Search

We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop., Comment: ICLR 2024

We introduce RNA-FrameFlow, the first generative model for 3D RNA backbone design. We build upon SE(3) flow matching for protein backbone generation and establish protocols for data preparation and evaluation to address unique challenges posed by RNA modeling. We formulate RNA structures as a set of rigid-body frames and associated loss functions which account for larger, more conformationally flexible RNA backbones (13 atoms per nucleotide) vs. proteins (4 atoms per residue). Toward tackling the lack of diversity in 3D RNA datasets, we explore training with structural clustering and cropping augmentations. Additionally, we define a suite of evaluation metrics to measure whether the generated RNA structures are globally self-consistent (via inverse folding followed by forward folding) and locally recover RNA-specific structural descriptors. The most performant version of RNA-FrameFlow generates locally realistic RNA backbones of 40-150 nucleotides, over 40% of which pass our validity criteria as measured by a self-consistency TM-score >= 0.45, at which two RNAs have the same global fold. Open-source code: https://github.com/rish-16/rna-backbone-design, Comment: To be presented as an Oral at ICML 2024 Structured Probabilistic Inference & Generative Modeling Workshop, and a Spotlight at ICML 2024 AI4Science Workshop

The oscillating magnetic field produced by unbalanced currents in radio-frequency ion traps induces transition frequency shifts and sideband transitions that can be harmful to precision spectroscopy experiments. Here, we describe a methodology, based on two-photon spectroscopy, for determining both the strength and direction of rf-induced magnetic fields without modifying any DC magnetic bias field or changing any trap RF power. The technique is readily applicable to any trapped-ion experiment featuring narrow linewidth transitions., Comment: 13 pages, 6 figures

Modern life sciences research is increasingly relying on artificial intelligence approaches to model biological systems, primarily centered around the use of machine learning (ML) models. Although ML is undeniably useful for identifying patterns in large, complex data sets, its widespread application in biological sciences represents a significant deviation from traditional methods of scientific inquiry. As such, the interplay between these models and scientific understanding in biology is a topic with important implications for the future of scientific research, yet it is a subject that has received little attention. Here, we draw from an epistemological toolkit to contextualize recent applications of ML in biological sciences under modern philosophical theories of understanding, identifying general principles that can guide the design and application of ML systems to model biological phenomena and advance scientific knowledge. We propose that conceptions of scientific understanding as information compression, qualitative intelligibility, and dependency relation modelling provide a useful framework for interpreting ML-mediated understanding of biological systems. Through a detailed analysis of two key application areas of ML in modern biological research - protein structure prediction and single cell RNA-sequencing - we explore how these features have thus far enabled ML systems to advance scientific understanding of their target phenomena, how they may guide the development of future ML models, and the key obstacles that remain in preventing ML from achieving its potential as a tool for biological discovery. Consideration of the epistemological features of ML applications in biology will improve the prospects of these methods to solve important problems and advance scientific understanding of living systems.

The non-equilibrium physics of many-body quantum systems harbors various unconventional phenomena. In this study, we experimentally investigate one of the most puzzling of these phenomena -- the quantum Mpemba effect, where a tilted ferromagnet restores its symmetry more rapidly when it is farther from the symmetric state compared to when it is closer. We present the first experimental evidence of the occurrence of this effect in a trapped-ion quantum simulator. The symmetry breaking and restoration are monitored through entanglement asymmetry, probed via randomized measurements, and postprocessed using the classical shadows technique. Our findings are further substantiated by measuring the Frobenius distance between the experimental state and the stationary thermal symmetric theoretical state, offering direct evidence of subsystem thermalization., Comment: 11 pages, 7 figures. Published version

