Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years. As NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks, it may serve as a catalyst for the next generation of AI. In the present paper, we provide a systematic overview of the important and recent developments of research on NeSy AI. Firstly, we introduce study history of this area, covering early work and foundations. We further discuss background concepts and identify key driving factors behind the development of NeSy. Afterward, we categorize recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality. Then, we briefly discuss the successful application of modern NeSy approaches in several domains. Finally, we identify the open problems together with potential future research directions. This survey is expected to help new researchers enter this rapidly-developing field and accelerate progress towards data-and knowledge-driven AI. <<<

The tumor microenvironment is a dynamic cellular milieu that interacts with cancer cells and promotes tumor progression and metastasis. However, the specific mechanisms by which the tumor microenvironment impacts cancer cells' behaviors remain poorly understood. In this study, enriched cancer-associated fibroblasts (CAFs) were observed in tumor tissues isolated from epidermal growth factor receptor tyrosine kinase inhibitors (EGFR TKIs) resistant non-small cell lung cancer (NSCLC) patients. CAFs isolated from tumor tissues were capable of producing tryptophan metabolite kynurenine (Kyn), which significantly increased the proliferation and EGFR TKIs resistance of NSCLC cells. In this study, it was further observed that the activation of tryptophan 2,3-dioxygenase (TDO) in CAFs, resulted in the enhanced capability of tryptophan metabolism in them compared to normal fibroblasts. As a result, Kyn produced by CAFs facilitated the up-regulation of Aryl Hydrocarbon Receptor (AhR) signals in NSCLC, thereby resulting in the downstream ATK and ERK signaling pathways activation. Finally, inhibition of AhR signals efficiently prevented tumor growth and development of EGFR TKIs resistance, eventually improved the outcome of EGFR TKIs, and described a promising therapeutic strategy for NSCLC. <<<

The medial (MEC) and lateral entorhinal cortex (LEC), widely studied in rodents, are well defined and characterized. In humans, however, the exact locations of their homologues remain uncertain. Previous functional magnetic resonance imaging (fMRI) studies have subdivided the human EC into posteromedial (pmEC) and anterolateral (alEC) parts, but uncertainty remains about the choice of imaging modality and seed regions, in particular in light of a substantial revision of the classical model of EC connectivity based on novel insights from rodent anatomy. Here, we used structural, not functional imaging, namely diffusion tensor imaging (DTI) and probabilistic tractography to segment the human EC based on differential connectivity to other brain regions known to project selectively to MEC or LEC. We defined MEC as more strongly connected with presubiculum and retrosplenial cortex (RSC), and LEC as more strongly connected with distal CA1 and proximal subiculum (dCA1pSub) and lateral orbitofrontal cortex (OFC). Although our DTI segmentation had a larger medial-lateral component than in the previous fMRI studies, our results show that the human MEC and LEC homologues have a border oriented both towards the posterior-anterior and medial-lateral axes, supporting the differentiation between pmEC and alEC. <<<

Image compression is a fundamental research field and many well-known compression standards have been developed for many decades. Recently, learned compression methods exhibit a fast development trend with promising results. However, there is still a performance gap between learned compression algorithms and reigning compression standards, especially in terms of widely used PSNR metric. In this paper, we explore the remaining redundancy of recent learned compression algorithms. We have found accurate entropy models for rate estimation largely affect the optimization of network parameters and thus affect the rate-distortion performance. Therefore, in this paper, we propose to use discretized Gaussian Mixture Likelihoods to parameterize the distributions of latent codes, which can achieve a more accurate and flexible entropy model. Besides, we take advantage of recent attention modules and incorporate them into network architecture to enhance the performance. Experimental results demonstrate our proposed method achieves a state-of-the-art performance compared to existing learned compression methods on both Kodak and high-resolution datasets. To our knowledge our approach is the first work to achieve comparable performance with latest compression standard Versatile Video Coding (VVC) regarding PSNR. More importantly, our approach generates more visually pleasant results when optimized by MS-SSIM. This project page is at this https URL this https URL <<<

