Toward understanding the role of genomic repeat elements in neurodegenerative diseases

Neurodegenerative diseases cause great medical and economic burdens for both patients and society; however, the complex molecular mechanisms thereof are not yet well understood. With the development of high-coverage sequencing technology, researchers have started to notice that genomic repeat regions, previously neglected in search of disease culprits, are active contributors to multiple neurodegenerative diseases. In this review, we describe the association between repeat element variants and multiple degenerative diseases through genome-wide association studies and targeted sequencing. We discuss the identification of disease-relevant repeat element variants, further powered by the advancement of long-read sequencing technologies and their related tools, and summarize recent findings in the molecular mechanisms of repeat element variants in brain degeneration, such as those causing transcriptional silencing or RNA-mediated gain of toxic function. Furthermore, we describe how in silico predictions using innovative computational models, such as deep learning language models, could enhance and accelerate our understanding of the functional impact of repeat element variants. Finally, we discuss future directions to advance current findings for a better understanding of neurodegenerative diseases and the clinical applications of genomic repeat elements.

RBProkCNN: Deep learning on appropriate contextual evolutionary information for RNA binding protein discovery in prokaryotes

RNA-binding proteins (RBPs) are central to key functions such as post-transcriptional regulation, mRNA stability, and adaptation to varied environmental conditions in prokaryotes. While the majority of research has concentrated on eukaryotic RBPs, recent developments underscore the crucial involvement of prokaryotic RBPs. Although computational methods have emerged in recent years to identify RBPs, they have fallen short in accurately identifying prokaryotic RBPs due to their generic nature. To bridge this gap, we introduce RBProkCNN, a novel machine learning-driven computational model meticulously designed for the accurate prediction of prokaryotic RBPs. The prediction process involves the utilization of eight shallow learning algorithms and four deep learning models, incorporating PSSM-based evolutionary features. By leveraging a convolutional neural network (CNN) and evolutionarily significant features selected through extreme gradient boosting variable importance measure, RBProkCNN achieved the highest accuracy in five-fold cross-validation, yielding 98.04% auROC and 98.19% auPRC. Furthermore, RBProkCNN demonstrated robust performance with an independent dataset, showcasing a commendable 95.77% auROC and 95.78% auPRC. Noteworthy is its superior predictive accuracy when compared to several state-of-the-art existing models. RBProkCNN is available as an online prediction tool (https://iasri-sg.icar.gov.in/rbprokcnn/), offering free access to interested users. This tool represents a substantial contribution, enriching the array of resources available for the accurate and efficient prediction of prokaryotic RBPs.

Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing

Purpose

The main aim of our study was to explore the utility of artificial intelligence (AI) in diagnosing autism spectrum disorder (ASD). The study primarily focused on using machine learning (ML) and deep learning (DL) models to detect ASD potential cases by analyzing text inputs, especially from social media platforms like Twitter. This is to overcome the ongoing challenges in ASD diagnosis, such as the requirement for specialized professionals and extensive resources. Timely identification, particularly in children, is essential to provide immediate intervention and support, thereby improving the quality of life for affected individuals.

Methods

We employed natural language processing (NLP) techniques along with ML models like decision trees, extreme gradient boosting (XGB), k-nearest neighbors algorithm (KNN), and DL models such as recurrent neural networks (RNN), long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), bidirectional encoder representations from transformers (BERT and BERTweet). We extracted a dataset of 404,627 tweets from Twitter users using the platform's API and classified them based on whether they were written by individuals claiming to have ASD (ASD users) or by those without ASD (non-ASD users). From this dataset, we used a subset of 90,000 tweets (45,000 from each classification group) for the training and testing of these models.

Results

The application of our AI models yielded promising results, with the predictive model reaching an accuracy of almost 88% when classifying texts that potentially originated from individuals with ASD.

Conclusion

Our research demonstrated the potential of using AI, particularly DL models, in enhancing the accuracy of ASD detection and diagnosis. This innovative approach signifies the critical role AI can play in advancing early diagnostic techniques, enabling better patient outcomes and underlining the importance of early identification of ASD, especially in children.

EM-COGLOAD: An investigation into age and cognitive load detection using eye tracking and deep learning

Alzheimer's Disease is the most prevalent neurodegenerative disease, and is a leading cause of disability among the elderly. Eye movement behaviour demonstrates potential as a non-invasive biomarker for Alzheimer's Disease, with changes detectable at an early stage after initial onset. This paper introduces a new publicly available dataset: EM-COGLOAD (available at https://osf.io/zjtdq/, DOI: 10.17605/OSF.IO/ZJTDQ). A dual-task paradigm was used to create effects of declined cognitive performance in 75 healthy adults as they carried out visual tracking tasks. Their eye movement was recorded, and time series classification of the extracted eye movement traces was explored using a range of deep learning techniques. The results of this showed that convolutional neural networks were able to achieve an accuracy of 87.5% when distinguishing between eye movement under low and high cognitive load, and 76% when distinguishing between the oldest and youngest age groups.

Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data

Objective

Classification tasks are an open challenge in the field of biomedicine. While several machine-learning techniques exist to accomplish this objective, several peculiarities associated with biomedical data, especially when it comes to omics measurements, prevent their use or good performance achievements. Omics approaches aim to understand a complex biological system through systematic analysis of its content at the molecular level. On the other hand, omics data are heterogeneous, sparse and affected by the classical "curse of dimensionality" problem, i.e. having much fewer observation, samples (n) than omics features (p). Furthermore, a major problem with multi-omics data is the imbalance either at the class or feature level. The objective of this work is to study whether feature extraction and/or feature selection techniques can improve the performances of classification machine-learning algorithms on omics measurements.

Methods

Among all omics, metabolomics has emerged as a powerful tool in cancer research, facilitating a deeper understanding of the complex metabolic landscape associated with tumorigenesis and tumor progression. Thus, we selected three publicly available metabolomics datasets, and we applied several feature extraction techniques both linear and non-linear, coupled or not with feature selection methods, and evaluated the performances regarding patient classification in the different configurations for the three datasets.

Results

We provide general workflow and guidelines on when to use those techniques depending on the characteristics of the data available. To further test the extension of our approach to other omics data, we have included a transcriptomics and a proteomics data. Overall, for all datasets, we showed that applying supervised feature selection improves the performances of feature extraction methods for classification purposes. Scripts used to perform all analyses are available at: https://github.com/Plant-Net/Metabolomic_project/.

From explainable to interpretable deep learning for natural language processing in healthcare: How far from reality?

Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP. The term "eXplainable and Interpretable Artificial Intelligence" (XIAI) is introduced to distinguish XAI from IAI. Different models are further categorized based on their functionality (model-, input-, output-based) and scope (local, global). Our analysis shows that attention mechanisms are the most prevalent emerging IAI technique. The use of IAI is growing, distinguishing it from XAI. The major challenges identified are that most XIAI does not explore "global" modelling processes, the lack of best practices, and the lack of systematic evaluation and benchmarks. One important opportunity is to use attention mechanisms to enhance multi-modal XIAI for personalized medicine. Additionally, combining DL with causal logic holds promise. Our discussion encourages the integration of XIAI in Large Language Models (LLMs) and domain-specific smaller models. In conclusion, XIAI adoption in healthcare requires dedicated in-house expertise. Collaboration with domain experts, end-users, and policymakers can lead to ready-to-use XIAI methods across NLP and medical tasks. While challenges exist, XIAI techniques offer a valuable foundation for interpretable NLP algorithms in healthcare.

