Search

Protein retrieval, which targets the deconstruction of the relationship between sequences, structures and functions, empowers the advancing of biology. Basic Local Alignment Search Tool (BLAST), a sequence-similarity-based algorithm, has proved the efficiency of this field. Despite the existing tools for protein retrieval, they prioritize sequence similarity and probably overlook proteins that are dissimilar but share homology or functionality. In order to tackle this problem, we propose a novel protein retrieval framework that mitigates the bias towards sequence similarity. Our framework initiatively harnesses protein language models (PLMs) to embed protein sequences within a high-dimensional feature space, thereby enhancing the representation capacity for subsequent analysis. Subsequently, an accelerated indexed vector database is constructed to facilitate expedited access and retrieval of dense vectors. Extensive experiments demonstrate that our framework can equally retrieve both similar and dissimilar proteins. Moreover, this approach enables the identification of proteins that conventional methods fail to uncover. This framework will effectively assist in protein mining and empower the development of biology., Comment: 16 pages, 12 figures

The advent of deep learning has introduced efficient approaches for de novo protein sequence design, significantly improving success rates and reducing development costs compared to computational or experimental methods. However, existing methods face challenges in generating proteins with diverse lengths and shapes while maintaining key structural features. To address these challenges, we introduce CPDiffusion-SS, a latent graph diffusion model that generates protein sequences based on coarse-grained secondary structural information. CPDiffusion-SS offers greater flexibility in producing a variety of novel amino acid sequences while preserving overall structural constraints, thus enhancing the reliability and diversity of generated proteins. Experimental analyses demonstrate the significant superiority of the proposed method in producing diverse and novel sequences, with CPDiffusion-SS surpassing popular baseline methods on open benchmarks across various quantitative measurements. Furthermore, we provide a series of case studies to highlight the biological significance of the generation performance by the proposed method. The source code is publicly available at https://github.com/riacd/CPDiffusion-SS, Comment: 10 pages, 4 figures

Deep learning has become a crucial tool in studying proteins. While the significance of modeling protein structure has been discussed extensively in the literature, amino acid types are typically included in the input as a default operation for many inference tasks. This study demonstrates with structure alignment task that embedding amino acid types in some cases may not help a deep learning model learn better representation. To this end, we propose ProtLOCA, a local geometry alignment method based solely on amino acid structure representation. The effectiveness of ProtLOCA is examined by a global structure-matching task on protein pairs with an independent test dataset based on CATH labels. Our method outperforms existing sequence- and structure-based representation learning methods by more quickly and accurately matching structurally consistent protein domains. Furthermore, in local structure pairing tasks, ProtLOCA for the first time provides a valid solution to highlight common local structures among proteins with different overall structures but the same function. This suggests a new possibility for using deep learning methods to analyze protein structure to infer function., Comment: 8 pages, 4 figures

Understanding protein solubility is essential for their functional applications. Computational methods for predicting protein solubility are crucial for reducing experimental costs and enhancing the efficiency and success rates of protein engineering. Existing methods either construct a supervised learning scheme on small-scale datasets with manually processed physicochemical properties, or blindly apply pre-trained protein language models to extract amino acid interaction information. The scale and quality of available training datasets leave significant room for improvement in terms of accuracy and generalization. To address these research gaps, we propose \sol, a novel deep learning method that combines pre-training and fine-tuning schemes for protein solubility prediction. ProtSolM integrates information from multiple dimensions, including physicochemical properties, amino acid sequences, and protein backbone structures. Our model is trained using \data, the largest solubility dataset that we have constructed. PDBSol includes over $60,000$ protein sequences and structures. We provide a comprehensive leaderboard of existing statistical learning and deep learning methods on independent datasets with computational and experimental labels. ProtSolM achieved state-of-the-art performance across various evaluation metrics, demonstrating its potential to significantly advance the accuracy of protein solubility prediction., Comment: 10 pages, 7 figures, 9 tables

