Applying Machine Learning to Blood Count Data Predicts Sepsis with ICU Admission.

BACKGROUND: Timely diagnosis is crucial for sepsis treatment. Current machine learning (ML) models suffer from high complexity and limited applicability. We therefore created an ML model using only complete blood count (CBC) diagnostics. METHODS: We collected non-intensive care unit (non-ICU) data from a German tertiary care centre (January 2014 to December 2021). Using patient age, sex, and CBC parameters (haemoglobin, platelets, mean corpuscular volume, white and red blood cells), we trained a boosted random forest, which predicts sepsis with ICU admission. Two external validations were conducted using data from another German tertiary care centre and the Medical Information Mart for Intensive Care IV database (MIMIC-IV). Using the subset of laboratory orders also including procalcitonin (PCT), an analogous model was trained with PCT as an additional feature. RESULTS: After exclusion, 1 381 358 laboratory requests (2016 from sepsis cases) were available. The CBC model shows an area under the receiver operating characteristic (AUROC) of 0.872 (95% CI, 0.857-0.887). External validations show AUROCs of 0.805 (95% CI, 0.787-0.824) for University Medicine Greifswald and 0.845 (95% CI, 0.837-0.852) for MIMIC-IV. The model including PCT revealed a significantly higher AUROC (0.857; 95% CI, 0.836-0.877) than PCT alone (0.790; 95% CI, 0.759-0.821; P < 0.001). CONCLUSIONS: Our results demonstrate that routine CBC results could significantly improve diagnosis of sepsis when combined with ML. The CBC model can facilitate early sepsis prediction in non-ICU patients with high robustness in external validations. Its implementation in clinical decision support systems has strong potential to provide an essential time advantage and increase patient safety.

Effective Amino Acid Sequencing of Intact Filgrastim by Multimodal Mass Spectrometry with Topdownr.

Therapeutic proteins, known as biologicals, are an important and growing class of drugs for treatment of a series of human ailments. Amino acid sequence variants of therapeutic proteins can affect their safety and efficacy. Top-down mass spectrometry is well suited for the sequence analysis of intact therapeutic proteins. Fine-tuning of tandem mass spectrometry (MS/MS) fragmentation conditions is essential for maximizing the amino acid sequence coverage but is often time-consuming. We used topdownr, an automated and integrated multimodal approach to systematically assess high mass accuracy MS/MS fragmentation parameters to characterize filgrastim, a 19 kDa recombinant human granulocyte colony-stimulating factor used in treating neutropenia. A total of 276 different MS/MS conditions were systematically tested, including the following parameters: protein charge state, HCD and CID collision energy, ETD reaction time, ETD supplemental activation, and UVPD activation time. Stringent and accurate evaluation and annotation of the MS/MS data was achieved by requiring a fragment ion mass error of 5 ppm, considering reproducible N- and C-terminal fragment ions only, and excluding internal fragment ion assignments. We report the first EThcD and UVPD MS/MS analysis of intact filgrastim, and these two techniques combined resulted in 98% amino acid sequence coverage. By combining all tested fragmentation modes, we obtained near-complete amino acid sequence coverage (99.4%) of intact filgrastim.

A Modular and Expandable Ecosystem for Metabolomics Data Annotation in R.

Liquid chromatography-mass spectrometry (LC-MS)-based untargeted metabolomics experiments have become increasingly popular because of the wide range of metabolites that can be analyzed and the possibility to measure novel compounds. LC-MS instrumentation and analysis conditions can differ substantially among laboratories and experiments, thus resulting in non-standardized datasets demanding customized annotation workflows. We present an ecosystem of R packages, centered around the MetaboCoreUtils, MetaboAnnotation and CompoundDb packages that together provide a modular infrastructure for the annotation of untargeted metabolomics data. Initial annotation can be performed based on MS1 properties such as m/z and retention times, followed by an MS2-based annotation in which experimental fragment spectra are compared against a reference library. Such reference databases can be created and managed with the CompoundDb package. The ecosystem supports data from a variety of formats, including, but not limited to, MSP, MGF, mzML, mzXML, netCDF as well as MassBank text files and SQL databases. Through its highly customizable functionality, the presented infrastructure allows to build reproducible annotation workflows tailored for and adapted to most untargeted LC-MS-based datasets. All core functionality, which supports base R data types, is exported, also facilitating its re-use in other R packages. Finally, all packages are thoroughly unit-tested and documented and are available on GitHub and through Bioconductor.

MSnbase, Efficient and Elegant R-Based Processing and Visualization of Raw Mass Spectrometry Data.

We present version 2 of the MSnbase R/Bioconductor package. MSnbase provides infrastructure for the manipulation, processing, and visualization of mass spectrometry data. We focus on the new on-disk infrastructure, that allows the handling of large raw mass spectrometry experiments on commodity hardware and illustrate how the package is used for elegant data processing, method development, and visualization.

Maximizing Sequence Coverage in Top-Down Proteomics By Automated Multimodal Gas-Phase Protein Fragmentation.