Identifying factors controlling cellular uptake of gold nanoparticles by machine learning

There is strong interest to improve the therapeutic potential of gold nanoparticles (GNPs) while ensuring their safe development. The utility of GNPs in medicine requires a molecular-level understanding of how GNPs interact with biological systems. Despite considerable research efforts devoted to monitoring the internalisation of GNPs, there is still insufficient understanding of the factors responsible for the variability in GNP uptake in different cell types. Data-driven models are useful for identifying the sources of this variability. Here, we trained multiple machine learning models on 2077 data points for 193 individual nanoparticles from 59 independent studies to predict cellular uptake level of GNPs and compared different algorithms for their efficacies of prediction. The five ensemble learners (Xgboost, random forest, bootstrap aggregation, gradient boosting, light gradient boosting machine) made the best predictions of GNP uptake, accounting for 80-90% of the variance in the test data. The models identified particle size, zeta potential, GNP concentration and exposure duration as the most important drivers of cellular uptake. We expect this proof-of-concept study will foster the more effective use of accumulated cellular uptake data for GNPs and minimise any methodological bias in individual studies that may lead to under- or over-estimation of cellular internalisation rates.

SERT-StructNet: Protein secondary structure prediction method based on multi-factor hybrid deep model

Protein secondary structure prediction (PSSP) is a pivotal research endeavour that plays a crucial role in the comprehensive elucidation of protein functions and properties. Current prediction methodologies are focused on deep-learning techniques, particularly focusing on multi-factor features. Diverging from existing approaches, in this study, we placed special emphasis on the effects of amino acid properties and protein secondary structure propensity scores (SSPs) on secondary structure during the meticulous selection of multi-factor features. This differential feature-selection strategy results in a distinctive and effective amalgamation of the sequence and property features. To harness these multi-factor features optimally, we introduced a hybrid deep feature extraction model. The model initially employs mechanisms such as dilated convolution (D-Conv) and a channel attention network (SENet) for local feature extraction and targeted channel enhancement. Subsequently, a combination of recurrent neural network variants (BiGRU and BiLSTM), along with a transformer module, was employed to achieve global bidirectional information consideration and feature enhancement. This approach to multi-factor feature input and multi-level feature processing enabled a comprehensive exploration of intricate associations among amino acid residues in protein sequences, yielding a Q 3 accuracy of 84.9% and an Sov score of 85.1%. The overall performance surpasses that of the comparable methods. This study introduces a novel and efficient method for determining the PSSP domain, which is poised to deepen our understanding of the practical applications of protein molecular structures.

DeepCORE: An interpretable multi-view deep neural network model to detect co-operative regulatory elements

Gene transcription is an essential process involved in all aspects of cellular functions with significant impact on biological traits and diseases. This process is tightly regulated by multiple elements that co-operate to jointly modulate the transcription levels of target genes. To decipher the complicated regulatory network, we present a novel multi-view attention-based deep neural network that models the relationship between genetic, epigenetic, and transcriptional patterns and identifies co-operative regulatory elements (COREs). We applied this new method, named DeepCORE, to predict transcriptomes in various tissues and cell lines, which outperformed the state-of-the-art algorithms. Furthermore, DeepCORE contains an interpreter that extracts the attention values embedded in the deep neural network, maps the attended regions to putative regulatory elements, and infers COREs based on correlated attentions. The identified COREs are significantly enriched with known promoters and enhancers. Novel regulatory elements discovered by DeepCORE showed epigenetic signatures consistent with the status of histone modification marks.

The use of artificial intelligence algorithms to detect macroplastics in aquatic environments: A critical review

The presence of macroplastic (MP) is having serious consequences on natural ecosystems, directly affecting biota and human wellbeing. Given this scenario, estimating MPs' abundance is crucial for assessing the issue and formulating effective waste management strategies. In this context, the main objective of this critical review is to analyze the use of machine learning (ML) techniques, with a particular interest in deep learning (DL) approaches, to detect, classify and quantify MPs in aquatic environments, supported by datasets such as satellite or aerial images and video recordings taken by unmanned aerial vehicles. This article provides a concise overview of artificial intelligence concepts, followed by a bibliometric analysis and a critical review. The search methodology aimed to categorize the scientific contributions through temporal and spatial criteria for bibliometric analysis, whereas the critical review was based on generating homogeneous groups according to the complexity of ML and DL methods, as well as the type of dataset. In light of the review carried out, classical ML techniques, such as random forest or support vector machines, showed robustness in MPs detection. However, it seems that achieving optimal efficiencies in multiclass classification is a limitation for these methods. Consequently, more advanced techniques such as DL approaches are taking the lead for the detection and multiclass classification of MPs. A series of architectures based on convolutional neural networks, and the use of complex pre-trained models through the transfer learning, are currently being explored (e.g., VGG16 and YOLO models), although currently the computational expense is high due to the need for processing large volumes of data. Additionally, there seems to be a trend towards detecting smaller plastic, which need higher resolution images. Finally, it is important to stress that since 2020 there has been a significant increase in scientific research focusing on transformer-based architectures for object detection. Although this can be considered the current state of the art, no studies have been identified that utilize these architectures for MP detection.

Recent advances in flexible hydrogel sensors: Enhancing data processing and machine learning for intelligent perception

With the advent of flexible electronics and sensing technology, hydrogel-based flexible sensors have exhibited considerable potential across a diverse range of applications, including wearable electronics and soft robotics. Recently, advanced machine learning (ML) algorithms have been integrated into flexible hydrogel sensing technology to enhance their data processing capabilities and to achieve intelligent perception. However, there are no reviews specifically focusing on the data processing steps and analysis based on the raw sensing data obtained by flexible hydrogel sensors. Here we provide a comprehensive review of the latest advancements and breakthroughs in intelligent perception achieved through the fusion of ML algorithms with flexible hydrogel sensors, across various applications. Moreover, this review thoroughly examines the data processing techniques employed in flexible hydrogel sensors, offering valuable perspectives expected to drive future data-driven applications in this field.

Advancements in remote sensing for active fire detection: A review of datasets and methods

This study comprehensively and critically reviews active fire detection advancements in remote sensing from 1975 to the present, focusing on two main perspectives: datasets and corresponding instruments, and detection algorithms. The study highlights the increasing role of machine learning, particularly deep learning techniques, in active fire detection. Looking forward, the review outlines current challenges and future research opportunities in remote sensing for active fire detection. These include exploring data quality management and multi-modal learning, developing spatiotemporally explicit models, investigating self-supervised learning models, improving explainable and interpretable models, integrating physical-process based models with machine learning, and building digital twins to replicate wildfire dynamics and perform what-if scenario analysis. The review aims to serve as a valuable resource for informing natural resource management and enhancing environmental protection efforts through the application of remote sensing technology.

Self-construal modulates default mode network connectivity in refugees with PTSD

BACKGROUND

While self-construal and posttraumatic stress disorder (PTSD) are independently associated with altered self-referential processes and underlying default mode network (DMN) functioning, no study has examined how self-construal affects DMN connectivity in PTSD.

