Biology subjects

Krawczyk, K.

Publications and source records attributed to Krawczyk, K..

At least 19 recordsLinked to original sources

bioRxiv2026

Protein Design Viz (PDV): lightweight protein structure visualization studio with validated quantitative analytics and antibody-specific toolkit

Motivation: Molecular visualization is dominated by two families of software. Desktop programs such as PyMOL, VMD and UCSF ChimeraX are powerful but heavy to install and operate. Web viewers such as Jmol, 3Dmol.js, NGL, Mol* and iCn3D are light and installation-free, but typically stop at rendering, lacking deeper functionality needed for even basic protein sequence, structural analyses and design tasks. Tools building upon these often lack comprehensive sequence/structure manipulation, surface, interface and antibody-specific analytics functionality or require an external backend. There is a need for a tool that is as frictionless as a web viewer yet carries the analytical depth normally reserved for the desktop or the command line software. Results: We present Protein Design Viz (PDV), a self-contained molecular visualization studio delivered as a single offline HTML file that runs entirely in the browser. Built as an extensive modification of 3Dmol.js, PDV combines a full visualization workflow: multi-object scenes, representations, coloring palette, linked sequence track, publication-quality outline rendering and portable sessions. Additionally we re-implemented four commonly used macromolecular analyses measures from scratch in client-side JavaScript: a Shrake-Rupley solvent-accessible surface area (SASA) engine, an antibody numbering and germline-assignment engine, a non-covalent interaction detector, and a developability-liability scanner. Each engine is validated against its established reference. PDV's SASA reproduces FreeSASA at Pearson r {approx} 0.997-0.998 across 2,582 structures spanning proteins, nucleic acids and ligands; its numbering reproduces RIOT for over 99.88% of 1.3 million residue positions across 16,996 sequences and four schemes; its interaction detector reproduces PLIP at macro-F1 0.82, matching Arpeggio as closely as PLIP itself does. PDV brings validated, quantitative structural analysis into a no-install, simple to use tool. Availability and implementation: PDV is a single HTML file, free for noncommercial use under the PolyForm Noncommercial License 1.0.0, available from pdv.naturalantibody.com. It requires only a WebGL-capable browser and runs fully offline.

bioinformatics↗

bioRxiv2026

KyDab - a comprehensive database of antibody discovery selection campaigns.

Preclinical antibody discovery relies on progressive screening and down-selection of candidate antibodies from large immune repertoires, yet this critical process is poorly represented in existing public databases. Here we introduce KyDab (Kymouse Antibody Database), a well-curated database of antibody discovery selection data generated using standardized workflows on the Kymouse humanized mouse platform. The current release includes 11 Kymouse platform mice immunisation studies covering 51 immunogens, more than 120,000 paired heavy-light chain sequences, and binding measurements for a selected subset of experimentally characterized clones. By capturing full-funnel selection data with consistent metadata and both positive and negative experimental outcomes, KyDab provides a valuable data resource for the development and evaluation of artificial intelligence models for antibody discovery. KyDab is accessible at https://kydab.naturalantibody.com/, and the database will be continuously updated as new datasets become available.

bioinformatics↗

bioRxiv2026

RePaRank: An Efficient Architecture for Antibody-Antigen Interface Prediction by Proximity Ranking

The prediction of protein-protein interactions is central to structural biology, yet leading models are often computationally expensive, creating an accessibility gap for many high-throughput applications. Furthermore, common evaluation metrics such as binary contact prediction can be unreliable. In this work, we address both challenges. We introduce RePaRank, a computationally efficient deep learning architecture with 39.4 million parameters that predicts antibody-antigen interfaces by reframing the problem as a proximity ranking task in a learned embedding space. We also propose the Precision AUC, a robust, ranking-based metric that provides a more stable assessment of model performance than traditional binary methods. Our experiments show that RePaRank consistently outperforms benchmark models in paratope prediction and is highly competitive in epitope prediction among models that do not require external resources such as Multiple Sequence Alignments (MSA). RePaRank offers a practical and powerful tool for the immunoinformatics community.

