Self-supervised deep learning of gene-gene interactions for improved gene expression recovery.

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool to gain biological insights at the cellular level. However, due to technical limitations of the existing sequencing technologies, low gene expression values are often omitted, leading to inaccurate gene counts. Existing methods, including advanced deep learning techniques, struggle to reliably impute gene expressions due to a lack of mechanisms that explicitly consider the underlying biological knowledge of the system. In reality, it has long been recognized that gene-gene interactions may serve as reflective indicators of underlying biology processes, presenting discriminative signatures of the cells. A genomic data analysis framework that is capable of leveraging the underlying gene-gene interactions is thus highly desirable and could allow for more reliable identification of distinctive patterns of the genomic data through extraction and integration of intricate biological characteristics of the genomic data. Here we tackle the problem in two steps to exploit the gene-gene interactions of the system. We first reposition the genes into a 2D grid such that their spatial configuration reflects their interactive relationships. To alleviate the need for labeled ground truth gene expression datasets, a self-supervised 2D convolutional neural network is employed to extract the contextual features of the interactions from the spatially configured genes and impute the omitted values. Extensive experiments with both simulated and experimental scRNA-seq datasets are carried out to demonstrate the superior performance of the proposed strategy against the existing imputation methods.

Role of cell metabolism in the pathophysiology of brain size-associated neurodevelopmental disorders.

Cell metabolism is a key regulator of human neocortex development and evolution. Several lines of evidence indicate that alterations in neural stem/progenitor cell (NPC) metabolism lead to abnormal brain development, particularly brain size-associated neurodevelopmental disorders, such as microcephaly. Abnormal NPC metabolism causes impaired cell proliferation and thus insufficient expansion of NPCs for neurogenesis. Therefore, the production of neurons, which is a major determinant of brain size, is decreased and the size of the brain, especially the size of the neocortex, is significantly reduced. This review discusses recent progress understanding NPC metabolism, focusing in particular on glucose metabolism, fatty acid metabolism and amino acid metabolism (e.g., glutaminolysis and serine metabolism). We provide an overview of the contributions of these metabolic pathways to brain development and evolution, as well as to the etiology of neurodevelopmental disorders. Furthermore, we discuss the advantages and disadvantages of various experimental models to study cell metabolism in the developing brain.

Synergistic effect of mesenchymal stem cell-derived extracellular vesicle and miR-137 alleviates autism-like behaviors by modulating the NF-κB pathway.

Autism spectrum disorder (ASD) is a multifaceted neurodevelopmental disorder predominant in childhood. Despite existing treatments, the benefits are still limited. This study explored the effectiveness of mesenchymal stem cell-derived extracellular vesicles (MSC-EVs) loaded with miR-137 in enhancing autism-like behaviors and mitigating neuroinflammation. Utilizing BTBR mice as an autism model, the study demonstrated that intranasal administration of MSC-miR137-EVs ameliorates autism-like behaviors and inhibits pro-inflammatory factors via the TLR4/NF-κB pathway. In vitro evaluation of LPS-activated BV2 cells revealed that MSC-miR137-EVs target the TLR4/NF-κB pathway through miR-137 inhibits proinflammatory M1 microglia. Moreover, bioinformatics analysis identified that MSC-EVs are rich in miR-146a-5p, which targets the TRAF6/NF-κB signaling pathway. In summary, the findings suggest that the integration of MSC-EVs with miR-137 may be a promising therapeutic strategy for ASD, which is worthy of clinical adoption.

Sulfur Migration Enhanced Proton-Coupled Electron Transfer for Efficient CO2 Desorption with Core-Shelled C@Mn3O4.

