Target-specific Information Research Articles

Contrastive fine-grained domain adaptation network for EEG-based vigilance estimation

Vigilance state is crucial for the effective performance of users in brain-computer interface (BCI) systems. Most vigilance estimation methods rely on a large amount of labeled data to train a satisfactory model for the specific subject, which limits the practical application of the methods. This study aimed to build a reliable vigilance estimation method using a small amount of unlabeled calibration data. We conducted a vigilance experiment in the designed BCI-based cursor-control task. Electroencephalogram (EEG) signals of eighteen participants were recorded in two sessions on two different days. And, we proposed a contrastive fine-grained domain adaptation network (CFGDAN) for vigilance estimation. Here, an adaptive graph convolution network (GCN) was built to project the EEG data of different domains into a common space. The fine-grained feature alignment mechanism was designed to weight and align the feature distributions across domains at the EEG channel level, and the contrastive information preservation module was developed to preserve the useful target-specific information during the feature alignment. The experimental results show that the proposed CFGDAN outperforms the compared methods in our BCI vigilance dataset and SEED-VIG dataset. Moreover, the visualization results demonstrate the efficacy of the designed feature alignment mechanisms. These results indicate the effectiveness of our method for vigilance estimation. Our study is helpful for reducing calibration efforts and promoting the practical application potential of vigilance estimation methods.

Deep Representation Learning With Sample Generation and Augmented Attention Module for Imbalanced ECG Classification.

Developing an efficient heartbeat monitoring system has become a focal point in numerous healthcare applications. Specifically, in the last few years, heartbeat classification for arrhythmia detection has gained considerable interest from researchers. This paper presents a novel deep representation learning method for the efficient detection of arrhythmic beats. To mitigate the issues associated with the imbalanced data distribution, a novel re-sampling strategy is introduced. Unlike the existing oversampling methods, the proposed technique transforms majority-class samples into minority-class samples with a novel translation loss function. This approach assists the model in learning a more generalized representation of crucially important minority class samples. Moreover, by exploiting an auxiliary feature, an augmented attention module is designed that focuses on the most relevant and target-specific information. We adopted an inter-patient classification paradigm to evaluate the proposed method. The experimental results of this study on the MIT-BIH arrhythmia database clearly indicate that the proposed model with augmented attention mechanism and over-sampling strategy significantly learns a balanced deep representation and improves the classification performance of vital heartbeats.

PET and SPECT imaging as a solid guide to detect and discriminate atypical phenotypes of neurodegenerative disorders

Introduction and aim. Atypical or mixed presentations of neurodegenerative disorders may postpone or confound the final diagnosis. Molecular imaging with positron emission tomography (PET) and single photon emission computed tomography (SPECT) radioligands provide target-specific information and may anticipate the diagnosis by “in vivo” detection of the neuro pathological substrate, as Aβ deposition, nigrostriatal dopaminergic depletion or tau inclusions. This concise review will dis cuss the potential of PET and SPECT imaging as a solid guide to better characterize atypical phenotypes of neurodegeneration in the clinical routine, with the potential to drive personalized interventions, improve cohort uniformity for clinical trials, and serve as biomarkers for targeted molecular therapies. Material and methods. Literature search was performed focusing on the role of PET and SPECT imaging in assessing atypical phenotypes of neurodegeneration, using the electronic source of database PubMed/MEDLINE and the web-based search engines Google, Google Scholar. Analysis of the literature. New disease-modifying drugs may increase their effect with early initiation, which is especially im portant in working persons and younger subjects presenting atypical symptoms. In older individuals, the coexistence of neu rodegeneration, age-related changes, cerebrovascular lesions, or depression makes challenging a definitive diagnosis. Quantitative tools able to measure tracer distribution increase the accuracy of molecular neuroimaging creating topographic maps that compare subject’s data with healthy controls databases. Conclusion. Atypical phenotypes may be associated with quantitative key-pattern allowing a more precise and early diagnosis of the neurodegenerative disorder. Finally, quantitative assessment of the pathological substrates allows us to track the disease process and measure treatment response.

