FM-FCN: A Neural Network with Filtering Modules for Accurate Vital Signs Extraction.

Neural networks excel at capturing local spatial patterns through convolutional modules, but they may struggle to identify and effectively utilize the morphological and amplitude periodic nature of physiological signals. In this work, we propose a novel network named filtering module fully convolutional network (FM-FCN), which fuses traditional filtering techniques with neural networks to amplify physiological signals and suppress noise. First, instead of using a fully connected layer, we use an FCN to preserve the time-dimensional correlation information of physiological signals, enabling multiple cycles of signals in the network and providing a basis for signal processing. Second, we introduce the FM as a network module that adapts to eliminate unwanted interference, leveraging the structure of the filter. This approach builds a bridge between deep learning and signal processing methodologies. Finally, we evaluate the performance of FM-FCN using remote photoplethysmography. Experimental results demonstrate that FM-FCN outperforms the second-ranked method in terms of both blood volume pulse (BVP) signal and heart rate (HR) accuracy. It substantially improves the quality of BVP waveform reconstruction, with a decrease of 20.23% in mean absolute error (MAE) and an increase of 79.95% in signal-to-noise ratio (SNR). Regarding HR estimation accuracy, FM-FCN achieves a decrease of 35.85% in MAE, 29.65% in error standard deviation, and 32.88% decrease in 95% limits of agreement width, meeting clinical standards for HR accuracy requirements. The results highlight its potential in improving the accuracy and reliability of vital sign measurement through high-quality BVP signal extraction. The codes and datasets are available online at https://github.com/zhaoqi106/FM-FCN.

Emulation and evaluation of tumor cell combined chemotherapy in isotropic/anisotropic collagen fiber microenvironments.

The rapid emergence of anisotropic collagen fibers in the tissue microenvironment is a critical transition point in late-stage breast cancer. Specifically, the fiber orientation facilitates the likelihood of high-speed tumor cell invasion and metastasis, which pose lethal threats to patients. Thus, based on this transition point, one key issue is how to determine and evaluate efficient combination chemotherapy treatments in late-stage cancer. In this study, we designed a collagen microarray chip containing 241 high-throughput microchambers with embedded metastatic breast cancer cell MDA-MB-231-RFP. By utilizing collagen's unique structure and hydromechanical properties, the chip constructed three-dimensional isotropic and anisotropic collagen fiber structures to emulate the tumor cell microenvironment at early and late stages. We injected different chemotherapeutic drugs into its four channels and obtained composite biochemical concentration profiles. Our results demonstrate that anisotropic collagen fibers promote cell proliferation and migration more than isotropic collagen fibers, suggesting that the geometric arrangement of fibers plays an important role in regulating cell behavior. Moreover, the presence of anisotropic collagen fibers may be a potential factor leading to the poor efficacy of combined chemotherapy in late-stage breast cancer. We investigated the efficacy of various chemotherapy drugs using cell proliferation inhibitors paclitaxel and gemcitabine and tumor cell migration inhibitors 7rh and PP2. To ensure the validity of our findings, we followed a systematic approach that involved testing the inhibitory effects of these drugs. According to our results, the drug combinations' effectiveness could be ordered as follows: paclitaxel + gemcitabine > gemcitabine + 7rh > PP2 + paclitaxel > 7rh + PP2. This study shows that the biomimetic chip system not only facilitates the creation of a realistic in vitro model for examining the cell migration mechanism in late-stage breast cancer but also has the potential to function as an effective tool for future chemotherapy assessment and personalized medicine.

SCTC: inference of developmental potential from single-cell transcriptional complexity.

Inferring the developmental potential of single cells from scRNA-Seq data and reconstructing the pseudo-temporal path of cell development are fundamental but challenging tasks in single-cell analysis. Although single-cell transcriptional diversity (SCTD) measured by the number of expressed genes per cell has been widely used as a hallmark of developmental potential, it may lead to incorrect estimation of differentiation states in some cases where gene expression does not decrease monotonously during the development process. In this study, we propose a novel metric called single-cell transcriptional complexity (SCTC), which draws on insights from the economic complexity theory and takes into account the sophisticated structure information of scRNA-Seq count matrix. We show that SCTC characterizes developmental potential more accurately than SCTD, especially in the early stages of development where cells typically have lower diversity but higher complexity than those in the later stages. Based on the SCTC, we provide an unsupervised method for accurate, robust, and transferable inference of single-cell pseudotime. Our findings suggest that the complexity emerging from the interplay between cells and genes determines the developmental potential, providing new insights into the understanding of biological development from the perspective of complexity theory.

