Search

The development of single-cell and spatial transcriptomics has revolutionized our capacity to investigate cellular properties, functions, and interactions in both cellular and spatial contexts. However, the analysis of single-cell and spatial omics data remains challenging. First, single-cell sequencing data are high-dimensional and sparse, often contaminated by noise and uncertainty, obscuring the underlying biological signals. Second, these data often encompass multiple modalities, including gene expression, epigenetic modifications, and spatial locations. Integrating these diverse data modalities is crucial for enhancing prediction accuracy and biological interpretability. Third, while the scale of single-cell sequencing has expanded to millions of cells, high-quality annotated datasets are still limited. Fourth, the complex correlations of biological tissues make it difficult to accurately reconstruct cellular states and spatial contexts. Traditional feature engineering-based analysis methods struggle to deal with the various challenges presented by intricate biological networks. Deep learning has emerged as a powerful tool capable of handling high-dimensional complex data and automatically identifying meaningful patterns, offering significant promise in addressing these challenges. This review systematically analyzes these challenges and discusses related deep learning approaches. Moreover, we have curated 21 datasets from 9 benchmarks, encompassing 58 computational methods, and evaluated their performance on the respective modeling tasks. Finally, we highlight three areas for future development from a technical, dataset, and application perspective. This work will serve as a valuable resource for understanding how deep learning can be effectively utilized in single-cell and spatial transcriptomics analyses, while inspiring novel approaches to address emerging challenges.

Accurate waveform templates of binary black holes (BBHs) with eccentric orbits are essential for the detection and precise parameter estimation of gravitational waves (GWs). While SEOBNRE produces accurate time-domain waveforms for eccentric BBH systems, its generation speed remains a critical bottleneck in analyzing such systems. Accelerating template generation is crucial to data analysis improvement and valuable information extraction from observational data. We present SEOBNRE_AIq5e2, an innovative AI-based surrogate model that crafted to accelerate waveform generation for eccentric, spin-aligned BBH systems. SEOBNRE_AIq5e2 incorporates an advanced adaptive resampling technique during training, enabling the generation of eccentric BBH waveforms with mass ratios up to 5, eccentricities below 0.2, and spins $|\chi_z|$ up to 0.6. It achieves an impressive generation speed of 4.3 ms per waveform with a mean mismatch of $1.02 \times 10^{-3}$. With the exceptional accuracy and rapid performance, SEOBNRE_AIq5e2 emerges as a promising waveform template for future analysis of eccentric gravitational wave data.

Protein function prediction is currently achieved by encoding its sequence or structure, where the sequence-to-function transcendence and high-quality structural data scarcity lead to obvious performance bottlenecks. Protein domains are "building blocks" of proteins that are functionally independent, and their combinations determine the diverse biological functions. However, most existing studies have yet to thoroughly explore the intricate functional information contained in the protein domains. To fill this gap, we propose a synergistic integration approach for a function-aware domain representation, and a domain-joint contrastive learning strategy to distinguish different protein functions while aligning the modalities. Specifically, we align the domain semantics with GO terms and text description to pre-train domain embeddings. Furthermore, we partition proteins into multiple sub-views based on continuous joint domains for contrastive training under the supervision of a novel triplet InfoNCE loss. Our approach significantly and comprehensively outperforms the state-of-the-art methods on various benchmarks, and clearly differentiates proteins carrying distinct functions compared to the competitor. Our implementation is available at https://github.com/AI-HPC-Research-Team/ProtFAD., Comment: 17 pages, 7 figures, 5 tables

The task of chemical reaction predictions (CRPs) plays a pivotal role in advancing drug discovery and material science. However, its effectiveness is constrained by the vast and uncertain chemical reaction space and challenges in capturing reaction selectivity, particularly due to existing methods' limitations in exploiting the data's inherent knowledge. To address these challenges, we introduce a data-curated self-feedback knowledge elicitation approach. This method starts from iterative optimization of molecular representations and facilitates the extraction of knowledge on chemical reaction types (RTs). Then, we employ adaptive prompt learning to infuse the prior knowledge into the large language model (LLM). As a result, we achieve significant enhancements: a 14.2% increase in retrosynthesis prediction accuracy, a 74.2% rise in reagent prediction accuracy, and an expansion in the model's capability for handling multi-task chemical reactions. This research offers a novel paradigm for knowledge elicitation in scientific research and showcases the untapped potential of LLMs in CRPs.

