Sci Rep. 2024 Dec 28;14(1):31277. doi: 10.1038/s41598-024-82612-3.

ABSTRACT

Traditional hydraulic structures rely on manual visual inspection for apparent integrity, which is not only time-consuming and labour-intensive but also inefficient. The efficacy of deep learning models is frequently constrained by the size of available data, resulting in limited scalability and flexibility. Furthermore, the paucity of data diversity leads to a singular function of the model that cannot provide comprehensive decision support for improving maintenance measures. This paper proposes an efficacious methodology for identifying diverse apparent damages in hydraulic structures to address the limitations of existing technologies. The advanced features of apparent damage in hydraulic structures were elucidated by fine-tuning the top-level parameters of the lightweight pre-trained model, thereby mitigating the data dependency issue inherent in the model. Ensemble learning algorithms are employed to classify high-dimensional samples to enhance the accuracy and stability of the classification. However, ensemble learning algorithms are subject to time consuming issues when applied to high-dimensional datasets. To this end, we propose a robust discriminative feature selection model to identify the most salient features, thereby enhancing the performance of apparent damage recognition in hydraulic structures while concurrently reducing the inference time. The results demonstrated that the accuracies of this method in identifying crack, fracture, hole and normal structures were 87.65%, 87.82%, 96.99%, and 95.25%, respectively. This methodology exhibits significant applicability and practical value for the intelligent inspection of hydraulic structures.

PMID:39732863 | DOI:10.1038/s41598-024-82612-3

Sci Rep. 2024 Dec 28;14(1):31257. doi: 10.1038/s41598-024-82676-1.

ABSTRACT

Surface electromyography (sEMG) data has been extensively utilized in deep learning algorithms for hand movement classification. This paper aims to introduce a novel method for hand gesture classification using sEMG data, addressing accuracy challenges seen in previous studies. We propose a U-Net architecture incorporating a MobileNetV2 encoder, enhanced by a novel Bidirectional Long Short-Term Memory (BiLSTM) and metaheuristic optimization for spatial feature extraction in hand gesture and motion recognition. Bayesian optimization is employed as the metaheuristic approach to optimize the BiLSTM model's architecture. To address the non-stationarity of sEMG signals, we employ a windowing strategy for signal augmentation within deep learning architectures. The MobileNetV2 encoder and U-Net architecture extract relevant features from sEMG spectrogram images. Edge computing integration is leveraged to further enhance innovation by enabling real-time processing and decision-making closer to the data source. Six standard databases were utilized, achieving an average accuracy of 90.23% with our proposed model, showcasing a 3-4% average accuracy improvement and a 10% variance reduction. Notably, Mendeley Data, BioPatRec DB3, and BioPatRec DB1 surpassed advanced models in their respective domains with classification accuracies of 88.71%, 90.2%, and 88.6%, respectively. Experimental results underscore the significant enhancement in generalizability and gesture recognition robustness. This approach offers a fresh perspective on prosthetic management and human-machine interaction, emphasizing its efficacy in improving accuracy and reducing variance for enhanced prosthetic control and interaction with machines through edge computing integration.

PMID:39732856 | DOI:10.1038/s41598-024-82676-1

BMC Res Notes. 2024 Dec 28;17(1):393. doi: 10.1186/s13104-024-07062-6.

ABSTRACT

This dataset contains demographic, morphological and pathological data, endoscopic images and videos of 191 patients with colorectal polyps. Morphological data is included based on the latest international gastroenterology classification references such as Paris, Pit and JNET classification. Pathological data includes the diagnosis of the polyps including Tubular, Villous, Tubulovillous, Hyperplastic, Serrated, Inflammatory and Adenocarcinoma with Dysplasia Grade & Differentiation.Objectives: Today the most important challenge of developing accurate algorithms for medical prediction, detection, diagnosis, treatment and prognosis is data. ERCPMP is an Endoscopic Image and Video Dataset for Recognition of Colorectal Polyps Morphology and Pathology. This dataset can be used for developing deep learning algorithms for polyps detection, classification, and segmentation.Data description: Images were captured with Olympus colonoscope and are presented in RGB format, JPG type with the resolution of 368 * 256 pixels and 96 dpi. The name of each file (image or video) includes pathological diagnosis, grade and JNet classification of the related polyp.