DP-GAN+B: A lightweight generative adversarial network based on depthwise separable convolutions for generating CT volumes.

X-rays, commonly used in clinical settings, offer advantages such as low radiation and cost-efficiency. However, their limitation lies in the inability to distinctly visualize overlapping organs. In contrast, Computed Tomography (CT) scans provide a three-dimensional view, overcoming this drawback but at the expense of higher radiation doses and increased costs. Hence, from both the patient's and hospital's standpoints, there is substantial medical and practical value in attempting the reconstruction from two-dimensional X-ray images to three-dimensional CT images. In this paper, we introduce DP-GAN+B as a pioneering approach for transforming two-dimensional frontal and lateral lung X-rays into three-dimensional lung CT volumes. Our method innovatively employs depthwise separable convolutions instead of traditional convolutions and introduces vector and fusion loss for superior performance. Compared to prior models, DP-GAN+B significantly reduces the generator network parameters by 21.104 M and the discriminator network parameters by 10.82 M, resulting in a total reduction of 31.924 M (44.17%). Experimental results demonstrate that our network can effectively generate clinically relevant, high-quality CT images from X-ray data, presenting a promising solution for enhancing diagnostic imaging while mitigating cost and radiation concerns.

Morphological entropy encodes cellular migration strategies on multiple length scales.

Cell migration is crucial for numerous physiological and pathological processes. A cell adapts its morphology, including the overall and nuclear morphology, in response to various cues in complex microenvironments, such as topotaxis and chemotaxis during migration. Thus, the dynamics of cellular morphology can encode migration strategies, from which diverse migration mechanisms can be inferred. However, deciphering the mechanisms behind cell migration encoded in morphology dynamics remains a challenging problem. Here, we present a powerful universal metric, the Cell Morphological Entropy (CME), developed by combining parametric morphological analysis with Shannon entropy. The utility of CME, which accurately quantifies the complex cellular morphology at multiple length scales through the deviation from a perfectly circular shape, is illustrated using a variety of normal and tumor cell lines in different in vitro microenvironments. Our results show how geometric constraints affect the MDA-MB-231 cell nucleus, the emerging interactions of MCF-10A cells migrating on collagen gel, and the critical transition from proliferation to invasion in tumor spheroids. The analysis demonstrates that the CME-based approach provides an effective and physically interpretable tool to measure morphology in real-time across multiple length scales. It provides deeper insight into cell migration and contributes to the understanding of different behavioral modes and collective cell motility in more complex microenvironments.

SeFilter-DIA: Squeeze-and-Excitation Network for Filtering High-Confidence Peptides of Data-Independent Acquisition Proteomics.

Mass spectrometry is crucial in proteomics analysis, particularly using Data Independent Acquisition (DIA) for reliable and reproducible mass spectrometry data acquisition, enabling broad mass-to-charge ratio coverage and high throughput. DIA-NN, a prominent deep learning software in DIA proteome analysis, generates peptide results but may include low-confidence peptides. Conventionally, biologists have to manually screen peptide fragment ion chromatogram peaks (XIC) for identifying high-confidence peptides, a time-consuming and subjective process prone to variability. In this study, we introduce SeFilter-DIA, a deep learning algorithm, aiming at automating the identification of high-confidence peptides. Leveraging compressed excitation neural network and residual network models, SeFilter-DIA extracts XIC features and effectively discerns between high and low-confidence peptides. Evaluation of the benchmark datasets demonstrates SeFilter-DIA achieving 99.6% AUC on the test set and 97% for other performance indicators. Furthermore, SeFilter-DIA is applicable for screening peptides with phosphorylation modifications. These results demonstrate the potential of SeFilter-DIA to replace manual screening, providing an efficient and objective approach for high-confidence peptide identification while mitigating associated limitations.

scGIR: deciphering cellular heterogeneity via gene ranking in single-cell weighted gene correlation networks.

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for investigating cellular heterogeneity through high-throughput analysis of individual cells. Nevertheless, challenges arise from prevalent sequencing dropout events and noise effects, impacting subsequent analyses. Here, we introduce a novel algorithm, Single-cell Gene Importance Ranking (scGIR), which utilizes a single-cell gene correlation network to evaluate gene importance. The algorithm transforms single-cell sequencing data into a robust gene correlation network through statistical independence, with correlation edges weighted by gene expression levels. We then constructed a random walk model on the resulting weighted gene correlation network to rank the importance of genes. Our analysis of gene importance using PageRank algorithm across nine authentic scRNA-seq datasets indicates that scGIR can effectively surmount technical noise, enabling the identification of cell types and inference of developmental trajectories. We demonstrated that the edges of gene correlation, weighted by expression, play a critical role in enhancing the algorithm's performance. Our findings emphasize that scGIR outperforms in enhancing the clustering of cell subtypes, reverse identifying differentially expressed marker genes, and uncovering genes with potential differential importance. Overall, we proposed a promising method capable of extracting more information from single-cell RNA sequencing datasets, potentially shedding new lights on cellular processes and disease mechanisms.