immunology↗

bioRxiv2025

ASD: Antigen-Specific Antibody Database

The development of computational models addressing therapeutic antibodies faces significant challenges due to the scarcity of data. A critical data element is the set of antibody-antigen interaction pairs associated with sequences. To address this issue, we developed the Antigen Specific Antibody Database (ASD, https://naturalantibody.com/agab/), a database aggregating antibody-antigen interaction data from multiple studies with standardized formatting and annotations. Our dataset compilation strategy resulted in data from 15 distinct sources, resulting in 1,097,946 unique antibody-antigen interactions (with 9,575 unique antigens). The ASD database captures diverse affinity measures and qualitative binding assessment, along with metadata including UniProt and PDB identifiers, target protein names, confidence levels, and experimental conditions. Through this integration drive, we make available an ample resource of interaction data gathered from the public domain to act as a foundation for model development and further data generation.

bioinformatics↗

bioRxiv2025

NAStructuralDB : Structural database to facilitate computational studies of molecular modeling and recognition of proteins with special focus on antibody-antigen interactions.

Studying the interactions between antibodies and antigens is fundamental to the development of novel therapeutic biologics. Predictions of such interactions start with data collection. Though there exist reliable resources to identify antibody structures in the Protein Data Bank (PDB), such data still requires substantial processing to be usable in predictive tasks. Redundancy in sequences needs to be removed to avoid data leakages between train, test and validation sets. Descriptors such as surface accessibility, secondary structure and antibody region information need to be additionally annotated. Information on inter- and intra-molecular contacts, which is crucial to studying paratope/epitope information, needs to be collected. The specialized immunoglobulin format of Nanobodies(R) requires a separate dataset mirroring that of antibodies, given that their structure contains only a single VHH chain. Because antibody-antigen structures account for a small amount of all protein-protein contacts, having a molecular contact reference from other proteins is also desired. To address these issues, we introduce NAStructuralDB (https://naturalantibody.com/na-structural/), a dataset of processed structures of antibodies, Nanobodies(R), proteins and their complexes with molecular contact information and associated annotations. We use the opportunity of having collected the contact data to provide a reference of binding propensities of different residues across distinct contact types. We anticipate that this dataset will accelerate a broad range of predictive tasks by standardizing common, time-consuming data preparation steps in antibody and protein design.

bioinformatics↗

bioRxiv2025

Herding cats: predicting immunogenicity from heterogeneous clinical trials data

Antibodies represent the largest and fastest growing class of biologic therapeutics, yet forecasting their clinical performance, particularly immunogenicity, remains a major hurdle in drug development. Despite hundreds of antibody-based drugs progressing through clinical pipelines, systematic integration of their clinical outcomes has been limited by fragmented and heterogeneous data. Here, we present the Therapeutic Antibody Database, a comprehensive and curated resource that links therapeutic antibodies to clinical trial outcomes, with a dedicated focus on immunogenicity. Our dataset is sourced from approximately 11,500 anti-drug antibody (ADA) measurements across diverse molecules and indications, offering an unprecedented view into the clinical manifestation of immune responses to biologics. In order to evaluate the main drivers of ADA, we evaluate gathered immunogenicity incidence and prevalence data against various therapeutic descriptors which includes sequence, structure and contextual features related to therapeutics. We find that most tools have very poor performance, and we pinpoint the causes of it, demonstrating the need for systems immunology approaches incorporating clinical metadata beyond biochemical properties of the molecules alone.

bioinformatics↗

bioRxiv2025

Benchmarking antigen-aware inverse folding methods for antibody design.

Computational antibody design has seen many recent advances pioneered via the use of language models and advanced structure prediction tools. Developing a de novo antibody against a specific antigen requires structural awareness that most language models lack. A prominent class of machine learning methods combining the best of language model and structural worlds is inverse folding. This approach aims to predict a sequence that would fit a given structure. Such methods are now increasingly used to predict alternate sequences given a structure of a binder. It is known that, just like language models, such methods have certain predictive power in identifying binders. Here we performed a set of tests to reveal where, if at all, such methods provide value in the realistic setting of antibody discovery.

bioinformatics↗

bioRxiv2025

AbDesign: Database of point mutants of antibodies with associated structures reveals poor generalization of binding predictions from machine learning models.

