Robustly interrogating machine learning-based scoring functions: what are they learning?

Motivation: Machine learning-based scoring functions (MLBSFs) have been found to exhibit inconsistent performance on different benchmarks and be prone to learning dataset bias. For the field to develop MLBSFs that learn a generalisable understanding of physics, a more rigorous understanding of how they perform is required.

Results: In this work, we compared the performance of a diverse set of popular MLBSFs (RFScore, SIGN, OnionNet-2, Pafnucy, and PointVS) to our proposed baseline models that can only learn dataset biases on a range of benchmarks.

Challenges and compromises: Predicting unbound antibody structures with deep learning.

Therapeutic antibodies are manufactured, stored and administered in the free state; this makes understanding the unbound form key to designing and improving development pipelines. Prediction of unbound antibodies is challenging, specifically modelling of the CDRH3 loop, where inaccuracies are potentially worse due to a bias in structural data towards antibody-antigen complexes. This class imbalance provides a challenge for deep learning models trained on this data, potentially limiting generalisation to unbound forms.

Fragmenstein: predicting protein-ligand structures of compounds derived from known crystallographic fragment hits using a strict conserved-binding-based methodology.

Current strategies centred on either merging or linking initial hits from fragment-based drug design (FBDD) crystallographic screens generally do not fully leaverage 3D structural information. We show that an algorithmic approach (Fragmenstein) that 'stitches' the ligand atoms from this structural information together can provide more accurate and reliable predictions for protein-ligand complex conformation than general methods such as pharmacophore-constrained docking. This approach works under the assumption of conserved binding: when a larger molecule is designed containing the initial fragment hit, the common substructure between the two will adopt the same binding mode.

The molecular reach of antibodies crucially underpins their viral neutralisation capacity.

Key functions of antibodies, such as viral neutralisation, depend on high-affinity binding. However, viral neutralisation poorly correlates with antigen affinity for reasons that have been unclear. Here, we use a new mechanistic model of bivalent binding to study  >45 patient-isolated IgG1 antibodies interacting with SARS-CoV-2 RBD surfaces.

Antibody Design with SE(3) Diffusion.

We introduce , 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 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.

Quantifying conformational changes in the TCR:pMHC-I binding interface.

Background: T cells form one of the key pillars of adaptive immunity. Using their surface bound T cell antigen receptors (TCRs), these cells screen millions of antigens presented by major histocompatibility complex (MHC) or MHC-like molecules. In other protein families, the dynamics of protein-protein interactions have important implications for protein function.

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.

Humatch - fast, gene-specific joint humanisation of antibody heavy and light chains.

Antibodies are a popular and powerful class of therapeutic due to their ability to exhibit high affinity and specificity to target proteins. However, the majority of antibody therapeutics are not genetically human, with initial therapeutic designs typically obtained from animal models. Humanization of these precursors is essential to reduce immunogenic risks when administered to humans.

p-IgGen: a paired antibody generative language model.

Summary: A key challenge in antibody drug discovery is designing novel sequences that are free from developability issues-such as aggregation, polyspecificity, poor expression, or low solubility. Here, we present p-IgGen, a protein language model for paired heavy-light chain antibody generation. The model generates diverse, antibody-like sequences with pairing properties found in natural antibodies.

Addressing the antibody germline bias and its effect on language models for improved antibody design.

Motivation: The versatile binding properties of antibodies have made them an extremely important class of biotherapeutics. However, therapeutic antibody development is a complex, expensive, and time-consuming task, with the final antibody needing to not only have strong and specific binding but also be minimally impacted by developability issues. The success of transformer-based language models in protein sequence space and the availability of vast amounts of antibody sequences, has led to the development of many antibody-specific language models to help guide antibody design.

The future of machine learning for small-molecule drug discovery will be driven by data.

Many studies have prophesied that the integration of machine learning techniques into small-molecule therapeutics development will help to deliver a true leap forward in drug discovery. However, increasingly advanced algorithms and novel architectures have not always yielded substantial improvements in results. In this Perspective, we propose that a greater focus on the data for training and benchmarking these models is more likely to drive future improvement, and explore avenues for future research and strategies to address these data challenges.

PLAbDab-nano: a database of camelid and shark nanobodies from patents and literature.