Intact protein sequencing by tandem mass spectrometry (MS/MS), known as top-down protein sequencing, relies on efficient gas-phase fragmentation at multiple experimental conditions to achieve extensive amino acid sequence coverage. We developed the "topdownr" R-package for automated construction of multimodal (i.e., involving CID, HCD, ETD, ETciD, EThcD, and UVPD) MS/MS fragmentation methods on an orbitrap instrument platform and systematic analysis of the resultant spectra. We used topdownr to generate and analyze thousands of MS/MS spectra for five intact proteins of 10-30 kDa. We achieved 90-100% coverage for the proteins tested and derived guiding principles for efficient sequencing of intact proteins. The data analysis workflow and statistical models of topdownr software and multimodal MS/MS experiments provide a framework for optimizing MS/MS sequencing for any intact protein. Refined topdownr software will be suited for comprehensive characterization of protein pharmaceuticals and eventually also for de novo sequencing and detailed characterization of intact proteins.

Differential protein expression and peak selection in mass spectrometry data by binary discriminant analysis.

MOTIVATION: Proteomic mass spectrometry analysis is becoming routine in clinical diagnostics, for example to monitor cancer biomarkers using blood samples. However, differential proteomics and identification of peaks relevant for class separation remains challenging. RESULTS: Here, we introduce a simple yet effective approach for identifying differentially expressed proteins using binary discriminant analysis. This approach works by data-adaptive thresholding of protein expression values and subsequent ranking of the dichotomized features using a relative entropy measure. Our framework may be viewed as a generalization of the 'peak probability contrast' approach of Tibshirani et al. (2004) and can be applied both in the two-group and the multi-group setting. Our approach is computationally inexpensive and shows in the analysis of a large-scale drug discovery test dataset equivalent prediction accuracy as a random forest. Furthermore, we were able to identify in the analysis of mass spectrometry data from a pancreas cancer study biological relevant and statistically predictive marker peaks unrecognized in the original study. AVAILABILITY AND IMPLEMENTATION: The methodology for binary discriminant analysis is implemented in the R package binda, which is freely available under the GNU General Public License (version 3 or later) from CRAN at URL http://cran.r-project.org/web/packages/binda/. R scripts reproducing all described analyzes are available from the web page http://strimmerlab.org/software/binda/. CONTACT: k.strimmer@imperial.ac.uk.

Visualization of proteomics data using R and bioconductor.

Data visualization plays a key role in high-throughput biology. It is an essential tool for data exploration allowing to shed light on data structure and patterns of interest. Visualization is also of paramount importance as a form of communicating data to a broad audience. Here, we provided a short overview of the application of the R software to the visualization of proteomics data. We present a summary of R's plotting systems and how they are used to visualize and understand raw and processed MS-based proteomics data.

Species determination of Culicoides biting midges via peptide profiling using matrix-assisted laser desorption ionization mass spectrometry.

BACKGROUND: Culicoides biting midges are vectors of bluetongue and Schmallenberg viruses that inflict large-scale disease epidemics in ruminant livestock in Europe. Methods based on morphological characteristics and sequencing of genetic markers are most commonly employed to differentiate Culicoides to species level. Proteomic methods, however, are also increasingly being used as an alternative method of identification. These techniques have the potential to be rapid and may also offer advantages over DNA-based techniques. The aim of this proof-of-principle study was to develop a simple MALDI-MS based method to differentiate Culicoides from different species by peptide patterns with the additional option of identifying discriminating peptides. METHODS: Proteins extracted from 7 Culicoides species were digested and resulting peptides purified. Peptide mass fingerprint (PMF) spectra were recorded using matrix-assisted laser desorption/ionization time of flight mass spectrometry (MALDI-TOF-MS) and peak patterns analysed in R using the MALDIquant R package. Additionally, offline liquid chromatography (LC) MALDI-TOF tandem mass spectrometry (MS/MS) was applied to determine the identity of peptide peaks in one exemplary MALDI spectrum obtained using an unfractionated extract. RESULTS: We showed that the majority of Culicoides species yielded reproducible mass spectra with peak patterns that were suitable for classification. The dendrogram obtained by MS showed tentative similarities to a dendrogram generated from cytochrome oxidase I (COX1) sequences. Using offline LC-MALDI-TOF-MS/MS we determined the identity of 28 peptide peaks observed in one MALDI spectrum in a mass range from 1.1 to 3.1 kDa. All identified peptides were identical to other dipteran species and derived from one of five highly abundant proteins due to an absence of available Culicoides data. CONCLUSION: Shotgun mass mapping by MALDI-TOF-MS has been shown to be compatible with morphological and genetic identification of specimens. Furthermore, the method performs at least as well as an alternative approach based on MS spectra of intact proteins, thus establishing the procedure as a method in its own right, with the additional option of concurrently using the same samples in other MS-based applications for protein identifications. The future availability of genomic information for different Culicoides species may enable a more stringent peptide detection based on Culicoides-specific sequence information.

MALDIquant: a versatile R package for the analysis of mass spectrometry data.

UNLABELLED: MALDIquant is an R package providing a complete and modular analysis pipeline for quantitative analysis of mass spectrometry data. MALDIquant is specifically designed with application in clinical diagnostics in mind and implements sophisticated routines for importing raw data, preprocessing, non-linear peak alignment and calibration. It also handles technical replicates as well as spectra with unequal resolution. AVAILABILITY: MALDIquant and its associated R packages readBrukerFlexData and readMzXmlData are freely available from the R archive CRAN (http://cran.r-project.org). The software is distributed under the GNU General Public License (version 3 or later) and is accompanied by example files and data. Additional documentation is available from http://strimmerlab.org/software/maldiquant/.