Recent advances in computational modelling of atomic systems, spanning molecules, proteins, and materials, represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space. In these graphs, the geometric attributes transform according to the inherent physical symmetries of 3D atomic systems, including rotations and translations in Euclidean space, as well as node permutations. In recent years, Geometric Graph Neural Networks have emerged as the preferred machine learning architecture powering applications ranging from protein structure prediction to molecular simulations and material generation. Their specificity lies in the inductive biases they leverage - such as physical symmetries and chemical properties - to learn informative representations of these geometric graphs. In this opinionated paper, we provide a comprehensive and self-contained overview of the field of Geometric GNNs for 3D atomic systems. We cover fundamental background material and introduce a pedagogical taxonomy of Geometric GNN architectures: (1) invariant networks, (2) equivariant networks in Cartesian basis, (3) equivariant networks in spherical basis, and (4) unconstrained networks. Additionally, we outline key datasets and application areas and suggest future research directions. The objective of this work is to present a structured perspective on the field, making it accessible to newcomers and aiding practitioners in gaining an intuition for its mathematical abstractions.

Deep generative models for structure-based drug design (SBDD), where molecule generation is conditioned on a 3D protein pocket, have received considerable interest in recent years. These methods offer the promise of higher-quality molecule generation by explicitly modelling the 3D interaction between a potential drug and a protein receptor. However, previous work has primarily focused on the quality of the generated molecules themselves, with limited evaluation of the 3D molecule \emph{poses} that these methods produce, with most work simply discarding the generated pose and only reporting a "corrected" pose after redocking with traditional methods. Little is known about whether generated molecules satisfy known physical constraints for binding and the extent to which redocking alters the generated interactions. We introduce PoseCheck, an extensive analysis of multiple state-of-the-art methods and find that generated molecules have significantly more physical violations and fewer key interactions compared to baselines, calling into question the implicit assumption that providing rich 3D structure information improves molecule complementarity. We make recommendations for future research tackling identified failure modes and hope our benchmark can serve as a springboard for future SBDD generative modelling work to have a real-world impact.

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.

Entanglement is a distinguishing feature of quantum many-body systems, and uncovering the entanglement structure for large particle numbers in quantum simulation experiments is a fundamental challenge in quantum information science. Here we perform experimental investigations of entanglement based on the entanglement Hamiltonian, as an effective description of the reduced density operator for large subsystems. We prepare ground and excited states of a 1D XXZ Heisenberg chain on a 51-ion programmable quantum simulator and perform sample-efficient `learning' of the entanglement Hamiltonian for subsystems of up to 20 lattice sites. Our experiments provide compelling evidence for a local structure of the entanglement Hamiltonian. This observation marks the first instance of confirming the fundamental predictions of quantum field theory by Bisognano and Wichmann, adapted to lattice models that represent correlated quantum matter. The reduced state takes the form of a Gibbs ensemble, with a spatially-varying temperature profile as a signature of entanglement. Our results also show the transition from area to volume-law scaling of Von Neumann entanglement entropies from ground to excited states. As we venture towards achieving quantum advantage, we anticipate that our findings and methods have wide-ranging applicability to revealing and understanding entanglement in many-body problems with local interactions including higher spatial dimensions., Comment: 14 pages, 7 figures

Much work has been devoted to devising architectures that build group-equivariant representations, while invariance is often induced using simple global pooling mechanisms. Little work has been done on creating expressive layers that are invariant to given symmetries, despite the success of permutation invariant pooling in various molecular tasks. In this work, we present Group Invariant Global Pooling (GIGP), an invariant pooling layer that is provably sufficiently expressive to represent a large class of invariant functions. We validate GIGP on rotated MNIST and QM9, showing improvements for the latter while attaining identical results for the former. By making the pooling process group orbit-aware, this invariant aggregation method leads to improved performance, while performing well-principled group aggregation.

