Methods to Discover and Validate Biofluid-Based Biomarkers in Neurodegenerative Dementias.

Neurodegenerative dementias are progressive diseases that cause neuronal network breakdown in different brain regions often because of accumulation of misfolded proteins in the brain extracellular matrix, such as amyloids or inside neurons or other cell types of the brain. Several diagnostic protein biomarkers in body fluids are being used and implemented, such as for Alzheimer's disease. However, there is still a lack of biomarkers for co-pathologies and other causes of dementia. Such biofluid-based biomarkers enable precision medicine approaches for diagnosis and treatment, allow to learn more about underlying disease processes, and facilitate the development of patient inclusion and evaluation tools in clinical trials. When designing studies to discover novel biofluid-based biomarkers, choice of technology is an important starting point. But there are so many technologies to choose among. To address this, we here review the technologies that are currently available in research settings and, in some cases, in clinical laboratory practice. This presents a form of lexicon on each technology addressing its use in research and clinics, its strengths and limitations, and a future perspective.

Structural flexibility and heterogeneity of recombinant human glial fibrillary acidic protein (GFAP).

Glial fibrillary acidic protein (GFAP) is a promising biomarker for brain and spinal cord disorders. Recent studies have highlighted the differences in the reliability of GFAP measurements in different biological matrices. The reason for these discrepancies is poorly understood as our knowledge of the protein's 3-dimensional conformation, proteoforms, and aggregation remains limited. Here, we investigate the structural properties of GFAP under different conditions. For this, we characterized recombinant GFAP proteins from various suppliers and applied hydrogen-deuterium exchange mass spectrometry (HDX-MS) to provide a snapshot of the conformational dynamics of GFAP in artificial cerebrospinal fluid (aCSF) compared to the phosphate buffer. Our findings indicate that recombinant GFAP exists in various conformational species. Furthermore, we show that GFAP dimers remained intact under denaturing conditions. HDX-MS experiments show an overall decrease in H-bonding and an increase in solvent accessibility of GFAP in aCSF compared to the phosphate buffer, with clear indications of mixed EX2 and EX1 kinetics. To understand possible structural interface regions and the evolutionary conservation profiles, we combined HDX-MS results with the predicted GFAP-dimer structure by AlphaFold-Multimer. We found that deprotected regions with high structural flexibility in aCSF overlap with predicted conserved dimeric 1B and 2B domain interfaces. Structural property predictions combined with the HDX data show an overall deprotection and signatures of aggregation in aCSF. We anticipate that the outcomes of this research will contribute to a deeper understanding of the structural flexibility of GFAP and ultimately shed light on its behavior in different biological matrices.

The GFAP proteoform puzzle: How to advance GFAP as a fluid biomarker in neurological diseases.

Glial fibrillary acidic protein (GFAP) is a well-established biomarker of reactive astrogliosis in the central nervous system because of its elevated levels following brain injury and various neurological disorders. The advent of ultra-sensitive methods for measuring low-abundant proteins has significantly enhanced our understanding of GFAP levels in the serum or plasma of patients with diverse neurological diseases. Clinical studies have demonstrated that GFAP holds promise both as a diagnostic and prognostic biomarker, including but not limited to individuals with Alzheimer's disease. GFAP exhibits diverse forms and structures, herein referred to as its proteoform complexity, encompassing conformational dynamics, isoforms and post-translational modifications (PTMs). In this review, we explore how the proteoform complexity of GFAP influences its detection, which may affect the differential diagnostic performance of GFAP in different biological fluids and can provide valuable insights into underlying biological processes. Additionally, proteoforms are often disease-specific, and our review provides suggestions and highlights areas to focus on for the development of new assays for measuring GFAP, including isoforms, PTMs, discharge mechanisms, breakdown products, higher-order species and interacting partners. By addressing the knowledge gaps highlighted in this review, we aim to support the clinical translation and interpretation of GFAP in both CSF and blood and the development of reliable, reproducible and specific prognostic and diagnostic tests. To enhance disease pathology comprehension and optimise GFAP as a biomarker, a thorough understanding of detected proteoforms in biofluids is essential.

Ten quick tips for sequence-based prediction of protein properties using machine learning.