Antibodies are naturally evolved molecular recognition scaffolds that can bind a variety of surfaces. Their designability is crucial to the development of biologics, with computational methods holding promise in accelerating the delivery of medicines to the clinic. Modeling antibody-antigen recognition is prohibitively difficult, with data paucity being one of the biggest hurdles. Current affinity datasets comprise a small number of experimental measurements, which are often not standardized between molecules. Here, we address these issues by creating a dataset of seven antigens with two antibodies each, for which we introduce a heterogeneous set of mutations to the CDR-H3 measured by ELISA. Each of the parental complexes has a known crystal structure. We perform benchmarking of state-of-the-art affinity prediction algorithms to gauge their effectiveness. Current computational methods exhibit significant limitations in accurately predicting the effects of single-point mutations. In contrast, the older empirical, physics-based method FoldX, performs well in identifying mutants that retain binding. These findings highlight the need for more resources like the one presented here -- large, molecularly diverse, and experimentally consistent datasets.

bioinformatics↗

bioRxiv2025

nanoFOLD : sequence design of nanobodies via inverse folding

Antibodies devoid of light chains are a promising class of biotherapeutics. Computational methods that address these molecules are crucially needed to accelerate the traditional, long and expensive experimental process of their discovery. Inverse folding, wherein one is tasked to predict a sequence given molecular coordinates, is an established method in scaffold-based protein design. Here we develop an inverse folding method speci[fi]c to nanobodies. We demonstrate its application in nanobody-engineering scenarios of enriching binders from next-generation sequencing experiments and novel binder design.

bioinformatics↗

bioRxiv2025

Deciphering the Host-Pathogen Interface in COVID-19: The precision molecular insight into epitranscriptomic modifications of high-impact transcripts

The COVID-19 pandemic, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has had a profound global impact since its emergence in late 2019. Characterized by a wide spectrum of clinical manifestations, ranging from asymptomatic infection to severe respiratory distress and death, COVID-19 has necessitated extensive research into the host-pathogen interactions that drive disease progression. Understanding the molecular mechanisms underlying the host response to SARS-CoV-2 infection is crucial for the development of effective therapeutic interventions and preventative strategies. This study employed a multi-omic approach that combined direct RNA sequencing (DRS) and Illumina cDNA sequencing to investigate whole blood transcriptomic profiles in COVID-19 patients. By leveraging the unique capabilities of Nanopore DRS, which provides long-read sequencing data, we were able to capture not only gene expression levels but also crucial RNA modifications, including poly(A) tail length, non-adenine residue (non-A), pseudouridylation (psU), and 5-methylcytosine (m5C) methylation. This comprehensive analysis allowed us to identify differentially expressed genes (DEGs) and explore the impact of these RNA modifications on gene expression and function within the context of COVID-19. Our findings reveal significant alterations in gene expression patterns, poly(A) tail lengths, non-A and the prevalence of psU and m5C modifications in COVID-19 patients compared to healthy controls. These results provide valuable insights into the complex interplay between viral infection, host immune response, and RNA processing, contributing to a deeper understanding of COVID-19 pathogenesis.

genetics↗

bioRxiv2024

Conserved heavy/light contacts and germline preferences revealed by a large-scale analysis of natively paired human antibody sequences and structural data.

Antibody next-generation sequencing (NGS) datasets have become crucial to develop computational models addressing this successful class of therapeutics. Although antibodies are composed of both heavy and light chains, most NGS sequencing depositions provide them in unpaired form, reducing their utility. Here we introduce PairedAbNGS, a novel database with paired heavy/light antibody chains. To the best of our knowledge, this is the largest resource for paired natural antibody sequences with 58 bioprojects and over 14 million assembled productive sequences. We make the database accessible at http://naturalantibody.com/paired-ngs as a valuable tool for biological and machine-learning applications. Using this dataset, we investigated heavy and light chain variable (V) gene pairing preferences and found significant biases beyond gene usage frequencies, possibly due to receptor editing favoring less autoreactive combinations. Analyzing the available antibody structures from the Protein Data Bank, we studied conserved contact residues between heavy and light chains, particularly interactions between the CDR3 region of one chain and the FWR2 region of the opposite chain. Examination of amino acid pairs at key contact sites revealed significant deviations of amino acids distributions compared to random pairings, in the heavy chains CDR3 region contacting the opposite chain, indicating specific interactions might be crucial for proper chain pairing. This observation is further reinforced by preferential IGHV-IGLJ and IGLV-IGHJ pairing preferences. We hope that both our resources and the findings would contribute to improving the engineering of biological drugs.

