Med Phys. 2024 May 21. doi: 10.1002/mp.17129. Online ahead of print.

ABSTRACT

BACKGROUND: Deformable registration is required to generate a time-integrated activity (TIA) map which is essential for voxel-based dosimetry. The conventional iterative registration algorithm using anatomical images (e.g., computed tomography (CT)) could result in registration errors in functional images (e.g., single photon emission computed tomography (SPECT) or positron emission tomography (PET)). Various deep learning-based registration tools have been proposed, but studies specifically focused on the registration of serial hybrid images were not found.

PURPOSE: In this study, we introduce CoRX-NET, a novel unsupervised deep learning network designed for deformable registration of hybrid medical images. The CoRX-NET structure is based on the Swin-transformer (ST), allowing for the representation of complex spatial connections in images. Its self-attention mechanism aids in the effective exchange and integration of information across diverse image regions. To augment the amalgamation of SPECT and CT features, cross-stitch layers have been integrated into the network.

METHODS: Two different 177 Lu DOTATATE SPECT/CT datasets were acquired at different medical centers. 22 sets from Seoul National University and 14 sets from Sunway Medical Centre are used for training/internal validation and external validation respectively. The CoRX-NET architecture builds upon the ST, enabling the modeling of intricate spatial relationships within images. To further enhance the fusion of SPECT and CT features, cross-stitch layers have been incorporated within the network. The network takes a pair of SPECT/CT images (e.g., fixed and moving images) and generates a deformed SPECT/CT image. The performance of the network was compared with Elastix and TransMorph using L1 loss and structural similarity index measure (SSIM) of CT, SSIM of normalized SPECT, and local normalized cross correlation (LNCC) of SPECT as metrics. The voxel-wise root mean square errors (RMSE) of TIA were compared among the different methods.

RESULTS: The ablation study revealed that cross-stitch layers improved SPECT/CT registration performance. The cross-stitch layers notably enhance SSIM (internal validation: 0.9614 vs. 0.9653, external validation: 0.9159 vs. 0.9189) and LNCC of normalized SPECT images (internal validation: 0.7512 vs. 0.7670, external validation: 0.8027 vs. 0.8027). CoRX-NET with the cross-stitch layer achieved superior performance metrics compared to Elastix and TransMorph, except for CT SSIM in the external dataset. When qualitatively analyzed for both internal and external validation cases, CoRX-NET consistently demonstrated superior SPECT registration results. In addition, CoRX-NET accomplished SPECT/CT image registration in less than 6 s, whereas Elastix required approximately 50 s using the same PC's CPU. When employing CoRX-NET, it was observed that the voxel-wise RMSE values for TIA were approximately 27% lower for the kidney and 33% lower for the tumor, compared to when Elastix was used.

CONCLUSION: This study represents a major advancement in achieving precise SPECT/CT registration using an unsupervised deep learning network. It outperforms conventional methods like Elastix and TransMorph, reducing uncertainties in TIA maps for more accurate dose assessments.

PMID:38772037 | DOI:10.1002/mp.17129

PLoS One. 2024 May 21;19(5):e0302537. doi: 10.1371/journal.pone.0302537. eCollection 2024.

ABSTRACT

BACKGROUND: Stem cell research, particularly in the domain of induced pluripotent stem cell (iPSC) technology, has shown significant progress. The integration of artificial intelligence (AI), especially machine learning (ML) and deep learning (DL), has played a pivotal role in refining iPSC classification, monitoring cell functionality, and conducting genetic analysis. These enhancements are broadening the applications of iPSC technology in disease modelling, drug screening, and regenerative medicine. This review aims to explore the role of AI in the advancement of iPSC research.

METHODS: In December 2023, data were collected from three electronic databases (PubMed, Web of Science, and Science Direct) to investigate the application of AI technology in iPSC processing.