Brain atlases are spatial references for integrating, processing, and analyzing brain features gathered from different individuals, sources, and scales. Here we introduce a collection of joint surface-volume atlases that chart postnatal development of the human brain in a spatiotemporally dense manner from two weeks to two years of age. Our month-specific atlases chart normative patterns and capture key traits of early brain development and are therefore conducive to identifying aberrations from normal developmental trajectories. These atlases will enhance our understanding of early structural and functional development by facilitating the mapping of diverse features of the infant brain to a common reference frame for precise multifaceted quantification of cortical and subcortical changes. <<<

Jimin Tan, Nina Shenker-Tauris, Javier Rodriguez-Hernaez, Eric Wang, Theodore Sakellaropoulos, Francesco Boccalatte, Palaniraja Thandapani, Jane Skok, Iannis Aifantis, David Fenyö, Bo Xia, Aristotelis Tsirigos <<<

Investigating how chromatin organization determines cell-type-specific gene expression remains challenging. Experimental methods for measuring three-dimensional chromatin organization, such as Hi-C, are costly and have technical limitations, restricting their broad application particularly in high-throughput genetic perturbations. We present C.Origami, a multimodal deep neural network that performs de novo prediction of cell-type-specific chromatin organization using DNA sequence and two cell-type-specific genomic features-CTCF binding and chromatin accessibility. C.Origami enables in silico experiments to examine the impact of genetic changes on chromatin interactions. We further developed an in silico genetic screening approach to assess how individual DNA elements may contribute to chromatin organization and to identify putative cell-type-specific trans-acting regulators that collectively determine chromatin architecture. Applying this approach to leukemia cells and normal T cells, we demonstrate that cell-type-specific in silico genetic screening, enabled by C.Origami, can be used to systematically discover novel chromatin regulation circuits in both normal and disease-related biological systems. <<<

Although the quantitative trait locus (QTL) on chromosome 18 (BTA18) associated with paternal calving ease and stillbirth in Holstein Friesian cattle and its cross has been known for over 20 years, to our knowledge, the exact causal genetic sequence has yet escaped identification. The aim of this study was to re-examine the region of the published QTL on BTA18 and to investigate the possible reasons behind this elusiveness. For this purpose, we carried out a combined linkage disequilibrium and linkage analysis using genotyping data of 2,697 German Holstein Friesian (HF) animals and subsequent whole-genome sequencing (WGS) data analyses and genome assembly of HF samples. We confirmed the known QTL in the 95% confidence interval of 1.089 Mbp between 58.34 and 59.43 Mbp on BTA18. Additionally, these 4 SNPs in the near-perfect linkage disequilibrium with the QTL haplotype were identified: rs381577268 (on 57,816,137 bp, C/T), rs381878735 (on 59,574,329 bp, A/T), rs464221818 (on 59,329,176 bp, C/T), and rs472502785 (on 59,345,689 bp, T/C). Search for the causal mutation using short and long-read sequences, and methylation data of the BTA18 QTL region did not reveal any candidates though. The assembly showed problems in the region, as well as an abundance of segmental duplications within and around the region. Taking the QTL of BTA18 in Holstein cattle as an example, the data presented in this study comprehensively characterize the genomic features that could also be relevant for other such elusive QTL in various other cattle breeds and livestock species as well. <<<

Three distinct neurodevelopmental disorders arise primarily from deletions or duplications that occur at the 15q11-q13 locus: Prader-Willi syndrome, Angelman syndrome, and 15q11-q13 duplication syndrome. Each of these disorders results from the loss of function or overexpression of at least 1 imprinted gene. This article discusses the clinical background, genetic cause, diagnostic strategy, and management of each of these 3 disorders. <<<

Modern CNNs are learning the weights of vast numbers of convolutional operators. In this paper, we raise the fundamental question if this is actually necessary. We show that even in the extreme case of only randomly initializing and never updating spatial filters, certain CNN architectures can be trained to surpass the accuracy of standard training. By reinterpreting the notion of pointwise (1×1) convolutions as an operator to learn linear combinations (LC) of frozen (random) spatial filters, we are able to analyze these effects and propose a generic LC convolution block that allows tuning of the linear combination rate. Empirically, we show that this approach not only allows us to reach high test accuracies on CIFAR and ImageNet but also has favorable properties regarding model robustness, generalization, sparsity, and the total number of necessary weights. Additionally, we propose a novel weight sharing mechanism, which allows sharing of a single weight tensor between all spatial convolution layers to massively reduce the number of weights. <<<