YTHDF1-CLOCK axis contributes to pathogenesis of allergic airway inflammation through LLPS.

N6-methyladenosine (m6A) modification has been implicated in many cell processes and diseases. YTHDF1, a translation-facilitating m6A reader, has not been previously shown to be related to allergic airway inflammation. Here, we report that YTHDF1 is highly expressed in allergic airway epithelial cells and asthmatic patients and that it influences proinflammatory responses. CLOCK, a subunit of the circadian clock pathway, is the direct target of YTHDF1. YTHDF1 augments CLOCK translation in an m6A-dependent manner. Allergens enhance the liquid-liquid phase separation (LLPS) of YTHDF1 and drive the formation of a complex comprising dimeric YTHDF1 and CLOCK mRNA, which is distributed to stress granules. Moreover, YTHDF1 strongly activates NLRP3 inflammasome production and interleukin-1ß secretion leading to airway inflammatory responses, but these phenotypes are abolished by deleting CLOCK. These findings demonstrate that YTHDF1 is an important regulator of asthmatic airway inflammation, suggesting a potential therapeutic target for allergic airway inflammation.

An entropy-based approach for assessing the directional persistence of cell migration.

Cell migration, which is primarily characterized by directional persistence, is essential for the development of normal tissues and organs, as well as for numerous pathological processes. However, there is a lack of simple and efficient tools to analyze the systematic properties of persistence based on cellular trajectory data. Here, we present a novel approach, the entropy of angular distribution , which combines cellular turning dynamics and Shannon entropy to explore the statistical and time-varying properties of persistence that strongly correlate with cellular migration modes. Our results reveal the changes in the persistence of multiple cell lines that are tightly regulated by both intra- and extracellular cues, including Arpin protein, collagen gel/substrate, and physical constraints. Significantly, some previously unreported distinctive details of persistence have also been captured, helping to elucidate how directional persistence is distributed and evolves in different cell populations. The analysis suggests that the entropy of angular distribution-based approach provides a powerful metric for evaluating directional persistence and enables us to better understand the relationships between cellular behaviors and multiscale cues, which also provides some insights into the migration dynamics of cell populations, such as collective cell invasion.

MEAs-Filter: a novel filter framework utilizing evolutionary algorithms for cardiovascular diseases diagnosis.

Cardiovascular disease management often involves adjusting medication dosage based on changes in electrocardiogram (ECG) signals' waveform and rhythm. However, the diagnostic utility of ECG signals is often hindered by various types of noise interference. In this work, we propose a novel filter based on a multi-engine evolution framework named MEAs-Filter to address this issue. Our approach eliminates the need for predefined dimensions and allows adaptation to diverse ECG morphologies. By leveraging state-of-the-art optimization algorithms as evolution engine and incorporating prior information inputs from classical filters, MEAs-Filter achieves superior performance while minimizing order. We evaluate the effectiveness of MEAs-Filter on a real ECG database and compare it against commonly used filters such as the Butterworth, Chebyshev filters, and evolution algorithm-based (EA-based) filters. The experimental results indicate that MEAs-Filter outperforms other filters by achieving a reduction of approximately 30% to 60% in terms of the loss function compared to the other algorithms. In denoising experiments conducted on ECG waveforms across various scenarios, MEAs-Filter demonstrates an improvement of approximately 20% in signal-to-noise (SNR) ratio and a 9% improvement in correlation. Moreover, it does not exhibit higher losses of the R-wave compared to other filters. These findings highlight the potential of MEAs-Filter as a valuable tool for high-fidelity extraction of ECG signals, enabling accurate diagnosis in the field of cardiovascular diseases.

AttnPep: A Self-Attention-Based Deep Learning Method for Peptide Identification in Shotgun Proteomics.