immunology↗

bioRxiv2024

Unlocking the Secrets of Amphibious Plant Adaptation: The Role of RNA Modifications

Post-transcriptional RNA modifications, such as N6-methyladenosine (m6A), 5-methylcytosine (m5C), and pseudouridine ({Psi}), are critical regulators of plant development, stress responses, and environmental adaptation. The modifications m6A, m5C, and {Psi} were insufficiently studied in plant stress responses. To investigate the epitranscriptomic landscape of these modifications, we employed direct RNA sequencing (DRS) to analyze native RNA from the amphibious plant Riccia fluitans grown in both aquatic and terrestrial environments. Our study revealed the presence of {Psi}, m5C, and m6A modifications in R. fluitans transcriptomes from diverse environments. We observed correlations between the occurrence of these modifications and transcript length, as well as poly(A) tail length. Furthermore, we analyzed the expression of genes encoding {Psi} synthases and methyltransferases to gain initial insights into the regulatory mechanisms underlying these processes in R. fluitans. By understanding how RNA modifications are regulated in response to environmental changes, we can unlock the secrets of the remarkable adaptability of amphibious plants. This knowledge could have eventually led to the understanding of the mechanisms of plant land colonization.

genetics↗

bioRxiv2024

RIOT - Rapid Immunoglobulin Overview Tool - annotation of nucleotide and amino acid immunoglobulin sequences using an open germline database.

Antibodies are a cornerstone of the immune system, playing a pivotal role in identifying and neutralizing infections caused by bacteria, viruses, and other pathogens. Understanding their structure, and function, can provide insights into both the bodys natural defenses and the principles behind many therapeutic interventions, including vaccines and antibody-based drugs. The analysis and annotation of antibody sequences, including the identification of variable, diversity, joining, and constant genes, as well as the delineation of framework regions and complementarity-determining regions, is essential for understanding their structure and function. Currently analyzing large volumes of antibody sequences is routine in antibody discovery, requiring fast and accurate tools. While there are existing tools designed for the annotation and numbering of antibody sequences, they often have limitations such as being restricted to either nucleotide or amino acid sequences, reliance on non-uniform germline databases, or slow execution times. Here we present Rapid Immunoglobulin Overview Tool (RIOT), a novel open-source solution for antibody numbering that addresses these shortcomings. RIOT handles nucleotide and amino acid sequence processing, comes with a free germline database, and is computationally efficient. We hope the tool will facilitate rapid annotation of antibody sequencing outputs for the benefit of understanding antibody biology and discovering novel therapeutics. AvailabilityRIOT is available at https://github.com/NaturalAntibody/riot_na.

bioinformatics↗

bioRxiv2024

Data mining antibody sequences for database searching in bottom-up proteomics

Mass spectrometry (MS)-based proteomics allows identifying and quantifying thousands of proteins but suffers from challenges when measuring human antibodies due to their vast variety. The mainly used bottom-up proteomics approaches rely on database searches that compare experimental values of peptides and their fragments to theoretical values derived from protein sequences in a database. While the human body can produce millions of distinct antibodies, the current databases for human antibodies such as UniProtKB/Swiss-Prot are limited to only 1095 sequences (as of 2024 Jan). This limitation may hinder the identification of new antibodies using mass spectrometry. Therefore, extending the database for mass spectrometry is an important task for discovering new antibodies. Recent genomic studies have compiled millions of human antibody sequences publicly accessible through the Observed Antibody Space (OAS) database. However, this data has yet to be exploited to confirm the presence of these antibodies. In this study, we adopted this extensive collection of antibody sequences for conducting efficient database searches in publicly available proteomics data with a focus on the SARS-CoV-2 disease. Thirty million heavy antibody sequences from 146 SARS-CoV-2 patients in the OAS database were digested in silico to obtain 18 million unique peptides. These peptides were then used to create new databases for bottom-up proteomics. We used those databases for searching new antibody peptides in publicly available SARS-CoV-2 human plasma samples in the Proteomics Identification Database (PRIDE). This approach avoids false positives in antibody peptide identification as confirmed by searching against negative controls (brain samples) and employing different database sizes. We show that the found sequences provide valuable information to distinguish diseased from healthy and expect that the newly discovered antibody peptides can be further employed to develop therapeutic antibodies. The method will be broadly applicable to find characteristic antibodies for other diseases.