The ubiquitous availability of genome sequencing data explains the popularity of machine learning-based methods for the prediction of protein properties from their amino acid sequences. Over the years, while revising our own work, reading submitted manuscripts as well as published papers, we have noticed several recurring issues, which make some reported findings hard to understand and replicate. We suspect this may be due to biologists being unfamiliar with machine learning methodology, or conversely, machine learning experts may miss some of the knowledge needed to correctly apply their methods to proteins. Here, we aim to bridge this gap for developers of such methods. The most striking issues are linked to a lack of clarity: how were annotations of interest obtained; which benchmark metrics were used; how are positives and negatives defined. Others relate to a lack of rigor: If you sneak in structural information, your method is not sequence-based; if you compare your own model to "state-of-the-art," take the best methods; if you want to conclude that some method is better than another, obtain a significance estimate to support this claim. These, and other issues, we will cover in detail. These points may have seemed obvious to the authors during writing; however, they are not always clear-cut to the readers. We also expect many of these tips to hold for other machine learning-based applications in biology. Therefore, many computational biologists who develop methods in this particular subject will benefit from a concise overview of what to avoid and what to do instead.

Identification of a Bromodomain-like Region in 15-Lipoxygenase-1 Explains Its Nuclear Localization.

Lipoxygenase (LOX) activity provides oxidative lipid metabolites, which are involved in inflammatory disorders and tumorigenesis. Activity-based probes to detect the activity of LOX enzymes in their cellular context provide opportunities to explore LOX biology and LOX inhibition. Here, we developed Labelox B as a potent covalent LOX inhibitor for one-step activity-based labeling of proteins with LOX activity. Labelox B was used to establish an ELISA-based assay for affinity capture and antibody-based detection of specific LOX isoenzymes. Moreover, Labelox B enabled efficient activity-based labeling of endogenous LOXs in living cells. LOX proved to localize in the nucleus, which was rationalized by identification of a functional bromodomain-like consensus motif in 15-LOX-1. This indicates that 15-LOX-1 is not only involved in oxidative lipid metabolism, but also in chromatin binding, which suggests a potential role in chromatin modifications.

PatchProt: hydrophobic patch prediction using protein foundation models.

Motivation: Hydrophobic patches on protein surfaces play important functional roles in protein-protein and protein-ligand interactions. Large hydrophobic surfaces are also involved in the progression of aggregation diseases. Predicting exposed hydrophobic patches from a protein sequence has shown to be a difficult task. Fine-tuning foundation models allows for adapting a model to the specific nuances of a new task using a much smaller dataset. Additionally, multitask deep learning offers a promising solution for addressing data gaps, simultaneously outperforming single-task methods. Results: In this study, we harnessed a recently released leading large language model Evolutionary Scale Models (ESM-2). Efficient fine-tuning of ESM-2 was achieved by leveraging a recently developed parameter-efficient fine-tuning method. This approach enabled comprehensive training of model layers without excessive parameters and without the need to include a computationally expensive multiple sequence analysis. We explored several related tasks, at local (residue) and global (protein) levels, to improve the representation of the model. As a result, our model, PatchProt, cannot only predict hydrophobic patch areas but also outperforms existing methods at predicting primary tasks, including secondary structure and surface accessibility predictions. Importantly, our analysis shows that including related local tasks can improve predictions on more difficult global tasks. This research sets a new standard for sequence-based protein property prediction and highlights the remarkable potential of fine-tuning foundation models enriching the model representation by training over related tasks. Availability and implementation: https://github.com/Deagogishvili/chapter-multi-task.

Proteome encoded determinants of protein sorting into extracellular vesicles.

Extracellular vesicles (EVs) are membranous structures released by cells into the extracellular space and are thought to be involved in cell-to-cell communication. While EVs and their cargo are promising biomarker candidates, sorting mechanisms of proteins to EVs remain unclear. In this study, we ask if it is possible to determine EV association based on the protein sequence. Additionally, we ask what the most important determinants are for EV association. We answer these questions with explainable AI models, using human proteome data from EV databases to train and validate the model. It is essential to correct the datasets for contaminants introduced by coarse EV isolation workflows and for experimental bias caused by mass spectrometry. In this study, we show that it is indeed possible to predict EV association from the protein sequence: a simple sequence-based model for predicting EV proteins achieved an area under the curve of 0.77 ± 0.01, which increased further to 0.84 ± 0.00 when incorporating curated post-translational modification (PTM) annotations. Feature analysis shows that EV-associated proteins are stable, polar, and structured with low isoelectric point compared to non-EV proteins. PTM annotations emerged as the most important features for correct classification; specifically, palmitoylation is one of the most prevalent EV sorting mechanisms for unique proteins. Palmitoylation and nitrosylation sites are especially prevalent in EV proteins that are determined by very strict isolation protocols, indicating they could potentially serve as quality control criteria for future studies. This computational study offers an effective sequence-based predictor of EV associated proteins with extensive characterisation of the human EV proteome that can explain for individual proteins which factors contribute to their EV association.

Discovery of novel CSF biomarkers to predict progression in dementia using machine learning.

