Search for: All records

Spatial transcriptomics (ST) has emerged as a powerful technology for bridging histology imaging with gene expression profiling. However, its application has been limited by low throughput and the need for specialized experimental facilities. Prior works sought to predict ST from whole-slide histology images to accelerate this process, but they suffer from two major limitations. First, they do not explicitly model cell-cell interaction as they factorize the joint distribution of whole-slide ST data and predict the gene expression of each spot independently. Second, their encoders struggle with memory constraints due to the large number of spots (often exceeding 10,000) in typical ST datasets. Herein, we propose STFlow, a flow matching generative model that considers cell-cell interaction by modeling the joint distribution of gene expression of an entire slide. It also employs an efficient slide-level encoder with local spatial attention, enabling whole-slide processing without excessive memory overhead. On the recently curated HEST-1k and STImage-1K4M benchmarks, STFlow substantially outperforms state-of-the-art baselines and achieves over 18% relative improvements over the pathology foundation models. 

Nucleic acid-based drugs like aptamers have recently demonstrated great therapeutic potential. However, experimental platforms for aptamer screening are costly, and the scarcity of labeled data presents a challenge for supervised methods to learn protein-aptamer binding. To this end, we develop an unsupervised learning approach based on the predicted pairwise contact map between a protein and a nucleic acid and demonstrate its effectiveness in protein-aptamer binding prediction. Our model is based on FAFormer, a novel equivariant transformer architecture that seamlessly integrates frame averaging (FA) within each transformer block. This integration allows our model to infuse geometric information into node features while preserving the spatial semantics of coordinates, leading to greater expressive power than standard FA models. Our results show that FAFormer outperforms existing equivariant models in contact map prediction across three protein complex datasets, with over 10% relative improvement. Moreover, we curate five real-world protein-aptamer interaction datasets and show that the contact map predicted by FAFormer serves as a strong binding indicator for aptamer screening. 

Abstract Observations of GeV gamma-ray emission from the well-studied mixed-morphology supernova remnant (SNR) W44 by Fermi-Large Area Telescope and AGILE imply that it is a site of significant cosmic-ray acceleration. The spectral energy distribution (SED) derived from the GeV data suggests that the gamma-ray emission likely originates from the decay of neutral pions generated by cosmic-ray interactions. It is essential to measure the SED of W44 in the X-ray and very-high-energy (VHE) gamma-ray bands to verify the hadronic origin of the emission and to gauge the potential contributions from leptonic emission. We report an upper limit of the nonthermal X-ray flux from W44 of 5  × 10⁻¹³erg cm⁻²s⁻¹in the 0.5–8.0 keV band based on  ∼300 ks of XMM-Newton observations. The X-ray upper limit is consistent with previously estimated hadronic models, but in tension with the leptonic models. We estimate the VHE flux upper limit of  ∼1.2  × 10⁻¹²erg s⁻¹cm⁻²in the 0.5–5.0 TeV range from W44 using data from the Very Energetic Radiation Imaging Telescope Array System. Our nondetection of W44 at VHE wavelengths is in agreement with observations from other imaging atmospheric Cherenkov telescopes and is perhaps consistent with the evolutionary stage of the SNR. 

Abstract Pulsar halos are regions around middle-aged pulsars extending out to tens of parsecs. The large extent of the halos and well-defined central cosmic-ray accelerators make this new class of Galactic sources an ideal laboratory for studying cosmic-ray transport. LHAASO J0621+3755 is a candidate pulsar halo associated with the middle-aged gamma-ray pulsar PSR J0622+3749. We observed LHAASO J0621+3755 with VERITAS and XMM-Newton in the TeV and X-ray bands, respectively. For this work, we developed a novel background estimation technique for imaging atmospheric Cherenkov telescope observations of such extended sources. No halo emission was detected with VERITAS (0.3–10 TeV) or XMM-Newton (2–7 keV) within 1^∘and $10^{\prime }$around PSR J0622+3749, respectively. Combined with the LHAASO Kilometer Square Array (KM2A) and Fermi-LAT data, VERITAS flux upper limits establish a spectral break at  ∼1–10 TeV, a unique feature compared with Geminga, the most studied pulsar halo. We model the gamma-ray spectrum and LHAASO-KM2A surface brightness as inverse Compton emission and find suppressed diffusion around the pulsar, similar to Geminga. A smaller diffusion suppression zone and harder electron injection spectrum than Geminga are necessary to reproduce the spectral cutoff. A magnetic field ≤1μG is required by our XMM-Newton observation and synchrotron spectral modeling, consistent with Geminga. Our findings support slower diffusion and lower magnetic field around pulsar halos than the Galactic averages, hinting at magnetohydrodynamic turbulence around pulsars. Additionally, we report the detection of an X-ray point source spatially coincident with PSR J0622+3749, whose periodicity is consistent with the gamma-ray spin period of 333.2 ms. The soft spectrum of this source suggests a thermal origin. 

