METHODS: This study relates to the FLORA trial cohort, where 31 patients with moderate-to-high peripheral PsA disease activity, despite at least 3 months of methotrexate treatment, were included in a 26-week, double-blind, randomised, sham-controlled trial. Participants were allocated to receive either one gastroscopic-guided healthy donor FMT (n=15) or sham (n=16). Patient plasma samples were collected at baseline, week 4, 12 and 26 while samples from 31 age-matched and sex-matched healthy controls (HC) were collected at baseline. Samples were analysed using proximity extension assay technology (Olink Target-96 Inflammation panel). RESULTS: Levels of 26 proteins differed significantly between PsA and HC pre-FMT (adjusted p<0.05), of which 10 proteins were elevated in PsA: IL-6, CCL20, CCL19, CDCP1, FGF-21, HGF, interferon-γ (IFN-γ), IL-18R1, monocyte chemotactic protein 3, and IL-2. In the FMT group, levels of 12 proteins changed significantly across all timepoints (tumour necrosis factor (TNF), CDCP1, IFN-γ, TWEAK, signalling lymphocytic activation molecule (SLAMF1), CD8A, CD5, Flt3L, CCL25, FGF-23, CD6, caspase-8). Significant differences in protein levels between FMT and sham-treated patients were observed for TNF (p=0.002), IFN-γ (p=0.011), stem cell factor (p=0.024), matrix metalloproteinase-1 (p=0.038), and SLAMF1 (p=0.042). FMT had the largest positive effect on IFN-γ, Axin-1 and CCL25 and the largest negative effect on CCL19 and IL-6. CONCLUSIONS: Patients with active PsA have a distinct immunological plasma protein signature compared with HC pre-FMT. FMT affects several of these disease markers, including sustained elevation of IFN-γ. TRIAL REGISTRATION NUMBER: NCT03058900.

Automated quantification of vacuole fusion and lipophagy in Saccharomyces cerevisiae from fluorescence and cryo-soft X-ray microscopy data using deep learning.

During starvation in the yeast Saccharomyces cerevisiae vacuolar vesicles fuse and lipid droplets (LDs) can become internalized into the vacuole in an autophagic process named lipophagy. There is a lack of tools to quantitatively assess starvation-induced vacuole fusion and lipophagy in intact cells with high resolution and throughput. Here, we combine soft X-ray tomography (SXT) with fluorescence microscopy and use a deep-learning computational approach to visualize and quantify these processes in yeast. We focus on yeast homologs of mammalian NPC1 (NPC intracellular cholesterol transporter 1; Ncr1 in yeast) and NPC2 proteins, whose dysfunction leads to Niemann Pick type C (NPC) disease in humans. We developed a convolutional neural network (CNN) model which classifies fully fused versus partially fused vacuoles based on fluorescence images of stained cells. This CNN, named Deep Yeast Fusion Network (DYFNet), revealed that cells lacking Ncr1 (ncr1∆ cells) or Npc2 (npc2∆ cells) have a reduced capacity for vacuole fusion. Using a second CNN model, we implemented a pipeline named LipoSeg to perform automated instance segmentation of LDs and vacuoles from high-resolution reconstructions of X-ray tomograms. From that, we obtained 3D renderings of LDs inside and outside of the vacuole in a fully automated manner and additionally measured droplet volume, number, and distribution. We find that ncr1∆ and npc2∆ cells could ingest LDs into vacuoles normally but showed compromised degradation of LDs and accumulation of lipid vesicles inside vacuoles. Our new method is versatile and allows for analysis of vacuole fusion, droplet size and lipophagy in intact cells.Abbreviations: BODIPY493/503: 4,4-difluoro-1,3,5,7,8-pentamethyl-4-bora-3a,4a-diaza-s-Indacene; BPS: bathophenanthrolinedisulfonic acid disodium salt hydrate; CNN: convolutional neural network; DHE; dehydroergosterol; npc2∆, yeast deficient in Npc2; DSC, Dice similarity coefficient; EM, electron microscopy; EVs, extracellular vesicles; FIB-SEM, focused ion beam milling-scanning electron microscopy; FM 4-64, N-(3-triethylammoniumpropyl)-4-(6-[4-{diethylamino} phenyl] hexatrienyl)-pyridinium dibromide; LDs, lipid droplets; Ncr1, yeast homolog of human NPC1 protein; ncr1∆, yeast deficient in Ncr1; NPC, Niemann Pick type C; NPC2, Niemann Pick type C homolog; OD600, optical density at 600 nm; ReLU, rectifier linear unit; PPV, positive predictive value; NPV, negative predictive value; MCC, Matthews correlation coefficient; SXT, soft X-ray tomography; UV, ultraviolet; YPD, yeast extract peptone dextrose.