The precise prediction of molecular properties is essential for advancements in drug development, particularly in virtual screening and compound optimization. The recent introduction of numerous deep learning-based methods has shown remarkable potential in enhancing molecular property prediction (MPP), especially improving accuracy and insights into molecular structures. Yet, two critical questions arise: does the integration of domain knowledge augment the accuracy of molecular property prediction and does employing multi-modal data fusion yield more precise results than unique data source methods? To explore these matters, we comprehensively review and quantitatively analyze recent deep learning methods based on various benchmarks. We discover that integrating molecular information significantly improves molecular property prediction (MPP) for both regression and classification tasks. Specifically, regression improvements, measured by reductions in root mean square error (RMSE), are up to 4.0%, while classification enhancements, measured by the area under the receiver operating characteristic curve (ROC-AUC), are up to 1.7%. We also discover that enriching 2D graphs with 1D SMILES boosts multi-modal learning performance for regression tasks by up to 9.1%, and augmenting 2D graphs with 3D information increases performance for classification tasks by up to 13.2%, with both enhancements measured using ROC-AUC. The two consolidated insights offer crucial guidance for future advancements in drug discovery.

Efficient molecular modeling and design are crucial for the discovery and exploration of novel molecules, and the incorporation of deep learning methods has revolutionized this field. In particular, large language models (LLMs) offer a fresh approach to tackle scientific problems from a natural language processing (NLP) perspective, introducing a research paradigm called scientific language modeling (SLM). However, two key issues remain: how to quantify the match between model and data modalities and how to identify the knowledge-learning preferences of models. To address these challenges, we propose a multi-modal benchmark, named ChEBI-20-MM, and perform 1263 experiments to assess the model's compatibility with data modalities and knowledge acquisition. Through the modal transition probability matrix, we provide insights into the most suitable modalities for tasks. Furthermore, we introduce a statistically interpretable approach to discover context-specific knowledge mapping by localized feature filtering. Our pioneering analysis offers an exploration of the learning mechanism and paves the way for advancing SLM in molecular science.

Gravitational wave (GW) astronomy has opened new frontiers in understanding the cosmos, while the integration of artificial intelligence (AI) in science promises to revolutionize data analysis methodologies. However, a significant gap exists, as there is currently no dedicated platform that enables scientists to develop, test, and evaluate AI algorithms efficiently. To address this gap, we introduce GWAI, a pioneering AI-centered software platform designed for gravitational wave data analysis. GWAI contains a three-layered architecture that emphasizes simplicity, modularity, and flexibility, covering the entire analysis pipeline. GWAI aims to accelerate scientific discoveries, bridging the gap between advanced AI techniques and astrophysical research., Comment: 10 pages, 5 figures

Space-based gravitational wave (GW) detection is one of the most anticipated GW detection projects in the next decade, which promises to detect abundant compact binary systems. At present, deep learning methods have not been widely explored for GW waveform generation and extrapolation. To solve the data processing difficulty and the increasing waveform complexity caused by the detector's response and second-generation time-delay interferometry (TDI 2.0), an interpretable pre-trained large model named CBS-GPT (Compact Binary Systems Waveform Generation with Generative Pre-trained Transformer) is proposed. For compact binary system waveforms, three models were trained to predict the waveforms of massive black hole binaries (MBHB), extreme mass-ratio inspirals (EMRIs), and galactic binaries (GB), achieving prediction accuracies of at most 99%, 91%, and 99%, respectively. The CBS-GPT model exhibits notable generalization and interpretability, with its hidden parameters effectively capturing the intricate information of waveforms, even with the complex instrument response and a wide parameter range. Our research demonstrates the potential of large models in the GW realm, opening up new opportunities and guidance for future researches such as complex waveforms generation, gap completion, and deep learning model design for GW science.