Autoencoder-Based Collaborative Attention GAN for Multi-Modal Image Synthesis

Multi-modal images are required in a wide range of practical scenarios, from clinical diagnosis to public security. However, certain modalities may be incomplete or unavailable because of the restricted imaging conditions, which commonly leads to decision bias in many real-world applications. Despite the significant advancement of existing image synthesis techniques, learning complementary information from multi-modal inputs remains challenging. To address this problem, we propose an autoencoder-based collaborative attention generative adversarial network (ACA-GAN) that uses available multi-modal images to generate the missing ones. The collaborative attention mechanism deploys a single-modal attention module and a multi-modal attention module to effectively extract complementary information from multiple available modalities. Considering the significant modal gap, we further developed an autoencoder network to extract the self-representation of target modality, guiding the generative model to fuse target-specific information from multiple modalities. This considerably improves cross-modal consistency with the desired modality, thereby greatly enhancing the image synthesis performance. Quantitative and qualitative comparisons for various multi-modal image synthesis tasks highlight the superiority of our approach over several prior methods by demonstrating more precise and realistic results. The source code will be available at: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/caohaifang123/ACA-GAN</uri> .

Domain Adaptive Sampling for Cross-Domain Point Cloud Recognition

Point cloud recognition has recently gained increasing research interest due to the huge potential in real-world applications such as autonomous driving, robotics, etc. However, the point clouds of similar objects often exhibit notable geometric variations due to the difference in capturing devices or environmental changes. This leads to significant performance degradation when the learned point cloud recognition model is applied to a new scenario, which is also known as the domain adaptation issue. In this work, we propose a new unsupervised domain adaptation approach for point cloud recognition via domain adaptive sampling (DAS). In particular, we propose a two-level sampling strategy of point level and instance level to improve the cross-domain recognition ability of the model. First, we propose a domain adaptive point sampling (DAPS) strategy to enhance the domain-invariant representation of point clouds by progressively focusing on representative points in each point cloud based on geometric consistency. Then, we further propose an instance-level domain adaptive cloud sampling (DACS) strategy to learn target-specific information based on a self-paced learning paradigm, where we select a set of pseudo-labeled target point clouds to train our designed light-weighted adapters without modifying the learned domain-invariant representation. We validate our domain adaptive sampling approach on the benchmark datasets PointDA-10 and GraspNetPC-10, where our method achieves new state-of-the-art performance.

EXABSUM: a new text summarization approach for generating extractive and abstractive summaries

Due to the exponential growth of online information, the ability to efficiently extract the most informative content and target specific information without extensive reading is becoming increasingly valuable to readers. In this paper, we present 'EXABSUM,' a novel approach to Automatic Text Summarization (ATS), capable of generating the two primary types of summaries: extractive and abstractive. We propose two distinct approaches: (1) an extractive technique (EXABSUMExtractive), which integrates statistical and semantic scoring methods to select and extract relevant, non-repetitive sentences from a text unit, and (2) an abstractive technique (EXABSUMive), which employs a word graph approach (including compression and fusion stages) and re-ranking based on keyphrases to generate abstractive summaries using the source document as an input. In the evaluation conducted on multi-domain benchmarks, EXABSUM outperformed extractive summarization methods and demonstrated competitiveness against abstractive baselines.

Dual Instance-Consistent Network for Cross-Domain Object Detection.

Cross-domain object detection aims to transfer knowledge from a labeled dataset to an unlabeled dataset. Most existing methods apply a unified embedding model to generate the tightly coupled source and target descriptions for domain alignment, leading to the destroyed feature distribution of the target domain because the embedding model is mainly controlled by the source domain. To reduce the representation bias of the target domain, we apply two independent networks to extract two types of discriminative descriptions with mutual consistency, i.e., a novel Dual Instance-Consistent Network (DICN) is proposed for cross-domain object detection. Especially, Dual Instance-Consistent Module containing the instance mutual consistency between Primary Network and Auxiliary Network is applied to align two domains, where Primary and Auxiliary Networks are used to obtain the source-specific and target-specific information, respectively. The instance mutual consistency consists of two terms: feature consistency and detection consistency, which is applied to align the instance feature and the output of detection head, respectively. With the instance mutual consistency, optimizing the Primary (Auxiliary) Network only with source (target) images by fixing the Auxiliary (Primary) Network can generate the source(target)-specific description. Extensive experiments on several benchmarks demonstrate the effectiveness of the proposed DICN, e.g., obtaining mAP of 44.10% for Cityscapes → Foggy Cityscapes, AP on car of 76.50% for Cityscapes → KITTI, MR -2 of 8.87%, 12.66%, 22.27%, and 42.06% for COCOPersons → Caltech, CityPersons → Caltech, COCOPersons → CityPersons, and Caltech → CityPersons, respectively.