The FeatureCloud Platform for Federated Learning in Biomedicine: Unified Approach.

BACKGROUND: Machine learning and artificial intelligence have shown promising results in many areas and are driven by the increasing amount of available data. However, these data are often distributed across different institutions and cannot be easily shared owing to strict privacy regulations. Federated learning (FL) allows the training of distributed machine learning models without sharing sensitive data. In addition, the implementation is time-consuming and requires advanced programming skills and complex technical infrastructures. OBJECTIVE: Various tools and frameworks have been developed to simplify the development of FL algorithms and provide the necessary technical infrastructure. Although there are many high-quality frameworks, most focus only on a single application case or method. To our knowledge, there are no generic frameworks, meaning that the existing solutions are restricted to a particular type of algorithm or application field. Furthermore, most of these frameworks provide an application programming interface that needs programming knowledge. There is no collection of ready-to-use FL algorithms that are extendable and allow users (eg, researchers) without programming knowledge to apply FL. A central FL platform for both FL algorithm developers and users does not exist. This study aimed to address this gap and make FL available to everyone by developing FeatureCloud, an all-in-one platform for FL in biomedicine and beyond. METHODS: The FeatureCloud platform consists of 3 main components: a global frontend, a global backend, and a local controller. Our platform uses a Docker to separate the local acting components of the platform from the sensitive data systems. We evaluated our platform using 4 different algorithms on 5 data sets for both accuracy and runtime. RESULTS: FeatureCloud removes the complexity of distributed systems for developers and end users by providing a comprehensive platform for executing multi-institutional FL analyses and implementing FL algorithms. Through its integrated artificial intelligence store, federated algorithms can easily be published and reused by the community. To secure sensitive raw data, FeatureCloud supports privacy-enhancing technologies to secure the shared local models and assures high standards in data privacy to comply with the strict General Data Protection Regulation. Our evaluation shows that applications developed in FeatureCloud can produce highly similar results compared with centralized approaches and scale well for an increasing number of participating sites. CONCLUSIONS: FeatureCloud provides a ready-to-use platform that integrates the development and execution of FL algorithms while reducing the complexity to a minimum and removing the hurdles of federated infrastructure. Thus, we believe that it has the potential to greatly increase the accessibility of privacy-preserving and distributed data analyses in biomedicine and beyond.

Plasma levels of multiple cardiovascular- and inflammation-related proteins analysed for associations with disease activity and anti-cyclic citrullinated peptide status in active early rheumatoid arthritis.

OBJECTIVES: To compare plasma levels of 92 cardiovascular- and inflammation-related proteins (CIRPs) and to analyse for associations with anti-cyclic citrullinated peptide (anti-CCP) status and disease activity in early and treatment-naive rheumatoid arthritis (RA). METHODS: Olink CVD-III-panel was used to measure 92 CIRP plasma levels in 180 early, treatment-naive, and highly inflamed RA patients from the OPERA trial. CIRP plasma levels as well as correlation between CIRP plasma levels and RA disease activity were compared between anti-CCP groups. CIRP level-based hierarchical cluster analysis was performed in each anti-CCP group separately. RESULTS: The study included 117 anti-CCP-positive and 63 anti-CCP-negative RA patients. Among the 92 CIRPs measured, the levels of chitotriosidase-1 (CHIT1) and tyrosine-protein-phosphatase non-receptor-type substrate-1 (SHPS-1) were increased and those of metalloproteinase inhibitor-4 (TIMP-4) decreased in the anti-CCP-negative group compared to anti-CCP-positive group. The strongest associations with RA disease activity were found for interleukin-2 receptor-subunit-alpha (IL2-RA) and E-selectin levels in the anti-CCP-negative group and for C-C-motif chemokine-16 levels (CCL16) in the anti-CCP-positive group. None of the differences passed the Hochberg sequential multiplicity test, however, the CIPRs were interacting and thus the prerequisites of the Hochberg procedure were not fulfilled. CIRP level-based cluster analysis identified two patient clusters in both anti-CCP groups. Demographic and clinical characteristics were similar in the two clusters for each anti-CCP group. CONCLUSIONS: In active and early RA, the findings regarding CHIT1, SHPS-1 TIMP-4, IL2-RA, E-selectin, and CCL16 differed between the two anti-CCP groups. In addition, we identified two patient clusters that were independent of the anti-CCP status.

POCT urine dipstick versus central laboratory analyses: Diagnostic performance and logistics in the medical emergency department.