RESULTS: This systematic scoping review encompassed 79 studies that met the inclusion criteria. The number of research studies in this area has increased over time, with the United States emerging as a leading contributor in this field. AI technologies have been diversely applied in iPSC technology, encompassing the classification of cell types, assessment of disease-specific phenotypes in iPSC-derived cells, and the facilitation of drug screening using iPSC. The precision of AI methodologies has improved significantly in recent years, creating a foundation for future advancements in iPSC-based technologies.

CONCLUSIONS: Our review offers insights into the role of AI in regenerative and personalized medicine, highlighting both challenges and opportunities. Although still in its early stages, AI technologies show significant promise in advancing our understanding of disease progression and development, paving the way for future clinical applications.

PMID:38771829 | DOI:10.1371/journal.pone.0302537

PLoS One. 2024 May 21;19(5):e0301969. doi: 10.1371/journal.pone.0301969. eCollection 2024.

ABSTRACT

PURPOSE: This study aims to introduce an innovative multi-step pipeline for automatic tumor-stroma ratio (TSR) quantification as a potential prognostic marker for pancreatic cancer, addressing the limitations of existing staging systems and the lack of commonly used prognostic biomarkers.

METHODS: The proposed approach involves a deep-learning-based method for the automatic segmentation of tumor epithelial cells, tumor bulk, and stroma from whole-slide images (WSIs). Models were trained using five-fold cross-validation and evaluated on an independent external test set. TSR was computed based on the segmented components. Additionally, TSR's predictive value for six-month survival on the independent external dataset was assessed.

RESULTS: Median Dice (inter-quartile range (IQR)) of 0.751(0.15) and 0.726(0.25) for tumor epithelium segmentation on internal and external test sets, respectively. Median Dice of 0.76(0.11) and 0.863(0.17) for tumor bulk segmentation on internal and external test sets, respectively. TSR was evaluated as an independent prognostic marker, demonstrating a cross-validation AUC of 0.61±0.12 for predicting six-month survival on the external dataset.

CONCLUSION: Our pipeline for automatic TSR quantification offers promising potential as a prognostic marker for pancreatic cancer. The results underscore the feasibility of computational biomarker discovery in enhancing patient outcome prediction, thus contributing to personalized patient management.

PMID:38771787 | DOI:10.1371/journal.pone.0301969

PLoS One. 2024 May 21;19(5):e0303278. doi: 10.1371/journal.pone.0303278. eCollection 2024.

ABSTRACT

Currently, numerous studies focus on employing fMRI-based deep neural networks to diagnose neurological disorders such as Alzheimer's Disease (AD), yet only a handful have provided results regarding explainability. We address this gap by applying several prevalent explainability methods such as gradient-weighted class activation mapping (Grad-CAM) to an fMRI-based 3D-VGG16 network for AD diagnosis to improve the model's explainability. The aim is to explore the specific Region of Interest (ROI) of brain the model primarily focuses on when making predictions, as well as whether there are differences in these ROIs between AD and normal controls (NCs). First, we utilized multiple resting-state functional activity maps including ALFF, fALFF, ReHo, and VMHC to reduce the complexity of fMRI data, which differed from many studies that utilized raw fMRI data. Compared to methods utilizing raw fMRI data, this manual feature extraction approach may potentially alleviate the model's burden. Subsequently, 3D-VGG16 were employed for AD classification, where the final fully connected layers were replaced with a Global Average Pooling (GAP) layer, aimed at mitigating overfitting while preserving spatial information within the feature maps. The model achieved a maximum of 96.4% accuracy on the test set. Finally, several 3D CAM methods were employed to interpret the models. In the explainability results of the models with relatively high accuracy, the highlighted ROIs were primarily located in the precuneus and the hippocampus for AD subjects, while the models focused on the entire brain for NC. This supports current research on ROIs involved in AD. We believe that explaining deep learning models would not only provide support for existing research on brain disorders, but also offer important referential recommendations for the study of currently unknown etiologies.

