High-resolution Density Maps Research Articles

CryoTRANS: predicting high-resolution maps of rare conformations from self-supervised trajectories in cryo-EM

Cryogenic electron microscopy (cryo-EM) has revolutionized structural biology, enabling efficient determination of structures at near-atomic resolutions. However, a common challenge arises from the severe imbalance among various conformations of vitrified particles, leading to low-resolution reconstructions in rare conformations due to a lack of particle images in these quasi-stable states. We introduce CryoTRANS, a method that predicts high-resolution maps of rare conformations by constructing a self-supervised pseudo-trajectory between density maps of varying resolutions. This trajectory is represented by an ordinary differential equation parameterized by a deep neural network, ensuring retention of detailed structures from high-resolution density maps. By leveraging a single high-resolution density map, CryoTRANS significantly improves the reconstruction of rare conformations and has been validated on four real-world datasets: alpha-2-macroglobulin, actin-binding protein complexes, SARS-CoV-2 spike glycoprotein, and the 70S ribosome. CryoTRANS can also predict high-resolution structures in cryogenic electron tomography maps using a high-resolution cryo-EM map.

Cryo2StructData: A Large Labeled Cryo-EM Density Map Dataset for AI-based Modeling of Protein Structures

The advent of single-particle cryo-electron microscopy (cryo-EM) has brought forth a new era of structural biology, enabling the routine determination of large biological molecules and their complexes at atomic resolution. The high-resolution structures of biological macromolecules and their complexes significantly expedite biomedical research and drug discovery. However, automatically and accurately building atomic models from high-resolution cryo-EM density maps is still time-consuming and challenging when template-based models are unavailable. Artificial intelligence (AI) methods such as deep learning trained on limited amount of labeled cryo-EM density maps generate inaccurate atomic models. To address this issue, we created a dataset called Cryo2StructData consisting of 7,600 preprocessed cryo-EM density maps whose voxels are labelled according to their corresponding known atomic structures for training and testing AI methods to build atomic models from cryo-EM density maps. Cryo2StructData is larger than existing, publicly available datasets for training AI methods to build atomic protein structures from cryo-EM density maps. We trained and tested deep learning models on Cryo2StructData to validate its quality showing that it is ready for being used to train and test AI methods for building atomic models.

Context Attention Fusion Network for crowd counting

Context information, which plays a crucial role in many computer vision tasks, can benefit deep networks to construct better cognitive competence from more comprehensive surrounding. However, most existing crowd counting methods often overlook the importance of context information extracted from both global and local views. To address or alleviate this problem, this paper proposes a novel Context Attention Fusion Network, which is abbreviated as CAFNet for crowd counting. The core idea behind CAFNet is the interaction of multiple context information, including local context, cross-level context, and cross-layer context. To explore local context, we design a local context aggregation module to extract hierarchically local semantic information and then integrate them adaptively. To utilize cross-level context, a guidance attention fusion module is designed to fuse low-level feature map as the guidance of high-level context information so that the spatial details can be effectively compensated. To make full use of cross-layer features, a multi-layer context fusion module is developed to exchange the potentiality of multi-layer information to generate a high-resolution density map. Experimental results on four challenging datasets manifest that the newly proposed CAFNet can deliver impressive results compared with other state-of-the-art crowd counting models.

From Prototype to Inference: A Pipeline to Apply Deep Learning in Sorghum Panicle Detection.

Head (panicle) density is a major component in understanding crop yield, especially in crops that produce variable numbers of tillers such as sorghum and wheat. Use of panicle density both in plant breeding and in the agronomy scouting of commercial crops typically relies on manual counts observation, which is an inefficient and tedious process. Because of the easy availability of red-green-blue images, machine learning approaches have been applied to replacing manual counting. However, much of this research focuses on detection per se in limited testing conditions and does not provide a general protocol to utilize deep-learning-based counting. In this paper, we provide a comprehensive pipeline from data collection to model deployment in deep-learning-assisted panicle yield estimation for sorghum. This pipeline provides a basis from data collection and model training, to model validation and model deployment in commercial fields. Accurate model training is the foundation of the pipeline. However, in natural environments, the deployment dataset is frequently different from the training data (domain shift) causing the model to fail, so a robust model is essential to build a reliable solution. Although we demonstrate our pipeline in a sorghum field, the pipeline can be generalized to other grain species. Our pipeline provides a high-resolution head density map that can be utilized for diagnosis of agronomic variability within a field, in a pipeline built without commercial software.

Less is more: Developing an approach for assessing clustering at the lower administrative boundaries that increases the yield of active screening for leprosy in Bihar, India.