OBJECTIVES: The aim of this study was to evaluate the logistics and diagnostic performances of dipstick analyses compared to their counterpart central laboratory analyses for detection of bacteriuria, proteinuria, hyperglycemia, ketosis and hematuria. DESIGN AND METHODS: Urine dipstick results, urine culture results, flow cytometric cell counts, U-albumin-to-creatinine ratio, P-glucose and P-beta-hydroxybutyrate were retrospectively reviewed in a cohort of consecutive patients admitted to the medical emergency departments of two Danish hospitals. Sensitivity, specificity and predictive values of traditional dipstick analysis were estimated and dipstick was compared to flow cytometry for detection of significant bacteriuria using logistic regression. Turn-around-time for central laboratory analyses were assessed. RESULTS: For each comparison, 1,997 patients or more were included. Traditional dipstick analyses for proteinuria, bacteriuria and ketosis reached sensitivities of up to 90%, while sensitivity for hyperglycemia was 59%. Flow cytometry outperformed traditional dipstick analysis for detection of bacteriuria with a difference in the area under the ROC-curve of 0.07. Turn-around-times for 95% delivery of central laboratory analysis results ranged from approximately 1½ to 2 h. CONCLUSIONS: For the detection of bacteriuria and albuminuria, central laboratory analyses reach better performance than dipstick analysis while achieving acceptable turn-around-times and are thus viable alternatives to dipstick analysis. For detection of ketosis and hyperglycemia, dipstick analysis does not perform adequately, but as very short turn-around-time is often required, these conditions may be best diagnosed by point-of-care blood test rather than dipstick or central laboratory analyses. Dipstick hemoglobin analysis, flow cytometry and microscopic evaluation may serve each their distinct purposes, and thus are relevant in the emergency department.

Hypothesis of a potential BrainBiota and its relation to CNS autoimmune inflammation.

Infectious agents have been long considered to play a role in the pathogenesis of neurological diseases as part of the interaction between genetic susceptibility and the environment. The role of bacteria in CNS autoimmunity has also been highlighted by changes in the diversity of gut microbiota in patients with neurological diseases such as Parkinson's disease, Alzheimer disease and multiple sclerosis, emphasizing the role of the gut-brain axis. We discuss the hypothesis of a brain microbiota, the BrainBiota: bacteria living in symbiosis with brain cells. Existence of various bacteria in the human brain is suggested by morphological evidence, presence of bacterial proteins, metabolites, transcripts and mucosal-associated invariant T cells. Based on our data, we discuss the hypothesis that these bacteria are an integral part of brain development and immune tolerance as well as directly linked to the gut microbiome. We further suggest that changes of the BrainBiota during brain diseases may be the consequence or cause of the chronic inflammation similarly to the gut microbiota.

MoSBi: Automated signature mining for molecular stratification and subtyping.

The improving access to increasing amounts of biomedical data provides completely new chances for advanced patient stratification and disease subtyping strategies. This requires computational tools that produce uniformly robust results across highly heterogeneous molecular data. Unsupervised machine learning methodologies are able to discover de novo patterns in such data. Biclustering is especially suited by simultaneously identifying sample groups and corresponding feature sets across heterogeneous omics data. The performance of available biclustering algorithms heavily depends on individual parameterization and varies with their application. Here, we developed MoSBi (molecular signature identification using biclustering), an automated multialgorithm ensemble approach that integrates results utilizing an error model-supported similarity network. We systematically evaluated the performance of 11 available and established biclustering algorithms together with MoSBi. For this, we used transcriptomics, proteomics, and metabolomics data, as well as synthetic datasets covering various data properties. Profiting from multialgorithm integration, MoSBi identified robust group and disease-specific signatures across all scenarios, overcoming single algorithm specificities. Furthermore, we developed a scalable network-based visualization of bicluster communities that supports biological hypothesis generation. MoSBi is available as an R package and web service to make automated biclustering analysis accessible for application in molecular sample stratification.

A Systematic Review of Tissue and Single Cell Transcriptome/Proteome Studies of the Brain in Multiple Sclerosis.

Multiple sclerosis (MS) is an inflammatory demyelinating and degenerative disease of the central nervous system (CNS). Although inflammatory responses are efficiently treated, therapies for progression are scarce and suboptimal, and biomarkers to predict the disease course are insufficient. Cure or preventive measures for MS require knowledge of core pathological events at the site of the tissue damage. Novelties in systems biology have emerged and paved the way for a more fine-grained understanding of key pathological pathways within the CNS, but they have also raised questions still without answers. Here, we systemically review the power of tissue and single-cell/nucleus CNS omics and discuss major gaps of integration into the clinical practice. Systemic search identified 49 transcriptome and 11 proteome studies of the CNS from 1997 till October 2021. Pioneering molecular discoveries indicate that MS affects the whole brain and all resident cell types. Despite inconsistency of results, studies imply increase in transcripts/proteins of semaphorins, heat shock proteins, myelin proteins, apolipoproteins and HLAs. Different lesions are characterized by distinct astrocytic and microglial polarization, altered oligodendrogenesis, and changes in specific neuronal subtypes. In all white matter lesion types, CXCL12, SCD, CD163 are highly expressed, and STAT6- and TGFß-signaling are increased. In the grey matter lesions, TNF-signaling seems to drive cell death, and especially CUX2-expressing neurons may be susceptible to neurodegeneration. The vast heterogeneity at both cellular and lesional levels may underlie the clinical heterogeneity of MS, and it may be more complex than the current disease phenotyping in the clinical practice. Systems biology has not solved the mystery of MS, but it has discovered multiple molecules and networks potentially contributing to the pathogenesis. However, these results are mostly descriptive; focused functional studies of the molecular changes may open up for a better interpretation. Guidelines for acceptable quality or awareness of results from low quality data, and standardized computational and biological pipelines may help to overcome limited tissue availability and the "snap shot" problem of omics. These may help in identifying core pathological events and point in directions for focus in clinical prevention.