Providing an accurate prognosis for individual dementia patients remains a challenge since they greatly differ in rates of cognitive decline. In this study, we used machine learning techniques with the aim to identify cerebrospinal fluid (CSF) biomarkers that predict the rate of cognitive decline within dementia patients. First, longitudinal mini-mental state examination scores (MMSE) of 210 dementia patients were used to create fast and slow progression groups. Second, we trained random forest classifiers on CSF proteomic profiles and obtained a well-performing prediction model for the progression group (ROC-AUC = 0.82). As a third step, Shapley values and Gini feature importance measures were used to interpret the model performance and identify top biomarker candidates for predicting the rate of cognitive decline. Finally, we explored the potential for each of the 20 top candidates in internal sensitivity analyses. TNFRSF4 and TGF [Formula: see text]-1 emerged as the top markers, being lower in fast-progressing patients compared to slow-progressing patients. Proteins of which a low concentration was associated with fast progression were enriched for cell signalling and immune response pathways. None of our top markers stood out as strong individual predictors of subsequent cognitive decline. This could be explained by small effect sizes per protein and biological heterogeneity among dementia patients. Taken together, this study presents a novel progression biomarker identification framework and protein leads for personalised prediction of cognitive decline in dementia.

How sticky are our proteins? Quantifying hydrophobicity of the human proteome.

Summary: Proteins tend to bury hydrophobic residues inside their core during the folding process to provide stability to the protein structure and to prevent aggregation. Nevertheless, proteins do expose some 'sticky' hydrophobic residues to the solvent. These residues can play an important functional role, e.g. in protein-protein and membrane interactions. Here, we first investigate how hydrophobic protein surfaces are by providing three measures for surface hydrophobicity: the total hydrophobic surface area, the relative hydrophobic surface area and-using our MolPatch method-the largest hydrophobic patch. Secondly, we analyze how difficult it is to predict these measures from sequence: by adapting solvent accessibility predictions from NetSurfP2.0, we obtain well-performing prediction methods for the THSA and RHSA, while predicting LHP is more challenging. Finally, we analyze implications of exposed hydrophobic surfaces: we show that hydrophobic proteins typically have low expression, suggesting cells avoid an overabundance of sticky proteins. Availability and implementation: The data underlying this article are available in GitHub at https://github.com/ibivu/hydrophobic_patches. Supplementary information: Supplementary data are available at Bioinformatics Advances online.

Multi-Omics Interdisciplinary Research Integration to Accelerate Dementia Biomarker Development (MIRIADE).

Proteomics studies have shown differential expression of numerous proteins in dementias but have rarely led to novel biomarker tests for clinical use. The Marie Curie MIRIADE project is designed to experimentally evaluate development strategies to accelerate the validation and ultimate implementation of novel biomarkers in clinical practice, using proteomics-based biomarker development for main dementias as experimental case studies. We address several knowledge gaps that have been identified in the field. First, there is the technology-translation gap of different technologies for the discovery (e.g., mass spectrometry) and the large-scale validation (e.g., immunoassays) of biomarkers. In addition, there is a limited understanding of conformational states of biomarker proteins in different matrices, which affect the selection of reagents for assay development. In this review, we aim to understand the decisions taken in the initial steps of biomarker development, which is done via an interim narrative update of the work of each ESR subproject. The results describe the decision process to shortlist biomarkers from a proteomics to develop immunoassays or mass spectrometry assays for Alzheimer's disease, Lewy body dementia, and frontotemporal dementia. In addition, we explain the approach to prepare the market implementation of novel biomarkers and assays. Moreover, we describe the development of computational protein state and interaction prediction models to support biomarker development, such as the prediction of epitopes. Lastly, we reflect upon activities involved in the biomarker development process to deduce a best-practice roadmap for biomarker development.

Siamese Recurrent Neural Network with a Self-Attention Mechanism for Bioactivity Prediction.

Activity prediction plays an essential role in drug discovery by directing search of drug candidates in the relevant chemical space. Despite being applied successfully to image recognition and semantic similarity, the Siamese neural network has rarely been explored in drug discovery where modelling faces challenges such as insufficient data and class imbalance. Here, we present a Siamese recurrent neural network model (SiameseCHEM) based on bidirectional long short-term memory architecture with a self-attention mechanism, which can automatically learn discriminative features from the SMILES representations of small molecules. Subsequently, it is used to categorize bioactivity of small molecules via N-shot learning. Trained on random SMILES strings, it proves robust across five different datasets for the task of binary or categorical classification of bioactivity. Benchmarking against two baseline machine learning models which use the chemistry-rich ECFP fingerprints as the input, the deep learning model outperforms on three datasets and achieves comparable performance on the other two. The failure of both baseline methods on SMILES strings highlights that the deep learning model may learn task-specific chemistry features encoded in SMILES strings.