arXiv subjects

Frédéric A. Dreyer

Publications and source records attributed to Frédéric A. Dreyer.

At least 19 recordsLinked to original sources

arXiv2026

Disentangling multispecific antibody function with graph neural networks

Multispecific antibodies offer transformative therapeutic potential by engaging multiple epitopes simultaneously, yet their efficacy is an emergent property governed by complex molecular architectures. Rational design is often bottlenecked by the inability to predict how subtle changes in domain topology influence functional outcomes, a challenge exacerbated by the scarcity of comprehensive experimental data. Here, we introduce a computational framework to address part of this gap. First, we present a generative method for creating large-scale, realistic synthetic functional landscapes that capture non-linear interactions where biological activity depends on domain connectivity. Second, we propose a graph neural network architecture that explicitly encodes these topological constraints, distinguishing between format configurations that appear identical to sequence-only models. We demonstrate that this model, trained on synthetic landscapes, recapitulates complex functional properties and, via transfer learning, has the potential to achieve high predictive accuracy on limited biological datasets. We showcase the model's utility by optimizing trade-offs between efficacy and toxicity in trispecific T-cell engagers and retrieving optimal common light chains. This work provides a robust benchmarking environment for disentangling the combinatorial complexity of multispecifics, accelerating the design of next-generation therapeutics.

q-bio.BM↗

arXiv2025

Tokenizing Loops of Antibodies

The complementarity-determining regions of antibodies are loop structures that are key to their interactions with antigens, and of high importance to the design of novel biologics. Since the 1980s, categorizing the diversity of CDR structures into canonical clusters has enabled the identification of key structural motifs of antibodies. However, existing approaches have limited coverage and cannot be readily incorporated into protein foundation models. Here we introduce ImmunoGlobulin LOOp Tokenizer, Igloo, a multimodal antibody loop tokenizer that encodes backbone dihedral angles and sequence. Igloo is trained using a contrastive learning objective to map loops with similar backbone dihedral angles closer together in latent space. Igloo can efficiently retrieve the closest matching loop structures from a structural antibody database, outperforming existing methods on identifying similar H3 loops by 5.9\%. Igloo assigns tokens to all loops, addressing the limited coverage issue of canonical clusters, while retaining the ability to recover canonical loop conformations. To demonstrate the versatility of Igloo tokens, we show that they can be incorporated into protein language models with IglooLM and IglooALM. On predicting binding affinity of heavy chain variants, IglooLM outperforms the base protein language model on 8 out of 10 antibody-antigen targets. Additionally, it is on par with existing state-of-the-art sequence-based and multimodal protein language models, performing comparably to models with $7\times$ more parameters. IglooALM samples antibody loops which are diverse in sequence and more consistent in structure than state-of-the-art antibody inverse folding models. Igloo demonstrates the benefit of introducing multimodal tokens for antibody loops for encoding the diverse landscape of antibody loops, improving protein foundation models, and for antibody CDR design.

q-bio.BM↗

arXiv2025

Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins

We introduce Ibex, a pan-immunoglobulin structure prediction model that achieves state-of-the-art accuracy in modeling the variable domains of antibodies, nanobodies, and T-cell receptors. Unlike previous approaches, Ibex explicitly distinguishes between bound and unbound protein conformations by training on labeled apo and holo structural pairs, enabling accurate prediction of both states at inference time. Using a comprehensive private dataset of high-resolution antibody structures, we demonstrate superior out-of-distribution performance compared to existing specialized and general protein structure prediction tools. Ibex combines the accuracy of cutting-edge models with significantly reduced computational requirements, providing a robust foundation for accelerating large molecule design and therapeutic development.

q-bio.BM↗

arXiv2024

Assessing interaction recovery of predicted protein-ligand poses

The field of protein-ligand pose prediction has seen significant advances in recent years, with machine learning-based methods now being commonly used in lieu of classical docking methods or even to predict all-atom protein-ligand complex structures. Most contemporary studies focus on the accuracy and physical plausibility of ligand placement to determine pose quality, often neglecting a direct assessment of the interactions observed with the protein. In this work, we demonstrate that ignoring protein-ligand interaction fingerprints can lead to overestimation of model performance, most notably in recent protein-ligand cofolding models which often fail to recapitulate key interactions.