Molecular property prediction, crucial for early drug candidate screening and optimization, has seen advancements with deep learning-based methods. While deep learning-based methods have advanced considerably, they often fall short in fully leveraging 3D spatial information. Specifically, current molecular encoding techniques tend to inadequately extract spatial information, leading to ambiguous representations where a single one might represent multiple distinct molecules. Moreover, existing molecular modeling methods focus predominantly on the most stable 3D conformations, neglecting other viable conformations present in reality. To address these issues, we propose 3D-Mol, a novel approach designed for more accurate spatial structure representation. It deconstructs molecules into three hierarchical graphs to better extract geometric information. Additionally, 3D-Mol leverages contrastive learning for pretraining on 20 million unlabeled data, treating their conformations with identical topological structures as weighted positive pairs and contrasting ones as negatives, based on the similarity of their 3D conformation descriptors and fingerprints. We compare 3D-Mol with various state-of-the-art baselines on 7 benchmarks and demonstrate our outstanding performance.

The detection of Extreme Mass Ratio Inspirals (EMRIs) is intricate due to their complex waveforms, extended duration, and low signal-to-noise ratio (SNR), making them more challenging to be identified compared to compact binary coalescences. While matched filtering-based techniques are known for their computational demands, existing deep learning-based methods primarily handle time-domain data and are often constrained by data duration and SNR. In addition, most existing work ignores time-delay interferometry (TDI) and applies the long-wavelength approximation in detector response calculations, thus limiting their ability to handle laser frequency noise. In this study, we introduce DECODE, an end-to-end model focusing on EMRI signal detection by sequence modeling in the frequency domain. Centered around a dilated causal convolutional neural network, trained on synthetic data considering TDI-1.5 detector response, DECODE can efficiently process a year's worth of multichannel TDI data with an SNR of around 50. We evaluate our model on 1-year data with accumulated SNR ranging from 50 to 120 and achieve a true positive rate of 96.3% at a false positive rate of 1%, keeping an inference time of less than 0.01 seconds. With the visualization of three showcased EMRI signals for interpretability and generalization, DECODE exhibits strong potential for future space-based gravitational wave data analyses., Comment: 11 pages, 5 figures, and 2 tables

Large language models have made significant strides in natural language processing, enabling innovative applications in molecular science by processing textual representations of molecules. However, most existing language models cannot capture the rich information with complex molecular structures or images. In this paper, we introduce GIT-Mol, a multi-modal large language model that integrates the Graph, Image, and Text information. To facilitate the integration of multi-modal molecular data, we propose GIT-Former, a novel architecture that is capable of aligning all modalities into a unified latent space. We achieve a 5%-10% accuracy increase in properties prediction and a 20.2% boost in molecule generation validity compared to the baselines. With the any-to-language molecular translation strategy, our model has the potential to perform more downstream tasks, such as compound name recognition and chemical reaction prediction., Comment: The article has been accepted by Computers in Biology and Medicine, with 14 pages and 4 figures

The direct observation of gravitational waves (GWs) opens a new window for exploring new physics from quanta to cosmos and provides a new tool for probing the evolution of universe. GWs detection in space covers a broad spectrum ranging over more than four orders of magnitude and enables us to study rich physical and astronomical phenomena. Taiji is a proposed space-based GW detection mission that will be launched in the 2030s. Taiji will be exposed to numerous overlapping and persistent GW signals buried in the foreground and background, posing various data analysis challenges. In order to empower potential scientific discoveries, the Mock LISA Data Challenge and the LISA Data Challenge (LDC) were developed. While LDC provides a baseline framework, the first LDC needs to be updated with more realistic simulations and adjusted detector responses for Taiji's constellation. In this paper, we review the scientific objectives and the roadmap for Taiji, as well as the technical difficulties in data analysis and the data generation strategy, and present the associated data challenges. In contrast to LDC, we utilize second-order Keplerian orbit and second-generation time delay interferometry techniques. Additionally, we employ a new model for the extreme-mass-ratio inspiral waveform and stochastic GW background spectrum, which enables us to test general relativity and measure the non-Gaussianity of curvature perturbations. Furthermore, we present a comprehensive showcase of parameter estimation using a toy dataset. This showcase not only demonstrates the scientific potential of the Taiji Data Challenge but also serves to validate the effectiveness of the pipeline. As the first data challenge for Taiji, we aim to build an open ground for data analysis related to Taiji sources and sciences. More details can be found on the official website at http://taiji-tdc.ictp-ap.org., Comment: 15 pages, 3 figures