Transforming hazardous species into active sites by ingenious material design was a promising and positive strategy to improve catalytic reactions in industrial applications. To synergistically address the issue of sluggish CO2 desorption kinetics and SO2-poisoning solvent of amine scrubbing, we propose a novel method for preparing a high-performance core-shell C@Mn3O4 catalyst for heterogeneous sulfur migration and in situ reconstruction to active -SO3H groups, and thus inducing an enhanced proton-coupled electron transfer (PCET) effect for CO2 desorption. As anticipated, the rate of CO2 desorption increases significantly, by 255%, when SO2 is introduced. On a bench scale, dynamic CO2 capture experiments reveal that the catalytic regeneration heat duty of SO2-poisoned solvent experiences a 32% reduction compared to the blank case, while the durability of the catalyst is confirmed. Thus, the enhanced PCET of C@Mn3O4, facilitated by sulfur migration and simultaneous transformation, effectively improves the SO2 resistance and regeneration efficiency of amine solvents, providing a novel route for pursuing cost-effective CO2 capture with an amine solvent.

Donor engineering of a benzothiadiazole-based D-A-D-type molecular semiconductor for perovskite solar cells: a theoretical study.

Due to the easy formation of compact molecular packing arrangements and the favorable photophysical and electrochemical properties, donor-acceptor-donor (D-A-D)-type small molecule hole-transporting materials (HTMs) have been widely synthesized and researched to improve the efficiency and stability of perovskite solar cells (PSCs). The main approach in recent experiments has been to seek good acceptors, whereas the influence of the electron-donating units has been less reported. In this work, six new benzothiadiazole-based D-A-D-type HTMs are tailored by employing the ethyl-substituted phenoxazine (POZ), phenothiazine (PTZ) and carbazole (CZ) as the donors. To obtain an elementary understanding of new HTMs, the electronic, optical, hole-transporting and interfacial properties are simulated with quantum chemistry methods. The results indicate that all tailored HTMs exhibit suitable energy alignment compared with the band structures of the perovskite, and the continuous highest occupied molecular orbital (HOMO) levels will be helpful for interfacial energy regulation. In comparison with the YN1, the maximum absorption wavelengths of the newly designed HTMs are red-shifted due to the decreased excitation energies from the ground-state to the first singlet excited-state. Importantly, the hole mobilities of all designed HTMs are distinctly higher than the referenced YN1, which is contributed by the better planarity of the molecular skeleton and the easier orbital overlapping between adjacent molecules. The interfacial simulations manifest that the FAPbI3/SM37 system displays a more stable adsorption configuration and greater charge redistributions at the interface compared to YN1, which further promotes the separation of photogenerated electron-hole pairs. Moreover, larger Stokes shifts and better solubility are also acquired for the new HTMs. In summary, our calculations not only propose several potential highly efficient HTMs, but also provide useful insights at the atomic level for the experimental synthesis of new D-A-D-type HTMs.

Adsorption-desorption behavior of florpyrauxifen-benzyl on three microplastics in aqueous environment as well as its mechanism and various influencing factors.

Microplastics (MPs) and pesticides are two categories contaminants with proposed negative impacts to aqueous ecosystems, and adsorption of pesticides on MPs may result in their long-range transport and compound combination effects. Florpyrauxifen-benzyl, a novel pyridine-2-carboxylate auxin herbicide has been widely used to control weeds in paddy field, but the insights of which are extremely limited. Therefore, adsorption and desorption behaviors of florpyrauxifen-benzyl on polyvinyl chloride (PVC), polyethylene (PE) and disposable face masks (DFMs) in five water environment were investigated. The impacts of various environmental factors on adsorption capacity were evaluated, as well as adsorption mechanisms. The results revealed significant variations in adsorption capacity of florpyrauxifen-benzyl on three MPs, with approximately order of DFMs > PE > PVC. The discrepancy can be attributed to differences in structural and physicochemical properties, as evidenced by various characterization analysis. The kinetics and isotherm of florpyrauxifen-benzyl on three MPs were suitable for different models, wherein physical force predominantly governed adsorption process. Thermodynamic analysis revealed that both high and low temperatures weakened PE and DFMs adsorption, whereas temperature exhibited negligible impact on PVC adsorption. The adsorption capacity was significantly influenced by most environmental factors, particularly pH, cations and coexisting herbicide. This study provides valuable insights into the fate of florpyrauxifen-benzyl in presence of MPs, suggesting that PVC, PE and DFMs can serve as carriers of florpyrauxifen-benzyl in aquatic environment.

An Adaptive Radon-Transform-Based Marker Detection and Localization Method for Displacement Measurements Using Unmanned Aerial Vehicles.