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity. We introduce gRNAde, a geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. Under the hood, gRNAde is a multi-state Graph Neural Network that generates candidate RNA sequences conditioned on one or more 3D backbone structures where the identities of the bases are unknown. On a single-state fixed backbone re-design benchmark of 14 RNA structures from the PDB identified by Das et al. [2010], gRNAde obtains higher native sequence recovery rates (56% on average) compared to Rosetta (45% on average), taking under a second to produce designs compared to the reported hours for Rosetta. We further demonstrate the utility of gRNAde on a new benchmark of multi-state design for structurally flexible RNAs, as well as zero-shot ranking of mutational fitness landscapes in a retrospective analysis of a recent RNA polymerase ribozyme structure. Open source code: https://github.com/chaitjo/geometric-rna-design, Comment: Previously titled 'Multi-State RNA Design with Geometric Multi-Graph Neural Networks', presented at ICML 2023 Computational Biology Workshop

The control over quantum states in atomic systems has led to the most precise optical atomic clocks to date. Their sensitivity is currently bounded by the standard quantum limit, a fundamental floor set by quantum mechanics for uncorrelated particles, which can nevertheless be overcome when operated with entangled particles. Yet demonstrating a quantum advantage in real world sensors is extremely challenging and remains to be achieved aside from two remarkable examples, LIGO and more recently HAYSTAC. Here we illustrate a pathway for harnessing scalable entanglement in an optical transition using 1D chains of up to 51 ions with state-dependent interactions that decay as a power-law function of the ion separation. We show our sensor can be made to behave as a one-axis-twisting (OAT) model, an iconic fully connected model known to generate scalable squeezing. The collective nature of the state manifests itself in the preservation of the total transverse magnetization, the reduced growth of finite momentum spin-wave excitations, the generation of spin squeezing comparable to OAT (a Wineland parameter of $-3.9 \pm 0.3$ dB for only N = 12 ions) and the development of non-Gaussian states in the form of atomic multi-headed cat states in the Q-distribution. The simplicity of our protocol enables scalability to large arrays with minimal overhead, opening the door to advances in timekeeping as well as new methods for preserving coherence in quantum simulation and computation. We demonstrate this in a Ramsey-type interferometer, where we reduce the measurement uncertainty by $-3.2 \pm 0.5$ dB below the standard quantum limit for N = 51 ions., Comment: During the completion of our work, we became aware of three related experiments using dressed Rydberg interactions in tweezer and microtrap array platforms. See arXiv:2303.08053, arXiv:2303.08078 and arXiv:2303.08805. This manuscript contains 14 Pages and 5 figures

The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test. However, standard GNNs and the WL framework are inapplicable for geometric graphs embedded in Euclidean space, such as biomolecules, materials, and other physical systems. In this work, we propose a geometric version of the WL test (GWL) for discriminating geometric graphs while respecting the underlying physical symmetries: permutations, rotation, reflection, and translation. We use GWL to characterise the expressive power of geometric GNNs that are invariant or equivariant to physical symmetries in terms of distinguishing geometric graphs. GWL unpacks how key design choices influence geometric GNN expressivity: (1) Invariant layers have limited expressivity as they cannot distinguish one-hop identical geometric graphs; (2) Equivariant layers distinguish a larger class of graphs by propagating geometric information beyond local neighbourhoods; (3) Higher order tensors and scalarisation enable maximally powerful geometric GNNs; and (4) GWL's discrimination-based perspective is equivalent to universal approximation. Synthetic experiments supplementing our results are available at \url{https://github.com/chaitjo/geometric-gnn-dojo}, Comment: ICML 2023

Over the recent years coherent, time-periodic modulation has been established as a versatile tool for realizing novel Hamiltonians. Using this approach, known as Floquet engineering, we experimentally realize a long-ranged, anisotropic Heisenberg model with tunable interactions in a trapped ion quantum simulator. We demonstrate that the spectrum of the model contains not only single magnon excitations but also composite magnon bound states. For the long-range interactions with the experimentally realized power-law exponent, the group velocity of magnons is unbounded. Nonetheless, for sufficiently strong interactions we observe bound states of these unconventional magnons which possess a non-diverging group velocity. By measuring the configurational mutual information between two disjoint intervals, we demonstrate the implications of the bound state formation on the entanglement dynamics of the system. Our observations provide key insights into the peculiar role of composite excitations in the non-equilibrium dynamics of quantum many-body systems.

