A5078060263- Protein Structure and Dynamics
- Machine Learning in Bioinformatics
- Genomics and Phylogenetic Studies
- Enzyme Structure and Function
- RNA and protein synthesis mechanisms
- Computational Drug Discovery Methods
- AI in cancer detection
- Bioinformatics and Genomic Networks
- Digital Imaging for Blood Diseases
- Genetics, Bioinformatics, and Biomedical Research
- Algorithms and Data Compression
- Peptidase Inhibition and Analysis
- Biomedical Text Mining and Ontologies
- Cell Image Analysis Techniques
- Advanced Biosensing Techniques and Applications
- Ubiquitin and proteasome pathways
- Scientific Computing and Data Management
- Chromosomal and Genetic Variations
- Medical Imaging Techniques and Applications
- Protein Degradation and Inhibitors
- Monoclonal and Polyclonal Antibodies Research
- Microbial Natural Products and Biosynthesis
- Microbial Metabolic Engineering and Bioproduction
- Advanced biosensing and bioanalysis techniques
- Electrowetting and Microfluidic Technologies
Wageningen University & Research
2016-2022
Institute of Bioinformatics
2022
Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of cell. Recent developments in computational methods for protein structure predictions have reached accuracy experimentally determined models. Although this has been independently verified, implementation these across structural-biology applications remains to be tested. Here, we evaluate use AlphaFold2 (AF2) study characteristic structural elements; impact missense variants;...
We are now entering a new era in protein sequence and structure annotation, with hundreds of millions predicted structures made available through the AlphaFold database1. These models cover nearly all proteins that known, including those challenging to annotate for function or putative biological role using standard homology-based approaches. In this study, we examine extent which database has structurally illuminated 'dark matter' natural universe at high accuracy. further describe...
Abstract Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of cell. Recent developments in computational methods have led to protein structure predictions reached accuracy experimentally determined models. While this has been independently verified, implementation these across structural biology applications remains be tested. Here, we evaluate use AlphaFold 2 (AF2) study characteristic elements; impact missense variants; ligand...
Abstract Protein-ligand interactions (PLI) are foundational to small molecule drug design. With computational methods striving towards experimental accuracy, there is a critical demand for well-curated and diverse PLI dataset. Existing datasets often limited in size diversity, commonly used evaluation sets suffer from training information leakage, hindering the realistic assessment of method generalization capabilities. To address these shortcomings, we present PLIN-DER, largest most...
Next-generation sequencing technology is generating a wealth of highly similar genome sequences for many species, paving the way transition from single-genome to pan-genome analyses. Accordingly, genomics research going switch reference-centric pan-genomic approaches. We define as comprehensive representation multiple annotated genomes, facilitating analyses on similarity and divergence constituent genomes at nucleotide, gene structure level. Current approaches do not thoroughly address...
Abstract Motivation As the number of experimentally solved protein structures rises, it becomes increasingly appealing to use structural information for predictive tasks involving proteins. Due large variation in sizes, folds and topologies, an attractive approach is embed into fixed-length vectors, which can be used machine learning algorithms aimed at predicting understanding functional physical properties. Many existing embedding approaches are alignment based, both time-consuming...
Abstract Protein-protein interactions (PPIs) are fundamental to understanding biological processes and play a key role in therapeutic advancements. As deep-learning docking methods for PPIs gain traction, benchmarking protocols datasets tailored effective training evaluation of their generalization capabilities performance across real-world scenarios become imperative. Aiming overcome limitations existing approaches, we introduce PINDER, comprehensive annotated dataset that uses structural...
The vast number of protein structures currently available opens exciting opportunities for machine learning on proteins, aimed at predicting and understanding functional properties. In particular, in combination with homology modelling, it is now possible to not only use sequence features as input learning, but also structure features. However, order do so, robust multiple alignments are imperative. Here we present Caretta, a alignment suite meant homologous sequentially divergent families...
Abstract The process of designing biomolecules, in particular proteins, is witnessing a rapid change available tooling and approaches, moving from design through physicochemical force fields, to producing plausible, complex sequences fast via end-to-end differentiable statistical models. To achieve conditional controllable protein design, researchers at the interface artificial intelligence biology leverage advances natural language processing (NLP) computer vision techniques, coupled with...
Abstract Driven by the development and upscaling of fast genome sequencing assembly pipelines, number protein-coding sequences deposited in public protein sequence databases is increasing exponentially. Recently, dramatic success deep learning-based approaches applied to structure prediction has done same for structures. We are now entering a new era annotation, with hundreds millions predicted structures made available through AlphaFold database. These models cover most catalogued natural...
Proteolysis-Targeting Chimeras (PROTACs) represent a novel class of small molecules which are designed to act as bridge between an E3 ligase and disease-relevant protein, thereby promoting its subsequent degradation. PROTACs composed two protein binding "active" domains, linked by "linker" domain. The design the linker domain is challenging due geometric chemical constraints given interactions, need maximize drug-likeness. To tackle these challenges, we introduce ShapeLinker, method for de...
Abstract Motivation As the number of experimentally solved protein structures rises, it becomes increasingly appealing to use structural information for predictive tasks involving proteins. Due large variation in sizes, folds, and topologies, an attractive approach is embed into fixed-length vectors, which can be used machine learning algorithms aimed at predicting understanding functional physical properties. Many existing embedding approaches are alignment-based, both time-consuming...
Abstract The growing prevalence and popularity of protein structure data, both experimental computationally modelled, necessitates fast tools algorithms to enable exploratory interpretable structure-based machine learning. Alignment-free approaches have been developed for divergent proteins, but proteins sharing func-tional structural similarity are often better understood via alignment, which has typically too expensive larger datasets. Here, we introduce the concept rotation-invariant...
Abstract The recent public release of the latest version AlphaFold database has given us access to over 200 million predicted protein structures. We use a “shape-mer” approach, structural fragmentation method analogous sequence k -mers, describe these structures and look for novelties - both in terms proteins with rare or novel composition possible functional annotation under-studied proteins. Data code will be made available at https://github.com/TurtleTools/afdb-shapemer-darkness
Abstract Detecting structural variation (SV) in eukaryotic genomes is of broad interest due to its often dramatic phenotypic effects, but remains a major, costly challenge based on DNA sequencing data. A cost-effective alternative detecting large-scale SV has become available with advances optical mapping technology. However, the algorithmic approaches identifying SVs from data are limited. Here, we propose novel, open-source detection tool, OptiDiff, which employs single molecule approach...
In genomics, optical mapping technology provides long-range contiguity information to improve genome sequence assemblies and detect structural variation. Originally a laborious manual process, Bionano Genomics platforms now offer high-throughput, automated based on chips packed with nanochannels through which unwound DNA is guided the fluorescent backbone specific restriction sites are recorded. Although raw image data obtained of high quality, processing assembly software accompanying...
Abstract In genomics, optical mapping technology provides long-range contiguity information to improve genome sequence assemblies and detect structural variation. Originally a laborious manual process, Bionano Genomics platforms now offer high-throughput, automated based on chips packed with nanochannels through which unwound DNA is guided the fluorescent backbone specific restriction sites are recorded. Although raw image data obtained of high quality, processing assembly software...