Deep learning (DL) is being successfully applied across multiple domains, yet these models learn in a most artificial way: they require large quantities of labeled data to grasp even simple concepts. Thus, the main bottleneck is often access to supervised data. Here, we highlight a trend in a potential solution to this challenge: synthetic data. Synthetic data are becoming accessible due to progress in rendering pipelines, generative adversarial models, and fusion models. Moreover, advancements in domain adaptation techniques help close the statistical gap between synthetic and real data. Paradoxically, this artificial solution is also likely to enable more natural learning, as seen in biological systems, including continual, multimodal, and embodied learning. Complementary to this, simulators and deep neural networks (DNNs) will also have a critical role in providing insight into the cognitive and neural functioning of biological systems. We also review the strengths of, and opportunities and novel challenges associated with, synthetic data. <<<

CNN-based image processing has been actively applied to histopathological analysis to detect and classify cancerous tumors automatically. However, CNN-based classifiers generally predict a label with overconfidence, which becomes a serious problem in the medical domain. The objective of this study is to propose a new training method, called MixPatch, designed to improve a CNN-based classifier by specifically addressing the prediction uncertainty problem and examine its effectiveness in improving diagnosis performance in the context of histopathological image analysis. MixPatch generates and uses a new sub-training dataset, which consists of mixed-patches and their predefined ground-truth labels, for every single mini-batch. Mixed-patches are generated using a small size of clean patches confirmed by pathologists while their ground-truth labels are defined using a proportion-based soft labeling method. Our results obtained using a large histopathological image dataset shows that the proposed method performs better and alleviates overconfidence more effectively than any other method examined in the study. More specifically, our model showed 97.06% accuracy, an increase of 1.6% to 12.18%, while achieving 0.76% of expected calibration error, a decrease of 0.6% to 6.3%, over the other models. By specifically considering the mixed-region variation characteristics of histopathology images, MixPatch augments the extant mixed image methods for medical image analysis in which prediction uncertainty is a crucial issue. The proposed method provides a new way to systematically alleviate the overconfidence problem of CNN-based classifiers and improve their prediction accuracy, contributing toward more calibrated and reliable histopathology image analysis. <<<

Short-read RNA sequencing and long-read RNA sequencing each have their strengths and weaknesses for transcriptome assembly. While short reads are highly accurate, they are rarely able to span multiple exons. Long-read technology can capture full-length transcripts, but its relatively high error rate often leads to mis-identified splice sites. Here we present a new release of StringTie that performs hybrid-read assembly. By taking advantage of the strengths of both long and short reads, hybrid-read assembly with StringTie is more accurate than long-read only or short-read only assembly, and on some datasets it can more than double the number of correctly assembled transcripts, while obtaining substantially higher precision than the long-read data assembly alone. Here we demonstrate the improved accuracy on simulated data and real data from Arabidopsis thaliana, Mus musculus, and human. We also show that hybrid-read assembly is more accurate than correcting long reads prior to assembly while also being substantially faster. StringTie is freely available as open source software at https://github.com/gpertea/stringtie. <<<

The volume of data is growing exponentially and becoming more valuable to organizations that collect it, from e-commerce data, shipping, audio and video logs, text messages, internet search queries, stock market activity, financial transactions, the Internet of Things, and various other sources. The major challenges are related with the way to extract insights from such a rich data environment and whether Deep Learning can be successful with Big Data. To get some insight on these topics, social network data are employed as a case study on how sentiments can affect decisions in stock market environments. In this paper, we propose a generalized Deep Learning-based classification framework for Stock Market Sentiment Analysis. This work comprises the study, the development, and implementation of an automatic classification system based on Deep Learning and the validation of its adequacy and efficiency in any scenario, particularly Stock Market Sentiment Analysis. Distinct datasets and several Deep Learning approaches with different layers and embedded techniques are used, and their performances are evaluated. These developments show how Deep Learning reacts to distinct contexts. The results also give context on how different techniques with different parameter combinations react to certain types of data. Convolution obtained the best results when dealing with complex data inputs, and long short-term layers kept a memory of data, allowing inputs which are not as common to still be considered for decisions. The models that resulted from Stock Market Sentiment Analysis datasets were applied with some success to real-life problems. The best models reached accuracies of 73% in training and 69% in certain test datasets. In a simulation, a model was able to provide a Return on Investment of 4.4%. The results contribute to understanding how to process Big Data efficiently using Deep Learning and specialized hardware techniques. <<<

