Biology subjects

Turnbull, O. M.

Publications and source records attributed to Turnbull, O. M..

8 recordsLinked to original sources

bioRxiv2026

Generative Language Modeling for Antibody CDR Grafting and Alignment-driven De Novo Design

Antibodies recognise their targets through hypervariable complementarity-determining regions (CDRs), which are interleaved with conserved frameworks in sequence space, making de novo CDR design an infilling problem. Autoregressive models generate residues left-to-right, which precludes full framework context during CDR generation and conflates framework and CDR likelihoods, leaving no natural prompt-response interface for feedback to steer generation. We present GenCDR, a family of LLaMa-based autoregressive language models that read all frameworks as a conditioning prompt and generate all CDRs jointly as a variable-length response, making CDR likelihoods a clean, separable target for reward attribution. The family comprises IgGenCDR, p-IgGenCDR, and NanoGenCDR, trained on unpaired, paired, and nanobody chains, respectively. GenCDR achieves the highest CDR recovery among autoregressive models and produces natural, diverse, human-like CDRs whose likelihoods correlate with fitness and developability assays. The prompt-response boundary also enables principled alignment: reward signals for binding affinity, expression, or developability can be composed to steer CDR generation. Over four rounds of alignment against antibody-antigen co-folding and developability objectives, we find that NanoGenCDR, which uses no explicit antigen encoding, can reach in silico structural interface metrics competitive with those of a structure-conditioned diffusion pipeline at roughly half the sampling budget, with more natural, developable designs. The same interface can be extended to integrate experimental feedback, opening a path to closed-loop antibody de novo design.

synthetic biology↗

bioRxiv2024

Tunicate metatranscriptomes reveal ancient virus-host co-divergence and inter-order recombination in the evolutionary history of disease-causing viruses

Tunicates are a key transitional taxon in animal evolution as the closest extant invertebrate relatives of the vertebrates. Their viruses may also reflect this transitional state. Yet, it is not known whether tunicate viruses are more closely related to vertebrate- or invertebrate-infecting viral lineages. We analysed primary and publicly available RNA libraries to extend the known diversity of tunicate-associated viruses and determine their relationship to viruses of other animals. We present evidence that influenza viruses, alphaviruses, and some mononegaviruses emerged prior to the evolution of vertebrates. We also show that the recombination of glycoproteins between different orders of RNA viruses, including between positive- and negative-sense viruses, may have shaped the evolution of multiple lineages. Our study reveals that some disease-causing RNA virus lineages were present in early chordates and highlights that the evolution of structural genes may be incongruent with that of the highly conserved RNA-dependent RNA polymerase.

microbiology↗

bioRxiv2024

Detection of exotic biosecurity threat ribgrass mosaic virus and novel tobamoviruses through metatranscriptomic sequencing of animal gut content

Ribgrass mosaic virus (RMV) and related viruses of the genus Tobamovirus (Virgaviridae) are cruciferous plant pathogens that represent a threat to global horticultural systems. In Australia, they are considered exotic biosecurity threats, and an incursion of these viruses would require rapid and strict control efforts. However, current surveillance methods for these viruses are limited. We examined whether RMV and related tobamoviruses could be detected by deep sequencing of gut metatranscriptomes of vertebrate animals and ticks. Using this method, we discovered that RMV, as well as a novel relative of RMV, and two highly diverse novel tobamoviruses are present in Australia. RMV was detected in multiple sites in both the Australian Capital Territory (ACT) and Tasmania, two regions separated by approximately 700km of land and 200km of water. The novel relative of RMV was detected in the ACT and New South Wales (NSW), while the highly divergent novel tobamoviruses were each detected in a single state, NSW and Queensland (QLD). In addition, Tobacco mild green mosaic virus, which is already known to be present in Australia, was detected in QLD using this method. This work highlights the potential utility of metatranscriptomic sequencing of wild animal gut for the surveillance of biosecurity threats to native and agricultural plant species. ImportancePlant viruses can have devastating impacts on global horticulture. Tobamoviruses (family Virgaviridae, genus Tobamovirus) are among the most damaging seed-borne viruses in horticultural crops, and Australia is free of many of the tobamoviruses that cause major crop losses in other countries. These viruses are extremely difficult to eradicate. Consequently, early detection of incursions is key to the control of these viruses in Australia, alongside rapid deployment of eradication and management plans. Current biosecurity surveillance methods in Australia rely on visual inspection, immunological assays, and molecular methods such as screening of imported seed lots. This study introduces a complementary approach that utilises unbiased metatranscriptomic sequencing of animal gut material to detect cryptic plant viruses circulating in nature. Using this approach, we detected five different tobamovirus circulating in Australia, including a virus thought to be exotic and three novel viruses. This unique approach highlights alternative options for surveillance/detection of exotic crop viruses.