PMID:38771733 | DOI:10.1371/journal.pone.0303278

IEEE Trans Neural Netw Learn Syst. 2024 May 21;PP. doi: 10.1109/TNNLS.2024.3394598. Online ahead of print.

ABSTRACT

Alzheimer's disease (AD) is a devastating neurodegenerative condition that precedes progressive and irreversible dementia; thus, predicting its progression over time is vital for clinical diagnosis and treatment. For this, numerous studies have implemented structural magnetic resonance imaging (MRI) to model AD progression, focusing on three integral aspects: 1) temporal variability; 2) incomplete observations; and 3) temporal geometric characteristics. However, many pioneer deep learning-based approaches addressing data variability and sparsity have yet to consider inherent geometrical properties sufficiently. These properties are integral to modeling as they correlate with brain region size, thickness, volume, and shape in AD progression. The ordinary differential equation-based geometric modeling method (ODE-RGRU) has recently emerged as a promising strategy for modeling time-series data by intertwining a recurrent neural network (RNN) and an ODE in Riemannian space. Despite its achievements, ODE-RGRU encounters limitations when extrapolating positive definite symmetric matrices from incomplete samples, leading to feature reverse occurrences that are particularly problematic, especially within the clinical facet. Therefore, this study proposes a novel geometric learning approach that models longitudinal MRI biomarkers and cognitive scores by combining three modules: topological space shift, ODE-RGRU, and trajectory estimation. We have also developed a training algorithm that integrates the manifold mapping with monotonicity constraints to reflect measurement transition irreversibility. We verify our proposed method's efficacy by predicting clinical labels and cognitive scores over time in regular and irregular settings. Furthermore, we thoroughly analyze our proposed framework through an ablation study.

PMID:38771688 | DOI:10.1109/TNNLS.2024.3394598

IEEE Trans Neural Syst Rehabil Eng. 2024 May 21;PP. doi: 10.1109/TNSRE.2024.3403723. Online ahead of print.

ABSTRACT

Electromyographic (EMG) signals have gained popularity for controlling prostheses and exoskeletons, particularly in the field of upper limbs for stroke patients. However, there is a lack of research in the lower limb area, and standardized open-source datasets of lower limb EMG signals, especially recording data of Asian race features, are scarce. Additionally, deep learning algorithms are rarely used for human motion intention recognition based on EMG, especially in the lower limb area. In response to these gaps, we present an open-source benchmark dataset of lower limb EMG with Asian race characteristics and large data volume, the JJ dataset, which includes approximately 13,350 clean EMG segments of 10 gait phases from 15 people. This is the first dataset of its kind to include the nine main muscles of human gait when walking. We used the processed time-domain signal as input and adjusted ResNet-18 as the classification tool. Our research explores and compares multiple key issues in this area, including the comparison of sliding time window method and other preprocessing methods, comparison of time-domain and frequency-domain signal processing effects, cross-subject motion recognition accuracy, and the possibility of using thigh and calf muscles in amputees. Our experiments demonstrate that the adjusted ResNet can achieve significant classification accuracy, with an average accuracy rate of 95.34% for human gait phases. Our research provides a valuable resource for future studies in this area and demonstrates the potential for ResNet as a robust and effective method for lower limb human motion intention pattern recognition.

PMID:38771681 | DOI:10.1109/TNSRE.2024.3403723

Health Care Manag Sci. 2024 May 21. doi: 10.1007/s10729-024-09673-8. Online ahead of print.

ABSTRACT

Proactive analysis of patient pathways helps healthcare providers anticipate treatment-related risks, identify outcomes, and allocate resources. Machine learning (ML) can leverage a patient's complete health history to make informed decisions about future events. However, previous work has mostly relied on so-called black-box models, which are unintelligible to humans, making it difficult for clinicians to apply such models. Our work introduces PatWay-Net, an ML framework designed for interpretable predictions of admission to the intensive care unit (ICU) for patients with symptoms of sepsis. We propose a novel type of recurrent neural network and combine it with multi-layer perceptrons to process the patient pathways and produce predictive yet interpretable results. We demonstrate its utility through a comprehensive dashboard that visualizes patient health trajectories, predictive outcomes, and associated risks. Our evaluation includes both predictive performance - where PatWay-Net outperforms standard models such as decision trees, random forests, and gradient-boosted decision trees - and clinical utility, validated through structured interviews with clinicians. By providing improved predictive accuracy along with interpretable and actionable insights, PatWay-Net serves as a valuable tool for healthcare decision support in the critical case of patients with symptoms of sepsis.

