Biology subjects

Marcatili, P.

Publications and source records attributed to Marcatili, P..

10 recordsLinked to original sources

bioRxiv2023

Variance Analysis of LC-MS Experimental Factors and Their Impact on Machine Learning

BackgroundMachine 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 re-scoring. ML models need large-scale datasets for training and re-purposing, 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. ResultsWe aim to facilitate ML efforts in MS data by conducting a systematic analysis of the potential sources of variance 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. ConclusionsOur findings show significantly higher levels of homogeneity within a project than between projects, which indicates that its 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-pre-trained model.

bioinformatics↗

bioRxiv2023

DiscoTope-3.0 - Improved B-cell epitope prediction using AlphaFold2 modeling and inverse folding latent representations

Accurate computational identification of B-cell epitopes is crucial for the development of vaccines, therapies, and diagnostic tools. However, current structure-based prediction methods face limitations due to the dependency on experimentally solved structures. Here, we introduce DiscoTope-3.0, a markedly improved B-cell epitope prediction tool that innovatively employs inverse folding structure representations and a positive-unlabelled learning strategy, and is explicitly adapted for both solved and predicted structures. Our tool demonstrates a considerable improvement in performance over existing methods, accurately predicting linear and conformational epitopes across multiple independent datasets. Most notably, DiscoTope-3.0 maintains high predictive performance across solved, relaxed and predicted structures, alleviating the need for experimental validation and extending the general applicability of accurate B-cell epitope prediction by more than 3 orders of magnitude. DiscoTope-3.0 is made widely accessible on two web servers, processing over 100 structures per submission, and as a downloadable package. In addition, the servers interface with RCSB and AlphaFoldDB, facilitating large-scale prediction across over 200 million cataloged proteins. DiscoTope-3.0 is available at: https://services.healthtech.dtu.dk/service.php?DiscoTope-3.0

immunology↗

bioRxiv2022

Bioinformatically predicted emulsifying peptides and potato protein hydrolysate improves the oxidative stability of microencapsulated fish oil

The aim of this study was to investigate the potential of potato proteins and peptides as emulsifiers in the microencapsulation of fish oil by spray-drying. Microcapsules were produced using a potato protein extract, and fractions enriched in patatin and protease inhibitors. Furthermore, bioinformatically predicted emulsifier peptides from abundant potato proteins and a hydrolysate, obtained through targeted proteolysis of the extract, were investigated. During 28 days of storage at 25{degrees}C, peptides and hydrolysate exhibited better emulsifying properties and higher encapsulation efficiencies compared to native proteins and sodium caseinate. Significant differences (p < 0.05) were observed in the peroxide value (PV) and secondary volatile oxidation products between the microcapsules produced with peptides and native proteins. Microcapsules produced with peptides and hydrolysate showed the highest oxidative stability, not exceeding a PV of 10 meq/kg oil, and with concentrations of volatiles below the odor threshold in oil for five of the six studied compounds. These results show the emulsifying potential of potato peptides and hydrolysate for use in microencapsulation of hydrophobic bioactive ingredients such as fish oil.

bioengineering↗

bioRxiv2022

BepiPred-3.0: Improved B-cell epitope prediction using protein language models

B-cell epitope prediction tools are of great medical and commercial interest due to their practical applications in vaccine development. The introduction of protein language models (LM) trained on unprecedented large datasets of protein sequences and structures, tap into a powerful numeric representation that can be exploited to accurately predict local and global protein structural features from amino acid sequences only. In this paper, we present BepiPred 3.0, a sequence-based epitope prediction tool that, by exploiting LM embeddings, greatly improves the prediction accuracy for both linear and conformational epitope prediction on several independent test sets. Furthermore, by carefully selecting additional input variables and epitope residue annotation strategy, performance can be further improved, thus achieving extraordinary results. Our tool can predict epitopes across hundreds of sequences in mere minutes. It is freely available as a web server with a user-friendly interface to navigate the results, as well as a standalone downloadable package.

bioinformatics↗

bioRxiv2022

DeepTMHMM predicts alpha and beta transmembrane proteins using deep neural networks

Transmembrane proteins span the lipid bilayer and are divided into two major structural classes, namely alpha helical and beta barrels. We introduce DeepTMHMM, a deep learning protein language model-based algorithm that can detect and predict the topology of both alpha helical and beta barrels proteins with unprecedented accuracy. DeepTMHMM (https://dtu.biolib.com/DeepTMHMM) scales to proteomes and covers all domains of life, which makes it ideal for metagenomics analyses.

bioinformatics↗

bioRxiv2020

Proteomic characterization of pilot scale hot-water extracts from the industrial carrageenan red seaweed Eucheuma denticulatum