PMID:39732672 | DOI:10.1186/s13104-024-07062-6

BMC Genomics. 2024 Dec 28;25(1):1253. doi: 10.1186/s12864-024-11168-3.

ABSTRACT

Long non-coding RNAs (lncRNAs) play crucial roles in numerous biological processes and are involved in complex human diseases through interactions with proteins. Accurate identification of lncRNA-protein interactions (LPI) can help elucidate the functional mechanisms of lncRNAs and provide scientific insights into the molecular mechanisms underlying related diseases. While many sequence-based methods have been developed to predict LPIs, efficiently extracting and effectively integrating potential feature information that reflects functional attributes from lncRNA and protein sequences remains a significant challenge. This paper proposes a Dinucleotide-Codon Fusion Feature encoding (DNCFF) and constructs an LPI prediction model based on deep learning, termed LPI-DNCFF. The Dual Nucleotide Visual Fusion Feature encoding (DNVFF) incorporates positional information of single nucleotides with subsequent nucleotide connections, while Codon Fusion Feature encoding (CFF) considers the specificity, molecular weight, and physicochemical properties of each amino acid. These encoding methods encapsulate rich and intuitive sequence information in limited encoding dimensions. The model comprehensively predicts LPIs by integrating global, local, and structural features, and inputs them into BiLSTM and attention layers to form a hybrid deep learning model. Experimental results demonstrate that LPI-DNCFF effectively predicts LPIs. The BiLSTM layer and attention mechanism can learn long-term dependencies and identify weighted key features, enhancing model performance. Compared to one-hot encoding, DNCFF more efficiently and thoroughly extracts potential sequence features. Compared to other existing methods, LPI-DNCFF achieved the best performance on the RPI1847 and ATH948 datasets, with MCC values of approximately 97.84% and 84.58%, respectively, outperforming the state-of-the-art method by about 1.44% and 3.48%.

PMID:39732642 | DOI:10.1186/s12864-024-11168-3

Acad Radiol. 2024 Dec 27:S1076-6332(24)00894-8. doi: 10.1016/j.acra.2024.11.049. Online ahead of print.

ABSTRACT

RATIONALE AND OBJECTIVES: To evaluate and compare image quality of different energy levels of virtual monochromatic images (VMIs) using standard versus strong deep learning spectral reconstruction (DLSR) on dual-energy CT pulmonary angiogram (DECT-PA).

MATERIALS AND METHODS: A retrospective study was performed on 70 patients who underwent DECT-PA (15 PE present; 55 PE absent) scans. VMIs were reconstructed at different energy levels ranging from 35 to 200 keV using standard and strong levels with deep learning spectral reconstruction. Quantitative assessment was performed using region of interest (ROI) analysis of eleven different anatomical areas, measuring absolute attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). In addition, CNR of clot compared to normally opacified lumen was calculated in cases that were positive for PE. For qualitative analysis, four different keV levels (40-60-80-100) were evaluated.

RESULTS: The image noise was significantly lower, and the cardiovascular SNR (24.9 ± 5.85 vs. 21.98 ± 5.49) and CNR (23.72 ± 8.00 vs. 20.31 ± 6.44) were significantly higher, on strong Deep Learning Spectral reconstruction (DLSR) than standard DLSR (p < 0.0001). PE-specific CNR (8.58 ± 4.47 vs. 6.25 ± 3.19) was significantly higher on strong DLSR than standard (p < 0.0001). The subjective image quality scores were diagnostically acceptable at four different keV levels (40-60-80-100 keV) evaluated using both standard and strong DLSR, with no qualitative differences observed at those energies.

CONCLUSION: Strong DLSR improves image quality with an increase of the SNR and CNR in DECT-PA compared to standard DLSR.

PMID:39732618 | DOI:10.1016/j.acra.2024.11.049

Am J Pathol. 2024 Dec 26:S0002-9440(24)00469-3. doi: 10.1016/j.ajpath.2024.10.023. Online ahead of print.