Rapid progress of industrial development, urbanization and traffic has caused air quality reduction that negatively affects human health and environmental sustainability, especially among developed countries. Numerous studies on the development of air quality forecasting model using machine learning have been conducted to control air pollution. As such, there are significant numbers of reviews on the application of machine learning in air quality forecasting. Shallow architectures of machine learning exhibit several limitations and yield lower forecasting accuracy than deep learning architecture. Deep learning is a new technology in computational intelligence; thus, its application in air quality forecasting is still limited. This study aims to investigate the deep learning applications in time series air quality forecasting. Owing to this, literature search is conducted thoroughly from all scientific databases to avoid unnecessary clutter. This study summarizes and discusses different types of deep learning algorithms applied in air quality forecasting, including the theoretical backgrounds, hyperparameters, applications and limitations. Hybrid deep learning with data decomposition, optimization algorithm and spatiotemporal models are also presented to highlight those techniques' effectiveness in tackling the drawbacks of individual deep learning models. It is clearly stated that hybrid deep learning was able to forecast future air quality with higher accuracy than individual models. At the end of the study, some possible research directions are suggested for future model development. The main objective of this review study is to provide a comprehensive literature summary of deep learning applications in time series air quality forecasting that may benefit interested researchers for subsequent research. <<<

在语言的形而上学中，最值得关注的有三大基本原理：一、语言的自否定本质，语言本质上是辩证法的，它的“是”即蕴含着“不是”,任何“真话”都隐含着“谎言”,否则不成其为语言；二、语言的自欺功能，有意识的自欺或假扮游戏是语言的灵魂和生命，它基于人类自我意识的自欺结构，同时又给这种结构提供了现实的确证；三、语言的修辞学或诗学属性，一切语言都由诗性而发生，这也是语言中的语法和逻辑功能的起源。我所设想的“语言学之后”的形而上学所要探讨的正是语言的诗性功能和逻辑功能的关系，双方不仅是“对立统一”的关系，而且处于“自否定”的辩证进展中，这构成了“语言学之后”的最基本的原理。 <<<

The emergency use authorizations (EUAs) of two mRNA-based severe acute respiratory syndrome coronavirus (SARS-CoV)-2 vaccines approximately 11 months after publication of the viral sequence highlights the transformative potential of this nucleic acid technology. Most clinical applications of mRNA to date have focused on vaccines for infectious disease and cancer for which low doses, low protein expression and local delivery can be effective because of the inherent immunostimulatory properties of some mRNA species and formulations. In addition, work on mRNA-encoded protein or cellular immunotherapies has also begun, for which minimal immune stimulation, high protein expression in target cells and tissues, and the need for repeated administration have led to additional manufacturing and formulation challenges for clinical translation. Building on this momentum, the past year has seen clinical progress with second-generation coronavirus disease 2019 (COVID-19) vaccines, Omicron-specific boosters and vaccines against seasonal influenza, Epstein-Barr virus, human immunodeficiency virus (HIV) and cancer. Here we review the clinical progress of mRNA therapy as well as provide an overview and future outlook of the transformative technology behind these mRNA-based drugs. <<<

Conceptual and mathematical models of neurons have lagged behind empirical understanding for decades. Here we extend previous work in modeling biological systems with fully scale-independent quantum information-theoretic tools to develop a uniform, scalable representation of synapses, dendritic and axonal processes, neurons, and local networks of neurons. In this representation, hierarchies of quantum reference frames act as hierarchical active-inference systems. The resulting model enables specific predictions of correlations between synaptic activity, dendritic remodeling, and trophic reward. We summarize how the model may be generalized to nonneural cells and tissues in developmental and regenerative contexts. <<<

BACKGROUND: Drug-target interactions (DTIs) are critical for drug repurposing and elucidation of drug mechanisms, and are manually curated by large databases, such as ChEMBL, BindingDB, DrugBank and DrugTargetCommons. However, the number of curated articles likely constitutes only a fraction of all the articles that contain experimentally determined DTIs. Finding such articles and extracting the experimental information is a challenging task, and there is a pressing need for systematic approaches to assist the curation of DTIs. To this end, we applied Bidirectional Encoder Representations from Transformers (BERT) to identify such articles. Because DTI data intimately depends on the type of assays used to generate it, we also aimed to incorporate functions to predict the assay format.RESULTS: Our novel method identified 0.6 million articles (along with drug and protein information) which are not previously included in public DTI databases. Using 10-fold cross-validation, we obtained ~ 99% accuracy for identifying articles containing quantitative drug-target profiles. The F1 micro for the prediction of assay format is 88%, which leaves room for improvement in future studies.CONCLUSION: The BERT model in this study is robust and the proposed pipeline can be used to identify previously overlooked articles containing quantitative DTIs. Overall, our method provides a significant advancement in machine-assisted DTI extraction and curation. We expect it to be a useful addition to drug mechanism discovery and repurposing. <<<