The critical dynamics of Model H with a conserved order parameter coupled to a transverse momentum density which describes the gas-liquid or binary-fluid transitions is investigated within the functional renormalization group approach formulated on the closed time path. According to the dynamic scaling analysis, Model H and QCD critical end point belong to the same dynamic universality class in the critical region. The higher-order correction of the transport coefficient $\bar\lambda$ and shear viscosity $\bar\eta$ arising from mode-couplings are obtained by calculating the two-point correlation functions. The flow equation of a dimensionless coupling constant for nondissipative interactions is derived to look for the fixed-point solution of the system. The scaling relation between the critical exponent of the transport coefficient and that of the shear viscosity is estimated. Finally, the dynamic critical exponent $z$ is obtained as a function of the spatial dimension $d$., Comment: 10 pages, 6 figures

Online action detection (OAD) aims to identify ongoing actions from streaming video in real-time, without access to future frames. Since these actions manifest at varying scales of granularity, ranging from coarse to fine, projecting an entire set of action frames to a single latent encoding may result in a lack of local information, necessitating the acquisition of action features across multiple scales. In this paper, we propose a multi-scale action learning transformer (MALT), which includes a novel recurrent decoder (used for feature fusion) that includes fewer parameters and can be trained more efficiently. A hierarchical encoder with multiple encoding branches is further proposed to capture multi-scale action features. The output from the preceding branch is then incrementally input to the subsequent branch as part of a cross-attention calculation. In this way, output features transition from coarse to fine as the branches deepen. We also introduce an explicit frame scoring mechanism employing sparse attention, which filters irrelevant frames more efficiently, without requiring an additional network. The proposed method achieved state-of-the-art performance on two benchmark datasets (THUMOS'14 and TVSeries), outperforming all existing models used for comparison, with an mAP of 0.2% for THUMOS'14 and an mcAP of 0.1% for TVseries., Comment: 8 pages, 3 figures

Acoustic waves in fluid with spin-0 nature have been long believed not to support spin Hall effect and strong orbital Hall effect that enables experimental observation. Here we report the first theoretical explication and experimental demonstration of giant acoustic geometric spin and orbital Hall effect characterized by a large transverse shift. We reveal that this effect occurs when a vortex beam is observed from a tilted reference frame free of wave-interface interactions or gradient-index media needed for observing conventional ones, and can be amplified by simply binding the beam tightly. Thanks to this mechanism, large transverse shifts proportional to angular momentum are observed in a compact system. Our work provides deeper insights into the physics of angular momentum of classic waves.

Fine-tuning Pre-trained protein language models (PLMs) has emerged as a prominent strategy for enhancing downstream prediction tasks, often outperforming traditional supervised learning approaches. As a widely applied powerful technique in natural language processing, employing Parameter-Efficient Fine-Tuning techniques could potentially enhance the performance of PLMs. However, the direct transfer to life science tasks is non-trivial due to the different training strategies and data forms. To address this gap, we introduce SES-Adapter, a simple, efficient, and scalable adapter method for enhancing the representation learning of PLMs. SES-Adapter incorporates PLM embeddings with structural sequence embeddings to create structure-aware representations. We show that the proposed method is compatible with different PLM architectures and across diverse tasks. Extensive evaluations are conducted on 2 types of folding structures with notable quality differences, 9 state-of-the-art baselines, and 9 benchmark datasets across distinct downstream tasks. Results show that compared to vanilla PLMs, SES-Adapter improves downstream task performance by a maximum of 11% and an average of 3%, with significantly accelerated training speed by a maximum of 1034% and an average of 362%, the convergence rate is also improved by approximately 2 times. Moreover, positive optimization is observed even with low-quality predicted structures. The source code for SES-Adapter is available at https://github.com/tyang816/SES-Adapter., Comment: 30 pages, 4 figures, 8 tables