ABSTRACT

Understanding the tumor hypoxic microenvironment is crucial for grasping tumor biology, clinical progression, and treatment responses. This study presents a novel application of AI in computational histopathology to evaluate hypoxia in breast cancer. Weakly Supervised Deep Learning (WSDL) models can accurately detect morphological changes associated with hypoxia in routine Hematoxylin and Eosin (H&E) whole slide images (WSI). Our model, HypOxNet, was trained on H&E WSI from breast cancer primary sites (n=1016) at 40x magnification using data from The Cancer Genome Atlas (TCGA). We utilized the Hypoxia Buffa signature to measure hypoxia scores, which ranged from -43 to +47, and stratified the samples into hypoxic and normoxic based on these scores. This stratification represented the weak labels associated with each WSI. HypOxNet achieved an average Area Under the Curve (AUC) of 0.82 on test sets, identifying significant differences in cell morphology between hypoxic and normoxic tissue regions. Importantly, once trained, the HypOxNet model requires only the readily available H&E slides, making it especially valuable in low-resource settings where additional gene expression assays are not available. These AI-based hypoxia detection models can potentially be extended to other tumor types and seamlessly integrated into pathology workflows, offering a fast, cost-effective alternative to molecular testing.

PMID:39732389 | DOI:10.1016/j.ajpath.2024.10.023

Neurobiol Dis. 2024 Dec 26:106783. doi: 10.1016/j.nbd.2024.106783. Online ahead of print.

ABSTRACT

DYT-THAP1 dystonia is a monogenetic form of dystonia, a movement disorder characterized by the involuntary co-contraction of agonistic and antagonistic muscles. The disease is caused by mutations in the THAP1 gene, although the precise mechanisms by which these mutations contribute to the pathophysiology of dystonia remain unclear. The incomplete penetrance of DYT-THAP1 dystonia, estimated at 40 to 60 %, suggests that an environmental trigger may be required for the manifestation of the disease in genetically predisposed individuals. To investigate the gene-environment interaction in the development of dystonic features, we performed a sciatic nerve crush injury in a genetically predisposed DYT-THAP1 heterozygous knockout mouse model (Thap1+/-). We employed a multi-omic assessment to study the pathophysiological pathways underlying the disease. Phenotypic analysis using an unbiased deep learning algorithm revealed that nerve-injured Thap1+/- mice exhibited significantly more dystonia like movements (DLM) over the course of the 12-week experiment compared to naive Thap1+/- mice. In contrast, nerve-injured wildtype (wt) mice only showed a significant increase in DLM compared to their naive counterpart during the first weeks after injury. Furthermore, at week 11 after nerve crush, nerve-injured Thap1+/- mice displayed significantly more DLM than nerve-injured wt counterparts. Multi-omic analysis of the cerebellum, striatum and cortex in nerve-injured Thap1+/- mice revealed differences that are indicative of an altered energy metabolism compared to naive Thap1+/- and nerve-injured wt animals. These findings suggest that aberrant energy metabolism in brain regions relevant to dystonia may underlie the dystonic phenotype observed in nerve injured Thap1+/- mice.

PMID:39732371 | DOI:10.1016/j.nbd.2024.106783

Lab Invest. 2024 Dec 26:102221. doi: 10.1016/j.labinv.2024.102221. Online ahead of print.

ABSTRACT

Tumor cell nuclear size (NS) indicates malignant potential in breast cancer; however, its clinical significance in esophageal squamous cell carcinoma (ESCC) is unknown. Artificial intelligence (AI) can quantitatively evaluate histopathological findings. The aim was to measure NS in ESCC using AI and elucidate its clinical significance. We investigated the relationship between NS assessed by AI and prognosis in 138 patients with ESCC who underwent curative esophagectomy. Hematoxylin and eosin-stained slides from the deepest tumor sections were digitized. Using HALO-AI DenseNet v2, we created a deep learning classifier that identified tumor cells with an NS area >20 μm2. Median NS was 40.14 μm2, which was used to divide patients into NS-high and NS-low groups (n = 69 per group). Five-year overall survival (OS) and relapse-free survival rates were significantly lower in the NS-high group (43.2% and 39.6%) than in the NS-low group (67.7% and 49.6%). Multivariate analysis showed that greater tumor depth and NS-high status (hazard ratio [HR]: 1.79; p = 0.032) were independent risk factors for OS. In 77 cases with neoadjuvant chemotherapy, increased tumor depth and NS-high status (HR: 1.99; p = 0.048) were independent prognostic factors for unfavorable OS. Compared to the NS-low group, the NS-high group had significantly higher anisokaryosis, higher Ki-67 expression as calculated by AI analysis of immunostaining, and higher NS heterogeneity as examined by equidividing the tumors into square tiles. In conclusion, NS assessed by AI is a simple and useful prognostic factor for ESCC.