VERITAS: Harnessing the power of nomenclature in biologic discovery

ABSTRACT We are entering an era in which therapeutic proteins are assembled using building block-like strategies, with no standardized schema to discuss these formats. Existing nomenclatures, like AbML, sacrifice human readability for precision. Therefore, considering even a dozen such formats, in combination with hundreds of possible targets, can create confusion and increase the complexity of drug discovery. To address this challenge, we introduce Verified Taxonomy for Antibodies (VERITAS). This classification and nomenclature scheme is extensible to multispecific therapeutic formats and beyond. VERITAS names are easy to understand while drawing direct connections to the structure of a given format, with or without specific target information, making these names useful to adopt in scientific discourse and as inputs to machine learning algorithms for drug development.

Promoting spontaneous analogical transfer by idealizing target representations.

Recent results demonstrate that inducing an abstract representation of target analogs at retrieval time aids access to analogous situations with mismatching surface features (i.e., the late abstraction principle). A limitation of current implementations of this principle is that they either require the external provision of target-specific information or demand very high intellectual effort. Experiment 1 demonstrated that constructing an idealized situation model of a target problem increases the rate of correct solutions compared with constructing either concrete simulations or no simulations. Experiment 2 confirmed that these results were based on an advantage for accessing the base analog, and not merely an advantage of idealized simulations for understanding the target problem in its own terms. This target idealization strategy has broader applicability than prior interventions based on the late abstraction principle because it can be achieved by a greater proportion of participants and without the need to receive target-specific information. We present a computational model, SampComp, that predicts successful retrieval of a stored situation to understand a target based on the overlap of a random, but potentially biased, sample of features from each. SampComp is able to account for the relative benefits of base and target idealization, and their interaction.

Boosting unsupervised domain adaptation: A Fourier approach

By using unsupervised domain adaptation (UDA), knowledge is transferred from a label-rich source domain to a target domain that contains relevant information but has no labels. Most existing UDA algorithms primarily align domain-invariant features are primarily aligned during training, whereas target-specific information is ignored when learning the domain-invariant features. To address this issue, we attempted to boost the performance of unsupervised domain adaptation using a Fourier approach (FUDA). Specifically. FUDA is inspired by the fact that the amplitude of the Fourier spectrum mainly primarily preserves low-level statistics. Thus, the source domain can be augmented in FUDA to effectively equip with some low-level information in a target domain by fusing the amplitude of the two domains in the Fourier domain. Meanwhile, we propose Fourier transform channel attention, which represents the weight of Fourier transform to capture feature diversity. On the basis of Fourier analysis, we further show that the conventional attention that is built upon global average pooling is a special case of our proposed attention. Our method is evaluated by using four domain adaptation benchmarks, such as Office-31, Office-Home, VisDA-2017 and DomainNet, demonstrating the effectiveness of our FUDA.

Boosting target-level infrared and visible image fusion with regional information coordination

The target-level infrared and visible image fusion aims to prominently retain the feature of target areas in the entire scene of fusion results. Nonetheless, most of existing fusion methods tend to evaluate the global information and ignore the retention of specific target information during feature extraction. A few existing target-level fusion methods also have the problem of missing target or scene information under special conditions. In order to address the challenges of image fusion and make further deployment planning in high-level image vision tasks, we propose a target-level infrared and visible image fusion method. In our method, a scene texture attention module is designed to enhance the complementary description of global scene information, and a target extraction module with the target-level loss function is designed to prominently retain the feature of target areas. Furthermore, target information and scene information are equilibrated by the coordination of target-scene information loss function. A large number of comparison experiments with the state-of-the-art methods demonstrate that our fusion method has competitive advantages in highlighting target features and describing global scene. More importantly, in downstream target detection and depth estimation tasks, the excellent performance in accuracy and speed considerably enhances the portability of our method.

You Only Infer Once: Cross-Modal Meta-Transfer for Referring Video Object Segmentation

We present YOFO (You Only inFer Once), a new paradigm for referring video object segmentation (RVOS) that operates in an one-stage manner. Our key insight is that the language descriptor should serve as target-specific guidance to identify the target object, while a direct feature fusion of image and language can increase feature complexity and thus may be sub-optimal for RVOS. To this end, we propose a meta-transfer module, which is trained in a learning-to-learn fashion and aims to transfer the target-specific information from the language domain to the image domain, while discarding the uncorrelated complex variations of language description. To bridge the gap between the image and language domains, we develop a multi-scale cross-modal feature mining block that aggregates all the essential features required by RVOS from both domains and generates regression labels for the meta-transfer module. The whole system can be trained in an end-to-end manner and shows competitive performance against state-of-the-art two-stage approaches.

PET Molecular Imaging in Drug Development: The Imaging and Chemistry Perspective.