In India, leprosy clusters at hamlet level but detailed information is lacking. We aim to identify high-incidence hamlets to be targeted for active screening and post-exposure prophylaxis. We paid home visits to a cohort of leprosy patients registered between April 1st, 2020, and March 31st, 2022. Patients were interviewed and household members were screened for leprosy. We used an open-source app(ODK) to collect data on patients' mobility, screening results of household members, and geographic coordinates of their households. Clustering was analysed with Kulldorff's spatial scan statistic(SaTScan). Outlines of hamlets and population estimates were obtained through an open-source high-resolution population density map(https://data.humdata.org), using kernel density estimation in QGIS, an open-source software. We enrolled 169 patients and screened 1,044 household contacts in Bisfi and Benipatti blocks of Bihar. Median number of years of residing in the village was 17, interquartile range(IQR)12-30. There were 11 new leprosy cases among 658 household contacts examined(167 per 10,000), of which seven had paucibacillary leprosy, one was a child under 14 years, and none had visible disabilities. We identified 739 hamlets with a total population of 802,788(median 163, IQR 65-774). There were five high incidence clusters including 12% of the population and 46%(78/169) of the leprosy cases. One highly significant cluster with a relative risk (RR) of 4.7(p<0.0001) included 32 hamlets and 27 cases in 33,609 population. A second highly significant cluster included 32 hamlets and 24 cases in 33,809 population with a RR of 4.1(p<0.001). The third highly significant cluster included 16 hamlets and 17 cases in 19,659 population with a RR of 4.8(p<0.001). High-risk clusters still need to be screened door-to-door. We found a high yield of active household contact screening. Our tools for identifying high-incidence hamlets appear effective. Focusing labour-intensive interventions such as door-to-door screening on such hamlets could increase efficiency.

Crowd counting in complex scenes based on an attention aware CNN network

Crowd counting with density estimation has been an active research community due to its significant applications in the fields of public security, video surveillance, traffic monitoring. However, Crowd counting for congested scenes often suffers from some obstacles including severe occlusions, large scale variations, noise interference, etc. In this paper, using the first ten layers of a modified VGG16 and dilated convolution layers as the framework, we have proposed a CNN based crowd counting and density estimation model improved by the attention aware modules with residual connections. To tackle the problem of noise interference, convolutional block attention modules have been introduced into the deep network to segment the foreground and background to focus on interest information, refining deeper features of the input image. To improve information transmission and reuse, residual connections are utilized to link 3 attention blocks. Meanwhile, dilated convolution layers keep larger reception fields and obtain high-resolution density maps. The proposed method has been evaluated on three public benchmarks, i.e. Shanghai Tech A & B, UCF-QNRF and MALL, achieving the mean absolute errors of 64.6 & 8.3, 113.8 and 1.68, respectively. The results outperform some existing excellent approaches. This indicates that the proposed model has high accuracy and better robustness, which is suitable for crowd counting and density estimation in various congested scenes.

PO-687-01 REDO CATHETER ABLATION IN HIGHLY SYMPTOMATIC PATIENTS WITH INAPPROPRIATE SINUS TACHYCARDIA: THE USEFULNESS OF THE NOVEL SUPERMAP FEATURE OF DIPOLE CHARGE DENSITY MAPPING

Inappropriate sinus tachycardia (IAST) is an unusual form of supraventricular arrhythmia defined by inexplicably high sinus node frequency in individuals without apparent cardiovascular disease. Mapping and catheter ablation (CA) of IAST achieves reasonably good primary success, however, symptomatic relief decreases substantially, and patients require multiple redo procedures. By offering a global endocardial 3D anatomical map combined with high-resolution charge density maps of electrical activation, the AcQMap mapping system offers advantages for ablation of symptomatic IAST.

Herschel Investigation of Cores and Filamentary Structures in the Perseus Molecular Cloud

Abstract Cores and filamentary structures are the prime birthplaces of stars, and play key roles in the process of star formation. Latest advances in the methods of multi-scale source and filament extraction, and in making high-resolution column density map from Herschel multi-wavelength observations enable us to detect the filamentary network structures in highly complex molecular cloud environments. The statistics for physical parameters shows that core mass strongly correlates with core dust temperature, and M/L strongly correlates with M/T, which is in line with the prediction of the blackbody radiation, and can be used to trace evolutionary sequence from unbound starless cores to robust prestellar cores. Crest column densities of the filamentary structures are clearly related with mass per unit length (M line), but are uncorrelated by three orders ranging from ∼1020 to ∼1022 cm−2 with widths. Full width at half maximum has a median value of 0.15 pc, which is consistent with the 0.1 pc typical inner width of the filamentary structures reported by previous research. We find 70% of robust prestellar cores (135/199) embedded in supercritical filaments with M line &gt; 16 M ⊙ pc−1, which implies that the gravitationally bound cores come from fragmentation of supercritical filaments. On the basis of observational evidence that the probability distribution function with power-law distribution in the Perseus south is flatter than in the north, the number of young stellar objects in the south is significantly less than that in the north, and dust temperature is different. We infer that the south region is more gravitationally bound than the north region.