Satellite based Quantum Key Distribution (QKD) in Low Earth Orbit (LEO) is currently the only viable technology to span thousands of kilometres. Since the typical overhead pass of a satellite lasts for a few minutes, it is crucial to increase the the signal rate to maximise the secret key length. For the QUARC CubeSat mission due to be launched within two years, we are designing a dual wavelength, weak-coherent-pulse decoy-state Bennett-Brassard '84 (WCP DS BB84) QKD source. The optical payload is designed in a $12{\times}9{\times}5 cm^3$ bespoke aluminium casing. The Discrete Variable QKD Source consists of two symmetric sources operating at 785 nm and 808 nm. The laser diodes are fixed to produce Horizontal,Vertical, Diagonal, and Anti-diagonal (H,V,D,A) polarisation respectively, which are combined and attenuated to a mean photon number of 0.3 and 0.5 photons/pulse. We ensure that the source is secure against most side channel attacks by spatially mode filtering the output beam and characterising their spectral and temporal characterstics. The extinction ratio of the source contributes to the intrinsic Qubit Error Rate(QBER) with $0.817 \pm 0.001\%$. This source operates at 200MHz, which is enough to provide secure key rates of a few kilo bits per second despite 40 dB of estimated loss in the free space channel

Quantum networks have been shown to connect users with full-mesh topologies without trusted nodes. We present advancements on our scalable polarisation entanglement-based quantum network testbed, which has the ability to perform protocols beyond simple quantum key distribution. Our approach utilises wavelength multiplexing, which is ideal for quantum networks across local metropolitan areas due to the ease of connecting additional users to the network without increasing the resource requirements per user. We show a 10 user fully connected quantum network with metropolitan scale deployed fibre links, demonstrating polarisation stability and the ability to generate secret keys over a period of 10.8 days with a network wide average-effective secret key rate of 3.38 bps., Comment: 8 pages, 4 figures, 2 tables, SPIE Photonex 2022 conference proceedings

Quantum key distribution (QKD) is a theoretically proven future-proof secure encryption method that inherits its security from fundamental physical principles. Craft Prospect, working with a number of UK organisations, has been focused on miniaturising the technologies that enable QKD so that they may be used in smaller platforms including nanosatellites. The significant reduction of size, and therefore the cost of launching quantum communication technologies either on a dedicated platform or hosted as part of a larger optical communications will improve potential access to quantum encryption on a relatively quick timescale. The ROKS mission seeks to be among the first to send a QKD payload on a CubeSat into low Earth orbit, demonstrating the capabilities of newly developed modular quantum technologies. The ROKS payload comprises a quantum source module that supplies photons randomly in any of four linear polarisation states fed from a quantum random number generator; an acquisition, pointing, and tracking system to fine-tune alignment of the quantum source beam with an optical ground station; an imager that will detect cloud cover autonomously; and an onboard computer that controls and monitors the other modules, which manages the payload and assures the overall performance and security of the system. Each of these modules have been developed with low SWaP for CubeSats, but with interoperability in mind for other satellite form factors. We present each of the listed components, together with the initial test results from our test bench and the performance of our protoflight models prior to initial integration with the 6U CubeSat platform systems. The completed ROKS payload will be ready for flight at the end of 2022, with various modular components already being baselined for flight and integrated into third party communication missions., Comment: 13 pages with 25 figures. Presented at Small Satellite Conference: https://digitalcommons.usu.edu/smallsat/2022/all2022/163/. Any comments are welcome