Modern CNNs are learning the weights of vast numbers of convolutional operators. In this paper, we raise the fundamental question if this is actually necessary. We show that even in the extreme case of only randomly initializing and never updating spatial filters, certain CNN architectures can be trained to surpass the accuracy of standard training. By reinterpreting the notion of pointwise (1×1) convolutions as an operator to learn linear combinations (LC) of frozen (random) spatial filters, we are able to analyze these effects and propose a generic LC convolution block that allows tuning of the linear combination rate. Empirically, we show that this approach not only allows us to reach high test accuracies on CIFAR and ImageNet but also has favorable properties regarding model robustness, generalization, sparsity, and the total number of necessary weights. Additionally, we propose a novel weight sharing mechanism, which allows sharing of a single weight tensor between all spatial convolution layers to massively reduce the number of weights. <<<

Handwritten Chinese text recognition (HCTR) has been an active research topic for decades. However, most previous studies solely focus on the recognition of cropped text line images, ignoring the error caused by text line detection in real-world applications. Although some approaches aimed at page-level text recognition have been proposed in recent years, they either are limited to simple layouts or require very detailed annotations including expensive line-level and even character-level bounding boxes. To this end, we propose PageNet for end-to-end weakly supervised page-level HCTR. PageNet detects and recognizes characters and predicts the reading order between them, which is more robust and flexible when dealing with complex layouts including multi-directional and curved text lines. Utilizing the proposed weakly supervised learning framework, PageNet requires only transcripts to be annotated for real data; however, it can still output detection and recognition results at both the character and line levels, avoiding the labor and cost of labeling bounding boxes of characters and text lines. Extensive experiments conducted on five datasets demonstrate the superiority of PageNet over existing weakly supervised and fully supervised page-level methods. These experimental results may spark further research beyond the realms of existing methods based on connectionist temporal classification or attention. The source code is available at https://github.com/shannanyinxiang/PageNet. <<<

A somewhat contradictory published body of evidence suggests that sex impacts severity outcomes of human leptospirosis. In this study, we used an acute animal model of disease to analyze leptospirosis in male and female hamsters infected side by side with low but increasing doses of serovar Copenhageni. We found that male hamsters were considerably more susceptible to leptospirosis, given that only 6.3% survived infection, whereas 68.7% of the females survived the same infection doses. In contrast to the females, male hamsters had high burdens of in kidney and high histopathological scores after exposure to low infection doses (∼10 bacteria). In hamsters infected with higher doses of (∼10 bacteria), differences in pathogen burdens as well as cytokine and fibrosis transcript levels in kidney were not distinct between sexes. Our results indicate that male hamsters infected with are more susceptible to severe leptospirosis after exposure to lower infectious doses than females. <<<

Tumor-derived circulating cell-free DNA (cfDNA) provides critical clues for cancer early diagnosis, yet it often suffers from low sensitivity. Here, we present a cancer early diagnosis approach using tumor fractions deciphered from circulating cfDNA methylation signatures. We show that the estimated fractions of tumor-derived cfDNA from cancer patients increase significantly as cancer progresses in two independent datasets. Employing the predicted tumor fractions, we establish a Bayesian diagnostic model in which training samples are only derived from late-stage patients and healthy individuals. When validated on early-stage patients and healthy individuals, this model exhibits a sensitivity of 86.1% for cancer early detection and an average accuracy of 76.9% for tumor localization at a specificity of 94.7%. By highlighting the potential of tumor fractions on cancer early diagnosis, our approach can be further applied to cancer screening and tumor progression monitoring. <<<

Erika Erickson, Japheth E Gado, Luisana Avilán, Felicia Bratti, Richard K Brizendine, Paul A Cox, Raj Gill, Rosie Graham, Dong-Jin Kim, Gerhard König, William E Michener, Saroj Poudel, Kelsey J Ramirez, Thomas J Shakespeare, Michael Zahn, Eric S Boyd, Christina M Payne, Jennifer L DuBois, Andrew R Pickford, Gregg T Beckham, John E McGeehan <<<