With the advent of gravitational-wave astronomy and the discovery of more compact binary coalescences, data quality improvement techniques are desired to handle the complex and overwhelming noise in gravitational wave (GW) observational data. Though recent machine learning-based studies have shown promising results for data denoising, they are unable to precisely recover both the GW signal amplitude and phase. To address such an issue, we develop a deep neural network centered workflow, WaveFormer, for significant noise suppression and signal recovery on observational data from the Laser Interferometer Gravitational-Wave Observatory (LIGO). The WaveFormer has a science-driven architecture design with hierarchical feature extraction across a broad frequency spectrum. As a result, the overall noise and glitch are decreased by more than one order of magnitude and the signal recovery error is roughly 1% and 7% for the phase and amplitude, respectively. Moreover, on 75 reported binary black hole (BBH) events of LIGO we obtain a significant improvement of inverse false alarm rate. Our work highlights the potential of large neural networks in gravitational wave data analysis and, while primarily demonstrated on LIGO data, its adaptable design indicates promise for broader application within the International Gravitational-Wave Observatories Network (IGWN) in future observational runs.

We present the results of the first Machine Learning Gravitational-Wave Search Mock Data Challenge (MLGWSC-1). For this challenge, participating groups had to identify gravitational-wave signals from binary black hole mergers of increasing complexity and duration embedded in progressively more realistic noise. The final of the 4 provided datasets contained real noise from the O3a observing run and signals up to a duration of 20 seconds with the inclusion of precession effects and higher order modes. We present the average sensitivity distance and runtime for the 6 entered algorithms derived from 1 month of test data unknown to the participants prior to submission. Of these, 4 are machine learning algorithms. We find that the best machine learning based algorithms are able to achieve up to 95% of the sensitive distance of matched-filtering based production analyses for simulated Gaussian noise at a false-alarm rate (FAR) of one per month. In contrast, for real noise, the leading machine learning search achieved 70%. For higher FARs the differences in sensitive distance shrink to the point where select machine learning submissions outperform traditional search algorithms at FARs $\geq 200$ per month on some datasets. Our results show that current machine learning search algorithms may already be sensitive enough in limited parameter regions to be useful for some production settings. To improve the state-of-the-art, machine learning algorithms need to reduce the false-alarm rates at which they are capable of detecting signals and extend their validity to regions of parameter space where modeled searches are computationally expensive to run. Based on our findings we compile a list of research areas that we believe are the most important to elevate machine learning searches to an invaluable tool in gravitational-wave signal detection., Comment: 25 pages, 6 figures, 4 tables, additional material available at https://github.com/gwastro/ml-mock-data-challenge-1

Space-based gravitational wave (GW) detectors will be able to observe signals from sources that are otherwise nearly impossible from current ground-based detection. Consequently, the well established signal detection method, matched filtering, will require a complex template bank, leading to a computational cost that is too expensive in practice. Here, we develop a high-accuracy GW signal detection and extraction method for all space-based GW sources. As a proof of concept, we show that a science-driven and uniform multi-stage self-attention-based deep neural network can identify synthetic signals that are submerged in Gaussian noise. Our method exhibits a detection rate exceeding 99% in identifying signals from various sources, with the signal-to-noise ratio at 50, at a false alarm rate of 1%. while obtaining at least 95% similarity compared with target signals. We further demonstrate the interpretability and strong generalization behavior for several extended scenarios., Comment: 19 pages, 7 figures