We demonstrate a novel MIR methane sensor shifting measurement wavelength to SWIR (1.55$\mu$m) by using non-linear interferometry. The technique exploits the interference effects seen in three-wave mixing when pump, signal, and idler modes make a double pass through a nonlinear crystal. The method allows sensing at wavelengths where detectors are poor ($>$3$\mu$m) and detection at wavelengths where photon counting sensitivity can be achieved. In a first experimental demonstration, we measured a small methane concentration inside a gas cell with high precision. This interferometer can be built in a compact design for field operations and potentially enable the detection of low concentrations of methane at up to 100m range. Signal-to-noise ratio calculations show that the method can outperform existing short wavelength ($\sim$1.65$\mu$m) integrated path differential absorption direct sensing at high ($>$$10^{-4}$) non-linear gain., Comment: Title change, new data, significant revision, 10 pages 5 figures

The information-theoretic unconditional security offered by quantum key distribution has spurred the development of larger quantum communication networks. However, as these networks grow so does the strong need to reduce complexity and overheads. Polarization based entanglement distribution networks are a promising approach due to their scalability and lack of trusted nodes. Nevertheless, they are only viable if the birefringence of all optical distribution fibres in the network is compensated to preserve the polarization based quantum state. The brute force approach would require a few hundred fibre polarization controllers for even a moderately sized network. Instead, we propose and investigate four different methods of polarization compensation. We compare them based on complexity, effort, level of disruption to network operations and performance.

Ramsey interferometry is a widely used tool for precisely measuring transition frequencies between two energy levels of a quantum system, with applications in time-keeping, precision spectroscopy, quantum optics, and quantum information. Often, the coherence time of the quantum system surpasses the one of the oscillator probing the system, thereby limiting the interrogation time and associated spectral resolution. Correlation spectroscopy overcomes this limitation by probing two quantum systems with the same noisy oscillator for a measurement of their transition frequency difference; this technique has enabled very precise comparisons of atomic clocks. Here, we extend correlation spectroscopy to the case of multiple quantum systems undergoing strong correlated dephasing. We model Ramsey correlation spectroscopy with $N$ particles as a multi-parameter phase estimation problem and demonstrate that multiparticle quantum correlations can assist in reducing the measurement uncertainties even in the absence of entanglement. We derive precision limits and optimal sensing techniques for this problem and compare the performance of probe states and measurement with and without entanglement. Using one- and two-dimensional ion Coulomb crystals with up to 91 qubits, we experimentally demonstrate the advantage of measuring multi-particle quantum correlations for reducing phase uncertainties, and apply correlation spectroscopy to measure ion-ion distances, transition frequency shifts, laser-ion detunings, and path-length fluctuations. Our method can be straightforwardly implemented in experimental setups with globally-coherent qubit control and qubit-resolved single-shot read-out and is thus applicable to other physical systems such as neutral atoms in tweezer arrays., Comment: 22 pages, 12 figures

Quantum simulators have recently enabled experimental observations of quantum many-body systems' internal thermalization. Often, the global energy and particle number are conserved, and the system is prepared with a well-defined particle number - in a microcanonical subspace. However, quantum evolution can also conserve quantities, or charges, that fail to commute with each other. Noncommuting charges have recently emerged as a subfield at the intersection of quantum thermodynamics and quantum information. Until now, this subfield has remained theoretical. We initiate the experimental testing of its predictions, with a trapped-ion simulator. We prepare 6-21 spins in an approximate microcanonical subspace, a generalization of the microcanonical subspace for accommodating noncommuting charges, which cannot necessarily have well-defined nontrivial values simultaneously. We simulate a Heisenberg evolution using laser-induced entangling interactions and collective spin rotations. The noncommuting charges are the three spin components. We find that small subsystems equilibrate to near a recently predicted non-Abelian thermal state. This work bridges quantum many-body simulators to the quantum thermodynamics of noncommuting charges, whose predictions can now be tested., Comment: 6.5 pages (3 figures) + appendices (10 pages); increased system size to 21 qubits; updated to match the version published in PRX Quantum