UAVs have been widely used in deformation monitoring because of their high availability and flexibility. However, the quality of UAV images is affected by changing attitude and surveying environments, resulting in a low monitoring accuracy. Cross-shaped markers are used to improve the accuracy of UAV monitoring due to their distinct center contrast and absence of eccentricity. However, existing methods cannot rapidly and precisely detect these markers in UAV images. To address these problems, this paper proposes an adaptive Radon-transform-based marker detection and localization method for UAV displacement measurements, focusing on two critical detection parameters, namely, the radius of marker information acquisition and the edge width of the cross-shaped scoring template. The experimental results show that the marker detection rate is 97.2% under different combinations of flight altitudes, radius ratios of marker information acquisition, and marker sizes. Furthermore, the root mean square error of detection and localization is 0.57 pixels, significantly surpassing the performance and accuracy of other methods. We also derive the critical detection radius and appropriate parameter combinations for different heights to further improve the practicality of the method.

A novel turn-on near-infrared fluorescent probe for highly sensitive in vitro and in vivo detection of acetylcholinesterase activity.

Acetylcholinesterase (AChE) is a key enzyme in the cholinergic pathway of the nervous systems, with its aberrant expression linked to various diseases. In this study, we have developed a novel Turn-On near-infrared fluorescent probe, TQ-AChE, for the sensitive and selective detection of AChE activity. Characterized by its near-infrared emission at 740 nm, TQ-AChE effectively overcomes the limitations of traditional fluorescent probes, such as short excitation wavelengths and limited tissue penetration, crucial for both in vitro and in vivo applications. The probe's low limit of detection (LOD) of 0.02 U/mL for AChE makes it highly sensitive, enabling rapid quantification of AChE activity in serum effectively. Cell imaging studies demonstrate that TQ-AChE can confirm higher AChE activity expression in normal liver cells compared to liver cancer cells. TQ-AChE can also monitor AChE fluctuations in APAP-induced acute effectively, facilitating the evaluation of the efficacy of liver detoxifying agents. Additionally, in vivo studies in mouse models validate the potential of the probe in real-time monitoring of AChE expression in liver injury. The ability of TQ-AChE to visualize AChE expression signifies its potential as a promising tool for early liver disease diagnosis and therapeutic monitoring, opening new possibilities in hepatological research and clinical diagnostics.

Deciphering the Feature Representation of Deep Neural Networks for High-Performance AI.

AI driven by deep learning is transforming many aspects of science and technology. The enormous success of deep learning stems from its unique capability of extracting essential features from Big Data for decision-making. However, the feature extraction and hidden representations in deep neural networks (DNNs) remain inexplicable, primarily because of lack of technical tools to comprehend and interrogate the feature space data. The main hurdle here is that the feature data are often noisy in nature, complex in structure, and huge in size and dimensionality, making it intractable for existing techniques to analyze the data reliably. In this work, we develop a computational framework named contrastive feature analysis (CFA) to facilitate the exploration of the DNN feature space and improve the performance of AI. By utilizing the interaction relations among the features and incorporating a novel data-driven kernel formation strategy into the feature analysis pipeline, CFA mitigates the limitations of traditional approaches and provides an urgently needed solution for the analysis of feature space data. The technique allows feature data exploration in unsupervised, semi-supervised and supervised formats to address different needs of downstream applications. The potential of CFA and its applications for pruning of neural network architectures are demonstrated using several state-of-the-art networks and well-annotated datasets across different disciplines.

Quantifying particle concentration via AI-enhanced optical coherence tomography.

Efficient and robust quantification of the number of nanoparticles in solution is not only essential but also insufficient in nanotechnology and biomedical research. This paper proposes to use optical coherence tomography (OCT) to quantify the number of gold nanorods, which exemplify the nanoparticles with high light scattering signals. Additionally, we have developed an AI-enhanced OCT image processing to improve the accuracy and robustness of the quantification result.

The WuC-Adam algorithm based on joint improvement of Warmup and cosine annealing algorithms.