PMID:38771522 | DOI:10.1007/s10729-024-09673-8

Skeletal Radiol. 2024 May 21. doi: 10.1007/s00256-024-04692-6. Online ahead of print.

ABSTRACT

OBJECTIVE: This study aims to explore the feasibility of employing convolutional neural networks for detecting and localizing implant cutouts on anteroposterior pelvic radiographs.

MATERIALS AND METHODS: The research involves the development of two Deep Learning models. Initially, a model was created for image-level classification of implant cutouts using 40191 pelvic radiographs obtained from a single institution. The radiographs were partitioned into training, validation, and hold-out test datasets in a 6/2/2 ratio. Performance metrics including the area under the receiver operator characteristics curve (AUROC), sensitivity, and specificity were calculated using the test dataset. Additionally, a second object detection model was trained to localize implant cutouts within the same dataset. Bounding box visualizations were generated on images predicted as cutout-positive by the classification model in the test dataset, serving as an adjunct for assessing algorithm validity.

RESULTS: The classification model had an accuracy of 99.7%, sensitivity of 84.6%, specificity of 99.8%, AUROC of 0.998 (95% CI: 0.996, 0.999) and AUPRC of 0.774 (95% CI: 0.646, 0.880). From the pelvic radiographs predicted as cutout-positive, the object detection model could achieve 95.5% localization accuracy on true positive images, but falsely generated 14 results from the 15 false-positive predictions.

CONCLUSION: The classification model showed fair accuracy for detection of implant cutouts, while the object detection model effectively localized cutout. This serves as proof of concept of using a deep learning-based approach for classification and localization of implant cutouts from pelvic radiographs.

PMID:38771507 | DOI:10.1007/s00256-024-04692-6

Theor Appl Genet. 2024 May 21;137(6):138. doi: 10.1007/s00122-024-04649-2.

ABSTRACT

Residual neural network genomic selection is the first GS algorithm to reach 35 layers, and its prediction accuracy surpasses previous algorithms. With the decrease in DNA sequencing costs and the development of deep learning, phenotype prediction accuracy by genomic selection (GS) continues to improve. Residual networks, a widely validated deep learning technique, are introduced to deep learning for GS. Since each locus has a different weighted impact on the phenotype, strided convolutions are more suitable for GS problems than pooling layers. Through the above technological innovations, we propose a GS deep learning algorithm, residual neural network for genomic selection (ResGS). ResGS is the first neural network to reach 35 layers in GS. In 15 cases from four public data, the prediction accuracy of ResGS is higher than that of ridge-regression best linear unbiased prediction, support vector regression, random forest, gradient boosting regressor, and deep neural network genomic prediction in most cases. ResGS performs well in dealing with gene-environment interaction. Phenotypes from other environments are imported into ResGS along with genetic data. The prediction results are much better than just providing genetic data as input, which demonstrates the effectiveness of GS multi-modal learning. Standard deviation is recommended as an auxiliary GS evaluation metric, which could improve the distribution of predicted results. Deep learning for GS, such as ResGS, is becoming more accurate in phenotype prediction.

PMID:38771334 | DOI:10.1007/s00122-024-04649-2

Phys Chem Chem Phys. 2024 May 21. doi: 10.1039/d4cp00974f. Online ahead of print.