Variability analysis of LC-MS experimental factors and their impact on machine learning.

BACKGROUND: Machine learning (ML) technologies, especially deep learning (DL), have gained increasing attention in predictive mass spectrometry (MS) for enhancing the data-processing pipeline from raw data analysis to end-user predictions and rescoring. ML models need large-scale datasets for training and repurposing, which can be obtained from a range of public data repositories. However, applying ML to public MS datasets on larger scales is challenging, as they vary widely in terms of data acquisition methods, biological systems, and experimental designs. RESULTS: We aim to facilitate ML efforts in MS data by conducting a systematic analysis of the potential sources of variability in public MS repositories. We also examine how these factors affect ML performance and perform a comprehensive transfer learning to evaluate the benefits of current best practice methods in the field for transfer learning. CONCLUSIONS: Our findings show significantly higher levels of homogeneity within a project than between projects, which indicates that it is important to construct datasets most closely resembling future test cases, as transferability is severely limited for unseen datasets. We also found that transfer learning, although it did increase model performance, did not increase model performance compared to a non-pretrained model.

MS2AI: automated repurposing of public peptide LC-MS data for machine learning applications.

MOTIVATION: Liquid-chromatography mass-spectrometry (LC-MS) is the established standard for analyzing the proteome in biological samples by identification and quantification of thousands of proteins. Machine learning (ML) promises to considerably improve the analysis of the resulting data, however, there is yet to be any tool that mediates the path from raw data to modern ML applications. More specifically, ML applications are currently hampered by three major limitations: (i) absence of balanced training data with large sample size; (ii) unclear definition of sufficiently information-rich data representations for e.g. peptide identification; (iii) lack of benchmarking of ML methods on specific LC-MS problems. RESULTS: We created the MS2AI pipeline that automates the process of gathering vast quantities of MS data for large-scale ML applications. The software retrieves raw data from either in-house sources or from the proteomics identifications database, PRIDE. Subsequently, the raw data are stored in a standardized format amenable for ML, encompassing MS1/MS2 spectra and peptide identifications. This tool bridges the gap between MS and AI, and to this effect we also present an ML application in the form of a convolutional neural network for the identification of oxidized peptides. AVAILABILITY AND IMPLEMENTATION: An open-source implementation of the software can be found at https://gitlab.com/roettgerlab/ms2ai. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Federated horizontally partitioned principal component analysis for biomedical applications.

Motivation: Federated learning enables privacy-preserving machine learning in the medical domain because the sensitive patient data remain with the owner and only parameters are exchanged between the data holders. The federated scenario introduces specific challenges related to the decentralized nature of the data, such as batch effects and differences in study population between the sites. Here, we investigate the challenges of moving classical analysis methods to the federated domain, specifically principal component analysis (PCA), a versatile and widely used tool, often serving as an initial step in machine learning and visualization workflows. We provide implementations of different federated PCA algorithms and evaluate them regarding their accuracy for high-dimensional biological data using realistic sample distributions over multiple data sites, and their ability to preserve downstream analyses. Results: Federated subspace iteration converges to the centralized solution even for unfavorable data distributions, while approximate methods introduce error. Larger sample sizes at the study sites lead to better accuracy of the approximate methods. Approximate methods may be sufficient for coarse data visualization, but are vulnerable to outliers and batch effects. Before the analysis, the PCA algorithm, as well as the number of eigenvectors should be considered carefully to avoid unnecessary communication overhead. Availability and implementation: Simulation code and notebooks for federated PCA can be found at https://gitlab.com/roettgerlab/federatedPCA; the code for the federated app is available at https://github.com/AnneHartebrodt/fc-federated-pca. Supplementary information: Supplementary data are available at Bioinformatics Advances online.

Correction: Quantifying Online News Media Coverage of the COVID-19 Pandemic: Text Mining Study and Resource.

[This corrects the article DOI: 10.2196/28253.].