Recently, in studies of holographic models and hydrodynamics with spontaneous breaking of approximate symmetries, it has been proposed that the damping of pseudo-Goldstone modes at finite temperatures is universally constrained in the way that $\Omega_{\varphi}/m_{\varphi}^2\simeq D_{\varphi}$ in the broken phase, where $\Omega_{\varphi}$ and $m_{\varphi} $ are the relaxation rate at zero wavenumber and the mass of pseudo-Goldstones, $D_{\varphi}$ is the Goldstone diffusivity in the limit of purely spontaneous breaking. In this paper, we investigate the pseudo-Goldstone damping in a purely relaxational O($N$) model by performing the functional renormalization group calculations at the full quantum and stochastic level within the Schwinger-Keldysh formalism. We find that, away from the critical temperature, the proposed relation is always valid. When the temperature is very close to the critical value such that the mass of the Higgs mode is comparable to the mass of the pseudo-Goldstone modes, the pseudo-Goldstone damping displays a novel scaling behavior that follows $\Omega_\varphi/m_\varphi^2\propto m_{\varphi}^{\Delta_\eta}$ with a correction $\Delta_\eta$ controlled by the critical universalities. Moreover, we study how the correction depends on the value of $N$ and show that $\Delta_\eta \rightarrow 0$ when fluctuations are infinitely suppressed in the large $N$ limit. In this case, the proposed relation works even in the critical region. Finally, we match our results to the dissipative sector of the pion dynamics near the chiral phase transition., Comment: V2:minor revision, references added, discussion on the pure SSB case has been moved to the supplement

In [1], we initiated a program for the quantitative investigation of dynamical chiral symmetry breaking and resonant bound states in QCD with the functional renormalisation group, concentrating on the full infrared dynamics of four-quark scatterings. In the present work we extend this study and take into account a three-momentum channel approximation ($s,t,u$-channel) for the Fierz-complete four-quark vertices. We find that the four-quark vertex in this approximation is quantitatively reliable. In particular, we have computed the pion pole mass, pion decay constant, Bethe-Salpeter amplitudes, the quark mass function and wave function. Our results confirm previous findings that low energy effective theories only reproduce QCD quantitatively, if initiated with a relatively low ultraviolet cutoff scale of the order of 500 MeV. The quantitative description set up here paves the way for reliable quantitative access to the resonance structure in QCD within the fRG approach to QCD., Comment: 20 pages, 19 figures; v2: minor typos corrected

The Schwinger-Keldysh functional renormalization group (fRG) developed in [1] is employed to investigate critical dynamics related to a second-order phase transition. The effective action of model A is expanded to the order of $O(\partial^2)$ in the derivative expansion for the $O(N)$ symmetry. By solving the fixed-point equations of effective potential and wave function, we obtain static and dynamic critical exponents for different values of the spatial dimension $d$ and the field component number $N$. It is found that one has $z \geq 2$ in the whole range of $2\leq d\leq 4$ for the case of $N=1$, while in the case of $N=4$ the dynamic critical exponent turns to $z < 2$ when the dimension approach towards $d=2$., Comment: 11 pages, 11 figures

The chiral crossover of QCD at finite temperature and vanishing baryon density turns into a second order phase transition if lighter than physical quark masses are considered. If this transition occurs sufficiently close to the physical point, its universal critical behaviour would largely control the physics of the QCD phase transition. We quantify the size of this region in QCD using functional approaches, both Dyson-Schwinger equations and the functional renormalisation group. The latter allows us to study both critical and non-critical effects on an equal footing, facilitating a precise determination of the scaling regime. We find that the physical point is far away from the critical region. Importantly, we show that the physics of the chiral crossover is dominated by soft modes even far beyond the critical region. While scaling functions determine all thermodynamic properties of the system in the critical region, the order parameter potential is the relevant quantity away from it. We compute this potential in QCD using the functional renormalisation group and Dyson-Schwinger equations and provide a simple parametrisation for phenomenological applications., Comment: 7+8 pages, 5+4 figures