microbiology↗

bioRxiv2024

p-IgGen: A Paired Antibody Generative Language Model

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 heavylight chain antibody generation. The model generates diverse, antibody-like sequences with pairing properties found in natural antibodies. We also create a finetuned version of p-IgGen that biases the model to generate antibodies with 3D biophysical properties that fall within distributions seen in clinical-stage therapeutic antibodies.

immunology↗

bioRxiv2024

The Observed T cell receptor Space database enables paired-chain repertoire mining, coherence analysis and language modelling

T cell activation is governed through T cell receptors (TCRs), heterodimers of two sequence-variable chains (often an alpha [] and beta [{beta}] chain) that recognise linear antigen fragments presented on the cell surfaces. Early sequencing technologies limited the study of immune repertoire TCRs to unpaired transcripts, leading to extensive analysis of {beta}-chain data alone as its greater sequence diversity suggested it should dominate antigen recognition. Over time, structural data has revealed that both and {beta} chains contribute to binding most antigens and highthroughput single-cell handling technologies have been increasingly applied to obtain samples of complete TCR variable region sequences from repertoires. Despite this, there is currently no repository dedicated to the curation of publicly available paired TCR sequence data. We have addressed this gap by creating the Observed T cell receptor Space (OTS) database, a source of consistently processed and annotated, full-length, paired-chain TCR sequencing data from 50 studies and at least 75 individuals. Currently, OTS contains 5.35M redundant (1.63M nonredundant) predominantly human TCR sequences and, based on recent data availability trends, will grow rapidly. We perform an initial analysis of OTS, leading to the identification of pairing biases, public TCRs, and distinct chain coherence patterns relative to antibodies. We also harness the data to build a publicly available paired-chain TCR language model, providing paired embedding representations and a method for residue in-filling that is conditional on the partner chain. OTS will be updated and maintained as a central community resource and is freely downloadable and available as a web application at https://opig.stats.ox.ac.uk/webapps/ots.

immunology↗

bioRxiv2023

Contextualising the developability risk of antibodies with lambda light chains using enhanced therapeutic antibody profiling

Antibodies with lambda light chains ({lambda}-antibodies) are generally considered to be less developable than those with kappa light chains ({kappa}-antibodies), leading to substantial systematic biases in drug discovery pipelines. This has contributed to kappa dominance amongst clinical-stage therapeutics. However, the identification of increasing numbers of epitopes preferentially engaged by{lambda} -antibodies shows there is a functional cost to neglecting them as potential lead candidates during discovery campaigns. Here, we update our Therapeutic Antibody Profiler (TAP) tool to use the latest data and machine learning-based structure prediction methods, and apply this new protocol to evaluate developability risk profiles for{kappa} -antibodies and{lambda} -antibodies based on their surface physicochemical properties. We find that{lambda} -antibodies are on average at a higher risk of poor developability -- as an indication, over 40% of single-cell sequenced human{lambda} -antibodies are flagged by TAP for risk-prone patches of surface hydrophobicity (PSH), compared to around 11% of human{kappa} -antibodies. Nonetheless, a substantial proportion of natural{lambda} -antibodies are assigned more moderate risk profiles by TAP and should therefore represent more tractable candidates for therapeutic development. We also analyse the populations of high and low risk antibodies, highlighting opportunities for strategic design that TAP suggests would enrich for more developable{lambda} -based candidates. Overall, we provide context to the differing developability of{kappa} - and{lambda} -antibodies, enabling a rational approach to incorporate more diversity into the initial pool of immunotherapeutic candidates.

