Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning.

Imputation techniques provide means to replace missing measurements with a value and are used in almost all downstream analysis of mass spectrometry (MS) based proteomics data using label-free quantification (LFQ). Here we demonstrate how collaborative filtering, denoising autoencoders, and variational autoencoders can impute missing values in the context of LFQ at different levels. We applied our method, proteomics imputation modeling mass spectrometry (PIMMS), to an alcohol-related liver disease (ALD) cohort with blood plasma proteomics data available for 358 individuals. Removing 20 percent of the intensities we were able to recover 15 out of 17 significant abundant protein groups using PIMMS-VAE imputations. When analyzing the full dataset we identified 30 additional proteins (+13.2%) that were significantly differentially abundant across disease stages compared to no imputation and found that some of these were predictive of ALD progression in machine learning models. We, therefore, suggest the use of deep learning approaches for imputing missing values in MS-based proteomics on larger datasets and provide workflows for these.

Proteomic profiling reveals diagnostic signatures and pathogenic insights in multisystem inflammatory syndrome in children.

Multisystem inflammatory syndrome in children (MIS-C) is a severe disease that emerged during the COVID-19 pandemic. Although recognized as an immune-mediated condition, the pathogenesis remains unresolved. Furthermore, the absence of a diagnostic test can lead to delayed immunotherapy. Using state-of-the-art mass-spectrometry proteomics, assisted by artificial intelligence (AI), we aimed to identify a diagnostic signature for MIS-C and to gain insights into disease mechanisms. We identified a highly specific 4-protein diagnostic signature in children with MIS-C. Furthermore, we identified seven clusters that differed between MIS-C and controls, indicating an interplay between apolipoproteins, immune response proteins, coagulation factors, platelet function, and the complement cascade. These intricate protein patterns indicated MIS-C as an immunometabolic condition with global hypercoagulability. Our findings emphasize the potential of AI-assisted proteomics as a powerful and unbiased tool for assessing disease pathogenesis and suggesting avenues for future interventions and impact on pediatric disease trajectories through early diagnosis.

Mass spectrometry-based proteomics data from thousands of HeLa control samples.

Here we provide a curated, large scale, label free mass spectrometry-based proteomics data set derived from HeLa cell lines for general purpose machine learning and analysis. Data access and filtering is a tedious task, which takes up considerable amounts of time for researchers. Therefore we provide machine based metadata for easy selection and overview along the 7,444 raw files and MaxQuant search output. For convenience, we provide three filtered and aggregated development datasets on the protein groups, peptides and precursors level. Next to providing easy to access training data, we provide a SDRF file annotating each raw file with instrument settings allowing automated reprocessing. We encourage others to enlarge this data set by instrument runs of further HeLa samples from different machine types by providing our workflows and analysis scripts.

Discovery of plasma proteins associated with ventricular fibrillation during first ST-elevation myocardial infarction via proteomics.

AIMS: The underlying biological mechanisms of ventricular fibrillation (VF) during acute myocardial infarction are largely unknown. To our knowledge, this is the first proteomic study for this trait, with the aim to identify and characterize proteins that are associated with VF during first ST-elevation myocardial infarction (STEMI). METHODS AND RESULTS: We included 230 participants from a Danish ongoing case-control study on patients with first STEMI with VF (case, n = 110) and without VF (control, n = 120) before guided catheter insertion for primary percutaneous coronary intervention. The plasma proteome was investigated using mass spectrometry-based proteomics on plasma samples collected within 24 h of symptom onset, and one patient was excluded in quality control. In 229 STEMI patients {72% men, median age 62 years [interquartile range (IQR): 54-70]}, a median of 257 proteins (IQR: 244-281) were quantified per patient. A total of 26 proteins were associated with VF; these proteins were involved in several biological processes including blood coagulation, haemostasis, and immunity. After correcting for multiple testing, two up-regulated proteins remained significantly associated with VF, actin beta-like 2 [ACTBL2, fold change (FC) 2.25, P < 0.001, q = 0.023], and coagulation factor XIII-A (F13A1, FC 1.48, P < 0.001, q = 0.023). None of the proteins were correlated with anterior infarct location. CONCLUSION: Ventricular fibrillation due to first STEMI was significantly associated with two up-regulated proteins (ACTBL2 and F13A1), suggesting that they may represent novel underlying molecular VF mechanisms. Further research is needed to determine whether these proteins are predictive biomarkers or acute phase response proteins to VF during acute ischaemia.

Diagnosis trajectories of prior multi-morbidity predict sepsis mortality.

Sepsis affects millions of people every year, many of whom will die. In contrast to current survival prediction models for sepsis patients that primarily are based on data from within-admission clinical measurements (e.g. vital parameters and blood values), we aim for using the full disease history to predict sepsis mortality. We benefit from data in electronic medical records covering all hospital encounters in Denmark from 1996 to 2014. This data set included 6.6 million patients of whom almost 120,000 were diagnosed with the ICD-10 code: A41 'Other sepsis'. Interestingly, patients following recurrent trajectories of time-ordered co-morbidities had significantly increased sepsis mortality compared to those who did not follow a trajectory. We identified trajectories which significantly altered sepsis mortality, and found three major starting points in a combined temporal sepsis network: Alcohol abuse, Diabetes and Cardio-vascular diagnoses. Many cancers also increased sepsis mortality. Using the trajectory based stratification model we explain contradictory reports in relation to diabetes that recently have appeared in the literature. Finally, we compared the predictive power using 18.5 years of disease history to scoring based on within-admission clinical measurements emphasizing the value of long term data in novel patient scores that combine the two types of data.