Gentle all-atom MD refinement to cryo-EM densities via Bayes' approach

Better detectors and automated data collection has created a flood of high-resolution cryo-EM density maps, which in turn has renewed interest in improving methods for determining atomic structure models corresponding to these maps. Automatically fitting atoms to a density is increasingly difficult as the resolution increases and the refinement potential has a large number of local minima. In practice the problem is even more complex when one also wants to balance fit to maps with maintaining good stereochemistry and allowing protein secondary structure to change as part of the fitting.

Improvement of a Dasymetric Method for Implementing Sustainable Development Goal 11 Indicators at an Intra-Urban Scale

Local and Regional Authorities require indicators at the intra-urban scale to design adequate policies to foster the achievement of the objectives of Sustainable Development Goal (SDG) 11. Updated high-resolution population density and settlement maps are the basic input products for such indicators and their sub-indicators. When provided at the intra-urban scale, these essential variables can facilitate the extraction of population flows, including both local and regular migrant components. This paper discusses a modification of the dasymetric method implemented in our previous work, aimed at improving the population density estimation. The novelties of our paper include the introduction of building height information and site-specific weight values for population density correction. Based on the proposed improvements, selected indicators/sub-indicators of four SDG 11 targets were updated or newly implemented. The output density map error values are provided in terms of the mean absolute error, root mean square error and mean absolute percentage indicators. The values obtained (i.e., 2.3 and 4.1 people, and 8.6%, respectively) were lower than those of the previous dasymetric method. The findings suggest that the new methodology can provide updated information about population fluxes and processes occurring over the period 2011–2020 in the study site—Bari city in southern Italy.

CFFNet: Coordinated feature fusion network for crowd counting

Long skip connection or encoder-decoder networks for crowd counting have proven to be effective methods to generate high-resolution density maps. However, the simple and coarse feature fusion ignores the disharmony between features, that is, spatial misalignment and semantic inconsistency, which will weaken feature representation and degrade network performance. In this paper, we propose an end-to-end trainable architecture called Coordinated Feature Fusion Network (CFFNet) to tackle the aforementioned problems. The proposed model contains a powerful baseline network and embeds two primary modules: Spatial Alignment Module (SAM) and Semantic Consistency Module (SCM). Specifically, the SAM can learn the transformation offset of pixels to alleviate the spatial misalignment caused by the feature resolution difference; the SCM based on the multi-scale attention mechanism can capture pixel-wise weight to alleviate the semantic inconsistency due to the feature level gap. Extensive experiments on four benchmark crowd datasets (the ShanghaiTech, the UCF-QNRF, the JHU-CRWORD++ and the NWPU-Crowd), indicate that CFFNet can achieve state-of-the-art counting performance and high robustness.

Multi‐level feature fusion network for crowd counting

Crowd counting has become a noteworthy vision task due to the needs of numerous practical applications, but it remains challenging. State-of-the-art methods generally estimate the density map of the crowd image with the high-level semantic features of various deep convolutional networks. However, the absence of low-level spatial information may result in counting errors in the local details of the density map. To this end, a novel framework named Multi-level Feature Fusion Network (MFFN) for single image crowd counting is proposed. The proposed MFFN, which is constructed in an encoder–decoder fashion, incorporates semantic and spatial information for generating high-resolution density maps of input crowd images. Skip connections are developed between the encoder and the decoder so that low-level spatial information and high-level semantic features can be combined by element-wise addition. In addition, a dense dilated convolution block is placed behind the encoder, extracting multi-scale context features to guide feature fusion by a channel attention mechanism. The model is trained by multi-task learning; semantic segmentation supervision is introduced to enhance feature representation. Extensive experiments are conducted on three crowd counting datasets (ShanghaiTech, UCF_CC_50, UCF-QNRF), and the results show that MFFN outperforms state-of-the-art methods. In addition, sufficient ablation studies are performed to verify the effectiveness of each component in our proposed method.