Seaweeds have a long history as a resource for polysaccharides/hydrocolloids extraction for use in the food industry due to their functionality as stabilizing agents. In addition to the carbohydrate content, seaweeds also contains a significant amount of protein, which may find application in food and feed. Here, we present a novel combination of transcriptomics, proteomics, and bioinformatics to determine the protein composition in two pilot-scale extracts from Eucheuma denticilatum (Spinosum) obtained via hot-water extraction. The extracts were characterized by qualitative and quantitative proteomics using LC-MS/MS and a de-novo transcriptome assembly for construction of a novel proteome. Using label-free, relative quantification, we were able to identify the most abundant proteins in the extracts and determined that the majority of quantified protein in the extracts (>75%) is constituted by merely three previously uncharacterized proteins. Putative subcellular localization for the quantified proteins was determined by bioinformatic prediction, and by correlating with the expected copy number from the transcriptome analysis, we determined that the extracts were highly enriched in extracellular proteins. This implies that the method predominantly extracts extracellular proteins, and thus appear ineffective for cellular disruption and subsequent release of intracellular proteins. Ultimately, this study highlight the power of quantitative proteomics as a novel tool for characterization of alternative protein sources intended for use in foods. Additionally, the study showcases the potential of proteomics for evaluation of protein extraction methods and as powerful tool in the development of an efficient extraction process.

biochemistry↗

bioRxiv2020

Data mining patented antibody sequences

Patent literature should be a reflection of thirty years of engineering efforts in developing monoclonal antibody therapeutics. Such information is potentially valuable for rational antibody design. Patents however are not designed to convey scientific knowledge, but rather legal protection. It is unclear whether antibody information from patent documents, such as antibody sequences could be useful for the therapeutic antibody sphere in conveying engineering know-how rather than act as legal reference only. To assess the utility of patent data for therapeutic antibody engineering, we quantified the amount of antibody sequences in patents destined for medicinal purposes and how well they reflect the primary sequences of therapeutic antibodies in clinical use. We identified 16,526 patent families from major jurisdictions (e.g. USPTO and WIPO) that contained antibody sequences. These families held 245,109 unique antibody chains (135,397 heavy chains and 109,712 light chains) that we compiled in our Patented Antibody Database (PAD, http://naturalantibody.com/pad). We find that antibodies make up a non-trivial proportion of all patent amino acid sequence depositions (e.g. 10.95% of USPTO Full Text database). Our analysis of the 16,526 families demonstrates that the volume of patent documents with antibody sequences is growing with the majority of documents classified as containing antibodies for medicinal purposes. We further studied the 245,109 antibody chains from patent literature to reveal that they very well reflect the primary sequences of antibody therapeutics in clinical use. This suggests that patent literature could serve as a reference of previous engineering efforts to improve rational antibody design.

bioinformatics↗

bioRxiv2018

NetTCR: sequence-based prediction of TCR binding to peptide-MHC complexes using convolutional neural networks

Predicting epitopes recognized by cytotoxic T cells has been a long standing challenge within the field of immuno- and bioinformatics. While reliable predictions of peptide binding are available for most Major Histocompatibility Complex class I (MHCI) alleles, prediction models of T cell receptor (TCR) interactions with MHC class I-peptide complexes remain poor due to the limited amount of available training data. Recent next generation sequencing projects have however generated a considerable amount of data relating TCR sequences with their cognate HLA-peptide complex target. Here, we utilize such data to train a sequence-based predictor of the interaction between TCRs and peptides presented by the most common human MHCI allele, HLA-A*02:01. Our model is based on convolutional neural networks, which are especially designed to meet the challenges posed by the large length variations of TCRs. We show that such a sequence-based model allows for the identification of TCRs binding a given cognate peptide-MHC target out of a large pool of non-binding TCRs.

bioinformatics↗

bioRxiv2018

NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning

The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unravelling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed.\n\nHere, we present an updated and extended version of the NetSurfP tool (http://www.cbs.dtu.dk/services/NetSurfP-2.0/), that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP-2.0 is sequence-based and uses an architecture composed of convolutional and long short-term memory neural networks trained on solved protein structures. Using a single integrated model, NetSurfP-2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences.\n\nWe assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features. We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3-class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1,000 proteins in less than 2 hours, and complete proteomes in less than 1 day.

bioinformatics↗

bioRxiv2017

NetMHCpan 4.0: Improved peptide-MHC class I interaction predictions integrating eluted ligand and peptide binding affinity data

Cytotoxic T cells are of central importance in the immune systems response to disease. They recognize defective cells by binding to peptides presented on the cell surface by MHC (major histocompatibility complex) class I molecules. Peptide binding to MHC molecules is the single most selective step in the antigen presentation pathway. On the quest for T cell epitopes, the prediction of peptide binding to MHC molecules has therefore attracted large attention.\n\nIn the past, predictors of peptide-MHC interaction have in most cases been trained on binding affinity data. Recently an increasing amount of MHC presented peptides identified by mass spectrometry has been published containing information about peptide processing steps in the presentation pathway and the length distribution of naturally presented peptides. Here, we present NetMHCpan-4.0, a method trained on both binding affinity and eluted ligand data leveraging the information from both data types. Large-scale benchmarking of the method demonstrates an increased predictive performance compared to state-of-the-art when it comes to identification of naturally processed ligands, cancer neoantigens, and T cell epitopes.

bioinformatics↗