Timothy Atkinson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Timothy Atkinson has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Detlef Plump
University of York United Kingdom
4 shared publications - Susan Stepney
University of York
4 shared publications Jerry Swan
University of York
2 shared publications- Thomas Daniel Barrett
InstaDeep
2 shared publications Alex Graves
InstaDeep, London, England
1 shared publicationAlexandre Laterre
InstaDeep, London, England
1 shared publication
Latest Publications
- Open Access
- 3 April 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-14
Protein sequence modelling with Bayesian flow networks
Exploring the vast and largely uncharted territory of amino acid sequences is crucial for understanding complex protein functions and the engineering of novel therapeutic proteins. Whilst generative machine learning has advanced protein sequence modelling, no existing approach is proficient in both unconditional and conditional generation. In this work, we propose that Bayesian Flow Networks (BFNs), a recently introduced framework for generative modelling, can address these challenges. We present ProtBFN, a 650M parameter model trained on protein sequences curated from UniProtKB, which generates natural-like, diverse, structurally coherent, and novel protein sequences, significantly outperforming leading autoregressive and discrete diffusion models. Further, we fine-tune ProtBFN on heavy chains from the Observed Antibody Space to obtain an antibody-specific model, AbBFN, which we use to evaluate zero-shot conditional generation capabilities. AbBFN is found to be competitive with or better than antibody-specific BERT-style models when applied to predicting individual framework or complimentary determining regions.
- 3 April 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-14
Open AccessProtein sequence modelling with Bayesian flow networks
Exploring the vast and largely uncharted territory of amino acid sequences is crucial for understanding complex protein functions and the engineering of novel therapeutic proteins. Whilst generative machine learning has advanced protein sequence modelling, no existing approach is proficient in both unconditional and conditional generation. In this work, we propose that Bayesian Flow Networks (BFNs), a recently introduced framework for generative modelling, can address these challenges. We present ProtBFN, a 650M parameter model trained on protein sequences curated from UniProtKB, which generates natural-like, diverse, structurally coherent, and novel protein sequences, significantly outperforming leading autoregressive and discrete diffusion models. Further, we fine-tune ProtBFN on heavy chains from the Observed Antibody Space to obtain an antibody-specific model, AbBFN, which we use to evaluate zero-shot conditional generation capabilities. AbBFN is found to be competitive with or better than antibody-specific BERT-style models when applied to predicting individual framework or complimentary determining regions.
- Open Access
Contrasting Sequence with Structure: Pre-training Graph Representations with PLMs
Understanding protein function is vital for drug discovery, disease diagnosis, and protein engineering. While Protein Language Models (PLMs) pre-trained on vast protein sequence datasets have achieved remarkable success, equivalent Protein Structure Models (PSMs) remain underrepresented. We attribute this to the relative lack of high-confidence structural data and suitable pre-training objectives. In this context, we introduce BioCLIP, a contrastive learning framework that pre-trains PSMs by leveraging PLMs, generating meaningful per-residue and per-chain structural representations. When evaluated on tasks such as protein-protein interaction, Gene Ontology annotation, and Enzyme Commission number prediction, BioCLIP-trained PSMs consistently outperform models trained from scratch and further enhance performance when merged with sequence embeddings. Notably, BioCLIP approaches, or exceeds, specialized methods across all benchmarks using its singular pre-trained design. Our work addresses the challenges of obtaining quality structural data and designing self-supervised objectives, setting the stage for more comprehensive models of protein function. Source code is publicly available 2 .
Open AccessContrasting Sequence with Structure: Pre-training Graph Representations with PLMs
Understanding protein function is vital for drug discovery, disease diagnosis, and protein engineering. While Protein Language Models (PLMs) pre-trained on vast protein sequence datasets have achieved remarkable success, equivalent Protein Structure Models (PSMs) remain underrepresented. We attribute this to the relative lack of high-confidence structural data and suitable pre-training objectives. In this context, we introduce BioCLIP, a contrastive learning framework that pre-trains PSMs by leveraging PLMs, generating meaningful per-residue and per-chain structural representations. When evaluated on tasks such as protein-protein interaction, Gene Ontology annotation, and Enzyme Commission number prediction, BioCLIP-trained PSMs consistently outperform models trained from scratch and further enhance performance when merged with sequence embeddings. Notably, BioCLIP approaches, or exceeds, specialized methods across all benchmarks using its singular pre-trained design. Our work addresses the challenges of obtaining quality structural data and designing self-supervised objectives, setting the stage for more comprehensive models of protein function. Source code is publicly available 2 .