METHODS

A final sample of 93 refugee participants (48 with DSM-5 PTSD or sub-syndromal PTSD and 45 matched trauma-exposed controls) completed a 5-minute resting state fMRI scan to enable the observation of connectivity in the DMN and other core networks. A self-construal index was calculated by substracting scores on the collectivistic and individualistic sub-scales of the Self Construal Scale.

RESULTS

Independent components analysis identified 9 active networks-of-interest, and functional network connectivity was determined. A significant interaction effect between PTSD and self-construal index was observed in the anterior ventromedial DMN, with spatial maps localizing this to the left ventromedial prefrontal cortex (vmPFC), extending to the ventral anterior cingulate cortex. This effect revealed that connectivity in the vMPFC showed greater reductions in those with PTSD with higher levels of collectivistic self-construal.

LIMITATIONS

This is an observational study and causality cannot be assumed. The specialized sample of refugees means that the findings may not generalize to other trauma-exposed populations.

CONCLUSIONS

Such a finding indicates that self-construal may shape the core neural architecture of PTSD, given that functional disruptions to the vmPFC underpin the core mechanisms of extinction learning, emotion dysregulation and self-referential processing in PTSD. Results have important implications for understanding the universality of neural disturbances in PTSD, and suggest that self-construal could be an important consideration in the assessment and treatment of post-traumatic stress reactions.

Soil data augmentation and model construction based on spectral difference and content difference

Soil analysis makes for developing precision agriculture and monitoring land quality, while the models available for spectroscopy-based chemometrics are constrained by limited samples from small areas. The paper proposed sample expansion and model construction based on spectral difference and content difference, realizing data augmentation and deep learning applied to original samples with limited numbers. The spectral subtraction based on maximum or minimum values exploited the maximum or minimum values to acquire the spectral difference and content difference, which provided a new data form for model construction. Keeping enhanced samples whose spectral difference and content difference were all zero was useful for improving model performance. Augmentation of all data or training data based on maximum or minimum values-based spectral subtraction, which sorted the contents and made them the maximum or minimum values in sequence, achieved sample expansion by the spectral difference and content difference. The model utilized the random vector functional link (RVFL) network, extreme learning machine (ELM), and one-dimensional convolutional neural network (1D CNN), which could predict the content of new samples through ensemble averaging when predicting content difference. The experimental result showed the model of the spectral subtraction based on maximum or minimum values had a similar performance to that of the original samples. Augmentation of all data improved model performance by only RVFL and ELM. Augmentation of training data verified 1D CNN was better than RVFL and ELM. The paper implements a new data augmentation method and applies CNN to original samples with inadequate numbers, which lays the foundation for an improved model and applying spectral preprocessing.

The free energy principle induces intracellular compartmentalization

Living systems at all scales are compartmentalized into interacting subsystems. This paper reviews a mechanism that drives compartmentalization in generic systems at any scale. It first discusses three symmetries of generic physical interactions in a quantum-theoretic description. It then shows that if one of these, a permutation symmetry on the inter-system boundary, is spontaneously broken, the symmetry breaking is amplified by the Free Energy Principle (FEP). It thus shows how compartmentalization generically results from permutation symmetry breaking under the FEP. It finally notes that the FEP asymptotically restores the broken symmetry, showing that the FEP can be regarded as a theory of fluctuations away from a permutation-symmetric boundary, and hence from an entangled joint state of the interacting systems.

Temporal prediction of suicidal ideation in an ecological momentary assessment study with recurrent neural networks

INTRODUCTION

Ecological Momentary Assessment (EMA) holds promise for providing insights into daily life experiences when studying mental health phenomena. However, commonly used mixed-effects linear statistical models do not fully utilize the richness of the ultidimensional time-varying data that EMA yields. Recurrent Neural Networks (RNNs) provide an alternative data analytic method to leverage more information and potentially improve prediction, particularly for non-normally distributed outcomes.

METHODS

As part of a broader research study of suicidal thoughts and behavior in people with borderline personality disorder (BPD), eighty-four participants engaged in EMA data collection over one week, answering questions multiple times each day about suicidal ideation (SI), stressful events, coping strategy use, and affect. RNNs and mixed-effects linear regression models (MEMs) were trained and used to predict SI. Root mean squared error (RMSE), mean absolute percent error (MAPE), and a pseudo-R2 accuracy metric were used to compare SI prediction accuracy between the two modeling methods.

RESULTS

RNNs had superior accuracy metrics (full model: RMSE = 3.41, MAPE = 42 %, pseudo-R2 = 26 %) compared with MEMs (full model: RMSE = 3.84, MAPE = 56 %, pseudo-R2 = 16 %). Importantly, RNNs showed significantly more accurate prediction at higher values of SI. Additionally, RNNs predicted, with significantly higher accuracy, the SI scores of participants with depression diagnoses and of participants with higher depression scores at baseline.

CONCLUSION

In this EMA study with a moderately sized sample, RNNs were better able to learn and predict daily SI compared with mixed-effects models. RNNs should be considered as an option for EMA analysis.

Parallel EEG assessment of different sound predictability levels in tinnitus

Tinnitus denotes the perception of a non-environmental sound and might result from aberrant auditory prediction. Successful prediction of formal (e.g., type) and temporal sound characteristics facilitates the filtering of irrelevant information, also labelled as 'sensory gating' (SG). Here, we explored if and how parallel manipulations of formal prediction violations and temporal predictability affect SG in persons with and without tinnitus. Age-, education- and sex-matched persons with and without tinnitus (N = 52) participated and listened to paired-tone oddball sequences, varying in formal (standard vs. deviant pitch) and temporal predictability (isochronous vs. random timing). EEG was recorded from 128 channels and data were analyzed by means of temporal spatial principal component analysis (tsPCA). SG was assessed by amplitude suppression for the 2nd tone in a pair and was observed in P50-like activity in both timing conditions and groups. Correspondingly, deviants elicited overall larger amplitudes than standards. However, only persons without tinnitus displayed a larger N100-like deviance response in the isochronous compared to the random timing condition. This result might imply that persons with tinnitus do not benefit similarly as persons without tinnitus from temporal predictability in deviance processing. Thus, persons with tinnitus might display less temporal sensitivity in auditory processing than persons without tinnitus.

NPEX: Never give up protein exploration with deep reinforcement learning

Elucidating unknown structures of proteins, such as metastable states, is critical in designing therapeutic agents. Protein structure exploration has been performed using advanced computational methods, especially molecular dynamics and Markov chain Monte Carlo simulations, which require untenably long calculation times and prior structural knowledge. Here, we developed an innovative method for protein structure determination called never give up protein exploration (NPEX) with deep reinforcement learning. The NPEX method leverages the soft actor-critic algorithm and the intrinsic reward system, effectively adding a bias potential without the need for prior knowledge. To demonstrate the method's effectiveness, we applied it to four models: a double well, a triple well, the alanine dipeptide, and the tryptophan cage. Compared with Markov chain Monte Carlo simulations, NPEX had markedly greater sampling efficiency. The significantly enhanced computational efficiency and lack of prior domain knowledge requirements of the NPEX method will revolutionize protein structure exploration.