In shotgun proteomics, the proteome search engine analyzes mass spectra obtained by experiments, and then a peptide-spectra match (PSM) is reported for each spectrum. However, most of the PSMs identified are incorrect, and therefore various postprocessing software have been developed for reranking the peptide identifications. Yet these methods suffer from issues such as dependency on distribution, reliance on shallow models, and limited effectiveness. In this work, we propose AttnPep, a deep learning model for rescoring PSM scores that utilizes the Self-Attention module. This module helps the neural network focus on features relevant to the classification of PSMs and ignore irrelevant features. This allows AttnPep to analyze the output of different search engines and improve PSM discrimination accuracy. We considered a PSM to be correct if it achieves a q-value <0.01 and compared AttnPep with existing mainstream software PeptideProphet, Percolator, and proteoTorch. The results indicated that AttnPep found an average increase in correct PSMs of 9.29% relative to the other methods. Additionally, AttnPep was able to better distinguish between correct and incorrect PSMs and found more synthetic peptides in the complex SWATH data set.

SUnet: A multi-organ segmentation network based on multiple attention.

Organ segmentation in abdominal or thoracic computed tomography (CT) images plays a crucial role in medical diagnosis as it enables doctors to locate and evaluate organ abnormalities quickly, thereby guiding surgical planning, and aiding treatment decision-making. This paper proposes a novel and efficient medical image segmentation method called SUnet for multi-organ segmentation in the abdomen and thorax. SUnet is a fully attention-based neural network. Firstly, an efficient spatial reduction attention (ESRA) module is introduced not only to extract image features better, but also to reduce overall model parameters, and to alleviate overfitting. Secondly, SUnet's multiple attention-based feature fusion module enables effective cross-scale feature integration. Additionally, an enhanced attention gate (EAG) module is considered by using grouped convolution and residual connections, providing richer semantic features. We evaluate the performance of the proposed model on synapse multiple organ segmentation dataset and automated cardiac diagnostic challenge dataset. SUnet achieves an average Dice of 84.29% and 92.25% on these two datasets, respectively, outperforming other models of similar complexity and size, and achieving state-of-the-art results.

Polygenic regression uncovers trait-relevant cellular contexts through pathway activation transformation of single-cell RNA sequencing data.

Advances in single-cell RNA sequencing (scRNA-seq) techniques have accelerated functional interpretation of disease-associated variants discovered from genome-wide association studies (GWASs). However, identification of trait-relevant cell populations is often impeded by inherent technical noise and high sparsity in scRNA-seq data. Here, we developed scPagwas, a computational approach that uncovers trait-relevant cellular context by integrating pathway activation transformation of scRNA-seq data and GWAS summary statistics. scPagwas effectively prioritizes trait-relevant genes, which facilitates identification of trait-relevant cell types/populations with high accuracy in extensive simulated and real datasets. Cellular-level association results identified a novel subpopulation of naive CD8+ T cells related to COVID-19 severity and oligodendrocyte progenitor cell and microglia subsets with critical pathways by which genetic variants influence Alzheimer's disease. Overall, our approach provides new insights for the discovery of trait-relevant cell types and improves the mechanistic understanding of disease variants from a pathway perspective.

A physical understanding and quantification for the regulation of orexin on sleep.

The orexinergic neurons located in the lateral hypothalamus play a vital role in maintaining wakefulness and regulating sleep stability. Previous research has demonstrated that the absence of orexin (Orx) can trigger narcolepsy, a condition characterized by frequent shifts between wakefulness and sleep. However, the specific mechanisms and temporal patterns through which Orx regulates wakefulness/sleep are not fully understood. In this study, we developed a new model that combines the classical Phillips-Robinson sleep model with the Orx network. Our model incorporates a recently discovered indirect inhibition of Orx on sleep-promoting neurons in the ventrolateral preoptic nucleus. By integrating appropriate physiological parameters, our model successfully replicated the dynamic behavior of normal sleep under the influence of circadian drive and homeostatic processes. Furthermore, our results from the new sleep model unveiled two distinct effects of Orx: excitation of wake-active neurons and inhibition of sleep-active neurons. The excitation effect helps to sustain wakefulness, while the inhibition effect contributes to arousal, consistent with experimental findings [De Luca et al., Nat. Commun. 13, 4163 (2022)]. Moreover, we utilized the theory of potential landscapes to investigate the physical mechanisms underlying the frequent transitions observed in narcolepsy. The topography of the underlying landscape delineated the brain's capacity to transition between different states. Additionally, we examined the impact of Orx on barrier height. Our analysis demonstrated that a reduced level of Orx led to a bistable state with an extremely low threshold, contributing to the development of narcoleptic sleep disorder.

Identifying SARS-CoV-2 infected cells with scVDN.