PMID:39732367 | DOI:10.1016/j.labinv.2024.102221

Neural Netw. 2024 Dec 20;184:107053. doi: 10.1016/j.neunet.2024.107053. Online ahead of print.

ABSTRACT

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To address this, some methods propose replaying data from previous tasks during new task learning, typically using extra memory to store replay data. However, it is not expected in practice due to memory constraints and data privacy issues. Instead, data-free replay methods invert samples from the classification model. While effective, these methods face inconsistencies between inverted and real training data, overlooked in recent works. To that effect, we propose to measure the data consistency quantitatively by some simplification and assumptions. Using this measurement, we gain insight to develop a novel loss function that reduces inconsistency. Specifically, the loss minimizes the KL divergence between distributions of inverted and real data under a tied multivariate Gaussian assumption, which is simple to implement in continual learning. Additionally, we observe that old class weight norms decrease continually as learning progresses. We analyze the reasons and propose a regularization term to balance class weights, making old class samples more distinguishable. To conclude, we introduce Consistency-enhanced data replay with a Debiased classifier for class incremental learning (CwD). Extensive experiments on CIFAR-100, Tiny-ImageNet, and ImageNet100 show consistently improved performance of CwD compared to previous approaches.

PMID:39732067 | DOI:10.1016/j.neunet.2024.107053

Comput Biol Med. 2024 Dec 27;186:109629. doi: 10.1016/j.compbiomed.2024.109629. Online ahead of print.

ABSTRACT

BACKGROUND: Studying influential nodes (I-nodes) in brain networks is of great significance in the field of brain imaging. Most existing studies consider brain connectivity hubs as I-nodes such as the regions of high centrality or rich-club organization. However, this approach relies heavily on prior knowledge from graph theory, which may overlook the intrinsic characteristics of the brain network, especially when its architecture is not fully understood. In contrast, self-supervised deep learning dispenses with manual features, allowing it to learn meaningful representations directly from the data. This approach enables the exploration of I-nodes for brain networks, which is also lacking in current studies.

METHOD: This paper proposes a Self-Supervised Graph Reconstruction framework based on Graph-Transformer (SSGR-GT) to identify I-nodes, which has three main characteristics. First, as a self-supervised model, SSGR-GT extracts the importance of brain nodes to the reconstruction. Second, SSGR-GT uses Graph-Transformer, which is well-suited for extracting features from brain graphs, combining both local and global characteristics. Third, multimodal analysis of I-nodes uses graph-based fusion technology, combining functional and structural brain information.

RESULTS: The I-nodes we obtained are distributed in critical areas such as the superior frontal lobe, lateral parietal lobe, and lateral occipital lobe, with a total of 56 identified across different experiments. These I-nodes are involved in more brain networks than other regions, have longer fiber connections, and occupy more central positions in structural connectivity. They also exhibit strong connectivity and high node efficiency in both functional and structural networks. Furthermore, there is a significant overlap between the I-nodes and both the structural and functional rich-club.

CONCLUSIONS: Experimental results verify the effectiveness of the proposed method, and I-nodes are obtained and discussed. These findings enhance our understanding of the I-nodes within the brain network, and provide new insights for future research in further understanding the brain working mechanisms.

PMID:39731922 | DOI:10.1016/j.compbiomed.2024.109629

J Am Med Inform Assoc. 2024 Dec 28:ocae316. doi: 10.1093/jamia/ocae316. Online ahead of print.