- Open Access
- 3 February 2020
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 21 (3) , 321-347
Horizontal gene transfer for recombining graphs
We introduce a form of neutral horizontal gene transfer (HGT) to evolving graphs by graph programming (EGGP). We introduce the $$\mu \times \lambda$$ evolutionary algorithm (EA), where $$\mu$$ parents each produce $$\lambda$$ children who compete only with their parents. HGT events then copy the entire active component of one surviving parent into the inactive component of another parent, exchanging genetic information without reproduction. Experimental results from symbolic regression problems show that the introduction of the $$\mu \times \lambda$$ EA and HGT events improve the performance of EGGP. Comparisons with genetic programming and Cartesian genetic programming strongly favour our proposed approach. We also investigate the effect of using HGT events in neuroevolution tasks. We again find that the introduction of HGT improves the performance of EGGP, demonstrating that HGT is an effective cross-domain mechanism for recombining graphs.- 3 February 2020
- Published by Springer Nature in Genetic Programming and Evolvable Machines
- Vol. 21 (3) , 321-347
Open AccessHorizontal gene transfer for recombining graphs
We introduce a form of neutral horizontal gene transfer (HGT) to evolving graphs by graph programming (EGGP). We introduce the $$\mu \times \lambda$$ evolutionary algorithm (EA), where $$\mu$$ parents each produce $$\lambda$$ children who compete only with their parents. HGT events then copy the entire active component of one surviving parent into the inactive component of another parent, exchanging genetic information without reproduction. Experimental results from symbolic regression problems show that the introduction of the $$\mu \times \lambda$$ EA and HGT events improve the performance of EGGP. Comparisons with genetic programming and Cartesian genetic programming strongly favour our proposed approach. We also investigate the effect of using HGT events in neuroevolution tasks. We again find that the introduction of HGT improves the performance of EGGP, demonstrating that HGT is an effective cross-domain mechanism for recombining graphs. - Open Access
- 29 October 2019
- Published by Springer Nature in Natural Computing
- Vol. 20 (1) , 127-143
Evolving graphs with semantic neutral drift
We introduce the concept of Semantic Neutral Drift (SND) for genetic programming (GP), where we exploit equivalence laws to design semantics preserving mutations guaranteed to preserve individuals’ fitness scores. A number of digital circuit benchmark problems have been implemented with rule-based graph programs and empirically evaluated, demonstrating quantitative improvements in evolutionary performance. Analysis reveals that the benefits of the designed SND reside in more complex processes than simple growth of individuals, and that there are circumstances where it is beneficial to choose otherwise detrimental parameters for a GP system if that facilitates the inclusion of SND.
- 29 October 2019
- Published by Springer Nature in Natural Computing
- Vol. 20 (1) , 127-143
Open AccessEvolving graphs with semantic neutral drift
We introduce the concept of Semantic Neutral Drift (SND) for genetic programming (GP), where we exploit equivalence laws to design semantics preserving mutations guaranteed to preserve individuals’ fitness scores. A number of digital circuit benchmark problems have been implemented with rule-based graph programs and empirically evaluated, demonstrating quantitative improvements in evolutionary performance. Analysis reveals that the benefits of the designed SND reside in more complex processes than simple growth of individuals, and that there are circumstances where it is beneficial to choose otherwise detrimental parameters for a GP system if that facilitates the inclusion of SND.
- 27 March 2019
- Published by Springer Nature
- p. 19-34
Quantum Program Synthesis: Swarm Algorithms and Benchmarks
- 27 March 2019
- Published by Springer Nature
- p. 19-34
Quantum Program Synthesis: Swarm Algorithms and Benchmarks
- 29 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 11 (3) , 260-266
The Text-Based Adventure AI Competition
In 2016, 2017, and 2018 at the IEEE Conference on Computational Intelligence in Games, the authors of this paper ran a competition for agents that can play classic text-based adventure games. This competition fills a gap in existing game AI competitions that have typically focussed on traditional card/board games or modern video games with graphical interfaces. By providing a platform for evaluating agents in text-based adventures, the competition provides a novel benchmark for game AI with unique challenges for natural language understanding and generation. This paper summarises the three competitions ran in 2016, 2017, and 2018 (including details of open source implementations of both the competition framework and our competitors) and presents the results of an improved evaluation of these competitors across 20 games.
- 29 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 11 (3) , 260-266
The Text-Based Adventure AI Competition
In 2016, 2017, and 2018 at the IEEE Conference on Computational Intelligence in Games, the authors of this paper ran a competition for agents that can play classic text-based adventure games. This competition fills a gap in existing game AI competitions that have typically focussed on traditional card/board games or modern video games with graphical interfaces. By providing a platform for evaluating agents in text-based adventures, the competition provides a novel benchmark for game AI with unique challenges for natural language understanding and generation. This paper summarises the three competitions ran in 2016, 2017, and 2018 (including details of open source implementations of both the competition framework and our competitors) and presents the results of an improved evaluation of these competitors across 20 games.
- Open Access
The Text-Based Adventure AI Competition
In 2016, 2017, and 2018 at the IEEE Conference on Computational Intelligence in Games, the authors of this paper ran a competition for agents that can play classic text-based adventure games. This competition fills a gap in existing game AI competitions that have typically focussed on traditional card/board games or modern video games with graphical interfaces. By providing a platform for evaluating agents in text-based adventures, the competition provides a novel benchmark for game AI with unique challenges for natural language understanding and generation. This paper summarises the three competitions ran in 2016, 2017, and 2018 (including details of open source implementations of both the competition framework and our competitors) and presents the results of an improved evaluation of these competitors across 20 games.
Open AccessThe Text-Based Adventure AI Competition
In 2016, 2017, and 2018 at the IEEE Conference on Computational Intelligence in Games, the authors of this paper ran a competition for agents that can play classic text-based adventure games. This competition fills a gap in existing game AI competitions that have typically focussed on traditional card/board games or modern video games with graphical interfaces. By providing a platform for evaluating agents in text-based adventures, the competition provides a novel benchmark for game AI with unique challenges for natural language understanding and generation. This paper summarises the three competitions ran in 2016, 2017, and 2018 (including details of open source implementations of both the competition framework and our competitors) and presents the results of an improved evaluation of these competitors across 20 games.
- 29 May 2018
- Published by Springer Nature
- p. 63-78
Probabilistic Graph Programs for Randomised and Evolutionary Algorithms
- 29 May 2018
- Published by Springer Nature
- p. 63-78
Probabilistic Graph Programs for Randomised and Evolutionary Algorithms
- 1 October 1991
- Published by Elsevier in Oral Surgery, Oral Medicine, Oral Pathology
- Vol. 72 (4) , 408-411
Internal carotid artery thrombosis after blunt maxillofacial trauma
- 1 October 1991
- Published by Elsevier in Oral Surgery, Oral Medicine, Oral Pathology
- Vol. 72 (4) , 408-411
Internal carotid artery thrombosis after blunt maxillofacial trauma