q-bio.BM↗

arXiv2024

ABodyBuilder3: Improved and scalable antibody structure predictions

Accurate prediction of antibody structure is a central task in the design and development of monoclonal antibodies, notably to understand both their developability and their binding properties. In this article, we introduce ABodyBuilder3, an improved and scalable antibody structure prediction model based on ImmuneBuilder. We achieve a new state-of-the-art accuracy in the modelling of CDR loops by leveraging language model embeddings, and show how predicted structures can be further improved through careful relaxation strategies. Finally, we incorporate a predicted Local Distance Difference Test into the model output to allow for a more accurate estimation of uncertainties.

q-bio.BM↗

arXiv2024

De novo antibody design with SE(3) diffusion

We introduce IgDiff, an antibody variable domain diffusion model based on a general protein backbone diffusion framework which was extended to handle multiple chains. Assessing the designability and novelty of the structures generated with our model, we find that IgDiff produces highly designable antibodies that can contain novel binding regions. The backbone dihedral angles of sampled structures show good agreement with a reference antibody distribution. We verify these designed antibodies experimentally and find that all express with high yield. Finally, we compare our model with a state-of-the-art generative backbone diffusion model on a range of antibody design tasks, such as the design of the complementarity determining regions or the pairing of a light chain to an existing heavy chain, and show improved properties and designability.

q-bio.BM↗

arXiv2024

Large scale paired antibody language models

Antibodies are proteins produced by the immune system that can identify and neutralise a wide variety of antigens with high specificity and affinity, and constitute the most successful class of biotherapeutics. With the advent of next-generation sequencing, billions of antibody sequences have been collected in recent years, though their application in the design of better therapeutics has been constrained by the sheer volume and complexity of the data. To address this challenge, we present IgBert and IgT5, the best performing antibody-specific language models developed to date which can consistently handle both paired and unpaired variable region sequences as input. These models are trained comprehensively using the more than two billion unpaired sequences and two million paired sequences of light and heavy chains present in the Observed Antibody Space dataset. We show that our models outperform existing antibody and protein language models on a diverse range of design and regression tasks relevant to antibody engineering. This advancement marks a significant leap forward in leveraging machine learning, large scale data sets and high-performance computing for enhancing antibody design for therapeutic development.

q-bio.BM↗

arXiv2023

Inverse folding for antibody sequence design using deep learning

We consider the problem of antibody sequence design given 3D structural information. Building on previous work, we propose a fine-tuned inverse folding model that is specifically optimised for antibody structures and outperforms generic protein models on sequence recovery and structure robustness when applied on antibodies, with notable improvement on the hypervariable CDR-H3 loop. We study the canonical conformations of complementarity-determining regions and find improved encoding of these loops into known clusters. Finally, we consider the applications of our model to drug discovery and binder design and evaluate the quality of proposed sequences using physics-based methods.

q-bio.BM↗

arXiv2023

Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddings

Entity linking methods based on dense retrieval are an efficient and widely used solution in large-scale applications, but they fall short of the performance of generative models, as they are sensitive to the structure of the embedding space. In order to address this issue, this paper introduces DUCK, an approach to infusing structural information in the space of entity representations, using prior knowledge of entity types. Inspired by duck typing in programming languages, we propose to define the type of an entity based on the relations that it has with other entities in a knowledge graph. Then, porting the concept of box embeddings to spherical polar coordinates, we propose to represent relations as boxes on the hypersphere. We optimize the model to cluster entities of similar type by placing them inside the boxes corresponding to their relations. Our experiments show that our method sets new state-of-the-art results on standard entity-disambiguation benchmarks, it improves the performance of the model by up to 7.9 F1 points, outperforms other type-aware approaches, and matches the results of generative models with 18 times more parameters.