ABSTRACT

OBJECTIVE: Early detection of surgical complications allows for timely therapy and proactive risk mitigation. Machine learning (ML) can be leveraged to identify and predict patient risks for postoperative complications. We developed and validated the effectiveness of predicting postoperative complications using a novel surgical Variational Autoencoder (surgVAE) that uncovers intrinsic patterns via cross-task and cross-cohort presentation learning.

MATERIALS AND METHODS: This retrospective cohort study used data from the electronic health records of adult surgical patients over 4 years (2018-2021). Six key postoperative complications for cardiac surgery were assessed: acute kidney injury, atrial fibrillation, cardiac arrest, deep vein thrombosis or pulmonary embolism, blood transfusion, and other intraoperative cardiac events. We compared surgVAE's prediction performance against widely-used ML models and advanced representation learning and generative models under 5-fold cross-validation.

RESULTS: 89 246 surgeries (49% male, median [IQR] age: 57 [45-69]) were included, with 6502 in the targeted cardiac surgery cohort (61% male, median [IQR] age: 60 [53-70]). surgVAE demonstrated generally superior performance over existing ML solutions across postoperative complications of cardiac surgery patients, achieving macro-averaged AUPRC of 0.409 and macro-averaged AUROC of 0.831, which were 3.4% and 3.7% higher, respectively, than the best alternative method (by AUPRC scores). Model interpretation using Integrated Gradients highlighted key risk factors based on preoperative variable importance.

DISCUSSION AND CONCLUSION: Our advanced representation learning framework surgVAE showed excellent discriminatory performance for predicting postoperative complications and addressing the challenges of data complexity, small cohort sizes, and low-frequency positive events. surgVAE enables data-driven predictions of patient risks and prognosis while enhancing the interpretability of patient risk profiles.

PMID:39731515 | DOI:10.1093/jamia/ocae316

Adv Sci (Weinh). 2024 Dec 27:e2412670. doi: 10.1002/advs.202412670. Online ahead of print.

ABSTRACT

The biobased production of chemicals is essential for advancing a sustainable chemical industry. 1,5-Pentanediol (1,5-PDO), a five-carbon diol with considerable industrial relevance, has shown limited microbial production efficiency until now. This study presents the development and optimization of a microbial system to produce 1,5-PDO from glucose in Corynebacterium glutamicum via the l-lysine-derived pathway. Engineering began with creating a strain capable of producing 5-hydroxyvaleric acid (5-HV), a key precursor to 1,5-PDO, by incorporating enzymes from Pseudomonas putida (DavB, DavA, and DavT) and Escherichia coli (YahK). Two conversion pathways for further converting 5-HV to 1,5-PDO are evaluated, with the CoA-independent pathway-utilizing Mycobacterium marinum carboxylic acid reductase (CAR) and E. coli YqhD-proving greater efficiency. Further optimization continues with chromosomal integration of the 5-HV module, increasing 1,5-PDO production to 5.48 g L-1. An additional screening of 13 CARs identifies Mycobacterium avium K-10 (MAP1040) as the most effective, and its engineered M296E mutant further increases production to 23.5 g L-1. A deep-learning analysis reveals that Gluconobacter oxydans GOX1801 resolves the limitations of NADPH, allowing the final strain to produce 43.4 g L-1 1,5-PDO without 5-HV accumulation in fed-batch fermentation. This study demonstrates systematic approaches to optimizing microbial biosynthesis, positioning C. glutamicum as a promising platform for sustainable 1,5-PDO production.

PMID:39731342 | DOI:10.1002/advs.202412670

Adv Sci (Weinh). 2024 Dec 27:e2406797. doi: 10.1002/advs.202406797. Online ahead of print.