ABSTRACT

The manipulation of crystallographic defects in 2H-transition metal dichalcogenides (2H-TMDCs), whether pre- or post-synthesis, has garnered significant interest recently, as it holds the promise of tuning the thermal, chemical, and electronic properties of these materials. However, such desirable improvements often come at the cost of deteriorated elastic and inelastic properties, which may lead to serious concerns considering mechanical reliability issues. Therefore, persistent efforts are needed to explore the effects of energetically favorable vacancies on the mechanical properties of 2D TMDCs for an effective tuning of material properties for versatile applications. In this context, machine learning models trained on data based on molecular models can not only provide fast, efficient material models but also unearth crucial structure-property relations. However, such efforts are at an early stage of development. In this study, machine learning and deep learning techniques are used to analyze the mechanical properties of 2D transition metal dichalcogenides (TMDCs) in both pristine and defect forms. The goal is to predict failure stress, strain to failure, and strength based on chirality and strain. Various crystallographic defects were considered, and extensive molecular dynamics simulations were performed. XGBoost and densely connected neural network (DenseNet) algorithms were used to make accurate state-of-the-art predictions, and comparative evaluation and Shapley value analysis of both models are presented to improve interpretability.

PMID:38771309 | DOI:10.1039/d4cp00974f

JMIR Med Inform. 2024 May 17;12:e50117. doi: 10.2196/50117.

ABSTRACT

BACKGROUND: With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems.

OBJECTIVE: To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression.

METHODS: We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms.

RESULTS: Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results.

CONCLUSIONS: This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

PMID:38771237 | DOI:10.2196/50117

JMIR Med Inform. 2024 May 14;12:e57026. doi: 10.2196/57026.

ABSTRACT

BACKGROUND: Ventilator-associated pneumonia (VAP) is a serious complication of mechanical ventilation therapy that affects patients' treatments and prognoses. Owing to its excellent data mining capabilities, artificial intelligence (AI) has been increasingly used to predict VAP.

OBJECTIVE: This paper reviews VAP prediction models that are based on AI, providing a reference for the early identification of high-risk groups in future clinical practice.

METHODS: A scoping review was conducted in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. The Wanfang database, the Chinese Biomedical Literature Database, Cochrane Library, Web of Science, PubMed, MEDLINE, and Embase were searched to identify relevant articles. Study selection and data extraction were independently conducted by 2 reviewers. The data extracted from the included studies were synthesized narratively.

RESULTS: Of the 137 publications retrieved, 11 were included in this scoping review. The included studies reported the use of AI for predicting VAP. All 11 studies predicted VAP occurrence, and studies on VAP prognosis were excluded. Further, these studies used text data, and none of them involved imaging data. Public databases were the primary sources of data for model building (studies: 6/11, 55%), and 5 studies had sample sizes of <1000. Machine learning was the primary algorithm for studying the VAP prediction models. However, deep learning and large language models were not used to construct VAP prediction models. The random forest model was the most commonly used model (studies: 5/11, 45%). All studies only performed internal validations, and none of them addressed how to implement and apply the final model in real-life clinical settings.

CONCLUSIONS: This review presents an overview of studies that used AI to predict and diagnose VAP. AI models have better predictive performance than traditional methods and are expected to provide indispensable tools for VAP risk prediction in the future. However, the current research is in the model construction and validation stage, and the implementation of and guidance for clinical VAP prediction require further research.

PMID:38771220 | DOI:10.2196/57026

Small. 2024 May 21:e2402685. doi: 10.1002/smll.202402685. Online ahead of print.

ABSTRACT

Designing novel materials is greatly dependent on understanding the design principles, physical mechanisms, and modeling methods of material microstructures, requiring experienced designers with expertise and several rounds of trial and error. Although recent advances in deep generative networks have enabled the inverse design of material microstructures, most studies involve property-conditional generation and focus on a specific type of structure, resulting in limited generation diversity and poor human-computer interaction. In this study, a pioneering text-to-microstructure deep generative network (Txt2Microstruct-Net) is proposed that enables the generation of 3D material microstructures directly from text prompts without additional optimization procedures. The Txt2Microstruct-Net model is trained on a large microstructure-caption paired dataset that is extensible using the algorithms provided. Moreover, the model is sufficiently flexible to generate different geometric representations, such as voxels and point clouds. The model's performance is also demonstrated in the inverse design of material microstructures and metamaterials. It has promising potential for interactive microstructure design when associated with large language models and could be a user-friendly tool for material design and discovery.

