Cameron Mura

Born in London in 1953 and raised in Australia, Phil Bourne spent over four decades in science moving across scales: from crystal structures to the world’s premier structural biology database; from scientific journals to national data policy; from molecules to institutions. The International Society for Computational Biology (ISCB) chose Phil to receive its 2026 Outstanding Service Award. He passed away on 8 March 2026, in Charlottesville, VA, before he could receive it. This piece is in memory of Phil, who most recently served as the Founding Stephenson Dean of the University of Virginia’s School of Data Science and as a Professor of Biomedical Engineering—and who was, over the course of his career, a steadfast builder of Computational Biology and Bioinformatics, of Open Science and Data Science. A tribute site, https://philbourne.muchloved.com, invites those who knew Phil to share memories, photos, and reflections.

Our views of fold space implicitly rest upon many assumptions that impact how we analyze, interpret and understand protein structure, function and evolution. For instance, is there an optimal granularity in viewing protein structural similarities (e.g., architecture, topology or some other level)? Similarly, the discrete/continuous dichotomy of fold space is central, but remains unresolved. Discrete views of fold space bin similar folds into distinct, non-overlapping groups; unfortunately, such binning can miss remote relationships. While hierarchical systems like CATH are indispensable resources, less heuristic and more conceptually flexible approaches could enable more nuanced explorations of fold space. Building upon an Urfold model of protein structure, here we present a deep generative modeling framework, termed DeepUrfold, for analyzing protein relationships at scale. DeepUrfold’s learned embeddings occupy high-dimensional latent spaces that can be distilled for a given protein in terms of an amalgamated representation uniting sequence, structure and biophysical properties. This approach is structure-guided, versus being purely structure-based, and DeepUrfold learns representations that, in a sense, define superfamilies. Deploying DeepUrfold with CATH reveals evolutionarily-remote relationships that evade existing methodologies, and suggests a mostly-continuous view of fold space—a view that extends beyond simple geometric similarity, towards the realm of integrated sequence ↔ structure ↔ function properties.

Background: Machine learning (ML) has a rich history in structural bioinformatics, and modern approaches, such as deep learning, are revolutionizing our knowledge of the subtle relationships between biomolecular sequence, structure, function, dynamics and evolution. As with any advance that rests upon statistical learning approaches, the recent progress in biomolecular sciences is enabled by the availability of vast volumes of sufficiently-variable data. To be useful, such data must be well-structured, machine-readable, intelligible and manipulable. These and related requirements pose challenges that become especially acute at the computational scales typical in ML. Furthermore, in structural bioinformatics such data generally relate to protein three-dimensional (3D) structures, which are inherently more complex than sequence-based data. A significant and recurring challenge concerns the creation of large, high-quality, openly-accessible datasets that can be used for specific training and benchmarking tasks in ML pipelines for predictive modeling projects, along with reproducible splits for training and testing. Results: Here, we report ‘’, a platform that allows for the creation, sharing and extensible reuse of libraries of protein domains, featurized with biophysical and evolutionary properties that can range from detailed, atomically-resolved physicochemical quantities (e.g., electrostatics) to coarser, residue-level features (e.g., phylogenetic conservation). As a community resource, we also supply a ‘’ protein dataset, obtained by applying our approach to CATH. We have developed and deployed the framework, both in the cloud and on local HPC resources, to systematically and reproducibly create comprehensive datasets via the Highly Scalable Data Service (HSDS). Our datasets are freely accessible via a public HSDS instance, or they can be used with accompanying Python wrappers for popular ML frameworks. Conclusion: and its associated dataset can be of broad utility in at least three ways. Firstly, the workflow code can be customized and deployed on various cloud-based compute platforms, with scalability achieved largely by saving the results to distributed HDF5 files via HSDS. Secondly, the linked dataset provides a hand-crafted, already-featurized dataset of protein domains for 20 highly-populated CATH families; importantly, provision of this pre-computed resource can aid the more efficient development (and reproducible deployment) of ML pipelines. Thirdly, ’s construction explicitly takes into account (in creating datasets and data-splits) the enigma of ‘data leakage’, stemming from the evolutionary relationships between proteins.

Our views of fold space implicitly rest upon many assumptions that impact how we analyze, interpret and understand biological systems—from protein structure comparison and classification to function prediction and evolutionary analyses. For instance, is there an optimal granularity at which to view protein structural similarities (e.g., architecture, topology or some other level)? If so, how does it vary with the type of question being asked? Similarly, the discrete/continuous dichotomy of fold space is central in structural bioinformatics, but remains unresolved. Discrete views of fold space bin ‘similar’ folds into distinct, non-overlapping groups; unfortunately, such binning may inherently miss many remote relationships. While hierarchical databases like CATH, SCOP and ECOD represent major steps forward in protein classification, a scalable, objective and conceptually flexible method, with less reliance on assumptions and heuristics, could enable a more systematic and nuanced exploration of fold space, particularly as regards evolutionarily-distant relationships. Building upon a recent ‘Urfold’ model of protein structure, we have developed a new approach to analyze protein structure relationships. Termed ‘DeepUrfold’, this method is rooted in deep generative modeling via variational Bayesian inference, and we find it to be useful for comparative analysis across the protein universe. Critically, DeepUrfold leverages its deep generative model’s embeddings, which represent a distilled, lower-dimensional space of a given protein and its amalgamation of sequence, structure and biophysical properties. Notably, DeepUrfold is structure-guided, versus being purely structure-based, and its architecture allows each trained model to learn protein features (structural and otherwise) that, in a sense, ‘define’ different superfamilies. Deploying DeepUrfold with CATH suggests a new, mostly-continuous view of fold space—a view that extends beyond simple 3D structural/geometric similarity, towards the realm of integrated sequence↔structure↔function properties. We find that such an approach can quantitatively represent and detect evolutionarily-remote relationships that evade existing methods.