Central to the study of cognition is being able to specify the Subject that is making decisions and owning memories and preferences. However, all real cognitive agents are made of parts (such as brains made of cells). The integration of many active subunits into a coherent Self appearing at a larger scale of organization is one of the fundamental questions of evolutionary cognitive science. Typical biological model systems, whether basal or advanced, have a static anatomical structure which obscures important aspects of the mind-body relationship. Recent advances in bioengineering now make it possible to assemble, disassemble, and recombine biological structures at the cell, organ, and whole organism levels. Regenerative biology and controlled chimerism reveal that studies of cognition in intact, "standard", evolved animal bodies are just a narrow slice of a much bigger and as-yet largely unexplored reality: the incredible plasticity of dynamic morphogenesis of biological forms that house and support diverse types of cognition. The ability to produce living organisms in novel configurations makes clear that traditional concepts, such as body, organism, genetic lineage, death, and memory are not as well-defined as commonly thought, and need considerable revision to account for the possible spectrum of living entities. Here, I review fascinating examples of experimental biology illustrating that the boundaries demarcating somatic and cognitive Selves are fluid, providing an opportunity to sharpen inquiries about how evolution exploits physical forces for multi-scale cognition. Developmental (pre-neural) bioelectricity contributes a novel perspective on how the dynamic control of growth and form of the body evolved into sophisticated cognitive capabilities. Most importantly, the development of functional biobots - synthetic living machines with behavioral capacity - provides a roadmap for greatly expanding our understanding of the origin and capacities of cognition in all of its possible material implementations, especially those that emerge de novo, with no lengthy evolutionary history of matching behavioral programs to bodyplan. Viewing fundamental questions through the lens of new, constructed living forms will have diverse impacts, not only in basic evolutionary biology and cognitive science, but also in regenerative medicine of the brain and in artificial intelligence. <<<

Theories of consciousness and cognition that assume a neural substrate automatically regard phylogenetically basal, nonneural systems as nonconscious and noncognitive. Here, we advance a scale-free characterization of consciousness and cognition that regards basal systems, including synthetic constructs, as not only informative about the structure and function of experience in more complex systems but also as offering distinct advantages for experimental manipulation. Our "minimal physicalist" approach makes no assumptions beyond those of quantum information theory, and hence is applicable from the molecular scale upwards. We show that standard concepts including integrated information, state broadcasting via small-world networks, and hierarchical Bayesian inference emerge naturally in this setting, and that common phenomena including stigmergic memory, perceptual coarse-graining, and attention switching follow directly from the thermodynamic requirements of classical computation. We show that the self-representation that lies at the heart of human autonoetic awareness can be traced as far back as, and serves the same basic functions as, the stress response in bacteria and other basal systems. <<<

The Free Energy Principle (FEP) states that under suitable conditions of weak coupling, random dynamical systems with sufficient degrees of freedom will behave so as to minimize an upper bound, formalized as a variational free energy, on surprisal (a.k.a., self-information). This upper bound can be read as a Bayesian prediction error. Equivalently, its negative is a lower bound on Bayesian model evidence (a.k.a., marginal likelihood). In short, certain random dynamical systems evince a kind of self-evidencing. Here, we reformulate the FEP in the formal setting of spacetime-background free, scale-free quantum information theory. We show how generic quantum systems can be regarded as observers, which with the standard freedom of choice assumption become agents capable of assigning semantics to observational outcomes. We show how such agents minimize Bayesian prediction error in environments characterized by uncertainty, insufficient learning, and quantum contextuality. We show that in its quantum-theoretic formulation, the FEP is asymptotically equivalent to the Principle of Unitarity. Based on these results, we suggest that biological systems employ quantum coherence as a computational resource and - implicitly - as a communication resource. We summarize a number of problems for future research, particularly involving the resources required for classical communication and for detecting and responding to quantum context switches. <<<