cs.CL↗

arXiv2023

Multilingual End to End Entity Linking

Entity Linking is one of the most common Natural Language Processing tasks in practical applications, but so far efficient end-to-end solutions with multilingual coverage have been lacking, leading to complex model stacks. To fill this gap, we release and open source BELA, the first fully end-to-end multilingual entity linking model that efficiently detects and links entities in texts in any of 97 languages. We provide here a detailed description of the model and report BELA's performance on four entity linking datasets covering high- and low-resource languages.

cs.CL↗

arXiv2022

Precise predictions for double-Higgs production via vector-boson fusion

Theoretical predictions with next-to-next-to-leading order (NNLO) QCD accuracy combined with the next-to-leading order (NLO) electroweak (EW) corrections are presented for differential observables of the double-Higgs production process via vector-boson fusion. While the QCD corrections were previously known, the EW ones are computed here for the first time. The numerical results are obtained for a realistic experimental set-up at the LHC and are presented in the form of fiducial cross sections and differential distributions. Within this setup we find that the VBF approximation employed in the NNLO QCD correction is accurate at the sub-percent level. We find that the NLO EW corrections within the fiducial volume are $-6.1\%$, making them of almost the same order as the NLO QCD corrections. In some kinematic regions they can grow as large as $-30\%$ making them the dominant radiative corrections. When the EW corrections are combined with the NNLO QCD corrections we find a total correction of $-14.8\%$. The results presented here thus comprise the state-of-the-art theoretical predicition for the double-Higgs production via vector-boson fusion, which will be of value to the high-luminosity programme at the LHC.

hep-ph↗

arXiv2022

On the impact of non-factorisable corrections in VBF single and double Higgs production

We study the factorisable and non-factorisable QCD corrections to Vector-Boson Fusion single and double Higgs production and show the combined corrections for both processes at $\mathcal{O}(α_s^2)$. We investigate the validity of the eikonal approximation with and without selection cuts, and carry out an in-depth study of the relative size of the non-factorisable next-to-next-to-leading order corrections compared to the factorisable ones. In the case of single Higgs production, after selection cuts are applied, the non-factorisable corrections are found to be mostly contained within the factorisable scale uncertainty bands. When no cuts are applied, instead, the non-factorisable corrections are slightly outside the scale uncertainty band. Interestingly, for double Higgs production, we find that both before and after applying cuts, non-factorisable corrections are enhanced compared to the single Higgs case. We trace this enhancement to the existence of delicate cancellations between the various leading-order Feynman diagrams, which are partly spoiled by radiative corrections. All the studied contributions have been implemented in proVBFH v1.2.0 and proVBFHH v1.1.0.

hep-ph↗

arXiv2022

Leveraging universality of jet taggers through transfer learning

A significant challenge in the tagging of boosted objects via machine-learning technology is the prohibitive computational cost associated with training sophisticated models. Nevertheless, the universality of QCD suggests that a large amount of the information learnt in the training is common to different physical signals and experimental setups. In this article, we explore the use of transfer learning techniques to develop fast and data-efficient jet taggers that leverage such universality. We consider the graph neural networks LundNet and ParticleNet, and introduce two prescriptions to transfer an existing tagger into a new signal based either on fine-tuning all the weights of a model or alternatively on freezing a fraction of them. In the case of $W$-boson and top-quark tagging, we find that one can obtain reliable taggers using an order of magnitude less data with a corresponding speed-up of the training process. Moreover, while keeping the size of the training data set fixed, we observe a speed-up of the training by up to a factor of three. This offers a promising avenue to facilitate the use of such tools in collider physics experiments.