We believe that readers, particularly those at relatively early career stages, could benefit from ten simple rules (TSR) on the topic of "serving as an editor." By this phrase, we mean that role which may variously be called "handling editor," "academic editor," "scientific editor" and so on-in other words, the individual who oversees the process of shepherding a written piece of scientific work from the point of manuscript submission through to peer review and, ultimately, either publication or rejection. We mean this in contradistinction to, say, serving as an editorial advisory board member, a "section editor," or an editor-in-chief or such. Those roles are of interest too, in terms of career and professional development; however, those types of positions generally begin later in one's career (e.g., as a well-established scientist), versus nearer the start of an independent career (e.g., late-postdoc or early-faculty), spurring us to focus this piece more on the context of "handling editor." The goal of this TSR is to offer guidance that can help you, the reader-in your current or future roles as a novice handling editor-be the type of editor whom you might have liked to have dealt with yourself, in your own experience and interactions thus far in publishing your work. This piece can be viewed as complementary to an early TSR for reviewers [1], and the closest material of which we are aware is Erren and Erren's "Simple Rules for Editors'? Here is One Rule to Tackle Neglected Problems of Publishing," published as a correspondence in this journal 15 years ago [2]. That insightful piece suggested an "Editor Rule for Appropriate Recognition" as a way to improve the recognition and credit due to those who contribute to a submitted work, and yet who may be less visible or even entirely overlooked (possibly to the point of omission from an author list), perhaps because they are relatively young or less experienced than more senior authors. Specifically, Erren and Erren's proposed "rule" called on editors to ask authors for a written statement that (i) avows that no substantial contributors have been omitted from an authorship list; and (ii) explicitly delineates the oftentimes key role of more junior/overlooked authors (and/or researchers that the work cites) in formulating the hypotheses or rationale that underlies the submitted study. We agree with those proposed practices. In the present work, we focus chiefly on the mechanics and best practices of one's editorial responsibilities when handling a manuscript, starting at the initial point of being invited to serve as an editor.

Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space.

This Special Issue of Biomolecules

Background: Machine learning (ML) has a rich history in structural bioinformatics, and modern approaches, such as deep learning, are revolutionizing our knowledge of the subtle relationships between biomolecular sequence, structure, function, dynamics and evolution. As with any advance that rests upon statistical learning approaches, the recent progress in biomolecular sciences is enabled by the availability of vast volumes of sufficiently-variable data. To be useful, such data must be well-structured, machine-readable, intelligible and manipulable. These and related requirements pose challenges that become especially acute at the computational scales typical in ML. Furthermore, in structural bioinformatics such data generally relate to protein three-dimensional (3D) structures, which are inherently more complex than sequence-based data. A significant and recurring challenge concerns the creation of large, high-quality, openly-accessible datasets that can be used for specific training and benchmarking tasks in ML pipelines for predictive modeling projects, along with reproducible splits for training and testing. Results: Here, we report ‘Prop3D’, a platform that allows for the creation, sharing and extensible reuse of libraries of protein domains, featurized with biophysical and evolutionary properties that can range from detailed, atomically-resolved physicochemical quantities (e.g., electrostatics) to coarser, residue-level features (e.g., phylogenetic conservation). As a community resource, we also supply a ‘Prop3D-20sf’ protein dataset, obtained by applying our approach to CATH. We have developed and deployed the Prop3D framework, both in the cloud and on local HPC resources, to systematically and reproducibly create comprehensive datasets via the Highly Scalable Data Service (HSDS). Our datasets are freely accessible via a public HSDS instance, or they can be used with accompanying Python wrappers for popular ML frameworks. Conclusion: Prop3D and its associated Prop3D-20sf dataset can be of broad utility in at least three ways. Firstly, the Prop3D workflow code can be customized and deployed on various cloud-based compute platforms, with scalability achieved largely by saving the results to distributed HDF5 files via HSDS. Secondly, the linked Prop3D-20sf dataset provides a hand-crafted, already-featurized dataset of protein domains for 20 highly-populated CATH families; importantly, provision of this pre-computed resource can aid the more efficient development (and reproducible deployment) of ML pipelines. Thirdly, Prop3D-20sf’s construction explicitly takes into account (in creating datasets and data-splits) the enigma of ‘data leakage’, stemming from the evolutionary relationships between proteins.

This Special Issue of Biomolecules, commissioned in honor of Dr. Philip E. Bourne, focuses on a new field of biomolecular data science. In this brief retrospective, we consider the arc of Bourne's 40-year scientific and professional career, particularly as it relates to the origins of this new field.

The helpful Ten Simple Rules series in this journal (PLOS Computational Biology) does not yet offer a piece on the topic of “serving as an editor”. By this phrase we mean that role which may variously be called ‘handling editor’, ‘academic editor’, ‘scientific editor’ and so on—in other words, the individual who oversees the process of shepherding a written piece of scientific work from the point of manuscript submission through to peer review and, ultimately, either publication or rejection. Therefore, the present work aims to offer guidance that can help you, the reader—in your current or future roles as a novice handling editor—be the type of editor whom you might have liked to have dealt with yourself, in your own experience and interactions thus far in publishing your work. In this work, we primarily focus on the mechanics and best practices of one’s editorial responsibilities when handling a manuscript, starting at the initial point of being invited to serve as an editor.