Large protein language models are adept at capturing the underlying evolutionary information in primary structures, offering significant practical value for protein engineering. Compared to natural language models, protein amino acid sequences have a smaller data volume and a limited combinatorial space. Choosing an appropriate vocabulary size to optimize the pre-trained model is a pivotal issue. Moreover, despite the wealth of benchmarks and studies in the natural language community, there remains a lack of a comprehensive benchmark for systematically evaluating protein language model quality. Given these challenges, PETA trained language models with 14 different vocabulary sizes under three tokenization methods. It conducted thousands of tests on 33 diverse downstream datasets to assess the models' transfer learning capabilities, incorporating two classification heads and three random seeds to mitigate potential biases. Extensive experiments indicate that vocabulary sizes between 50 and 200 optimize the model, whereas sizes exceeding 800 detrimentally affect the model's representational performance. Our code, model weights and datasets are available at https://github.com/ginnm/ProteinPretraining., Comment: 46 pages, 4figures, 9 tables

Spin and orbital angular momenta (AM) are of fundamental interest in wave physics. Acoustic wave, as a typical longitudinal wave, has been well studied in terms of orbital AM, but still considered unable to carry non-zero integral spin AM or spin-orbital interaction in homogeneous media due to its spin-0 nature. Here we give the first self-consistent analytical calculations of spin, orbital and total AM of guided vortices under different boundary conditions, revealing that vortex field can carry non-zero integral spin AM. We also introduce for acoustic waves the canonical-Minkowski and kinetic-Abraham AM, which has aroused long-lasting debate in optics, and prove that only the former is conserved with the corresponding symmetries. Furthermore, we present the theoretical and experimental observation of the spin-orbit interaction of vortices in longitudinal acoustics, which is thought beyond attainable in longitudinal waves in the absence of spin degree of freedom. Our work provides a solid platform for future studies of the spin and orbital AM of guided acoustic waves and may open up a new dimension for acoustic vortex-based applications such as underwater communications and object manipulations.

Generative large language models (LLMs) have shown great success in various applications, including question-answering (QA) and dialogue systems. However, in specialized domains like traditional Chinese medical QA, these models may perform unsatisfactorily without fine-tuning on domain-specific datasets. To address this, we introduce MedChatZH, a dialogue model designed specifically for traditional Chinese medical QA. Our model is pre-trained on Chinese traditional medical books and fine-tuned with a carefully curated medical instruction dataset. It outperforms several solid baselines on a real-world medical dialogue dataset. We release our model, code, and dataset on https://github.com/tyang816/MedChatZH to facilitate further research in the domain of traditional Chinese medicine and LLMs., Comment: 7 pages, 3 figures

Non-destructive testing and medical diagnostic techniques using ultrasound has become indispensable in evaluating the state of materials or imaging the internal human body, respectively. To conduct spatially resolved high-quality observations, conventionally, sophisticated phased arrays are used both at the emitting and receiving ends of the setup. In comparison, single-sensor imaging techniques offer significant benefits including compact physical dimensions and reduced manufacturing expenses. However, recent advances such as compressive sensing have shown that this improvement comes at the cost of additional time-consuming dynamic spatial scanning or multi-mode mask switching, which severely hinders the quest for real-time imaging. Consequently, real-time single-sensor imaging, at low cost and simple design, still represents a demanding and largely unresolved challenge till this day. Here, we bestow on ultrasonic metasurface with both disorder and artificial intelligence (AI). The former ensures strong dispersion and highly complex scattering to encode the spatial information into frequency spectra at an arbitrary location, while the latter is used to decode instantaneously the amplitude and spectral component of the sample under investigation. Thus, thanks to this symbiosis, we demonstrate that a single fixed sensor suffices to recognize complex ultrasonic objects through the random scattered field from an unpretentious metasurface, which enables real-time and low-cost imaging, easily extendable to 3D.

Directed evolution plays an indispensable role in protein engineering that revises existing protein sequences to attain new or enhanced functions. Accurately predicting the effects of protein variants necessitates an in-depth understanding of protein structure and function. Although large self-supervised language models have demonstrated remarkable performance in zero-shot inference using only protein sequences, these models inherently do not interpret the spatial characteristics of protein structures, which are crucial for comprehending protein folding stability and internal molecular interactions. This paper introduces a novel pre-training framework that cascades sequential and geometric analyzers for protein primary and tertiary structures. It guides mutational directions toward desired traits by simulating natural selection on wild-type proteins and evaluates the effects of variants based on their fitness to perform the function. We assess the proposed approach using a public database and two new databases for a variety of variant effect prediction tasks, which encompass a diverse set of proteins and assays from different taxa. The prediction results achieve state-of-the-art performance over other zero-shot learning methods for both single-site mutations and deep mutations.