Perovskite light-emitting diodes (PeLEDs) have emerged as a strong contender for next-generation display and information technologies. However, similar to perovskite solar cells, the poor operational stability remains the main obstacle toward commercial applications. Here we demonstrate ultra-stable and efficient PeLEDs with extraordinary operational lifetimes (T50) of 1.0x10^4 h, 2.8x10^4 h, 5.4x10^5 h, and 1.9x10^6 h at initial radiance (or current densities) of 3.7 W/sr/m2 (~5 mA/cm2), 2.1 W/sr/m2 (~3.2 mA/cm2), 0.42 W/sr/m2 (~1.1 mA/cm2), and 0.21 W/sr/m2 (~0.7 mA/cm2) respectively, and external quantum efficiencies of up to 22.8%. Key to this breakthrough is the introduction of a dipolar molecular stabilizer, which serves two critical roles simultaneously. First, it prevents the detrimental transformation and decomposition of the alpha-phase FAPbI3 perovskite, by inhibiting the formation of lead and iodide intermediates. Secondly, hysteresis-free device operation and microscopic luminescence imaging experiments reveal substantially suppressed ion migration in the emissive perovskite. The record-long PeLED lifespans are encouraging, as they now satisfy the stability requirement for commercial organic LEDs (OLEDs). These results remove the critical concern that halide perovskite devices may be intrinsically unstable, paving the path toward industrial applications., Comment: This is a preprint of the paper prior to peer review. New and updated results may be available in the final version from the publisher

The plethora of complex artificial intelligence (AI) algorithms and available high performance computing (HPC) power stimulates the expeditious development of AI components with heterogeneous designs. Consequently, the need for cross-stack performance benchmarking of AI-HPC systems emerges rapidly. The de facto HPC benchmark LINPACK can not reflect AI computing power and I/O performance without representative workload. The current popular AI benchmarks like MLPerf have fixed problem size therefore limited scalability. To address these issues, we propose an end-to-end benchmark suite utilizing automated machine learning (AutoML), which not only represents real AI scenarios, but also is auto-adaptively scalable to various scales of machines. We implement the algorithms in a highly parallel and flexible way to ensure the efficiency and optimization potential on diverse systems with customizable configurations. We utilize operations per second (OPS), which is measured in an analytical and systematic approach, as the major metric to quantify the AI performance. We perform evaluations on various systems to ensure the benchmark's stability and scalability, from 4 nodes with 32 NVIDIA Tesla T4 (56.1 Tera-OPS measured), up to 512 nodes with 4096 Huawei Ascend 910 (194.53 Peta-OPS measured), and the results show near-linear weak scalability. With flexible workload and single metric, our benchmark can scale and rank AI-HPC easily.

The High Altitude Water Cherenkov Observatory (HAWC) has a wide field-of-view (FOV, $\sim$2sr) and a high duty cycle ($\sim$95\%), which make it a powerful survey and monitoring experiment for sources of TeV gamma rays. We present a systematic survey of gamma-ray sources based on the Fermi 3FHL catalog. Sources are restricted to HAWC's FOV (Declination 19$^\circ$ $\pm$ 40$^\circ$) and to extragalactic sources with redshift: 0.001 $<$ z $<$ 0.3. Extragalactic gamma-ray sources are dominated by active galactic nuclei (AGN) and TeV gamma-ray sources are mostly BL Lac-type blazars. The study of AGNs through high energy gamma rays has opened a new window into the extreme processes of particle acceleration in the jets of these objects and provides a way to study the photon propagation and extra-galactic background light. We have improved the HAWC sensitivity at low energies (100 GeV to 1 TeV) based on the Crab pulsar, which is an excellent calibration source for TeV gamma rays. We will present the results of searching for and monitoring nearby AGNs with the improved analysis., Comment: Presented at the 35th International Cosmic Ray Conference (ICRC2017), Bexco, Busan, Korea. See arXiv:1708.02572 for all HAWC contributions

The HAWC collaboration has recently completed the construction of a gamma-ray observatory at an altitude of 4100 meters on the slope of the Sierra Negra volcano in the state of Puebla, Mexico. In order to achieve an optimal angular resolution, energy reconstruction, and cosmic-ray background suppression for the air showers observed by HAWC, it is crucial to obtain good timing and charge calibrations of the photosensors in the detector. The HAWC calibration is based on a laser system which is able to deliver short light pulses to all the tanks in the array. The light intensity can range over 7 orders of magnitude, broad enough to cover all the dynamic range of the PMT readout electronics. In this contribution we will present the HAWC calibration system, together with the methods used to calibrate the detector., Comment: Presented at the 34th International Cosmic Ray Conference (ICRC2015), The Hague, The Netherlands. See arXiv:1508.03327 for all HAWC contributions