ABSTRACT

Digital PCR (dPCR) has transformed nucleic acid diagnostics by enabling the absolute quantification of rare mutations and target sequences. However, traditional dPCR detection methods, such as those involving flow cytometry and fluorescence imaging, may face challenges due to high costs, complexity, limited accuracy, and slow processing speeds. In this study, SAM-dPCR is introduced, a training-free open-source bioanalysis paradigm that offers swift and precise absolute quantification of biological samples. SAM-dPCR leverages the robustness of the zero-shot Segment Anything Model (SAM) to achieve rapid processing times (<4 seconds) with an accuracy exceeding 97.10%. This method has been extensively validated across diverse samples and reactor morphologies, demonstrating its broad applicability. Utilizing standard laboratory fluorescence microscopes, SAM-dPCR can measure nucleic acid template concentrations ranging from 0.154 copies µL-1 to 1.295 × 103 copies µL-1 for droplet dPCR and 0.160 × 103 to 3.629 × 103 copies µL-1 for microwell dPCR. Experimental validation shows a strong linear relationship (r2 > 0.96) between expected and determined sample concentrations. SAM-dPCR offers high accuracy, accessibility, and the ability to address bioanalytical needs in resource-limited settings, as it does not rely on hand-crafted "ground truth" data.

PMID:39731324 | DOI:10.1002/advs.202406797

J Med Eng Technol. 2024 Dec 27:1-13. doi: 10.1080/03091902.2024.2438150. Online ahead of print.

ABSTRACT

Nowadays, photoplethysmograph (PPG) technology is being used more often in smart devices and mobile phones due to advancements in information and communication technology in the health field, particularly in monitoring cardiac activities. Developing generative models to generate synthetic PPG signals requires overcoming challenges like data diversity and limited data available for training deep learning models. This paper proposes a generative model by adopting a genetic programming (GP) approach to generate increasingly diversified and accurate data using an initial PPG signal sample. Unlike conventional regression, the GP approach automatically determines the structure and combinations of a mathematical model. Given that mean square error (MSE) of 0.0001, root mean square error (RMSE) of 0.01, and correlation coefficient of 0.999, the proposed approach outperformed other approaches and proved effective in terms of efficiency and applicability in resource-constrained environments.

PMID:39731227 | DOI:10.1080/03091902.2024.2438150

Acta Ophthalmol. 2024 Dec 27. doi: 10.1111/aos.17434. Online ahead of print.

ABSTRACT

PURPOSE: The relationship between retinal morphology, as assessed by optical coherence tomography (OCT), and retinal function in microperimetry (MP) has not been well studied, despite its increasing importance as an essential functional endpoint for clinical trials and emerging therapies in retinal diseases. Normative databases of healthy ageing eyes are largely missing from literature.

METHODS: Healthy subjects above 50 years were examined using two MP devices, MP-3 (NIDEK) and MAIA (iCare). An identical grid, encompassing 45 stimuli was used for retinal sensitivity (RS) assessment. Deep-learning-based algorithms performed automated segmentation of ellipsoid zone (EZ), outer nuclear layer (ONL), ganglion cell layer (GCL) and retinal nerve fibre layer (RNFL) from OCT volumes (Spectralis, Heidelberg). Pointwise co-registration between each MP stimulus and corresponding location on OCT was performed via registration algorithm. Effect of age, eccentricity and layer thickness on RS was assessed by mixed effect models.

RESULTS: Three thousand six hundred stimuli from twenty eyes of twenty patients were included. Mean patient age was 68.9 ± 10.9 years. Mean RS for the first exam was 28.65 ± 2.49 dB and 25.5 ± 2.81 dB for MP-3 and MAIA, respectively. Increased EZ thickness, ONL thickness and GCL thickness were significantly correlated with increased RS (all p < 0.001). Univariate models showed lower RS with advanced age and higher eccentricity (both p < 0.05).

CONCLUSION: This work provides reference values for healthy age-related EZ and ONL-thicknesses without impairment of visual function and evidence for RS decrease with eccentricity and increasing age. This information is crucial for interpretation of future clinical trials in disease.

PMID:39731225 | DOI:10.1111/aos.17434

J Cheminform. 2024 Dec 27;16(1):146. doi: 10.1186/s13321-024-00941-x.