Where is Everyone? The Importance of Population Density Data: A Data Artefact Study of the Facebook Population Density Map

In this paper, we explore new and traditional approaches to measuring population density, and ways in which density information has frequently been used by humanitarian, private-sector and government actors to advance a range of private and public goals. We explain how new innovations are leading to fresh ways of collecting data—and fresh forms of data—and how this may open up new avenues for using density information in a variety of contexts. Section III examines one particular example: Facebook’s High-Resolution Population Density Maps (also referred to as HRSL, or high resolution settlement layer). This recent initiative, created in collaboration with a number of external organizations, shows not only the potential of mapping innovations but also the potential benefits of inter-sectoral partnerships and sharing. We examine three particular use cases of HRSL, and we follow with an assessment and some lessons learned. These lessons are applicable to HRSL in particular, but also more broadly. We conclude with some thoughts on avenues for future research.

Sample Preparation and Data Collection for Electron Crystallographic Studies on Membrane Protein Structures and Lipid-Protein Interaction.

Electron crystallography is a unique tool to study membrane protein structures and lipid-protein interactions in their native-like environments. Two-dimensional (2D) protein crystallization enables the lipids immobilized by the proteins, and the generated high-resolution density map allows us to model the atomic coordinates of the surrounding lipids to study lipid-protein interaction. This protocol describes the sample preparation for electron crystallographic studies, including back-injection method and carbon sandwich method. The protocols of data collection for electron crystallography, including electron imaging and diffraction, of the 2D membrane crystal will be followed.

HazDesNet: An End-to-End Network for Haze Density Prediction

Vision-based intelligent systems such as driver assistance systems and transportation systems should take into account weather conditions. The presence of haze in images can be a critical threat to driving scenarios. Haze density measures the visibility and usability of hazy images captured in real-world conditions. The prediction of haze density can be valuable in various vision-based intelligent systems, especially in those systems deployed in outdoor environments. Haze density prediction is a challenging task since the haze and many scene contents have a lot in common in appearance. Existing methods generally utilize different priors and design complex handcrafted features to predict the visibility or haze density of the image. In this article, we propose a novel end-to-end convolutional neural network (CNN) based method to predict haze density, named as HazDesNet. Our HazDesNet takes a hazy image as input and predicts a pixel-level haze density map. The density map is then refined and smoothed, and the average of the refined map is calculated as the global haze density of the image. To verify the performance of HazDesNet, a subjective human study is performed to build a Human Perceptual Haze Density (HPHD) database, which includes 500 real-world hazy images and 100 synthetic hazy images, and the corresponding human-rated perceptual haze density scores. Experimental results show that our method achieves the best haze density prediction performance on our built HPHD database and existing databases. Besides the global quantitative results, our HazDesNet is capable of predicting a continuous, stable, fine, and high-resolution haze density map. We will make the database and code publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/JiaheZhang/HazDesNet</uri> .

Crowd counting using cross-adversarial loss and global feature

Crowd density estimation is an important part of intelligent crowd monitoring. However, there are still many problems in density estimation due to the complexity of crowd scenes. Aiming at the high-density scenes with varied scales, we present a method based on cross-adversarial loss and global feature for crowd counting, so as to achieve the purpose of capturing more feature details and reducing the impact of background noise more effectively. First, we use the cross-adversarial loss to generate the residual map, which makes use of the consistency between different scales and solves the homogenization problem of fused density map. Then, we extract large-range context information and focus on key information in global spatial features for the generation of a residual map. Finally, the high-resolution density map is used to estimate the crowd counting. Experiments on three datasets confirm that the proposed method has good adaptability in scenes with obvious distribution change, not just in extracting high-quality features for density map estimation but also for accurate crowd counting.

Crowd counting via scale-communicative aggregation networks

Crowd counting is a fundamental computer vision task that draws increasing attention in recent years, due to its wide applications in commercial activities and public securities. Despite much process has been achieved by applying the resurgent neural networks in this task, critical challenges still lie in tremendous variation of crowd scales, together with other issues like background clutters and occlusions, making the crowd appearances hard to model. To address these challenges, we propose a scale-communicative aggregation network (SCANet) for crowd counting. Our model is characterized by three aspects: (i) It contains different streams of convolutional neural networks (CNNs), where each stream consumes an individual scaled version of the input image and communicates complementarily to produce a high-resolution density map. (ii) Each CNN stream obtains robust feature presentation via our proposed multi-scale feature encoders (MSFEs) with dilated convolutional layers, and skip connections are adopted to exploit multi-stage feature aggregation. (iii) A multi-scale structural similarity metric along with Euclidean distance is introduced for optimizing the quality of generated density maps. Extensive experiments and comparisons on several crowd counting benchmarks demonstrate the effectiveness of our proposed method.