AbstractActive inference offers a unified theory of perception, learning, and decision-making at computational and neural levels of description. In this article, we address the worry that active inference may be in tension with the belief–desire–intention (BDI) model within folk psychology because it does not include terms for desires (or other conative constructs) at the mathematical level of description. To resolve this concern, we first provide a brief review of the historical progression from predictive coding to active inference, enabling us to distinguish between active inference formulations of motor control (which need not have desires under folk psychology) and active inference formulations of decision processes (which do have desires within folk psychology). We then show that, despite a superficial tension when viewed at the mathematical level of description, the active inference formalism contains terms that are readily identifiable as encoding both the objects of desire and the strength of desire at the psychological level of description. We demonstrate this with simple simulations of an active inference agent motivated to leave a dark room for different reasons. Despite their consistency, we further show how active inference may increase the granularity of folk-psychological descriptions by highlighting distinctions between drives to seek information versus reward—and how it may also offer more precise, quantitative folk-psychological predictions. Finally, we consider how the implicitly conative components of active inference may have partial analogues (i.e., “as if” desires) in other systems describable by the broader free energy principle to which it conforms. <<<

Oliver Lester Saldanha, Philip Quirke, Nicholas P West, Jacqueline A James, Maurice B Loughrey, Heike I Grabsch, Manuel Salto-Tellez, Elizabeth Alwers, Didem Cifci, Narmin Ghaffari Laleh, Tobias Seibel, Richard Gray, Gordon G A Hutchins, Hermann Brenner, Marko van Treeck, Tanwei Yuan, Titus J Brinker, Jenny Chang-Claude, Firas Khader, Andreas Schuppert, Tom Luedde, Christian Trautwein, Hannah Sophie Muti, Sebastian Foersch, Michael Hoffmeister, Daniel Truhn, Jakob Nikolas Kather <<<

Artificial intelligence (AI) can predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets for which data collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL), in which partners jointly train AI models while avoiding data transfer and monopolistic data governance. Here, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images from over 5,000 patients. We show that AI models trained using SL can predict BRAF mutational status and microsatellite instability directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer. We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States, and validated the prediction performance in two independent datasets from the United Kingdom. Our data show that SL-trained AI models outperform most locally trained models, and perform on par with models that are trained on the merged datasets. In addition, we show that SL-based AI models are data efficient. In the future, SL can be used to train distributed AI models for any histopathology image analysis task, eliminating the need for data transfer. <<<

Ulrich Wagner, Christine Wong, Ulrike Camenisch, Kathrin Zimmermann, Markus Rechsteiner, Nadejda Valtcheva, Alexandre Theocharides, Corinne C Widmer, Markus G Manz, Holger Moch, Peter J Wild, Stefan Balabanov <<<

Next-generation sequencing has greatly advanced the molecular diagnostics of malignant hematological diseases and provides useful information for clinical decision making. Studies have shown that certain mutations are associated with prognosis and have a direct impact on treatment of affected patients. Therefore, reliable detection of pathogenic variants is critically important. Here, we compared four sequencing panels with different characteristics, from number of genes covered to technical aspects of library preparation and data analysis workflows, to find the panel with the best clinical utility for myeloid neoplasms with a special focus on acute myeloid leukemia. Using the Acrometrix Oncology Hotspot Control DNA and DNA from acute myeloid leukemia patients, panel performance was evaluated in terms of coverage, precision, recall, and reproducibility and different bioinformatics tools that can be used for the evaluation of any next-generation sequencing panel were tested. Taken together, our results support the reliability of the Acrometrix Oncology Hotspot Control to validate and compare sequencing panels for hematological diseases and show which panel-software combination (platform) has the best performance. <<<

Accompanying the rapid urbanization, many developing countries are suffering from serious air pollution problem. The demand for predicting future air quality is becoming increasingly more important to government's policy-making and people's decision making. In this paper, we predict the air quality of next 48 hours for each monitoring station, considering air quality data, meteorology data, and weather forecast data. Based on the domain knowledge about air pollution, we propose a deep neural network (DNN)-based approach (entitled DeepAir), which consists of a spatial transformation component and a deep distributed fusion network. Considering air pollutants' spatial correlations, the former component converts the spatial sparse air quality data into a consistent input to simulate the pollutant sources. The latter network adopts a neural distributed architecture to fuse heterogeneous urban data for simultaneously capturing the factors affecting air quality, e.g. meteorological conditions. We deployed DeepAir in our AirPollutionPrediction system, providing fine-grained air quality forecasts for 300+ Chinese cities every hour. The experimental results on the data from three-year nine Chinese-city demonstrate the advantages of DeepAir beyond 10 baseline methods. Comparing with the previous online approach in AirPollutionPrediction system, we have 2.4%, 12.2%, 63.2% relative accuracy improvements on short-term, long-term and sudden changes prediction, respectively. <<<