Enzymatic deconstruction of poly(ethylene terephthalate) (PET) is under intense investigation, given the ability of hydrolase enzymes to depolymerize PET to its constituent monomers near the polymer glass transition temperature. To date, reported PET hydrolases have been sourced from a relatively narrow sequence space. Here, we identify additional PET-active biocatalysts from natural diversity by using bioinformatics and machine learning to mine 74 putative thermotolerant PET hydrolases. We successfully express, purify, and assay 51 enzymes from seven distinct phylogenetic groups; observing PET hydrolysis activity on amorphous PET film from 37 enzymes in reactions spanning pH from 4.5-9.0 and temperatures from 30-70 °C. We conduct PET hydrolysis time-course reactions with the best-performing enzymes, where we observe differences in substrate selectivity as function of PET morphology. We employed X-ray crystallography and AlphaFold to examine the enzyme architectures of all 74 candidates, revealing protein folds and accessory domains not previously associated with PET deconstruction. Overall, this study expands the number and diversity of thermotolerant scaffolds for enzymatic PET deconstruction. <<<

AbstractNo sooner is an experience over than its neural memory representation begins to be strengthened and transformed through the process of memory replay. Using fMRI, we examined how memory strength manipulated through repetition during encoding modulates post-encoding replay in humans. Results revealed that repetition did not increase replay frequency in the hippocampus. However, replay in cortical regions and hippocampal-cortical coordinated replay were significantly enhanced for repeated events, suggesting that repetition accelerates the consolidation process. Interestingly, we found that replay frequency in both hippocampus and cortex modulated behavioral success on an immediate associative recognition test for the weakly encoded information, indicating a significant role for post-encoding replay in rescuing once-presented events. Together, our findings highlight the relationships of replay to stabilizing weak memories and accelerating cortical consolidation for strong memories. <<<

Simona Ceglia, Alyssa Berthelette, Kelsey Howley, Yun Li, Benedikt Mortzfeld, Shakti K Bhattarai, Nicole K H Yiew, Ying Xu, Robert Brink, Jason G Cyster, Lora V Hooper, Gwendalyn J Randolph, Vanni Bucci, Andrea Reboldi <<<

Immunoglobulin A (IgA) secretion by plasma cells, terminally differentiated B cells residing in the intestinal lamina propria, assures microbiome homeostasis and protects the host against enteric infections. Exposure to diet-derived and commensal-derived signals provides immune cells with organizing cues that instruct their effector function and dynamically shape intestinal immune responses at the mucosal barrier. Recent data have described metabolic and microbial inputs controlling T cell and innate lymphoid cell activation in the gut; however, whether IgA-secreting lamina propria plasma cells are tuned by local stimuli is completely unknown. Although antibody secretion is considered to be imprinted during B cell differentiation and therefore largely unaffected by environmental changes, a rapid modulation of IgA levels in response to intestinal fluctuations might be beneficial to the host. In the present study, we showed that dietary cholesterol absorption and commensal recognition by duodenal intestinal epithelial cells lead to the production of oxysterols, evolutionarily conserved lipids with immunomodulatory functions. Using conditional cholesterol 25-hydroxylase deleter mouse line we demonstrated that 7α,25-dihydroxycholesterol from epithelial cells is critical to restrain IgA secretion against commensal- and pathogen-derived antigens in the gut. Intestinal plasma cells sense oxysterols via the chemoattractant receptor GPR183 and couple their tissue positioning with IgA secretion. Our findings revealed a new mechanism linking dietary cholesterol and humoral immune responses centered around plasma cell localization for efficient mucosal protection. <<<

Cell-free DNA (cfDNA) in the circulating blood plasma of patients with cancer contains tumour-derived DNA sequences that can serve as biomarkers for guiding therapy, for the monitoring of drug resistance, and for the early detection of cancers. However, the analysis of cfDNA for clinical diagnostic applications remains challenging because of the low concentrations of cfDNA, and because cfDNA is fragmented into short lengths and is susceptible to chemical damage. Barcodes of unique molecular identifiers have been implemented to overcome the intrinsic errors of next-generation sequencing, which is the prevailing method for highly multiplexed cfDNA analysis. However, a number of methodological and pre-analytical factors limit the clinical sensitivity of the cfDNA-based detection of cancers from liquid biopsies. In this Review, we describe the state-of-the-art technologies for cfDNA analysis, with emphasis on multiplexing strategies, and discuss outstanding biological and technical challenges that, if addressed, would substantially improve cancer diagnostics and patient care. <<<

