Biology subjects

Demharter, S.

Publications and source records attributed to Demharter, S..

8 recordsLinked to original sources

bioRxiv2026

EpiRanha: Hunting for Epitope Similarity with a Structure- and Residue-Aware Graph Neural Network

AO_SCPLOWBSTRACTC_SCPLOWPrecise epitope recognition underpins the efficacy and safety of therapeutic antibodies, yet existing approaches to epitope similarity scoring rely largely on sequence identity or rigid structural superposition, limiting their ability to robustly assess cross-reactivity and potential off-target interactions. We introduce EpiRanha, a multimodal framework that integrates residue-level ESM-2 sequence embeddings with an E(n)-equivariant graph neural network operating on three-dimensional protein structure. EpiRanha produces per-residue "fingerprints" that jointly encode sequence-level context and spatial organization, and then applies a beam-search strategy to identify and rank multiple high-confidence epitope candidates across protein surfaces that are similar to a given query epitope. We evaluate EpiRanha against TM-align on nanobody-antigen complexes from SAbDab-nano and a set of AlphaFold-predicted proteins. EpiRanha consistently recovers the query epitope on its cognate antigen, including highly discontiguous conformational epitopes that rigid alignment methods such as TM-align often fail to capture, achieving lower structural loss and fewer false negatives through flexible residue-level mapping. Beyond these self-matches, EpiRanha also identifies biologically plausible epitope-level similarities on other proteins. Overall, EpiRanha advances epitope characterization beyond sequence or geometry alone, enabling more robust off-target risk assessment, informing training-set construction for predictive models, and more selective antibody design.

bioinformatics↗

bioRxiv2026

Effects of protein interface mutations on protein quality and affinity

Accurately modeling antibody-antigen interactions requires distinguishing intrinsic binding affinity ("protein-interaction") from protein biophysical properties ("protein-quality"), including folding, stability, and expression. However, high-throughput mutational measurements commonly used to train and benchmark computational models often conflate these effects, obscuring the true determinants of molecular recognition. Here, we present an experimental and analytical framework to disentangle protein-interaction effects from protein-quality effects in single-domain antibody (VHH)-antigen binding. Using a large-scale deep mutational scanning (DMS) dataset spanning four VHH-antigen complexes, with single and double mutations in both partners, we introduce control binders to quantify protein-quality changes independently of protein-interaction. This enables decomposition of experimentally measured affinity into protein-interaction and protein-quality components at scale. Leveraging the disentangled dataset, we evaluated state-of-the-art structure- and sequence-based models for protein-quality and protein-interaction prediction and show that their performance largely reflects protein-quality rather than protein-interaction effects. Our results highlight a major confounder in current datasets and suggest that accounting for protein-quality will be essential for training next-generation affinity-prediction models. Nomenclature Antibody related termsO_LIPrimary VHH: The VHH of a VHH-antigen complex for which the paratope and the epitope weremutated. C_LIO_LIControl VHH: A second VHH that binds to the same antigen as the primary VHH but has non-overlapping epitope positions and therefore does not bind to any of the mutated antigen positions. C_LI Affinity-related termsO_LIReal Affinity: "The strength of the interaction between two [...] molecules that bind reversibly (interact)" 1. In the context of antibody-antigen binding, it quantifies interactions between active proteins (which are expressed and correctly folded 2 and are therefore functionally and biologically active (see below). It is commonly quantified by the equilibrium dissociation constant, KD. C_LIO_LIObserved affinity ({degrees}KD): The interaction strength experimentally measured between two molecules. Unlike real affinity, this value is confounded by the biophysical properties of the individual binding partners, specifically their folding, stability, and expression levels. Consequently, the observed affinity often differs from the real/intrinsic affinity if a significant fraction of the protein population is inactive 3. NOTE: Unless otherwise specified, {degrees}KD is reported in - log10 space. For example, a {degrees}KD of -9 corresponds to 10-9M or 1nM. C_LIO_LIChange in observed affinity ({Delta}{degrees}KD): The shift in the observed affinity between two proteins upon mutation, reported as the log10-transformed fold change. A value of 1 reflects a 10-fold difference, a value of 2 a 100-fold difference, etc. This aggregate change resolves into two distinct biophysical components 2, 4: O_LIProtein-interaction change: The change in the intrinsic thermodynamic affinity between the two binding partners, each in its active state (i.e., the specific change in interface Gibbs free energy because both enthalpy and entropy are considered). C_LIO_LIProtein-quality change: The change in the fraction of the mutated protein population that is biologically active - meaning it is expressed, correctly folded, and stable 2, 5. O_LIFolding: The process that guides the polypeptide chain toward its native conformation, which is a prerequisite for forming a functional binding site. C_LIO_LIStability: The thermodynamic capacity to maintain the folded structure over time and under physiological conditions. Stability (decrease in Gibbs free energy from the unfolded to the folded state) ensures the binding interface remains intact and prevents competing processes such as aggregation 6. C_LIO_LIExpression: The steady-state abundance of the protein. This is largely dependent on proper folding and stability, as cellular quality control mechanisms degrade proteins that fail to fold or remain stable at functional concentrations. C_LI C_LI C_LIO_LIChange in relative affinity ({Delta}{Delta}{degrees}KD): the difference between the {Delta}{degrees}KD of the primary VHH compared to the control VHH for a given epitope mutation. C_LI Model-related termsO_LIESM-IF1 sc: Single-chain (sc) structure-conditioned inverse folding model (ESM-IF1), using the isolated monomer structure of the mutated protein: either the VHH or the antigen 7. C_LIO_LIESM-IF1 mc: Multi-chain (mc) structure-conditioned model (ESM-IF1), using the full complex structure (both antibody and antigen) 7. C_LIO_LIStability prediction score: Score that represents the predicted change in stability based on a single mutation, normally represented as {Delta}{Delta}G. C_LI