Gaby Schobers, Jolanda H Schieving, Helger G Yntema, Maartje Pennings, Rolph Pfundt, Ronny Derks, Tom Hofste, Ilse de Wijs, Nienke Wieskamp, Simone van den Heuvel, Jordi Corominas Galbany, Christian Gilissen, Marcel Nelen, Han G Brunner, Tjitske Kleefstra, Erik-Jan Kamsteeg, Michèl A A P Willemsen, Lisenka E L M Vissers <<<

BACKGROUND: Approximately two third of patients with a rare genetic disease remain undiagnosed after exome sequencing (ES). As part of our post-test counseling procedures, patients without a conclusive diagnosis are advised to recontact their referring clinician to discuss new diagnostic opportunities in due time. We performed a systematic study of genetically undiagnosed patients 5 years after their initial negative ES report to determine the efficiency of diverse reanalysis strategies.METHODS: We revisited a cohort of 150 pediatric neurology patients originally enrolled at Radboud University Medical Center, of whom 103 initially remained genetically undiagnosed. We monitored uptake of physician-initiated routine clinical and/or genetic re-evaluation (ad hoc re-evaluation) and performed systematic reanalysis, including ES-based resequencing, of all genetically undiagnosed patients (systematic re-evaluation).RESULTS: Ad hoc re-evaluation was initiated for 45 of 103 patients and yielded 18 diagnoses (including 1 non-genetic). Subsequent systematic re-evaluation identified another 14 diagnoses, increasing the diagnostic yield in our cohort from 31% (47/150) to 53% (79/150). New genetic diagnoses were established by reclassification of previously identified variants (10%, 3/31), reanalysis with enhanced bioinformatic pipelines (19%, 6/31), improved coverage after resequencing (29%, 9/31), and new disease-gene associations (42%, 13/31). Crucially, our systematic study also showed that 11 of the 14 further conclusive genetic diagnoses were made in patients without a genetic diagnosis that did not recontact their referring clinician.CONCLUSIONS: We find that upon re-evaluation of undiagnosed patients, both reanalysis of existing ES data as well as resequencing strategies are needed to identify additional genetic diagnoses. Importantly, not all patients are routinely re-evaluated in clinical care, prolonging their diagnostic trajectory, unless systematic reanalysis is facilitated. We have translated our observations into considerations for systematic and ad hoc reanalysis in routine genetic care. <<<

DNA molecules have been used as novel computing tools, by which Synthetic DNA was designed to execute computing processes with a programmable sequence. Here, we proposed a parallel computing method using DNA origamis as agents to solve the three-color problem, an example of the graph problem. Each agent was fabricated with a DNA origami of ∼50 nm diameter and contained DNA probes with programmable sticky ends that execute preset computing processes. With the interaction of different nanoagents, DNA molecules self-assemble into spatial nanostructures, which embody the computation results of the three-color problem with polynomial numbers of computing nanoagents in a one-pot annealing step. The computing results were confirmed by atomic force microscopy. Our method is completely different from existing DNA computing methods in its computing algorithm, and it has an advantage in terms of computational complexity and results detection for solving graph problems. <<<

Motivation: Amplicon sequencing is widely applied to explore heterogeneity and rare variants in genetic populations. Resolving true biological variants and quantifying their abundance is crucial for downstream analyses, but measured abundances are distorted by stochasticity and bias in amplification, plus errors during Polymerase Chain Reaction (PCR) and sequencing. One solution attaches Unique Molecular Identifiers (UMIs) to sample sequences before amplification eliminating amplification bias by clustering reads on UMI and counting clusters to quantify abundance. While modern methods improve over naive clustering by UMI identity, most do not account for UMI reuse, or collision, and they do not adequately model PCR and sequencing errors in the UMIs and sample sequences. Results: We introduce Deduplication and accurate Abundance estimation with UMIs (DAUMI), a probabilistic framework to detect true biological sequences and accurately estimate their deduplicated abundance from amplicon sequence data. DAUMI recognizes UMI collision, even on highly similar sequences, and detects and corrects most PCR and sequencing errors in the UMI and sampled sequences. We demonstrate DAUMI performs better on simulated and real data compared to other UMI-aware clustering methods. Availability: Source code is available at https://github.com/xiyupeng/AmpliCI-UMI. <<<