Somatic mutations in cancer cells can generate tumour-specific neoepitopes, which are recognized by autologous T cells in the host. As neoepitopes are not subject to central immune tolerance and are not expressed in healthy tissues, they are attractive targets for therapeutic cancer vaccines. Because the vast majority of cancer mutations are unique to the individual patient, harnessing the full potential of this rich source of targets requires individualized treatment approaches. Many computational algorithms and machine-learning tools have been developed to identify mutations in sequence data, to prioritize those that are more likely to be recognized by T cells and to design tailored vaccines for every patient. In this Review, we fill the gaps between the understanding of basic mechanisms of T cell recognition of neoantigens and the computational approaches for discovery of somatic mutations and neoantigen prediction for cancer immunotherapy. We present a new classification of neoantigens, distinguishing between guarding, restrained and ignored neoantigens, based on how they confer proficient antitumour immunity in a given clinical context. Such context-based differentiation will contribute to a framework that connects neoantigen biology to the clinical setting and medical peculiarities of cancer, and will enable future neoantigen-based therapies to provide greater clinical benefit. <<<

Linn Sofie Sæther , Thor Ueland , Beathe Haatveit , Luigi Angelo Maglanoc , Attila Szabo , Srdjan Djurovic , Pål Aukrust , Daniel Roelfs , Christine Mohn , Monica Bettina Elkjaer Greenwood Ormerod , Trine Vik Lagerberg , Nils Eiel Steen , Ingrid Melle , Ole Andreas Andreassen , Torill Ueland <<<

AbstractA potential relationship between dysregulation of immune/inflammatory pathways and cognitive impairment has been suggested in severe mental illnesses (SMI), such as schizophrenia (SZ) and bipolar (BD) spectrum disorders. However, multivariate relationships between peripheral inflammatory/immune-related markers and cognitive domains are unclear, and many studies do not account for inter-individual variance in both cognitive functioning and inflammatory/immune status. This study aimed to investigate covariance patterns between inflammatory/immune-related markers and cognitive domains and further elucidate heterogeneity in a large SMI and healthy control (HC) cohort (SZ = 343, BD = 289, HC = 770). We applied canonical correlation analysis (CCA) to identify modes of maximum covariation between a comprehensive selection of cognitive domains and inflammatory/immune markers. We found that poor verbal learning and psychomotor processing speed was associated with higher levels of interleukin-18 system cytokines and beta defensin 2, reflecting enhanced activation of innate immunity, a pattern augmented in SMI compared to HC. Applying hierarchical clustering on covariance patterns identified by the CCA revealed a high cognition—low immune dysregulation subgroup with predominantly HC (24% SZ, 45% BD, 74% HC) and a low cognition—high immune dysregulation subgroup predominantly consisting of SMI patients (76% SZ, 55% BD, 26% HC). These subgroups differed in IQ, years of education, age, CRP, BMI (all groups), level of functioning, symptoms and defined daily dose (DDD) of antipsychotics (SMI cohort). Our findings suggest a link between cognitive impairment and innate immune dysregulation in a subset of individuals with severe mental illness. <<<

Transfer learning enables the transfer of knowledge gained while learning to perform one task (source) to a related but different task (target), hence addressing the expense of data acquisition and labelling, potential computational power limitations and dataset distribution mismatches. We propose a new transfer learning framework for task-specific learning (functional regression in partial differential equations) under conditional shift based on the deep operator network (DeepONet). Task-specific operator learning is accomplished by fine-tuning task-specific layers of the target DeepONet using a hybrid loss function that allows for the matching of individual target samples while also preserving the global properties of the conditional distribution of the target data. Inspired by conditional embedding operator theory, we minimize the statistical distance between labelled target data and the surrogate prediction on unlabelled target data by embedding conditional distributions onto a reproducing kernel Hilbert space. We demonstrate the advantages of our approach for various transfer learning scenarios involving nonlinear partial differential equations under diverse conditions due to shifts in the geometric domain and model dynamics. Our transfer learning framework enables fast and efficient learning of heterogeneous tasks despite considerable differences between the source and target domains. <<<