Machine Learning on Large-Scale Proteomics Data Identifies Tissue and Cell-Type Specific Proteins

Proteomics and machine learning: Leveraging domain knowledge for feature selection in a skeletal muscle tissue meta-analysis

Omics techniques, such as proteomics, contain crucial data for understanding biological processes, but they remain underutilized due to their high dimensionality. Typically, proteomics research focuses narrowly on using a limited number of datasets, hindering cross-study comparisons, a problem that can potentially be addressed by machine learning. Despite this potential, machine learning has seen limited adoption in the field of proteomics. Here, skeletal muscle proteomics datasets from five separate studies were combined. These studies included conditions such as in vitro models (both 2D and 3D), in vivo skeletal muscle tissue, and adjacent tissues such as tendons. The collected data was preprocessed using MaxQuant, and then enriched using a Python script fetching structural and compositional details from UniProt and Ensembl databases. This was used to handle high-dimensional and sparsely labeled dataset by breaking it down into five smaller categories using cellular composition information and then training a Random Forest model for each category separately. Using biological context for interpreting the data resulted in improved model performance and made tailored analysis possible by reducing the dimensionality and increasing signal-to-noise ratio as well as only preserving biologically relevant features in each category. This integration of domain knowledge into data analysis and model training facilitated the discovery of new patterns while ensuring the retention of critical details, often overlooked when blind feature selection methods are used to exclude proteins with minimal expressions or variances. This approach was shown to be suitable for performing diverse analyses on individual as well as combined datasets within a broader biological context, ultimately leading to the identification of biologically relevant patterns. Besides from generating new biological insights, this approach can be used to perform tasks such as biomarker discovery, cluster analysis, classification, and anomaly detection more accurately, but incorporation of more datasets is needed to further expand the computational capabilities of such models in clinical settings.

Integrated meta-analysis of colorectal cancer public proteomic datasets for biomarker discovery and validation

The cancer biomarker field has been an object of thorough investigation in the last decades. Despite this, colorectal cancer (CRC) heterogeneity makes it challenging to identify and validate effective prognostic biomarkers for patient classification according to outcome and treatment response. Although a massive amount of proteomics data has been deposited in public data repositories, this rich source of information is vastly underused. Here, we attempted to reuse public proteomics datasets with two main objectives: i) to generate hypotheses (detection of biomarkers) for their posterior/downstream validation, and (ii) to validate, using an orthogonal approach, a previously described biomarker panel. Twelve CRC public proteomics datasets (mostly from the PRIDE database) were re-analysed and integrated to create a landscape of protein expression. Samples from both solid and liquid biopsies were included in the reanalysis. Integrating this data with survival annotation data, we have validated in silico a six-gene signature for CRC classification at the protein level, and identified five new blood-detectable biomarkers (CD14, PPIA, MRC2, PRDX1, and TXNDC5) associated with CRC prognosis. The prognostic value of these blood-derived proteins was confirmed using additional public datasets, supporting their potential clinical value. As a conclusion, this proof-of-the-concept study demonstrates the value of re-using public proteomics datasets as the basis to create a useful resource for biomarker discovery and validation. The protein expression data has been made available in the public resource Expression Atlas.

Deciphering Protein Secretion from the Brain to Cerebrospinal Fluid for Biomarker Discovery

Cerebrospinal fluid (CSF) is an essential matrix for the discovery of neurological disease biomarkers. However, the high dynamic range of protein concentrations in CSF hinders the detection of the least abundant protein biomarkers by untargeted mass spectrometry. It is thus beneficial to gain a deeper understanding of the secretion processes within the brain. Here, we aim to explore if and how the secretion of brain proteins to the CSF can be predicted. By combining a curated CSF proteome and the brain elevated proteome of the Human Protein Atlas, brain proteins were classified as CSF or non-CSF secreted. A machine learning model was trained on a range of sequence-based features to differentiate between CSF and non-CSF groups and effectively predict the brain origin of proteins. The classification model achieves an area under the curve of 0.89 if using high confidence CSF proteins. The most important prediction features include the subcellular localization, signal peptides, and transmembrane regions. The classifier generalized well to the larger brain detected proteome and is able to correctly predict novel CSF proteins identified by affinity proteomics. In addition to elucidating the underlying mechanisms of protein secretion, the trained classification model can support biomarker candidate selection.

Utilizing databases for astrocyte secretome research

INTRODUCTION

Astrocytes are the most abundant cell type in the central nervous system (CNS). They play a pivotal role in supporting neuronal function and maintaining homeostasis by releasing a variety of bioactive proteins, collectively known as the astrocyte secretome. Investigating secretome provides insights into the molecular mechanisms underlying astrocyte function and dysfunction, as well as novel strategies to prevent and treat diseases affecting the CNS.

AREAS COVERED

Proteomics databases are a valuable resource for studying the role of astrocytes in healthy and diseased brain function, as they provide information about gene expression, protein expression, and cellular function. In this review, we discuss existing databases that are useful for astrocyte secretome research.

EXPERT OPINION

Astrocyte secretomics is a field that is rapidly progressing, yet the availability of dedicated databases is currently limited. To meet the increasing demand for comprehensive omics data in glia research, developing databases specifically focused on astrocyte secretome is crucial. Such databases would allow researchers to investigate the intricate molecular landscape of astrocytes and comprehend their involvement in diverse physiological and pathological processes. Expanding resources through the development of databases dedicated to the astrocyte secretome may facilitate further advancements in this field.