The maximum entropy method (MEM) and the Gaussian process (GP) regression, which are both well-suited for the treatment of inverse problems, are used to reconstruct net-baryon number distributions based on a finite number of cumulants of the distribution. Baryon number distributions across the chiral phase transition are reconstructed. It is found that with the increase of the order of cumulants, distribution in the long tails, i.e., far away from the central number, would become more and more important. We also reconstruct the distribution function based on the experimentally measured cumulants at the collision energy $\sqrt{s_{NN}}=7.7$ GeV. Given the sizable error of the fourth-order cumulant measured in experiments, the calculation of MEM shows that with the increasing fourth-order cumulant, there is another peak in the distribution function developed in the region of large baryon number. This unnaturalness observed in the reconstructed distribution function might in turn be used to constrain the cumulants measured in experiments., Comment: 11 pages, 8 figures, 2 tables

Heart sound auscultation has been applied in clinical usage for early screening of cardiovascular diseases. Due to the high demand for auscultation expertise, automatic auscultation can help with auxiliary diagnosis and reduce the burden of training professional clinicians. Nevertheless, there is a limit to classic machine learning's performance improvement in the era of big data. Deep learning has outperformed classic machine learning in many research fields, as it employs more complex model architectures with a stronger capability of extracting effective representations. Moreover, it has been successfully applied to heart sound analysis in the past years. As most review works about heart sound analysis were carried out before 2017, the present survey is the first to work on a comprehensive overview to summarise papers on heart sound analysis with deep learning published in 2017--2022. This work introduces both classic machine learning and deep learning for comparison, and further offer insights about the advances and future research directions in deep learning for heart sound analysis. Our repository is publicly available at \url{https://github.com/zhaoren91/awesome-heart-sound-analysis}., Comment: Accepted by IEEE Computational Intelligence Magazine

Although many studies have successfully applied transfer learning to medical image segmentation, very few of them have investigated the selection strategy when multiple source tasks are available for transfer. In this paper, we propose a prior knowledge guided and transferability based framework to select the best source tasks among a collection of brain image segmentation tasks, to improve the transfer learning performance on the given target task. The framework consists of modality analysis, RoI (region of interest) analysis, and transferability estimation, such that the source task selection can be refined step by step. Specifically, we adapt the state-of-the-art analytical transferability estimation metrics to medical image segmentation tasks and further show that their performance can be significantly boosted by filtering candidate source tasks based on modality and RoI characteristics. Our experiments on brain matter, brain tumor, and white matter hyperintensities segmentation datasets reveal that transferring from different tasks under the same modality is often more successful than transferring from the same task under different modalities. Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance. And such similarity can be captured using the Structural Similarity index in the label space., Comment: Accepted by BIBM 2022

Fixed-point equations in the functional renormalization group approach are integrated from large to vanishing field, where an asymptotic potential in the limit of large field is implemented as initial conditions. This approach allows us to obtain a global fixed-point potential with high numerical accuracy, that incorporates the correct asymptotic behavior in the limit of large field. Our calculated global potential is in good agreement with the Taylor expansion in the region of small field, and it also coincides with the Laurent expansion in the regime of large field. Laurent expansion of the potential in the limit of large field for general case, that the spatial dimension $d$ is a continuous variable in the range $2\leq d \leq 4$, is obtained. Eigenfunctions and eigenvalues of perturbations near the Wilson-Fisher fixed point are computed with the method of eigenperturbations. Critical exponents for different values of $d$ and $N$ of the $O(N)$ universality class are calculated., Comment: 10 pages, 4 figures, 1 table; v2: minor changes, discussions and references added