The Adam algorithm is a common choice for optimizing neural network models. However, its application often brings challenges, such as susceptibility to local optima, overfitting and convergence problems caused by unstable learning rate behavior. In this article, we introduce an enhanced Adam optimization algorithm that integrates Warmup and cosine annealing techniques to alleviate these challenges. By integrating preheating technology into traditional Adam algorithms, we systematically improved the learning rate during the initial training phase, effectively avoiding instability issues. In addition, we adopt a dynamic cosine annealing strategy to adaptively adjust the learning rate, improve local optimization problems and enhance the model's generalization ability. To validate the effectiveness of our proposed method, extensive experiments were conducted on various standard datasets and compared with traditional Adam and other optimization methods. Multiple comparative experiments were conducted using multiple optimization algorithms and the improved algorithm proposed in this paper on multiple datasets. On the MNIST, CIFAR10 and CIFAR100 datasets, the improved algorithm proposed in this paper achieved accuracies of 98.87%, 87.67% and 58.88%, respectively, with significant improvements compared to other algorithms. The experimental results clearly indicate that our joint enhancement of the Adam algorithm has resulted in significant improvements in model convergence speed and generalization performance. These promising results emphasize the potential of our enhanced Adam algorithm in a wide range of deep learning tasks.

Adaptive fixed-time fuzzy containment control for uncertain nonlinear multiagent systems with unmeasurable states.

This paper addresses the adaptive fixed-time fuzzy containment control for uncertain nonlinear multiagent systems, where the states and nonlinear functions are not feasible for the controller design. To address the issue of unmeasurable states, a state observer is developed, and fuzzy logic systems are utilized to approximate unknown nonlinear functions. Under the framework of fixed-time Lyapunov function theory and cooperative control, an adaptive fixed-time fuzzy containment control protocol is derived via the adaptive backstepping and adding one power integrator method. The derived fixed-time containment controller can confirm that the closed-loop systems are practical fixed-time stable, which implies that all signals in the systems are bounded and all follower agents can converge to the convex hull formed by the leader agents within fixed-time in the presence of unmeasurable states and unknown nonlinear functions . Simulation examples are conducted to test the validity of the present control algorithm.

Potential of Progressive and Disruptive Innovation-Driven Cost Reductions of Green Hydrogen Production.

Green hydrogen from water electrolysis is a key driver for energy and industrial decarbonization. The prediction of the future green hydrogen cost reduction is required for investment and policy-making purposes but is complicated due to a lack of data, incomplete accounting for costs, and difficulty justifying trend predictions. A new AI-assisted data-driven prediction model is developed for an in-depth analysis of the current and future levelized costs of green hydrogen, driven by both progressive and disruptive innovations. The model uses natural language processing to gather data and generate trends for the technological development of key aspects of electrolyzer technology. Through an uncertainty analysis, green hydrogen costs have been shown to likely reach the key target of <$2.5 kg-1 by 2030 via progressive innovations, and beyond this point, disruptive technological developments are required to affect significantly further decease cost. Additionally, the global distribution of green hydrogen costs has been calculated. This work creates a comprehensive analysis of the levelized cost of green hydrogen, including the important balance of plant components, both now and as electrolyzer technology develops, and offers a likely prediction for how the costs will develop over time.

Nanoparticles targeting mutant p53 overcome chemoresistance and tumor recurrence in non-small cell lung cancer.

Non-small cell lung cancer (NSCLC) shows high drug resistance and leads to low survival due to the high level of mutated Tumor Protein p53 (TP53). Cisplatin is a first-line treatment option for NSCLC, and the p53 mutation is a major factor in chemoresistance. We demonstrate that cisplatin chemotherapy increases the risk of TP53 mutations, further contributing to cisplatin resistance. Encouragingly, we find that the combination of cisplatin and fluvastatin can alleviate this problem. Therefore, we synthesize Fluplatin, a prodrug consisting of cisplatin and fluvastatin. Then, Fluplatin self-assembles and is further encapsulated with poly-(ethylene glycol)-phosphoethanolamine (PEG-PE), we obtain Fluplatin@PEG-PE nanoparticles (FP NPs). FP NPs can degrade mutant p53 (mutp53) and efficiently trigger endoplasmic reticulum stress (ERS). In this study, we show that FP NPs relieve the inhibition of cisplatin chemotherapy caused by mutp53, exhibiting highly effective tumor suppression and improving the poor NSCLC prognosis.