PMID:38770745 | DOI:10.1002/smll.202402685

Int J Neural Syst. 2024 May 22:2450043. doi: 10.1142/S0129065724500436. Online ahead of print.

ABSTRACT

Neurodegenerative diseases pose a formidable challenge to medical research, demanding a nuanced understanding of their progressive nature. In this regard, latent generative models can effectively be used in a data-driven modeling of different dimensions of neurodegeneration, framed within the context of the manifold hypothesis. This paper proposes a joint framework for a multi-modal, common latent generative model to address the need for a more comprehensive understanding of the neurodegenerative landscape in the context of Parkinson's disease (PD). The proposed architecture uses coupled variational autoencoders (VAEs) to joint model a common latent space to both neuroimaging and clinical data from the Parkinson's Progression Markers Initiative (PPMI). Alternative loss functions, different normalization procedures, and the interpretability and explainability of latent generative models are addressed, leading to a model that was able to predict clinical symptomatology in the test set, as measured by the unified Parkinson's disease rating scale (UPDRS), with R2 up to 0.86 for same-modality and 0.441 cross-modality (using solely neuroimaging). The findings provide a foundation for further advancements in the field of clinical research and practice, with potential applications in decision-making processes for PD. The study also highlights the limitations and capabilities of the proposed model, emphasizing its direct interpretability and potential impact on understanding and interpreting neuroimaging patterns associated with PD symptomatology.

PMID:38770651 | DOI:10.1142/S0129065724500436

Oncoscience. 2024 May 20;11:49-50. doi: 10.18632/oncoscience.603. eCollection 2024.

NO ABSTRACT

PMID:38770445 | PMC:PMC11104407 | DOI:10.18632/oncoscience.603

Front Genet. 2024 May 6;15:1393406. doi: 10.3389/fgene.2024.1393406. eCollection 2024.

ABSTRACT

MOTIVATION: In recent years, there have been significant advances in various chromatin conformation capture techniques, and annotating the topological structure from Hi-C contact maps has become crucial for studying the three-dimensional structure of chromosomes. However, the structure and function of chromatin loops are highly dynamic and diverse, influenced by multiple factors. Therefore, obtaining the three-dimensional structure of the genome remains a challenging task. Among many chromatin loop prediction methods, it is difficult to fully extract features from the contact map and make accurate predictions at low sequencing depths.

RESULTS: In this study, we put forward a deep learning framework based on the diffusion model called CD-Loop for predicting accurate chromatin loops. First, by pre-training the input data, we obtain prior probabilities for predicting the classification of the Hi-C contact map. Then, by combining the denoising process based on the diffusion model and the prior probability obtained by pre-training, candidate loops were predicted from the input Hi-C contact map. Finally, CD-Loop uses a density-based clustering algorithm to cluster the candidate chromatin loops and predict the final chromatin loops. We compared CD-Loop with the currently popular methods, such as Peakachu, Chromosight, and Mustache, and found that in different cell types, species, and sequencing depths, CD-Loop outperforms other methods in loop annotation. We conclude that CD-Loop can accurately predict chromatin loops and reveal cell-type specificity. The code is available at https://github.com/wangyang199897/CD-Loop.

PMID:38770419 | PMC:PMC11102972 | DOI:10.3389/fgene.2024.1393406

Front Genet. 2024 May 6;15:1381997. doi: 10.3389/fgene.2024.1381997. eCollection 2024.