Deep Learning to Predict Protein Backbone Structure from High-Resolution Cryo-EM Density Maps

Cryo-electron microscopy (cryo-EM) has become a leading technology for determining protein structures. Recent advances in this field have allowed for atomic resolution. However, predicting the backbone trace of a protein has remained a challenge on all but the most pristine density maps (<2.5 Å resolution). Here we introduce a deep learning model that uses a set of cascaded convolutional neural networks (CNNs) to predict Cα atoms along a protein’s backbone structure. The cascaded-CNN (C-CNN) is a novel deep learning architecture comprised of multiple CNNs, each predicting a specific aspect of a protein’s structure. This model predicts secondary structure elements (SSEs), backbone structure, and Cα atoms, combining the results of each to produce a complete prediction map. The cascaded-CNN is a semantic segmentation image classifier and was trained using thousands of simulated density maps. This method is largely automatic and only requires a recommended threshold value for each protein density map. A specialized tabu-search path walking algorithm was used to produce an initial backbone trace with Cα placements. A helix-refinement algorithm made further improvements to the α-helix SSEs of the backbone trace. Finally, a novel quality assessment-based combinatorial algorithm was used to effectively map protein sequences onto Cα traces to obtain full-atom protein structures. This method was tested on 50 experimental maps between 2.6 Å and 4.4 Å resolution. It outperformed several state-of-the-art prediction methods including Rosetta de-novo, MAINMAST, and a Phenix based method by producing the most complete predicted protein structures, as measured by percentage of found Cα atoms. This method accurately predicted 88.9% (mean) of the Cα atoms within 3 Å of a protein’s backbone structure surpassing the 66.8% mark achieved by the leading alternate method (Phenix based fully automatic method) on the same set of density maps. The C-CNN also achieved an average root-mean-square deviation (RMSD) of 1.24 Å on a set of 50 experimental density maps which was tested by the Phenix based fully automatic method. The source code and demo of this research has been published at https://github.com/DrDongSi/Ca-Backbone-Prediction.

High-Resolution Crowd Density Maps Generation With Multi-Scale Fusion Conditional GAN

The major challenges for density maps estimation and accurate counting stem from the large-scale variations, serious occlusions, and perspective distortions. Existing methods generally suffer from the blurred density maps, which are caused by average convolution kernel, and the ineffective estimation across different crowd scenes. In this paper, we propose a multi-scale fusion conditional generative adversarial network (MFC-GAN) that can generate high-resolution and high-quality density maps. The fusion module of MFC-GAN is embedded in a multi-scale generator and discriminator architecture with a novel adversarial loss, which is designed to guide high-resolution density maps generation. In order to address the problem of scale variation, we further propose a bidirectional fusion module. It combines deep global semantic features and shallow local information by leveraging feature maps presented in different layers of the generator. Furthermore, in order to increase the effectiveness of the multi-scale fusion, we design a cross-attention fusion module, which weights the multi-scale fused feature and learns context-aware feature maps for generating high quality density maps. The experiments on four challenging datasets show the effectiveness, feasibility and robustness of the proposed MFC-GAN.

Physical properties and chemical composition of the cores in the California molecular cloud

Aims. We aim to reveal the physical properties and chemical composition of the cores in the California molecular cloud (CMC), so as to better understand the initial conditions of star formation. Methods. We made a high-resolution column density map (18.2′′) with Herschel data, and extracted a complete sample of the cores in the CMC with the fellwalker algorithm. We performed new single-pointing observations of molecular lines near 90 GHz with the IRAM 30m telescope along the main filament of the CMC. In addition, we also performed a numerical modeling of chemical evolution for the cores under the physical conditions. Results. We extracted 300 cores, of which 33 are protostellar and 267 are starless cores. About 51% (137 of 267) of the starless cores are prestellar cores. Three cores have the potential to evolve into high-mass stars. The prestellar core mass function (CMF) can be well fit by a log-normal form. The high-mass end of the prestellar CMF shows a power-law form with an index α = −0.9 ± 0.1 that is shallower than that of the Galactic field stellar mass function. Combining the mass transformation efficiency (ε) from the prestellar core to the star of 15 ± 1% and the core formation efficiency (CFE) of 5.5%, we suggest an overall star formation efficiency of about 1% in the CMC. In the single-pointing observations with the IRAM 30m telescope, we find that 6 cores show blue-skewed profile, while 4 cores show red-skewed profile. [HCO+]/[HNC] and [HCO+]/[N2H+] in protostellar cores are higher than those in prestellar cores; this can be used as chemical clocks. The best-fit chemical age of the cores with line observations is ~5 × 104 yr.