arXiv subjects

Joe G Greener

Publications and source records attributed to Joe G Greener.

5 recordsLinked to original sources

arXiv2026

Training a force field for proteins and small molecules from scratch

Force fields for molecular dynamics are usually developed manually, limiting their transferability and making systematic exploration of functional forms challenging. We developed a graph neural network that assigns all force field parameters for diverse molecules using continuous atom typing. The freely-available model, called Garnet, was trained on quantum mechanical, condensed phase and protein nuclear magnetic resonance data without the use of existing parameters. The resulting force field shows comparable performance to current force fields on small molecules, folded proteins, protein complexes and disordered proteins. It shows similar results to popular approaches for relative binding free energy predictions across a range of targets. Assessing different functional forms shows that the double exponential potential is a flexible and accurate alternative to the Lennard-Jones potential. Garnet provides a platform for automated, reproducible force field discovery that brings the benefits of machine learning to classical force fields.

q-bio.BM↗

arXiv2024

Reversible molecular simulation for training classical and machine learning force fields

The next generation of force fields for molecular dynamics will be developed using a wealth of data. Training systematically with experimental data remains a challenge, however, especially for machine learning potentials. Differentiable molecular simulation calculates gradients of observables with respect to parameters through molecular dynamics trajectories. Here we improve this approach by explicitly calculating gradients using a reverse-time simulation with effectively constant memory cost and a computation count similar to the forward simulation. The method is applied to learn all-atom water and gas diffusion models with different functional forms, and to train a machine learning potential for diamond from scratch. Comparison to ensemble reweighting indicates that reversible simulation can provide more accurate gradients and train to match time-dependent observables.

q-bio.BM↗

arXiv2020

Near-complete protein structural modelling of the minimal genome

Protein tertiary structure prediction has improved dramatically in recent years. A considerable fraction of various proteomes can be modelled in the absence of structural templates. We ask whether our DMPfold method can model all the proteins without templates in the JCVI-syn3.0 minimal genome, which contains 438 proteins. We find that a useful tertiary structure annotation can be provided for all but 10 proteins. The models may help annotate function in cases where it is unknown, and provide coverage for 29 predicted protein-protein interactions which lacked monomer models. We also show that DMPfold performs well on proteins with structures released since initial publication. It is likely that the minimal genome will have complete structural coverage within a few years.

q-bio.BM↗

arXiv2019

Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints

The inapplicability of amino acid covariation methods to small protein families has limited their use for structural annotation of whole genomes. Recently, deep learning has shown promise in allowing accurate residue-residue contact prediction even for shallow sequence alignments. Here we introduce DMPfold, which uses deep learning to predict inter-atomic distance bounds, the main chain hydrogen bond network, and torsion angles, which it uses to build models in an iterative fashion. DMPfold produces more accurate models than two popular methods for a test set of CASP12 domains, and works just as well for transmembrane proteins. Applied to all Pfam domains without known structures, confident models for 25% of these so-called dark families were produced in under a week on a small 200 core cluster. DMPfold provides models for 16% of human proteome UniProt entries without structures, generates accurate models with fewer than 100 sequences in some cases, and is freely available.

q-bio.BM↗

arXiv2018

Design of metalloproteins and novel protein folds using variational autoencoders

The design of novel proteins has many applications but remains an attritional process with success in isolated cases. Meanwhile, deep learning technologies have exploded in popularity in recent years and are increasingly applicable to biology due to the rise in available data. We attempt to link protein design and deep learning by using variational autoencoders to generate protein sequences conditioned on desired properties. Potential copper and calcium binding sites are added to non-metal binding proteins without human intervention and compared to a hidden Markov model. In another use case, a grammar of protein structures is developed and used to produce sequences for a novel protein topology. One candidate structure is found to be stable by molecular dynamics simulation. The ability of our model to confine the vast search space of protein sequences and to scale easily has the potential to assist in a variety of protein design tasks.

q-bio.BM↗