Nanobodies are essential proteins of the adaptive immune systems of camelid and shark species, complementing conventional antibodies. Properties such as their relatively small size, solubility and high thermostability make VHH (variable heavy domain of the heavy chain) and VNAR (variable new antigen receptor) modalities a promising therapeutic format and a valuable resource for a wide range of biological applications. The volume of academic literature and patents related to nanobodies has risen significantly over the past decade.

A comparative study of the developability of full-length antibodies, fragments, and bispecific formats reveals higher stability risks for engineered constructs.

Engineered antibody formats, such as antibody fragments and bispecifics, have the potential to offer improved therapeutic efficacy compared to traditional full-length monoclonal antibodies (mAbs). However, the translation of these non-natural molecules into successful therapeutics can be hampered by developability challenges. Here, we systematically analyzed 64 different antibody constructs targeting Tumor Necrosis Factor (TNF) which cover 8 distinct molecular format families, encompassing full-length antibodies, various types of single chain variable fragments, and bispecifics.

ABodyBuilder3: improved and scalable antibody structure predictions.

Summary: In this article, we introduce ABodyBuilder3, an improved and scalable antibody structure prediction model based on ABodyBuilder2. 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.

Towards the accurate modelling of antibody-antigen complexes from sequence using machine learning and information-driven docking.

Motivation: Antibody-antigen complex modelling is an important step in computational workflows for therapeutic antibody design. While experimentally determined structures of both antibody and the cognate antigen are often not available, recent advances in machine learning-driven protein modelling have enabled accurate prediction of both antibody and antigen structures. Here, we analyse the ability of protein-protein docking tools to use machine learning generated input structures for information-driven docking.

Assessing AF2's ability to predict structural ensembles of proteins.

Recent breakthroughs in protein structure prediction have enhanced the precision and speed at which protein configurations can be determined. Additionally, molecular dynamics (MD) simulations serve as a crucial tool for capturing the conformational space of proteins, providing valuable insights into their structural fluctuations. However, the scope of MD simulations is often limited by the accessible timescales and the computational resources available, posing challenges to comprehensively exploring protein behaviors.

The Observed T Cell Receptor Space database enables paired-chain repertoire mining, coherence analysis, and language modeling.

T cell activation is governed through T cell receptors (TCRs), heterodimers of two sequence-variable chains (often an α and β chain) that synergistically recognize antigen fragments presented on cell surfaces. Despite this, there only exist repositories dedicated to collecting single-chain, not paired-chain, TCR sequence data. We addressed this gap by creating the Observed TCR Space (OTS) database, a source of consistently processed and annotated, full-length, paired-chain TCR sequences.

Prospects for the computational humanization of antibodies and nanobodies.

To be viable therapeutics, antibodies must be tolerated by the human immune system. Rational approaches to reduce the risk of unwanted immunogenicity involve maximizing the 'humanness' of the candidate drug. However, despite the emergence of new discovery technologies, many of which start from entirely human gene fragments, most antibody therapeutics continue to be derived from non-human sources with concomitant humanization to increase their human compatibility.

Can AlphaFold's breakthrough in protein structure help decode the fundamental principles of adaptive cellular immunity?

T cells are essential immune cells responsible for identifying and eliminating pathogens. Through interactions between their T-cell antigen receptors (TCRs) and antigens presented by major histocompatibility complex molecules (MHCs) or MHC-like molecules, T cells discriminate foreign and self peptides. Determining the fundamental principles that govern these interactions has important implications in numerous medical contexts.

Prediction of polyspecificity from antibody sequence data by machine learning.

Antibodies are generated with great diversity in nature resulting in a set of molecules, each optimized to bind a specific target. Taking advantage of their diversity and specificity, antibodies make up for a large part of recently developed biologic drugs. For therapeutic use antibodies need to fulfill several criteria to be safe and efficient.

Orthogonal IMiD-Degron Pairs Induce Selective Protein Degradation in Cells.

Immunomodulatory imide drugs (IMiDs) including thalidomide, lenalidomide, and pomalidomide, can be used to induce degradation of a protein of interest that is fused to a short zinc finger (ZF) degron motif. These IMiDs, however, also induce degradation of endogenous neosubstrates, including IKZF1 and IKZF3. To improve degradation selectivity, we took a bump-and-hole approach to design and screen bumped IMiD analogs against 8380 ZF mutants.