ABSTRACT

Naming chemical compounds systematically is a complex task governed by a set of rules established by the International Union of Pure and Applied Chemistry (IUPAC). These rules are universal and widely accepted by chemists worldwide, but their complexity makes it challenging for individuals to consistently apply them accurately. A translation method can be employed to address this challenge. Accurate translation of chemical compounds from SMILES notation into their corresponding IUPAC names is crucial, as it can significantly streamline the laborious process of naming chemical structures. Here, we present STOUT (SMILES-TO-IUPAC-name translator) V2, which addresses this challenge by introducing a transformer-based model that translates string representations of chemical structures into IUPAC names. Trained on a dataset of nearly 1 billion SMILES strings and their corresponding IUPAC names, STOUT V2 demonstrates exceptional accuracy in generating IUPAC names, even for complex chemical structures. The model's ability to capture intricate patterns and relationships within chemical structures enables it to generate precise and standardised IUPAC names. While established deterministic algorithms remain the gold standard for systematic chemical naming, our work, enabled by access to OpenEye's Lexichem software through an academic license, demonstrates the potential of neural approaches to complement existing tools in chemical nomenclature.Scientific contribution STOUT V2, built upon transformer-based models, is a significant advancement from our previous work. The web application enhances its accessibility and utility. By making the model and source code fully open and well-documented, we aim to promote unrestricted use and encourage further development.

PMID:39731139 | DOI:10.1186/s13321-024-00941-x

BMC Cancer. 2024 Dec 27;24(1):1581. doi: 10.1186/s12885-024-13320-4.

ABSTRACT

Glioblastoma Multiforme (GBM), classified as a grade IV glioma by the World Health Organization (WHO), is a prevalent and notably aggressive form of brain tumor derived from glial cells. It stands as one of the most severe forms of primary brain cancer in humans. The median survival time of GBM patients is only 12-15 months, making it the most lethal type of brain tumor. Every year, about 200,000 people worldwide succumb to this disease. GBM is also highly heterogeneous, meaning that its characteristics and behavior vary widely among different patients. This leads to different outcomes and survival times for each individual. Predicting the survival of GBM patients accurately can have multiple benefits. It can enable optimal and personalized treatment planning based on the patient's condition and prognosis. It can also support the patients and their families to cope with the possible outcomes and make informed decisions about their care and quality of life. Furthermore, it can assist the researchers and scientists to discover the most relevant biomarkers, features, and mechanisms of the disease and to design more effective and personalized therapies. Artificial intelligence methods, such as machine learning and deep learning, have been widely applied to survival prediction in various fields, such as breast cancer, lung cancer, gastric cancer, cervical cancer, liver cancer, prostate cancer, and covid 19. This systematic review summarizes the current state-of-the-art methods for predicting glioblastoma survival using different types of input data, such as clinical features, molecular markers, imaging features, radiomics features, omics data or a combination of them. Following PRISMA guidelines, we searched databases from 2015 to 2024, reviewing 107 articles meeting our criteria. We analyzed the data sources, methods, performance metrics and outcomes of the studies. We found that random forest was the most popular method, and a combination of radiomics and clinical data was the most common input data.

PMID:39731064 | DOI:10.1186/s12885-024-13320-4

BMC Bioinformatics. 2024 Dec 27;25(1):392. doi: 10.1186/s12859-024-06013-z.

ABSTRACT

BACKGROUND: Cancer classification has consistently been a challenging problem, with the main difficulties being high-dimensional data and the collection of patient samples. Concretely, obtaining patient samples is a costly and resource-intensive process, and imbalances often exist between samples. Moreover, expression data is characterized by high dimensionality, small samples and high noise, which could easily lead to struggles such as dimensionality catastrophe and overfitting. Thus, we incorporate prior knowledge from the pathway and combine AutoEncoder and Generative Adversarial Network (GAN) to solve these difficulties.

RESULTS: In this study, we propose an effective and efficient deep learning method, named AEGAN, which combines the capabilities of AutoEncoder and GAN to generate synthetic samples of the minority class in imbalanced gene expression data. The proposed data balancing technique has been demonstrated to be useful for cancer classification and improving the performance of classifier models. Additionally, we integrate prior knowledge from the pathway and employ the pathifier algorithm to calculate pathway scores for each sample. This data augmentation approach, referred to as AEGAN-Pathifier, not only preserves the biological functionality of the data but also possesses dimensional reduction capabilities. Through validation with various classifiers, the experimental results show an improvement in classifier performance.