Positron emission tomography with selective radioligands advances the drug discovery and development process by revealing information about target engagement, proof of mechanism, pharmacokinetic and pharmacodynamic profiles. Positron emission tomography (PET) is an essential and highly significant tool to study therapeutic drug development, dose regimen, and the drug plasma concentrations of new drug candidates. Selective radioligands bring up target-specific information in several disease states including cancer, cardiovascular, and neurological conditions by quantifying various rates of biological processes with PET, which are associated with its physiological changes in living subjects, thus it reveals disease progression and also advances the clinical investigation. This study explores the major roles, applications, and advances of PET molecular imaging in drug discovery and development process with a wide range of radiochemistry as well as clinical outcomes of positron-emitting carbon-11 and fluorine-18 radiotracers.

Automated Radiosynthesis and Molecular Docking Studies of Coumarin- Triazole Hybrid with fluorine-18: A feasibility study.

Fluorine-18 is one of the promising radiotracers that can report target specific information related to its physiology to understand the disease status through the PET modality. In the current study, the radiochemical synthesis, purification, and molecular docking studies of fluorine-18 (18F) radiolabeled coumarin-triazole hybrid have been performed. To develop target specific fluorine-18 radiotracer for the diagnosis in oncology. GE Tracer-lab FX2N module with few modifications in the line connections was used for the radiosynthesis and purification of target molecule [18F]SG-2, 4-((2,6-dimethylmorpholino) methyl)-7-((1-(4-(fluoro-18F) benzyl)-1H-1,2,3-triazol-4-yl) oxy)-2H-chromen-2-one, through the nucleophilic radiofluorination mechanism. The radiochemical purity was measured by HPLC, and TLC analytical methods. The kryptofix levels were also evaluated by using the TLC method. The residual solvents like DMF, ethanol were measured using GC. The Schrödinger drug discovery suite 2018 was used to study the protein and ligand interactions. The quality control parameters revealed the purity, chemical identity, and limits of residual solvents. The radiochemical purity was 95.5 ± 2.3%, and dimethylformamide solvent limit was 89 ± 3 ppm. The molecular docking results had suggested that the cold target molecule has made strong electronic interactions and showed the possible pharmacokinetic (ADME) properties with galectin-1 protein. Overall, these results showed that [[18F]SG-2 radiolabeling with 18F radionuclide was feasible, and support of molecular docking studies suggest possible interactions with Galectin- 1. we reported a feasibility study for labeling coumarin-triazole hybrid with fluorine-18 through aromatic nucleophilic fluorination reaction (SNAr).

Carbon-11: Radiochemistry and Target-Based PET Molecular Imaging Applications in Oncology, Cardiology, and Neurology.

The positron emission tomography (PET) molecular imaging technique has gained its universal value as a remarkable tool for medical diagnosis and biomedical research. Carbon-11 is one of the promising radiotracers that can report target-specific information related to its pharmacology and physiology to understand the disease status. Currently, many of the available carbon-11 (t1/2 = 20.4 min) PET radiotracers are heterocyclic derivatives that have been synthesized using carbon-11 inserted different functional groups obtained from primary and secondary carbon-11 precursors. A spectrum of carbon-11 PET radiotracers has been developed against many of the upregulated and emerging targets for the diagnosis, prognosis, prediction, and therapy in the fields of oncology, cardiology, and neurology. This review focuses on the carbon-11 radiochemistry and various target-specific PET molecular imaging agents used in tumor, heart, brain, and neuroinflammatory disease imaging along with its associated pathology.

Central Hub M&amp;A Advisors

Abstract We examine how an M&amp;A advisor’s position in the network of investment banks affects its ability to create value for acquirers in takeover transactions. We show that acquirers enlisting the services of more centrally positioned M&amp;A advisors enjoy higher announcement abnormal returns and pay lower takeover premiums. Consistent with the idea that central network positions convey an information advantage, we find that the effects are stronger for acquirers facing greater target information asymmetry and for M&amp;A advisors depending more on networks for target-specific information. The information advantage primarily comes from network contacts that had previously assisted the targets in equity issuance. Centrally positioned advisors charge premium fees; network banks appear to enjoy a significant advantage in the competition for future co-advisory appointments.

Biased Docking for Protein-Ligand Pose Prediction.