A time- and space-saving Monte Carlo simulation method using post-collimation generative adversarial network for dose calculation of an O-ring gantry Linac.

PURPOSE: This study explores the feasibility of employing Generative Adversarial Networks (GANs) to model the RefleXion X1 Linac. The aim is to investigate the accuracy of dose simulation and assess the potential computational benefits. METHODS: The X1 Linac is a new radiotherapy machine with a binary multi-leaf collimation (MLC) system, facilitating innovative biology-guided radiotherapy. A total of 34 GAN generators, each representing a desired MLC aperture, were developed. Each generator was trained using a phase space file generated underneath the corresponding aperture, enabling the generation of particles and serving as a beam source for Monte Carlo simulation. Dose distributions in water were simulated for each aperture using both the GAN and phase space sources. The agreement between dose distributions was evaluated. The computational time reduction from bypassing the collimation simulation and storage space savings were estimated. RESULTS: The percentage depth dose at 10 cm, penumbra, and full-width half maximum of the GAN simulation agree with the phase space simulation, with differences of 0.4 % ± 0.2 %, 0.32 ± 0.66 mm, and 0.26 ± 0.44 mm, respectively. The gamma passing rate (1 %/1mm) for the planar dose exceeded 90 % for all apertures. The estimated time-saving for simulating an plan using 5766 beamlets was 530 CPU hours. The storage usage was reduced by a factor of 102. CONCLUSION: The utilization of the GAN in simulating the X1 Linac demonstrated remarkable accuracy and efficiency. The reductions in both computational time and storage requirements make this approach highly valuable for future dosimetry studies and beam modeling.

Electronic Documentation of Intraoperative Observation of Cystoscopic Procedures Using the cMDX Information System.

PURPOSE: Accurate documentation of lesions during transurethral resection of bladder tumors (TURBT) is essential for precise diagnosis, treatment planning, and follow-up care. However, optimizing schematic documentation techniques for bladder lesions has received limited attention. MATERIALS AND METHODS: This prospective observational study used a cMDX-based documentation system that facilitates graphical representation, a lesion-specific questionnaire, and heatmap analysis with a posterization effect. We designed a graphical scheme for bladder covering bladder landmarks to visualize anatomic features and to document the lesion location. The lesion-specific questionnaire was integrated for comprehensive lesion characterization. Finally, spatial analyses were applied to investigate the anatomic distribution patterns of bladder lesions. RESULTS: A total of 97 TURBT cases conducted between 2021 and 2023 were included, identifying 176 lesions. The lesions were distributed in different bladder areas with varying frequencies. The distribution pattern, sorted by frequency, was observed in the following areas: posterior, trigone, lateral right and anterior, and lateral left and dome. Suspicious levels were assigned to the lesions, mostly categorized either as indeterminate or moderate. Lesion size analysis revealed that most lesions fell between 5 and 29 mm. CONCLUSION: The study highlights the potential of schematic documentation techniques for informed decision making, quality assessment, primary research, and secondary data utilization of intraoperative data in the context of TURBT. Integrating cMDX and heatmap analysis provides valuable insights into lesion distribution and characteristics.

Virtual multiplexed immunofluorescence staining from non-antibody-stained fluorescence imaging for gastric cancer prognosis.

BACKGROUND: Multiplexed immunofluorescence (mIF) staining, such as CODEX and MIBI, holds significant clinical value for various fields, such as disease diagnosis, biological research, and drug development. However, these techniques are often hindered by high time and cost requirements. METHODS: Here we present a Multimodal-Attention-based virtual mIF Staining (MAS) system that utilises a deep learning model to extract potential antibody-related features from dual-modal non-antibody-stained fluorescence imaging, specifically autofluorescence (AF) and DAPI imaging. The MAS system simultaneously generates predictions of mIF with multiple survival-associated biomarkers in gastric cancer using self- and multi-attention learning mechanisms. FINDINGS: Experimental results with 180 pathological slides from 94 patients with gastric cancer demonstrate the efficiency and consistent performance of the MAS system in both cancer and noncancer gastric tissues. Furthermore, we showcase the prognostic accuracy of the virtual mIF images of seven gastric cancer related biomarkers, including CD3, CD20, FOXP3, PD1, CD8, CD163, and PD-L1, which is comparable to those obtained from the standard mIF staining. INTERPRETATION: The MAS system rapidly generates reliable multiplexed staining, greatly reducing the cost of mIF and improving clinical workflow. FUNDING: Stanford 2022 HAI Seed Grant; National Institutes of Health 1R01CA256890.