Introduction: Single-cell RNA sequencing (scRNA-seq) is a powerful tool for understanding cellular heterogeneity and identifying cell types in virus-related research. However, direct identification of SARS-CoV-2-infected cells at the single-cell level remains challenging, hindering the understanding of viral pathogenesis and the development of effective treatments. Methods: In this study, we propose a deep learning framework, the single-cell virus detection network (scVDN), to predict the infection status of single cells. The scVDN is trained on scRNA-seq data from multiple nasal swab samples obtained from several contributors with varying cell types. To objectively evaluate scVDN's performance, we establish a model evaluation framework suitable for real experimental data. Results and Discussion: Our results demonstrate that scVDN outperforms four state-of-the-art machine learning models in identifying SARS-CoV-2-infected cells, even with extremely imbalanced labels in real data. Specifically, scVDN achieves a perfect AUC score of 1 in four cell types. Our findings have important implications for advancing virus research and improving public health by enabling the identification of virus-infected cells at the single-cell level, which is critical for diagnosing and treating viral infections. The scVDN framework can be applied to other single-cell virus-related studies, and we make all source code and datasets publicly available on GitHub at https://github.com/studentiz/scvdn.

Predicting metabolite-disease associations based on auto-encoder and non-negative matrix factorization.

Metabolism refers to a series of orderly chemical reactions used to maintain life activities in organisms. In healthy individuals, metabolism remains within a normal range. However, specific diseases can lead to abnormalities in the levels of certain metabolites, causing them to either increase or decrease. Detecting these deviations in metabolite levels can aid in diagnosing a disease. Traditional biological experiments often rely on a lot of manpower to do repeated experiments, which is time consuming and labor intensive. To address this issue, we develop a deep learning model based on the auto-encoder and non-negative matrix factorization named as MDA-AENMF to predict the potential associations between metabolites and diseases. We integrate a variety of similarity networks and then acquire the characteristics of both metabolites and diseases through three specific modules. First, we get the disease characteristics from the five-layer auto-encoder module. Later, in the non-negative matrix factorization module, we extract both the metabolite and disease characteristics. Furthermore, the graph attention auto-encoder module helps us obtain metabolite characteristics. After obtaining the features from three modules, these characteristics are merged into a single, comprehensive feature vector for each metabolite-disease pair. Finally, we send the corresponding feature vector and label to the multi-layer perceptron for training. The experiment demonstrates our area under the receiver operating characteristic curve of 0.975 and area under the precision-recall curve of 0.973 in 5-fold cross-validation, which are superior to those of existing state-of-the-art predictive methods. Through case studies, most of the new associations obtained by MDA-AENMF have been verified, further highlighting the reliability of MDA-AENMF in predicting the potential relationships between metabolites and diseases.

Mitochondrial outer membrane permeabilization and inner membrane permeabilization in regulating apoptosis and inflammation.

Recent studies delineate an intimate crosstalk between apoptosis and inflammation. However, the dynamic mechanism linking them by mitochondrial membrane permeabilization remains elusive. Here, we construct a mathematical model consisting of four functional modules. Bifurcation analysis reveals that bistability stems from Bcl-2 family member interaction and time series shows that the time difference between Cyt c and mtDNA release is around 30 min, which are consistent with previous works. The model predicts that Bax aggregation kinetic determines cells to undergo apoptosis or inflammation, and that modulating the inhibitory effect of caspase 3 on IFN-ß production allows the concurrent occurrence of apoptosis and inflammation. This work provides a theoretical framework for exploring the mechanism of mitochondrial membrane permeabilization in controlling cell fate.

Dear-DIAXMBD: Deep Autoencoder Enables Deconvolution of Data-Independent Acquisition Proteomics.

Data-independent acquisition (DIA) technology for protein identification from mass spectrometry and related algorithms is developing rapidly. The spectrum-centric analysis of DIA data without the use of spectra library from data-dependent acquisition data represents a promising direction. In this paper, we proposed an untargeted analysis method, Dear-DIAXMBD, for direct analysis of DIA data. Dear-DIAXMBD first integrates the deep variational autoencoder and triplet loss to learn the representations of the extracted fragment ion chromatograms, then uses the k-means clustering algorithm to aggregate fragments with similar representations into the same classes, and finally establishes the inverted index tables to determine the precursors of fragment clusters between precursors and peptides and between fragments and peptides. We show that Dear-DIAXMBD performs superiorly with the highly complicated DIA data of different species obtained by different instrument platforms. Dear-DIAXMBD is publicly available at https://github.com/jianweishuai/Dear-DIA-XMBD.