bioinformatics↗

bioRxiv2024

nanoBERT: A deep learning model for gene agnostic navigation of the nanobody mutational space

Nanobodies are a subclass of immunoglobulins, whose binding site consists of only one peptide chain, bestowing favorable biophysical properties. Recently, the first nanobody therapy was approved, paving the way for further clinical applications of this antibody format. Further development of nanobody-based therapeutics could be streamlined by computational methods. One of such methods is infilling - positional prediction of biologically feasible mutations in nanobodies. Being able to identify possible positional substitutions based on sequence context, facilitates functional design of such molecules. Here we present nanoBERT, a nanobody-specific transformer to predict amino acids in a given position in a query sequence. We demonstrate the need to develop such machine-learning based protocol as opposed to gene-specific positional statistics since appropriate genetic reference is not available. We benchmark nanoBERT with respect to human-based language models and ESM-2, demonstrating the benefit for domain-specific language models. We also demonstrate the benefit of employing nanobody-specific predictions for fine-tuning on experimentally measured thermostability dataset. We hope that nanoBERT will help engineers in a range of predictive tasks for designing therapeutic nanobodies. Availabilityhttps://huggingface.co/NaturalAntibody/

bioinformatics↗

bioRxiv2023

Cartography of the developability landscapes of native and human-engineered antibodies

Designing effective monoclonal antibody (mAb) therapeutics faces a multi-parameter optimization challenge known as "developability", which reflects an antibodys ability to progress through development stages based on its physicochemical properties. While natural antibodies may provide valuable guidance for mAb selection, we lack a comprehensive understanding of natural developability parameter (DP) plasticity (redundancy, predictability, sensitivity) and how the DP landscapes of human-engineered and natural antibodies relate to one another. These gaps hinder fundamental developability profile cartography. To chart natural and engineered DP landscapes, we computed 40 sequence- and 46 structure-based DPs of over two million native and human-engineered single-chain antibody sequences. We found lower redundancy among structure-based compared to sequence-based DPs. Sequence DP sensitivity to single amino acid substitutions varied by antibody region and DP, and structure DP values varied across the conformational ensemble of antibody structures. Sequence DPs were more predictable than structure-based ones across different machine-learning tasks and embeddings, indicating a constrained sequence-based design space. Human-engineered antibodies were localized within the developability and sequence landscapes of natural antibodies, suggesting that human-engineered antibodies explore mere subspaces of the natural one. Our work quantifies the plasticity of antibody developability, providing a fundamental resource for multi-parameter therapeutic mAb design.

bioinformatics↗

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↗

bioRxiv2022

Structural pre-training improves physical accuracy of antibody structure prediction using deep learning.

Protein folding problem obtained a practical solution recently, owing to advances in deep learning. There are classes of proteins though, such as antibodies, that are structurally unique, where the general solution still lacks. In particular, the prediction of the CDR-H3 loop, which is an instrumental part of an antibody in its antigen recognition abilities, remains a challenge. Antibody-specific deep learning frameworks were proposed to tackle this problem noting great progress, both on accuracy and speed fronts. Oftentimes though, the original networks produce physically implausible bond geometries that then need to undergo a time-consuming energy minimization process. Here we hypothesized that pre-training the network on a large, augmented set of models with correct physical geometries, rather than a small set of real antibody X-ray structures, would allow the network to learn better bond geometries. We show that fine-tuning such a pre-trained network on a task of shape prediction on real X-ray structures improves the number of correct peptide bond distances. We further demonstrate that pre-training allows the network to produce physically plausible shapes on an artificial set of CDR-H3s, showing the ability to generalize to the vast antibody sequence space. We hope that our strategy will benefit the development of deep learning antibody models that rapidly generate physically plausible geometries, without the burden of time-consuming energy minimization.

bioinformatics↗