Value-based decision-making in regular alcohol consumers following experimental manipulation of alcohol value

BACKGROUND

Devaluation of alcohol leads to reductions in alcohol choice and consumption; however, the cognitive mechanisms that underpin this relationship are not well-understood. In this study we applied a computational model of value-based decision-making (VBDM) to decisions made about alcohol and alcohol-unrelated cues following experimental manipulation of alcohol value.

METHOD

Using a pre-registered within-subject design, thirty-six regular alcohol consumers (≥14 UK units per week) completed a two-alternative forced choice task where they chose between two alcohol images (in one block) or two soft drink images (in a different block) after watching videos that emphasised the positive (alcohol value), and separately, the negative (alcohol devalue) consequences of alcohol. On each block, participants pressed a key to select the image depicting the drink they would rather consume. A drift-diffusion model (DDM) was fitted to reaction time and choice data to estimate evidence accumulation (EA) processes and response thresholds during the different blocks in each experimental condition.

FINDINGS

In the alcohol devalue condition, soft drink EA rates were significantly higher compared to alcohol EA rates (p = 0.04, d = 0.31), and compared to soft drink EA rates in the alcohol value condition (p = 0.01, d = 0.38). However, EA rates for alcoholic drinks and response thresholds (for either drink type) were unaffected by the experimental manipulation.

CONCLUSIONS

In line with behavioural economic models of addiction that emphasise the important role of alternative reinforcement, experimentally manipulating alcohol value is associated with changes in the internal cognitive processes that precede soft drink choice.

A study on diversion behavior in weaving segments: Individualized traffic conflict prediction and causal mechanism analysis

Lane change behavior disrupts traffic flow and increases the potential for traffic conflicts, especially on expressway weaving segments. Focusing on the diversion process, this study incorporating individual driving patterns into conflict prediction and causation analysis can help develop individualized intervention measures to avoid risky diversion behaviors. First, to minimize measurement errors, this study introduces a lane line reconstruction method. Second, several unsupervised clustering methods, including k-means, agglomerative clustering, gaussian mixture, and spectral clustering, are applied to explore diversion patterns. Moreover, machine learning methods, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Attention-based LSTM, eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), and Multilayer Perceptron (MLP), are employed for real-time traffic conflict prediction. Finally, mixed logit models are developed using pre-conflict condition data to investigate the causal mechanisms of traffic conflicts. The results indicate that the K-means algorithm with four clusters exhibits the highest Calinski-Harabasz and Silhouette scores and the lowest Davies-Bouldin scores. With superior classification accuracy and generalization ability, the LSTM is used to develop the personalized traffic conflict prediction model. Sensitivity analysis indicates that incorporating the diversion patterns into the LSTM model results in an improvement of 3.64% in Accuracy, 7.15% in Precision, and 1.34% in Recall. Results from the four mixed logit models indicate significant differences in factors contributing to traffic conflicts within each diversion pattern. For instance, increasing the speed difference between the target vehicle and the right preceding vehicle benefits traffic conflict during acceleration diversions but decreases the likelihood of traffic conflicts during deceleration diversions. These results can help traffic engineers propose individualized solutions to reduce unsafe diversion behavior.

Emergence of integrated behaviors through direct optimization for homeostasis

Homeostasis is a self-regulatory process, wherein an organism maintains a specific internal physiological state. Homeostatic reinforcement learning (RL) is a framework recently proposed in computational neuroscience to explain animal behavior. Homeostatic RL organizes the behaviors of autonomous embodied agents according to the demands of the internal dynamics of their bodies, coupled with the external environment. Thus, it provides a basis for real-world autonomous agents, such as robots, to continually acquire and learn integrated behaviors for survival. However, prior studies have generally explored problems pertaining to limited size, as the agent must handle observations of such coupled dynamics. To overcome this restriction, we developed an advanced method to realize scaled-up homeostatic RL using deep RL. Furthermore, several rewards for homeostasis have been proposed in the literature. We identified that the reward definition that uses the difference in drive function yields the best results. We created two benchmark environments for homeostasis and performed a behavioral analysis. The analysis showed that the trained agents in each environment changed their behavior based on their internal physiological states. Finally, we extended our method to address vision using deep convolutional neural networks. The analysis of a trained agent revealed that it has visual saliency rooted in the survival environment and internal representations resulting from multimodal input.

Real-time driving risk prediction using a self-attention-based bidirectional long short-term memory network based on multi-source data

Early warning of driving risks can effectively prevent collisions. However, numerous studies that predicted driving risks have suffered from the use of single data sources, insufficiently advanced models, and lack of time window analysis. To address these issues, this paper proposes a self-attention-based bidirectional long short-term memory (Att-Bi-LSTM) network model to predict driving risk based on multi-source data. First, driving simulation tests are conducted. Driver demographic, operation, visual, and physiological data as well as kinematic data are collected. Then, the driving risks are classified into no risk, low risk, medium risk, and high risk. Next, the Att-Bi-LSTM model is constructed, and convolutional neural network (CNN), CNN-LSTM, CatBoost, LightGBM, and XGBoost are employed for comparison. To generate the inputs and outputs of the models, observation, interval, and prediction time windows are introduced. The results show that the Att-Bi-LSTM model using early-fusion method significantly outperforms the five comparison models, with a macro-average F1-score of 0.914. The results of ablation studies indicate that the Bi-LSTM layers and self-attention layer have achieved the expected effect, which is crucial for improving the model's performance. As the interval or prediction time window is extended, the accuracy of the prediction results gradually decreases. However, as the observation time window is extended, the results first improve and then become stable. Compared to using only relative kinematic data, using all data (i.e., multi-source data) is shown to improve the F1-score by 0.061. This study provides an effective method for driving risk prediction and supports the improvement of advanced driver assistance systems.

Regularization, early-stopping and dreaming: A Hopfield-like setup to address generalization and overfitting

In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices turn out to be a class of matrices which correspond to Hebbian kernels revised by a reiterated unlearning protocol. Remarkably, the extent of such unlearning is proved to be related to the regularization hyperparameter of the loss function and to the training time. Thus, we can design strategies to avoid overfitting that are formulated in terms of regularization and early-stopping tuning. The generalization capabilities of these attractor networks are also investigated: analytical results are obtained for random synthetic datasets, next, the emerging picture is corroborated by numerical experiments that highlight the existence of several regimes (i.e., overfitting, failure and success) as the dataset parameters are varied.

Modeling Bellman-error with logistic distribution with applications in reinforcement learning

In modern Reinforcement Learning (RL) approaches, optimizing the Bellman error is a critical element across various algorithms, notably in deep Q-Learning and related methodologies. Traditional approaches predominantly employ the mean-squared Bellman error (MSELoss) as the standard loss function. However, the assumption of Bellman errors following the Gaussian distribution may oversimplify the nuanced characteristics of RL applications. In this work, we revisit the distribution of Bellman error in RL training, demonstrating that it tends to follow the Logistic distribution rather than the commonly assumed Normal distribution. We propose replacing MSELoss with a Logistic maximum likelihood function (LLoss) and rigorously test this hypothesis through extensive numerical experiments across diverse online and offline RL environments. Our findings consistently show that integrating the Logistic correction into the loss functions of various baseline RL methods leads to superior performance compared to their MSE counterparts. Additionally, we employ Kolmogorov-Smirnov tests to substantiate that the Logistic distribution offers a more accurate fit for approximating Bellman errors. This study also offers a novel theoretical contribution by establishing a clear connection between the distribution of Bellman error and the practice of proportional reward scaling, a common technique for performance enhancement in RL. Moreover, we explore the sample-accuracy trade-off involved in approximating the Logistic distribution, leveraging the Bias-Variance decomposition to mitigate excessive computational resources. The theoretical and empirical insights presented in this study lay a significant foundation for future research, potentially advancing methodologies, and understanding in RL, particularly in the distribution-based optimization of Bellman error.