bioinformatics↗

bioRxiv2022

PointVS: A Machine Learning Scoring Function that Identifies Important Binding Interactions

Over the last few years, many machine learning-based scoring functions for predicting the binding of small molecules to proteins have been developed. Their objective is to approximate the distribution which takes two molecules as input and outputs the energy of their interaction. Only a scoring function that accounts for the interatomic interactions involved in binding can accurately predict binding affinity on unseen molecules. However, many scoring functions make predictions based on dataset biases rather than an understanding of the physics of binding. These scoring functions perform well when tested on similar targets to those in the training set, but fail to generalise to dissimilar targets. To test what a machine learning-based scoring function has learnt, input attribution--a technique for learning which features are important to a model when making a prediction on a particular data point--can be applied. If a model successfully learns something beyond dataset biases, attribution should give insight into the important binding interactions that are taking place. We built a machine learning-based scoring function that aimed to avoid the influence of bias via thorough train and test dataset filtering, and show that it achieves comparable performance on the CASF-2016 benchmark to other leading methods. We then use the CASF-2016 test set to perform attribution, and find that the bonds identified as important by PointVS, unlike those extracted from other scoring functions, have a high correlation with those found by a distance-based interaction profiler. We then show that attribution can be used to extract important binding pharmacophores from a given protein target when supplied with a number of bound structures. We use this information to perform fragment elaboration, and see improvements in docking scores compared to using structural information from a traditional, data-based approach. This not only provides definitive proof that the scoring function has learnt to identify some important binding interactions, but also constitutes the first deep learning-based method for extracting structural information from a target for molecule design.

bioinformatics↗

bioRxiv2020

Host evolutionary history and ecology shape virome composition in fishes

Revealing the determinants of virome composition is central to placing disease emergence in a broader evolutionary context. Fish are the most species-rich group of vertebrates and so provide an ideal model system to study the factors that shape virome compositions and their evolution. We characterised the viromes of 19 wild-caught species of marine fish using total RNA sequencing (meta-transcriptomics) combined with analyses of sequence and protein structural homology to identify divergent viruses that often evade characterisation. From this, we identified 25 new vertebrate-associated viruses and a further 22 viruses likely associated with fish diet or their microbiomes. The vertebrate-associated viruses identified here included the first fish virus in the Matonaviridae (single-strand, negative-sense RNA virus). Other viruses fell within the Astroviridae, Picornaviridae, Arenaviridae, Reoviridae, Hepadnaviridae, Paramyxoviridae, Rhabdoviridae, Hantaviridae, Filoviridae and Flaviviridae and were sometimes phylogenetically distinct from known fish viruses. We also show how key metrics of virome composition - viral richness, abundance and diversity - can be analysed along with host ecological and biological factors as a means to understand virus ecology. Accordingly, these data suggest that that the vertebrate-associated viromes of the fish sampled here are predominantly shaped by the phylogenetic history (i.e. taxonomic order) of their hosts, along with several biological factors including water temperature, habitat depth, community diversity and swimming behaviour. No such correlations were found for viruses associated with porifera, molluscs, arthropods, fungi and algae, that are unlikely to replicate in fish hosts. Overall, these data indicate that fish harbour particularly large and complex viromes and the vast majority of fish viromes are undescribed.

microbiology↗