The interaction between a protein and its ligands is one of the basic and most important processes in biological chemistry. Docking methods aim to predict the molecular 3D structure of protein-ligand complexes starting from coordinates of the protein and the ligand separately. They are widely used in both industry and academia, especially in the context of drug development projects. AutoDock4 is one of the most popular docking tools and, as for any docking method, its performance is highly system dependent. Knowledge about specific protein-ligand interactions on a particular target can be used to successfully overcome this limitation. Here, we describe how to apply the AutoDock Bias protocol, a simple and elegant strategy that allows users to incorporate target-specific information through a modified scoring function that biases the ligand structure towards those poses (or conformations) that establish selected interactions. We discuss two examples using different bias sources. In the first, we show how to steer dockings towards interactions derived from crystal structures of the receptor with different ligands; in the second example, we define and apply hydrophobic biases derived from Molecular Dynamics simulations in mixed solvents. Finally, we discuss general concepts of biased docking, its performance in pose prediction, and virtual screening campaigns as well as other potential applications.

Evaluating recall error in preschoolers: Category expectations influence episodic memory for color

Despite limited memory capacity, children are exceptional learners. How might children engage in meaningful learning despite limited memory systems? Past research suggests that adults integrate category knowledge and noisy episodic traces to aid recall when episodic memory is noisy or incomplete (e.g. Hemmer & Steyvers, 2009a,b). We suspect children utilize a similar process but integrate category and episodic traces in recall to a different degree. Here we conduct two experiments to empirically assess children’s color category knowledge (Study 1) and recall of target hue values (Study 2). In Study 1, although children’s generated hue values appear to be noisier than adults, we found no significant difference between children and adult’s generated color category means (prototypes), suggesting that preschool-aged children’s color categories are well established. In Study 2, we found that children’s (like adult’s) free recall of target hue values regressed towards color category means. We implemented three probabilistic memory models: one that combines category knowledge and specific target information (Integrative), a category only (Noisy Prototype) model, and a target only (Noisy Target) model to computationally evaluate recall performance. Consistent with previous studies with older children (Duffy, Huttenlocher, & Crawford, 2006), quantitative fits of the models to aggregate group-level data provided strong support for the Integrative process. However, at the individual subject level, a greater proportion of preschoolers’ recall was better fit by a Prototype only model. Our results provide evidence that the integration of category knowledge in episodic memory comes online early and strongly. Implications for how the greater reliance on category knowledge by preschoolers relative to adults might track with developmental shifts in relational episodic memory are discussed.

Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction

Enabling precise forecasting of the remaining useful life (RUL) for machines can reduce maintenance cost, increase availability, and prevent catastrophic consequences. Data-driven RUL prediction methods have already achieved acclaimed performance. However, they usually assume that the training and testing data are collected from the same condition (same distribution or domain), which is generally not valid in real industry. Conventional approaches to address domain shift problems attempt to derive domain-invariant features, but fail to consider target-specific information, leading to limited performance. To tackle this issue, in this article, we propose a contrastive adversarial domain adaptation (CADA) method for cross-domain RUL prediction. The proposed CADA approach is built upon an adversarial domain adaptation architecture with a contrastive loss, such that it is able to take target-specific information into consideration when learning domain-invariant features. To validate the superiority of the proposed approach, comprehensive experiments have been conducted to predict the RULs of aeroengines across 12 cross-domain scenarios. The experimental results show that the proposed method significantly outperforms state-of-the-arts with over 21% and 38% improvements in terms of two different evaluation metrics.

Mass Spectrometry Imaging of atherosclerosis-affine Gadofluorine following Magnetic Resonance Imaging

Molecular imaging of atherosclerosis by Magnetic Resonance Imaging (MRI) has been impaired by a lack of validation of the specific substrate responsible for the molecular imaging signal. We therefore aimed to investigate the additive value of mass spectrometry imaging (MSI) of atherosclerosis-affine Gadofluorine P for molecular MRI of atherosclerotic plaques. Atherosclerotic Ldlr−/− mice were investigated by high-field MRI (7 T) at different time points following injection of atherosclerosis-affine Gadofluorine P as well as at different stages of atherosclerosis formation (4, 8, 16 and 20 weeks of HFD). At each imaging time point mice were immediately sacrificed after imaging and aortas were excised for mass spectrometry imaging: Matrix Assisted Laser Desorption Ionization (MALDI) Imaging and Laser Ablation – Inductively Coupled Plasma – Mass Spectrometry (LA-ICP-MS) imaging. Mass spectrometry imaging allowed to visualize the localization and measure the concentration of the MR imaging probe Gadofluorine P in plaque tissue ex vivo with high spatial resolution and thus adds novel and more target specific information to molecular MR imaging of atherosclerosis.