SSTE: Syllable-Specific Temporal Encoding to FORCE-learn audio sequences with an associative memory approach

The circuitry and pathways in the brains of humans and other species have long inspired researchers and system designers to develop accurate and efficient systems capable of solving real-world problems and responding in real-time. We propose the Syllable-Specific Temporal Encoding (SSTE) to learn vocal sequences in a reservoir of Izhikevich neurons, by forming associations between exclusive input activities and their corresponding syllables in the sequence. Our model converts the audio signals to cochleograms using the CAR-FAC model to simulate a brain-like auditory learning and memorization process. The reservoir is trained using a hardware-friendly approach to FORCE learning. Reservoir computing could yield associative memory dynamics with far less computational complexity compared to RNNs. The SSTE-based learning enables competent accuracy and stable recall of spatiotemporal sequences with fewer reservoir inputs compared with existing encodings in the literature for similar purpose, offering resource savings. The encoding points to syllable onsets and allows recalling from a desired point in the sequence, making it particularly suitable for recalling subsets of long vocal sequences. The SSTE demonstrates the capability of learning new signals without forgetting previously memorized sequences and displays robustness against occasional noise, a characteristic of real-world scenarios. The components of this model are configured to improve resource consumption and computational intensity, addressing some of the cost-efficiency issues that might arise in future implementations aiming for compactness and real-time, low-power operation. Overall, this model proposes a brain-inspired pattern generation network for vocal sequences that can be extended with other bio-inspired computations to explore their potentials for brain-like auditory perception. Future designs could inspire from this model to implement embedded devices that learn vocal sequences and recall them as needed in real-time. Such systems could acquire language and speech, operate as artificial assistants, and transcribe text to speech, in the presence of natural noise and corruption on audio data.

A Forward Learning Algorithm for Neural Memory Ordinary Differential Equations

The deep neural network, based on the backpropagation learning algorithm, has achieved tremendous success. However, the backpropagation algorithm is consistently considered biologically implausible. Many efforts have recently been made to address these biological implausibility issues, nevertheless, these methods are tailored to discrete neural network structures. Continuous neural networks are crucial for investigating novel neural network models with more biologically dynamic characteristics and for interpretability of large language models. The neural memory ordinary differential equation (nmODE) is a recently proposed continuous neural network model that exhibits several intriguing properties. In this study, we present a forward-learning algorithm, called nmForwardLA, for nmODE. This algorithm boasts lower computational dimensions and greater efficiency. Compared with the other learning algorithms, experimental results on MNIST, CIFAR10, and CIFAR100 demonstrate its potency.

The perception of emotion in music by people with hearing loss and people with cochlear implants

Music is an important part of life for many people. It can evoke a wide range of emotions, including sadness, happiness, anger, tension, relief and excitement. People with hearing loss and people with cochlear implants have reduced abilities to discriminate some of the features of musical sounds that may be involved in evoking emotions. This paper reviews these changes in perceptual abilities and describes how they affect the perception of emotion in music. For people with acquired partial hearing loss, it appears that the perception of emotion in music is almost normal, whereas congenital partial hearing loss is associated with impaired perception of music emotion. For people with cochlear implants, the ability to discriminate changes in fundamental frequency (associated with perceived pitch) is much worse than normal and musical harmony is hardly perceived. As a result, people with cochlear implants appear to judge emotion in music primarily using tempo and rhythm cues, and this limits the range of emotions that can be judged. This article is part of the theme issue 'Sensing and feeling: an integrative approach to sensory processing and emotional experience'.

Sensing, feeling and consciousness

Living organisms achieve homeostasis by using distinct mechanisms tailored to their physiological complexity. Unicellular organisms as well as plants, which are devoid of nervous systems, rely on covert sensing/detecting and equally covert responding mechanisms. Organisms with nervous systems rely on overt consciousness which is based on homeostatic feelings and the experiences and consequent subjectivity they generate. This article is part of the theme issue 'Sensing and feeling: an integrative approach to sensory processing and emotional experience'.

A hybrid model for enhanced forecasting of PM2.5 spatiotemporal concentrations with high resolution and accuracy

Forecasting concentrations of PM2.5 is important due to its known impacts on public health and environment. However, PM2.5 concentrations can vary significantly over short distances and time, which can be influenced by local emissions and short-term weather patterns. This spatiotemporal variability makes accurate PM2.5 forecasting an inherently complex and challenging task. This study presented novel methodologies for short-term PM2.5 concentration forecast by combining the atmospheric chemistry transport model Community Multiscale Air Quality Modeling System (CMAQ) with data-driven machine learning methods, namely long short-term memory (LSTM) and random forest (RF) models. The combined model system forecast PM2.5 with 1 h, 1km × 1 km spatiotemporal resolution. The LSTM system forecast time-dependent PM2.5 concentrations at observation sites with a maximum root mean square error (RMSE) of 3.66 μg/m3 for 1-hr forecast and 23.75 μg/m3 for 72-hr forecast, leveraging results obtained from the atmospheric transport model with RMSE of 45.81 μg/m3. Wavelet transform in the LSTM system allowed learning and prediction of PM2.5 concentrations at different frequencies, capturing temporal variability of PM2.5 at various time scales. The RF model predicted distributions of PM2.5 concentrations by learning LSTM results and integrating crucial features such as CMAQ results, meteorological and topographical information. The feature significance of CMAQ results was the highest among the input features in RF models. Overall, the hybrid model could help with managing and mitigating the adverse effects of air pollution by enabling informed decision-making at the individual, community and policy levels.

Incorporation of water quality index models with machine learning-based techniques for real-time assessment of aquatic ecosystems

Water quality index (WQI) is a well-established tool for assessing the overall quality of fresh inland-waters. However, the effectiveness of real-time assessment of aquatic ecosystems using the WQI is usually impacted by the absence of some water quality parameters in which their accurately in-situ measurements are impossible and face difficulties. Using a rich water quality dataset spanned from 1980 to 2023, we employed four machine learning-based models to estimate the British Colombia WQI (BCWQI) in the Lake Päijänne, Finland, without parameters like chemical oxygen demand (COD) and total phosphorus (TP). Measurement of both COD and TP is time-consuming, needs laboratory equipment and labor costs, and faces sampling-related difficulties. Our results suggest the machine learning-based models successfully estimate the BCWQI in Lake Päijänne when TP and COD are omitted from the dataset. The long-short term memory model is the least sensitive model to exclusion of COD and TP from inputs. This model with the coefficient of determination and root-mean squared error of 0.91 and 0.11, respectively, outperforms the support vector regression, random forest, and neural network models in real-time estimation of the BCWQI in Lake Päijänne. Incorporation of BCWQI with the machine learning-based models could enhance assessment of overall quality of inland-waters with a limited database in a more economical and time-saving way. Our proposed method is an effort to replace the traditional offline water quality assessment tools with a real-time model and improve understanding of decision-makers on the effectiveness of management practices on the changes in lake water quality.