hep-ph↗

arXiv2021

Higher-order non-global logarithms from jet calculus

Non-global QCD observables are characterised by a sensitivity to the full angular distribution of soft radiation emitted coherently in hard scattering processes. This complexity poses a challenge to their all-order resummation, that was formulated at the leading-logarithmic order about two decades ago. In this article we present a solution to the long-standing problem of their resummation beyond this order, and carry out the first complete next-to-leading logarithmic calculation for non-global observables. This is achieved by solving numerically the recently derived set of non-linear differential equations which describe the evolution of soft radiation in the planar, large-$N_c$ limit. As a case study we address the calculation of the transverse energy distribution in the interjet rapidity region in $e^+e^-\to$ dijet production. The calculation is performed by means of an algorithm that we formulate in the language of jet-calculus generating functionals, which also makes the resummation technique applicable to more general non-global problems, such as those that arise in hadronic collisions. We find that NLL corrections are substantial and their inclusion leads to a significant reduction of the perturbative scale uncertainties for these observables. The computer code used in the calculations is made publicly available.

hep-ph↗

arXiv2021

Next-to-leading non-global logarithms in QCD

Non-global logarithms arise from the sensitivity of collider observables to soft radiation in limited angular regions of phase space. Their resummation to next-to-leading logarithmic (NLL) order has been a long standing problem and its solution is relevant in the context of precision all-order calculations in a wide variety of collider processes and observables. In this article, we consider observables sensitive only to soft radiation, characterised by the absence of Sudakov double logarithms, and we derive a set of integro-differential equations that describes the resummation of NLL soft corrections in the planar, large-$N_c$ limit. The resulting set of evolution equations is derived in dimensional regularisation and we additionally provide a formulation that is manifestly finite in four space-time dimensions. The latter is suitable for a numerical integration and can be generalised to treat other infrared-safe observables sensitive solely to soft wide-angle radiation. We use the developed formalism to carry out a fixed-order calculation to ${\cal O}(α_s^2)$ in full colour for both the transverse energy and energy distribution in the interjet region between two cone jets in $e^+e^-$ collisions. We find that the expansion of the resummed cross section correctly reproduces the logarithmic structure of the full QCD result.

hep-ph↗

arXiv2021

Jet tagging in the Lund plane with graph networks

The identification of boosted heavy particles such as top quarks or vector bosons is one of the key problems arising in experimental studies at the Large Hadron Collider. In this article, we introduce LundNet, a novel jet tagging method which relies on graph neural networks and an efficient description of the radiation patterns within a jet to optimally disentangle signatures of boosted objects from background events. We apply this framework to a number of different benchmarks, showing significantly improved performance for top tagging compared to existing state-of-the-art algorithms. We study the robustness of the LundNet taggers to non-perturbative and detector effects, and show how kinematic cuts in the Lund plane can mitigate overfitting of the neural network to model-dependent contributions. Finally, we consider the computational complexity of this method and its scaling as a function of kinematic Lund plane cuts, showing an order of magnitude improvement in speed over previous graph-based taggers.

hep-ph↗

arXiv2021

Framing energetic top-quark pair production at the LHC

Top-quark pair production is central to many facets of LHC physics. At leading order, the top and anti-top are produced in a back-to-back topology, however this topology accounts only for a minority of $t \bar t$ events with TeV-scale momentum transfer. The remaining events instead involve the splitting of an initial or final-state gluon to $t \bar t$. We provide simple quantitative arguments that explain why this is the case and examine the interplay between different topologies and a range of variables that characterise the event hardness. We then develop a method to classify the topologies of individual events and use it to illustrate our findings in the context of simulated events, using both top partons and suitably defined fiducial tops. For events with large $t \bar t$ invariant mass, we comment on additional features that have important experimental and theoretical implications.

hep-ph↗

arXiv2020

Parton showers beyond leading logarithmic accuracy

Parton showers are among the most widely used tools in collider physics. Despite their key importance, none so far has been able to demonstrate accuracy beyond a basic level known as leading logarithmic (LL) order, with ensuing limitations across a broad spectrum of physics applications. In this letter, we propose criteria for showers to be considered next-to-leading logarithmic (NLL) accurate. We then introduce new classes of shower, for final-state radiation, that satisfy the main elements of these criteria in the widely used large-$N_C$ limit. As a proof of concept, we demonstrate these showers' agreement with all-order analytical NLL calculations for a range of observables, something never so far achieved for any parton shower.

hep-ph↗