Environmental heterogeneity of cold seep by biological trait analysis of marine nematodes at Site F cold seep in South China Sea.

Cold seeps provide high environmental heterogeneity for marine benthos. Site F is one of the active cold seeps in the South China Sea. In this study, free-living marine nematode communities were investigated at Site F and the adjacent deep-sea area. A total of 67 genera and 32 families were identified. The mean density at cold seep sites ranged from 13.6 to 181.8 ind./10 cm2, and that at the adjacent deep-sea sites ranged from 36.9 to 301.4 ind./10 cm2. At cold seep sites, the most dominant nematode genera were Desmoscolex, Pierrickia, Sabatieria, Halalaimus, and Dorylaimopsis while at deep-sea sites, the most dominant genera were Retrotheristus, Thalassomonhystera, Desmoscolex, Cobbia, and Halalaimus. Deposit feeders of nematodes were dominant at all sites. Results of biological trait analysis showed that there was high environmental heterogeneity for nematodes at Site F. Water depth, sediment organic matter content, and sand proportion had important influences on nematode communities.

In situ Raman spectral observation of succinimide intermediates in amyloid fibrillation kinetics.

Succinimide intermediates play the crucial role in the nucleation process for protein amyloid fibril formation, as they can usually induce a non-native conformation in a fraction of soluble proteins to render amyloidogenicity and neurotoxicity. Thus, in situ detection of succinimide intermediates during amyloid fibrillation kinetics is of considerable importance, albeit challenging, because these succinimides are generally unstable in physiological conditions. Here, we found an in situ Raman spectral fingerprint to trace the succinimide intermediates in amyloid fibril formation, wherein the carbonyl symmetric stretching of cyclic imide in the succinimide derivative is located at ca. 1790 cm-1. Using its intensity as an indicator of succinimide intermediates, we have in situ detected and unravelled the role of succinimide intermediates during the oligomer formation from the Bz-Asp-Gly-NH2 dipeptide or the amyloid fibrillation kinetics of lysozyme with thermal/acid treatment.

Performance and mechanisms of alkaline solid waste in CO2 mineralization and utilization.

CO2 mineral sequestration using alkaline solid waste (ASW) is a promising strategy for synergistically reducing CO2 emissions and reusing industrial waste. However, improvement the carbonation degree still remains challenges due to the sluggish leaching rate of Ca/Mg ion at low pH. To the issues, this study proposed an amine-mediated CO2 absorption and mineralization process with six common ASWs, as well an ecological utilization route of CO2-ASW productions. Experimental results indicated that calcium carbide slag (CS) had greater CO2 mineralization capacity (86.2 g-CO2/kg-CS) than other ASWs, while stirring rate and particle size played a more important role during CO2 capture. Amine-mediated CO2 capture was verified to be more excellent with steel slag (SS) as mineral medium. When the MEA concentration was increased to 2 mol/L, the extraction efficiency of Ca2+ was increased by 35 %, leaded to the CO2 removal efficiency significantly promoted from 49 % to 92 %. The characterization of structural morphology referred spherical aragonite or needle-bar calcite was dominant for the porous mineralization products (30.6 m2/g). High germination index of pea seed (112.1 % at a dose of 10 g/L) inferred the negligible toxicological effects of tiny MEA residue over SS mineralization products, after centrifugally washing treatment. Pea seeds cultivated with mineralized products after centrifugal washing can achieve a growth rate of about 4 mm/d. Overall, this work provides a feasible route to apply the porous CO2-ASWs production into water conservation in arid and sandy land.