Recent advances in algal bloom detection and prediction technology using machine learning

Harmful algal blooms (HAB) including red tides and cyanobacteria are a significant environmental issue that can have harmful effects on aquatic ecosystems and human health. Traditional methods of detecting and managing algal blooms have been limited by their reliance on manual observation and analysis, which can be time-consuming and costly. Recent advances in machine learning (ML) technology have shown promise in improving the accuracy and efficiency of algal bloom detection and prediction. This paper provides an overview of the latest developments in using ML for algal bloom detection and prediction using various water quality parameters and environmental factors. First, we introduced ML for algal bloom prediction using regression and classification models. Then we explored image-based ML for algae detection by utilizing satellite images, surveillance cameras, and microscopic images. This study also highlights several real-world examples of successful implementation of ML for algal bloom detection and prediction. These examples show how ML can enhance the accuracy and efficiency of detecting and predicting algal blooms, contributing to the protection of aquatic ecosystems and human health. The study also outlines recent efforts to enhance the field applicability of ML models and suggests future research directions. A recent interest in explainable artificial intelligence (XAI) was discussed in an effort to understand the most influencing environmental factors on algal blooms. XAI facilitates interpretations of ML model results, thereby enhancing the models' usability for decision-making in field management and improving their overall applicability in real-world settings. We also emphasize the significance of obtaining high-quality, field-representative data to enhance the efficiency of ML applications. The effectiveness of ML models in detecting and predicting algal blooms can be improved through management strategies for data quality, such as pre-treating missing data and integrating diverse datasets into a unified database. Overall, this paper presents a comprehensive review of the latest advancements in managing algal blooms using ML technology and proposes future research directions to enhance the utilization of ML techniques.

Frontal Norepinephrine Represents a Threat Prediction Error Under Uncertainty

BACKGROUND

To adapt to threats in the environment, animals must predict them and engage in defensive behavior. While the representation of a prediction error signal for reward has been linked to dopamine, a neuromodulatory prediction error for aversive learning has not been identified.

METHODS

We measured and manipulated norepinephrine release during threat learning using optogenetics and a novel fluorescent norepinephrine sensor.

RESULTS

We found that norepinephrine response to conditioned stimuli reflects aversive memory strength. When delays between auditory stimuli and footshock are introduced, norepinephrine acts as a prediction error signal. However, temporal difference prediction errors do not fully explain norepinephrine dynamics. To explain noradrenergic signaling, we used an updated reinforcement learning model with uncertainty about time and found that it explained norepinephrine dynamics across learning and variations in temporal and auditory task structure.

CONCLUSIONS

Norepinephrine thus combines cognitive and affective information into a predictive signal and links time with the anticipation of danger.

Information consumption city and carbon emission efficiency: Evidence from China's quasi-natural experiment

The transformation of public consumption patterns has become a burning question, but there are few studies on public consumption patterns. Therefore, evaluating the impact of Information consumption city (ICC) policy on carbon emission efficiency holds significant implications. This study settles on 104 pilot cities in China from 2006 to 2020 to assess the impact and the response mechanism of ICC policy on carbon emission efficiency through the time-vary Difference-in-Difference (DID) model. The result shows that: (1) ICC policy significantly promotes the local carbon emission efficiency, which remains robust after a battery of sensitivity tests. (2) It improves carbon emission efficiency through production factors agglomeration effect, industrial structural changing effect, innovation promotion effect, and environmental attention effect; (3) The direct impact of ICC policy on carbon emission efficiency varies across regions with different information consumption and carbon emission base. (4) ICC can improve carbon emission efficiency through the joint implementation of smart city (SC), new urbanization (NU), ecological civilization city construction (EC), Belt and Road Initiative (BR), Broadband China (BC), low-carbon city pilot policy (LCC), and air quality standards (AQS) policy.

Biological computations: Limitations of attractor-based formalisms and the need for transients

Living systems, from single cells to higher vertebrates, receive a continuous stream of non-stationary inputs that they sense, for e.g. via cell surface receptors or sensory organs. By integrating these time-varying, multi-sensory, and often noisy information with memory using complex molecular or neuronal networks, they generate a variety of responses beyond simple stimulus-response association, including avoidance behavior, life-long-learning or social interactions. In a broad sense, these processes can be understood as a type of biological computation. Taking as a basis generic features of biological computations, such as real-time responsiveness or robustness and flexibility of the computation, we highlight the limitations of the current attractor-based framework for understanding computations in biological systems. We argue that frameworks based on transient dynamics away from attractors are better suited for the description of computations performed by neuronal and signaling networks. In particular, we discuss how quasi-stable transient dynamics from ghost states that emerge at criticality have a promising potential for developing an integrated framework of computations, that can help us understand how living system actively process information and learn from their continuously changing environment.

Machine learning for accuracy in density functional approximations

Machine learning techniques have found their way into computational chemistry as indispensable tools to accelerate atomistic simulations and materials design. In addition, machine learning approaches hold the potential to boost the predictive power of computationally efficient electronic structure methods, such as density functional theory, to chemical accuracy and to correct for fundamental errors in density functional approaches. Here, recent progress in applying machine learning to improve the accuracy of density functional and related approximations is reviewed. Promises and challenges in devising machine learning models transferable between different chemistries and materials classes are discussed with the help of examples applying promising models to systems far outside their training sets.

Using artificial intelligence to rapidly identify microplastics pollution and predict microplastics environmental behaviors

With the massive release of microplastics (MPs) into the environment, research related to MPs is advancing rapidly. Effective research methods are necessary to identify the chemical composition, shape, distribution, and environmental impacts of MPs. In recent years, artificial intelligence (AI)-driven machine learning methods have demonstrated excellent performance in analyzing MPs in soil and water. This review provides a comprehensive overview of machine learning methods for the prediction of MPs for various tasks, and discusses in detail the data source, data preprocessing, algorithm principle, and algorithm limitation of applied machine learning. In addition, this review discusses the limitation of current machine learning methods for various task analysis in MPs along with future prospect. Finally, this review finds research potential in future work in building large generalized MPs datasets, designing high-performance but low-computational-complexity algorithms, and evaluating model interpretability.

Score-based generative model-assisted information compensation for high-quality limited-view reconstruction in photoacoustic tomography

Photoacoustic tomography (PAT) regularly operates in limited-view cases owing to data acquisition limitations. The results using traditional methods in limited-view PAT exhibit distortions and numerous artifacts. Here, a novel limited-view PAT reconstruction strategy that combines model-based iteration with score-based generative model was proposed. By incrementally adding noise to the training samples, prior knowledge can be learned from the complex probability distribution. The acquired prior is then utilized as constraint in model-based iteration. The information of missing views can be gradually compensated by cyclic iteration to achieve high-quality reconstruction. The performance of the proposed method was evaluated with the circular phantom and in vivo experimental data. Experimental results demonstrate the outstanding effectiveness of the proposed method in limited-view cases. Notably, the proposed method exhibits excellent performance in limited-view case of 70° compared with traditional method. It achieves a remarkable improvement of 203% in PSNR and 48% in SSIM for the circular phantom experimental data, and an enhancement of 81% in PSNR and 65% in SSIM for in vivo experimental data, respectively. The proposed method has capability of reconstructing PAT images in extremely limited-view cases, which will further expand the application in clinical scenarios.