molecular biology↗

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

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↗

bioRxiv2024

A single dose of cocaine rewires the 3D genome structure of midbrain dopamine neurons

Midbrain dopamine neurons (DNs) respond to a first exposure to addictive drugs and play key roles in chronic drug usage1-3. As the synaptic and transcriptional changes that follow an acute cocaine exposure are mostly resolved within a few days4,5, the molecular changes that encode the long-term cellular memory of the exposure within DNs remain unknown. To investigate whether a single cocaine exposure induces long-term changes in the 3D genome structure of DNs, we applied Genome Architecture Mapping and single nucleus transcriptomic analyses in the mouse midbrain. We found extensive rewiring of 3D genome architecture at 24 hours past exposure which remains or worsens by 14 days, outlasting transcriptional responses. The cocaine-induced chromatin rewiring occurs at all genomic scales and affects genes with major roles in cocaine-induced synaptic changes. A single cocaine exposure triggers extensive long-lasting changes in chromatin condensation in post-synaptic and post-transcriptional regulatory genes, for example the unfolding of Rbfox1 which becomes most prominent 14 days post exposure. Finally, structurally remodeled genes are most expressed in a specific DN sub-type characterized by low expression of the dopamine auto-receptor Drd2, a key feature of highly cocaine-sensitive cells. These results reveal an important role for long-lasting 3D genome remodelling in the cellular memory of a single cocaine exposure, providing new hypotheses for understanding the inception of drug addiction and 3D genome plasticity.

genomics↗

bioRxiv2022

Identifying interactions in omics data for clinical biomarker discovery

The identification of predictive biomarker signatures from omics data for clinical applications is an active area of research. Recent developments in assay technologies and machine learning (ML) methods have led to significant improvements in predictive performance. However, most high-performing ML methods suffer from complex architectures and lack interpretability. Here, we present the application of a novel symbolic-regression-based algorithm, the QLattice, on a selection of clinical omics data sets. This approach generates parsimonious high-performing models that can both predict disease outcomes and reveal putative disease mechanisms. Due to their high performance, simplicity and explicit functional form, these biomarker signatures can be readily explained, thereby making them attractive tools for high-stakes applications in primary care, clinical decision making and patient stratification.

bioinformatics↗

bioRxiv2018

Wiring together large single-cell RNA-seq sample collections

Single-cell RNA-seq methods are being increasingly applied in complex study designs, which involve measurements of many samples, commonly spanning multiple individuals, conditions, or tissue compartments. Joint analysis of such extensive, and often heterogeneous, sample collections requires a way of identifying and tracking recurrent cell subpopulations across the entire collection. Here we describe a flexible approach, called Conos (Clustering On Network Of Samples), that relies on multiple plausible inter-sample mappings to construct a global graph connecting all measured cells. The graph can then be used to propagate information between samples and to identify cell communities that show consistent grouping across broad subsets of the collected samples. Conos results enable investigators to balance between resolution and breadth of the detected subpopulations. In this way, it is possible to focus on the fine-grained clusters appearing within more similar subsets of samples, or analyze coarser clusters spanning broader sets of samples in the collection. Such multi-resolution joint clustering provides an important basis for downstream analysis and interpretation of sizeable multi-sample single-cell studies and atlas-scale collections.

bioinformatics↗