We investigate dynamical chiral symmetry breaking and the emergence of mesonic bound states from the infrared dynamics of four-quark scatterings. Both phenomena originate from the resonant scalar-pseudoscalar channel of the four-quark scatterings, and we compute the functional renormalisation group (fRG) flows of the Fierz-complete four-quark interaction of up and down quarks with its $t$ channel momentum dependence. This is done in the isospin symmetric case, also including the flow of the quark two-point function. This system can be understood as the fRG analogues of the complete Bethe-Salpeter equations and quark gap equation. The pole mass of the pion is determined from both direct calculations of the four-quark flows in the Minkowski regime of momenta and the analytic continuation based on results in the Euclidean regime, which are consistent with each other., Comment: 26 pages, 20 figures, 3 tables; v2: minor typos corrected

In 2012, De Cristofaro et al. proposed a protocol to calculate the Private Set Intersection and Union cardinality(PSI-CA and PSU-CA). This protocol's security is based on the famous DDH assumption. Since its publication, it has gained lots of popularity because of its efficiency(linear complexity in computation and communication) and concision. So far, it's still considered one of the most efficient PSI-CA protocols and the most cited(more than 170 citations) PSI-CA paper based on the Google Scholar search. However, when we tried to implement this protocol, we couldn't get the correct result of the test data. Since the original paper lacks of experimental results to verify the protocol's correctness, we looked deeper into the protocol and found out it made a fundamental mistake. Needless to say, its correctness analysis and security proof are also wrong. In this paper, we will point out this PSI-CA protocol's mistakes, and provide the correct version of this protocol as well as the PSI protocol developed from this protocol. We also present a new security proof and some experimental results of the corrected protocol.

We propose two novel transferability metrics F-OTCE (Fast Optimal Transport based Conditional Entropy) and JC-OTCE (Joint Correspondence OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more transferable representations for cross-domain cross-task transfer learning. Unlike the existing metric that requires evaluating the empirical transferability on auxiliary tasks, our metrics are auxiliary-free such that they can be computed much more efficiently. Specifically, F-OTCE estimates transferability by first solving an Optimal Transport (OT) problem between source and target distributions, and then uses the optimal coupling to compute the Negative Conditional Entropy between source and target labels. It can also serve as a loss function to maximize the transferability of the source model before finetuning on the target task. Meanwhile, JC-OTCE improves the transferability robustness of F-OTCE by including label distances in the OT problem, though it may incur additional computation cost. Extensive experiments demonstrate that F-OTCE and JC-OTCE outperform state-of-the-art auxiliary-free metrics by 18.85% and 28.88%, respectively in correlation coefficient with the ground-truth transfer accuracy. By eliminating the training cost of auxiliary tasks, the two metrics reduces the total computation time of the previous method from 43 minutes to 9.32s and 10.78s, respectively, for a pair of tasks. When used as a loss function, F-OTCE shows consistent improvements on the transfer accuracy of the source model in few-shot classification experiments, with up to 4.41% accuracy gain., Comment: This work is accepted by IEEE TNNLS. Please see the official version https://ieeexplore.ieee.org/abstract/document/10420486.Copyright may be transferred without notice, after which this version may no longer be accessible

We derive renormalised finite functional flow equations for quantum field theories in real and imaginary time that incorporate scale transformations of the renormalisation conditions, hence implementing a flowing renormalisation. The flows are manifestly finite in general non-perturbative truncation schemes also for regularisation schemes that do not implement an infrared suppression of the loops in the flow. Specifically, this formulation includes finite functional flows for the effective action with a spectral Callan-Symanzik cutoff, and therefore gives access to Lorentz invariant spectral flows. The functional setup is fully non-perturbative and allows for the spectral treatment of general theories. In particular, this includes theories that do not admit a perturbative renormalisation such as asymptotically safe theories. Finally, the application of the Lorentz invariant spectral functional renormalisation group is briefly discussed for theories ranging from real scalar and Yukawa theories to gauge theories and quantum gravity., Comment: 31 pages, 1 figure