Bridging flexible goal-directed cognition and consciousness: The Goal-Aligning Representation Internal Manipulation theory

Goal-directed manipulation of internal representations is a key element of human flexible behaviour, while consciousness is commonly associated with higher-order cognition and human flexibility. Current perspectives have only partially linked these processes, thus preventing a clear understanding of how they jointly generate flexible cognition and behaviour. Moreover, these limitations prevent an effective exploitation of this knowledge for technological scopes. We propose a new theoretical perspective that extends our 'three-component theory of flexible cognition' toward higher-order cognition and consciousness, based on the systematic integration of key concepts from Cognitive Neuroscience and AI/Robotics. The theory proposes that the function of conscious processes is to support the alignment of representations with multi-level goals. This higher alignment leads to more flexible and effective behaviours. We analyse here our previous model of goal-directed flexible cognition (validated with more than 20 human populations) as a starting GARIM-inspired model. By bridging the main theories of consciousness and goal-directed behaviour, the theory has relevant implications for scientific and technological fields. In particular, it contributes to developing new experimental tasks and interpreting clinical evidence. Finally, it indicates directions for improving machine learning and robotics systems and for informing real-world applications (e.g., in digital-twin healthcare and roboethics).

TGIN: Document-level event extraction with two-phase graph inference network

Document-level event extraction aims to extract event records from a whole document that contain numerous entities scattered across multiple sentences. Efficiently modeling the interactions among these entities is crucial. However, previous methods suffer from two main shortcomings. Firstly, they tend to implicitly model key information, which can result in representations with higher levels of noise. Secondly, they excessively consider irrelevant entities, thereby reducing extraction efficiency and precision. To address these issues, we propose a novel Two-phase Graph Inference Network (TGIN) approach for extracting document-level events. In the first phase, TGIN constructs a heterogeneous document-level graph to capture complex interactions among nodes of different granularity, enabling the acquisition of document-aware features. Subsequently, a dedicated module is developed to extract relevant entity pairs within the same event record. This module utilizes a key information aggregator with an attention mechanism to explicitly aggregate key sentences for entity pairs. In the second phase, the entity links predicted in the first phase serve as prior information to construct the entity-level graph, which focuses on modeling interactions between entity pairs that potentially share the same event link, effectively reducing error propagation. Experimental results on the publicly available document-level event extraction dataset ChFinAnn demonstrate the superiority of our framework over most existing models.

Robust Visual Question Answering: Datasets, Methods, and Future Challenges

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often tend to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Third, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints.

The dynamic-static dual-branch deep neural network for urban speeding hotspot identification using street view image data

The visual information regarding the road environment can influence drivers' perception and judgment, often resulting in frequent speeding incidents. Identifying speeding hotspots in cities can prevent potential speeding incidents, thereby improving traffic safety levels. We propose the Dual-Branch Contextual Dynamic-Static Feature Fusion Network based on static panoramic images and dynamically changing sequence data, aiming to capture global features in the macro scene of the area and dynamically changing information in the micro view for a more accurate urban speeding hotspot area identification. For the static branch, we propose the Multi-scale Contextual Feature Aggregation Network for learning global spatial contextual association information. In the dynamic branch, we construct the Multi-view Dynamic Feature Fusion Network to capture the dynamically changing features of a scene from a continuous sequence of street view images. Additionally, we designed the Dynamic-Static Feature Correlation Fusion Structure to correlate and fuse dynamic and static features. The experimental results show that the model has good performance, and the overall recognition accuracy reaches 99.4%. The ablation experiments show that the recognition effect after the fusion of dynamic and static features is better than that of static and dynamic branches. The proposed model also shows better performance than other deep learning models. In addition, we combine image processing methods and different Class Activation Mapping (CAM) methods to extract speeding frequency visual features from the model perception results. The results show that more accurate speeding frequency features can be obtained by using LayerCAM and GradCAM-Plus for static global scenes and dynamic local sequences, respectively. In the static global scene, the speeding frequency features are mainly concentrated on the buildings and green layout on both sides of the road, while in the dynamic scene, the speeding frequency features shift with the scene changes and are mainly concentrated on the dynamically changing transition areas of greenery, roads, and surrounding buildings. The code and model used for identifying hotspots of urban traffic accidents in this study are available for access: https://github.com/gwt-ZJU/DCDSFF-Net.

SEGAL time series classification - Stable explanations using a generative model and an adaptive weighting method for LIME

Local Interpretability Model-agnostic Explanations (LIME) is a well-known post-hoc technique for explaining black-box models. While very useful, recent research highlights challenges around the explanations generated. In particular, there is a potential lack of stability, where the explanations provided vary over repeated runs of the algorithm, casting doubt on their reliability. This paper investigates the stability of LIME when applied to multivariate time series classification. We demonstrate that the traditional methods for generating neighbours used in LIME carry a high risk of creating 'fake' neighbours, which are out-of-distribution in respect to the trained model and far away from the input to be explained. This risk is particularly pronounced for time series data because of their substantial temporal dependencies. We discuss how these out-of-distribution neighbours contribute to unstable explanations. Furthermore, LIME weights neighbours based on user-defined hyperparameters which are problem-dependent and hard to tune. We show how unsuitable hyperparameters can impact the stability of explanations. We propose a two-fold approach to address these issues. First, a generative model is employed to approximate the distribution of the training data set, from which within-distribution samples and thus meaningful neighbours can be created for LIME. Second, an adaptive weighting method is designed in which the hyperparameters are easier to tune than those of the traditional method. Experiments on real-world data sets demonstrate the effectiveness of the proposed method in providing more stable explanations using the LIME framework. In addition, in-depth discussions are provided on the reasons behind these results.

PT-KGNN: A framework for pre-training biomedical knowledge graphs with graph neural networks

Biomedical knowledge graphs (KGs) serve as comprehensive data repositories that contain rich information about nodes and edges, providing modeling capabilities for complex relationships among biological entities. Many approaches either learn node features through traditional machine learning methods, or leverage graph neural networks (GNNs) to directly learn features of target nodes in the biomedical KGs and utilize them for downstream tasks. Motivated by the pre-training technique in natural language processing (NLP), we propose a framework named PT-KGNN (Pre-Training the biomedical KG with GNNs) to learn embeddings of nodes in a broader context by applying GNNs on the biomedical KG. We design several experiments to evaluate the effectivity of our proposed framework and the impact of the scale of KGs. The results of tasks consistently improve as the scale of the biomedical KG used for pre-training increases. Pre-training on large-scale biomedical KGs significantly enhances the drug-drug interaction (DDI) and drug-disease association (DDA) prediction performance on the independent dataset. The embeddings derived from a larger biomedical KG have demonstrated superior performance compared to those obtained from a smaller KG. By applying pre-training techniques on biomedical KGs, rich semantic and structural information can be learned, leading to enhanced performance on downstream tasks. it is evident that pre-training techniques hold tremendous potential and wide-ranging applications in bioinformatics.