CONCLUSION: AEGAN-Pathifier shows improved performance on the imbalanced datasets GSE25066, GSE20194, BRCA and Liver24. Results from various classifiers indicate that AEGAN-Pathifier has good generalization capability.

PMID:39731019 | DOI:10.1186/s12859-024-06013-z

BMC Genomics. 2024 Dec 27;25(1):1252. doi: 10.1186/s12864-024-11173-6.

ABSTRACT

BACKGROUND: The subcellular localization of mRNA plays a crucial role in gene expression regulation and various cellular processes. However, existing wet lab techniques like RNA-FISH are usually time-consuming, labor-intensive, and limited to specific tissue types. Researchers have developed several computational methods to predict mRNA subcellular localization to address this. These methods face the problem of class imbalance in multi-label classification, causing models to favor majority classes and overlook minority classes during training. Additionally, traditional feature extraction methods have high computational costs, incomplete features, and may lead to the loss of critical information. On the other hand, deep learning methods face challenges related to hardware performance and training time when handling complex sequences. They may suffer from the curse of dimensionality and overfitting problems. Therefore, there is an urgent need for more efficient and accurate prediction models.

RESULTS: To address these issues, we propose a multi-label classifier, EDCLoc, for predicting mRNA subcellular localization. EDCLoc reduces training pressure through a stepwise pooling strategy and applies grouped convolution blocks of varying sizes at different levels, combined with residual connections, to achieve efficient feature extraction and gradient propagation. The model employs global max pooling at the end to further reduce feature dimensions and highlight key features. To tackle class imbalance, we improved the focal loss function to enhance the model's focus on minority classes. Evaluation results show that EDCLoc outperforms existing methods in most subcellular regions. Additionally, the position weight matrix extracted by multi-scale CNN filters can match known RNA-binding protein motifs, demonstrating EDCLoc's effectiveness in capturing key sequence features.

CONCLUSIONS: EDCLoc outperforms existing prediction tools in most subcellular regions and effectively mitigates class imbalance issues in multi-label classification. These advantages make EDCLoc a reliable choice for multi-label mRNA subcellular localization. The dataset and source code used in this study are available at https://github.com/DellCode233/EDCLoc .

PMID:39731012 | DOI:10.1186/s12864-024-11173-6

Sci Rep. 2024 Dec 28;14(1):31193. doi: 10.1038/s41598-024-82562-w.

ABSTRACT

Deep Convolutional Neural Networks (DCNNs), due to their high computational and memory requirements, face significant challenges in deployment on resource-constrained devices. Network Pruning, an essential model compression technique, contributes to enabling the efficient deployment of DCNNs on such devices. Compared to traditional rule-based pruning methods, Reinforcement Learning(RL)-based automatic pruning often yields more effective pruning strategies through its ability to learn and adapt. However, the current research only set a single agent to explore the optimal pruning rate for all convolutional layers, ignoring the interactions and effects among multiple layers. To address this challenge, this paper proposes an automatic Filter Pruning method with a multi-agent reinforcement learning algorithm QMIX, named QMIX_FP. The multi-layer structure of DCNNs is modeled as a multi-agent system, which considers the varying sensitivity of each convolutional layer to the entire DCNN and the interactions among them. We employ the multi-agent reinforcement learning algorithm QMIX, where individual agent contributes to the system monotonically, to explore the optimal iterative pruning strategy for each convolutional layer. Furthermore, fine-tuning the pruned network using knowledge distillation accelerates model performance improvement. The efficiency of this method is demonstrated on two benchmark DCNNs, including VGG-16 and AlexNet, over CIFAR-10 and CIFAR-100 datasets. Extensive experiments under different scenarios show that QMIX_FP not only reduces the computational and memory requirements of the networks but also maintains their accuracy, making it a significant advancement in the field of model compression and efficient deployment of deep learning models on resource-constrained devices.

PMID:39730902 | DOI:10.1038/s41598-024-82562-w