In this work, we propose a novel approach for the real-time estimation of chip-level spatial power maps for commercial Google Coral M.2 TPU chips based on a machine-learning technique for the first time. The new method can enable the development of more robust runtime power and thermal control schemes to take advantage of spatial power information such as hot spots that are otherwise not available. Different from the existing commercial multi-core processors in which real-time performance-related utilization information is available, the TPU from Google does not have such information. To mitigate this problem, we propose to use features that are related to the workloads of running different deep neural networks (DNN) such as the hyperparameters of DNN and TPU resource information generated by the TPU compiler. The new approach involves the offline acquisition of accurate spatial and temporal temperature maps captured from an external infrared thermal imaging camera under nominal working conditions of a chip. To build the dynamic power density map model, we apply generative adversarial networks (GAN) based on the workload-related features. Our study shows that the estimated total powers match the manufacturer's total power measurements extremely well. Experimental results further show that the predictions of power maps are quite accurate, with the RMSE of only 4.98\rm mW/mm^2, or 2.6\% of the full-scale error. The speed of deploying the proposed approach on an Intel Core i7-10710U is as fast as 6.9ms, which is suitable for real-time estimation. 

2.5D chiplet-based technology promises an efficient integration technique for advanced designs with more functionality and higher performance. Temperature and related thermal optimization, heat removal are of critical importance for temperature-aware physical synthesis for chiplets. This paper presents a novel graph convolutional networks (GCN) architecture to estimate the thermal map of the 2.5D chiplet-based systems with the thermal resistance networks built by the compact thermal model (CTM). First, we take the total power of all chiplets as an input feature, which is a global feature. This additional global information can overcome the limitation that the GCN can only extract local information via neighborhood aggregation. Second, inspired by convolutional neural networks (CNN), we add skip connection into the GCN to pass the global feature directly across the hidden layers with the concatenation operation. Third, to consider the edge embedding feature, we propose an edge-based attention mechanism based on the graph attention networks (GAT). Last, with the multiple aggregators and scalers of principle neighborhood aggregation (PNA) networks, we can further improve the modeling capacity of the novel GCN. The experimental results show that the proposed GCN model can achieve an average RMSE of 0.31 K and deliver a 2.6$$\times$$ speedup over the fast steady-state solver of open-source {\it HotSpot} based on SuperLU. More importantly, the GCN model demonstrates more useful generalization or transferable capability. Our results show that the trained GCN can be directly applied to predict thermal maps of six unseen datasets with acceptable mean RMSEs of less than 0.67 K without retraining via inductive learning. 

Abstract Assuming Galactic cosmic rays originate in supernovae and the winds of massive stars, starburst galaxies should produce very-high-energy (VHE;E > 100 GeV) gamma-ray emission via the interaction of their copious quantities of cosmic rays with the large reservoirs of dense gas within the galaxies. Such VHE emission was detected by VERITAS from the starburst galaxy M82 in 2008–09. An extensive, multiyear campaign followed these initial observations, yielding a total of 254 hr of good-quality VERITAS data on M82. Leveraging modern analysis techniques and the larger exposure, these VERITAS data show a more statistically significant VHE signal (∼6.5 standard deviations,σ). The corresponding photon spectrum is well fit by a power law (Γ = 2.3 ± 0.3_stat ± 0.2_sys), and the observed integral flux isF(>450 GeV) = (3.2 ± 0.6_stat ± 0.6_sys) × 10⁻¹³cm⁻²s⁻¹, or ∼0.4% of the Crab Nebula flux above the same energy threshold. The improved VERITAS measurements, when combined with various multiwavelength data, enable modeling of the underlying emission and transport processes. A purely leptonic scenario is found to be a poor representation of the gamma-ray spectral energy distribution (SED). A lepto-hadronic scenario with cosmic rays following a power-law spectrum in momentum (indexs ≃ 2.25) and with significant bremsstrahlung below 1 GeV provides a good match to the observed SED. The synchrotron emission from the secondary electrons indicates that efficient nonradiative losses of cosmic-ray electrons may be related to advective escape from the starburst core.