Variational image registration with learned prior using multi-stage VAEs

Variational Autoencoders (VAEs) are an efficient variational inference technique coupled with the generated network. Due to the uncertainty provided by variational inference, VAEs have been applied in medical image registration. However, a critical problem in VAEs is that the simple prior cannot provide suitable regularization, which leads to the mismatch between the variational posterior and prior. An optimal prior can close the gap between the evidence's real and variational posterior. In this paper, we propose a multi-stage VAE to learn the optimal prior, which is the aggregated posterior. A lightweight VAE is used to generate the aggregated posterior as a whole. It is an effective way to estimate the distribution of the high-dimensional aggregated posterior that commonly exists in medical image registration based on VAEs. A factorized telescoping classifier is trained to estimate the density ratio of a simple given prior and aggregated posterior, aiming to calculate the KL divergence between the variational and aggregated posterior more accurately. We analyze the KL divergence and find that the finer the factorization, the smaller the KL divergence is. However, too fine a partition is not conducive to registration accuracy. Moreover, the diagonal hypothesis of the variational posterior's covariance ignores the relationship between latent variables in image registration. To address this issue, we learn a covariance matrix with low-rank information to enable correlations with each dimension of the variational posterior. The covariance matrix is further used as a measure to reduce the uncertainty of deformation fields. Experimental results on four public medical image datasets demonstrate that our proposed method outperforms other methods in negative log-likelihood (NLL) and achieves better registration accuracy.

Brain Networks, Neurotransmitters and Psychedelics: Towards a Neurochemistry of Self-Awareness

PURPOSE OF REVIEW

Self-awareness can be defined as the capacity of becoming the object of one's own awareness and, increasingly, it has been the target of scientific inquiry. Self-awareness has important clinical implications, and a better understanding of the neurochemical basis of self-awareness may help clarifying causes and developing interventions for different psychopathological conditions. The current article explores the relationship between neurochemistry and self-awareness, with special attention to the effects of psychedelics.

RECENT FINDINGS

The functioning of self-related networks, such as the default-mode network and the salience network, and how these are influenced by different neurotransmitters is discussed. The impact of psychedelics on self-awareness is reviewed in relation to specific processes, such as interoception, body ownership, agency, metacognition, emotional regulation and autobiographical memory, within a framework based on predictive coding. Improved outcomes in emotional regulation and autobiographical memory have been observed in association with the use of psychedelics, suggesting higher-order self-awareness changes, which can be modulated by relaxation of priors and improved coping mechanisms linked to cognitive flexibility. Alterations in bodily self-awareness are less consistent, being potentially impacted by doses employed, differences in acute/long-term effects and the presence of clinical conditions. Future studies investigating the effects of different molecules in rebalancing connectivity between resting-state networks may lead to novel therapeutic approaches and the refinement of existing treatments.

Astrocyte modulation in cerebral ischemia-reperfusion injury: A promising therapeutic strategy

Cerebral ischemia-reperfusion injury (CIRI) poses significant challenges for drug development due to its complex pathogenesis. Astrocyte involvement in CIRI pathogenesis has led to the development of novel astrocyte-targeting drug strategies. To comprehensively review the current literature, we conducted a thorough analysis from January 2012 to December 2023, identifying 82 drugs aimed at preventing and treating CIRI. These drugs target astrocytes to exert potential benefits in CIRI, and their primary actions include modulation of relevant signaling pathways to inhibit neuroinflammation and oxidative stress, reduce cerebral edema, restore blood-brain barrier integrity, suppress excitotoxicity, and regulate autophagy. Notably, active components from traditional Chinese medicines (TCM) such as Salvia miltiorrhiza, Ginkgo, and Ginseng exhibit these important pharmacological properties and show promise in the treatment of CIRI. This review highlights the potential of astrocyte-targeted drugs to ameliorate CIRI and categorizes them based on their mechanisms of action, underscoring their therapeutic potential in targeting astrocytes.

A landscape of consciousness: Toward a taxonomy of explanations and implications

Diverse explanations or theories of consciousness are arrayed on a roughly physicalist-to-nonphysicalist landscape of essences and mechanisms. Categories: Materialism Theories (philosophical, neurobiological, electromagnetic field, computational and informational, homeostatic and affective, embodied and enactive, relational, representational, language, phylogenetic evolution); Non-Reductive Physicalism; Quantum Theories; Integrated Information Theory; Panpsychisms; Monisms; Dualisms; Idealisms; Anomalous and Altered States Theories; Challenge Theories. There are many subcategories, especially for Materialism Theories. Each explanation is self-described by its adherents, critique is minimal and only for clarification, and there is no attempt to adjudicate among theories. The implications of consciousness explanations or theories are assessed with respect to four questions: meaning/purpose/value (if any); AI consciousness; virtual immortality; and survival beyond death. A Landscape of Consciousness, I suggest, offers perspective.

Blocked versus interleaved: How range contexts modulate time perception and its EEG signatures

Accurate time perception is a crucial element in a wide range of cognitive tasks, including decision-making, memory, and motor control. One commonly observed phenomenon is that when given a range of time intervals to consider, people's estimates often cluster around the midpoint of those intervals. Previous studies have suggested that the range of these intervals can also influence our judgments, but the neural mechanisms behind this "range effect" are not yet understood. We used both behavioral tests and electroencephalographic (EEG) measures to understand how the range of sample time intervals affects the accuracy of people's subsequent time estimates. Study participants were exposed to two different setups: In the "blocked-range" (BR) session, short and long intervals were presented in separate blocks, whereas in the "interleaved-range" (IR) session, intervals of various lengths were presented randomly. Our findings indicated that the BR context led to more accurate time estimates compared to the IR context. In terms of EEG data, the BR context resulted in quicker buildup of contingent negative variation (CNV), which also reached higher amplitude levels and dissolved more rapidly during the encoding stage. We also observed an enhanced amplitude in the offset P2 component of the EEG signal. Overall, our results suggest that the variability in time intervals, as defined by their range, influences the neural processes that underlie time estimation.

The neuroscience of active learning and direct instruction

Throughout the educational system, students experiencing active learning pedagogy perform better and fail less than those taught through direct instruction. Can this be ascribed to differences in learning from a neuroscientific perspective? This review examines mechanistic, neuroscientific evidence that might explain differences in cognitive engagement contributing to learning outcomes between these instructional approaches. In classrooms, direct instruction comprehensively describes academic content, while active learning provides structured opportunities for learners to explore, apply, and manipulate content. Synaptic plasticity and its modulation by arousal or novelty are central to all learning and both approaches. As a form of social learning, direct instruction relies upon working memory. The reinforcement learning circuit, associated agency, curiosity, and peer-to-peer social interactions combine to enhance motivation, improve retention, and build higher-order-thinking skills in active learning environments. When working memory becomes overwhelmed, additionally engaging the reinforcement learning circuit improves retention, providing an explanation for the benefits of active learning. This analysis provides a mechanistic examination of how emerging neuroscience principles might inform pedagogical choices at all educational levels.

Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping

Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and t-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as data-driven native mapping (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; P < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; P = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (R2 = 0.71 for native T1 maps vs LGE; R2 = 0.85 for DNM vs LGE; P < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. Keywords: Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping Supplemental material is available for this article. © RSNA, 2024.