ABSTRACT

Accurate identification of potential drug-target pairs is a crucial step in drug development and drug repositioning, which is characterized by the ability of the drug to bind to and modulate the activity of the target molecule, resulting in the desired therapeutic effect. As machine learning and deep learning technologies advance, an increasing number of models are being engaged for the prediction of drug-target interactions. However, there is still a great challenge to improve the accuracy and efficiency of predicting. In this study, we proposed a deep learning method called Multi-source Information Fusion and Attention Mechanism for Drug-Target Interaction (MIFAM-DTI) to predict drug-target interactions. Firstly, the physicochemical property feature vector and the Molecular ACCess System molecular fingerprint feature vector of a drug were extracted based on its SMILES sequence. The dipeptide composition feature vector and the Evolutionary Scale Modeling -1b feature vector of a target were constructed based on its amino acid sequence information. Secondly, the PCA method was employed to reduce the dimensionality of the four feature vectors, and the adjacency matrices were constructed by calculating the cosine similarity. Thirdly, the two feature vectors of each drug were concatenated and the two adjacency matrices were subjected to a logical OR operation. And then they were fed into a model composed of graph attention network and multi-head self-attention to obtain the final drug feature vectors. With the same method, the final target feature vectors were obtained. Finally, these final feature vectors were concatenated, which served as the input to a fully connected layer, resulting in the prediction output. MIFAM-DTI not only integrated multi-source information to capture the drug and target features more comprehensively, but also utilized the graph attention network and multi-head self-attention to autonomously learn attention weights and more comprehensively capture information in sequence data. Experimental results demonstrated that MIFAM-DTI outperformed state-of-the-art methods in terms of AUC and AUPR. Case study results of coenzymes involved in cellular energy metabolism also demonstrated the effectiveness and practicality of MIFAM-DTI. The source code and experimental data for MIFAM-DTI are available at https://github.com/Search-AB/MIFAM-DTI.

PMID:38770418 | PMC:PMC11102998 | DOI:10.3389/fgene.2024.1381997

Front Hum Neurosci. 2024 May 6;18:1348154. doi: 10.3389/fnhum.2024.1348154. eCollection 2024.

ABSTRACT

INTRODUCTION: The primary objective of this research is to examine acrophobia, a widely prevalent and highly severe phobia characterized by an overwhelming dread of heights, which has a substantial impact on a significant proportion of individuals worldwide. The objective of our study was to develop a real-time and precise instrument for evaluating levels of acrophobia by utilizing electroencephalogram (EEG) signals.

METHODS: EEG data was gathered from a sample of 18 individuals diagnosed with acrophobia. Subsequently, a range of classifiers, namely Support Vector Classifier (SVC), K-nearest Neighbors (KNN), Random Forest (RF), Decision Tree (DT), Adaboost, Linear Discriminant Analysis (LDA), Convolutional Neural Network (CNN), and Artificial Neural Network (ANN), were employed in the analysis. These methodologies encompass both machine learning (ML) and deep learning (DL) techniques.

RESULTS: The Convolutional Neural Network (CNN) and Artificial Neural Network (ANN) models demonstrated notable efficacy. The Convolutional Neural Network (CNN) model demonstrated a training accuracy of 96% and a testing accuracy of 99%, whereas the Artificial Neural Network (ANN) model attained a training accuracy of 96% and a testing accuracy of 97%. The findings of this study highlight the effectiveness of the proposed methodology in accurately categorizing real-time degrees of acrophobia using EEG data. Further investigation using correlation matrices for each level of acrophobia showed substantial EEG frequency band connections. Beta and Gamma mean values correlated strongly, suggesting cognitive arousal and acrophobic involvement could synchronize activity. Beta and Gamma activity correlated strongly with acrophobia, especially at higher levels.

DISCUSSION: The results underscore the promise of this innovative approach as a dependable and sophisticated method for evaluating acrophobia. This methodology has the potential to make a substantial contribution toward the comprehension and assessment of acrophobia, hence facilitating the development of more individualized and efficacious therapeutic interventions.

PMID:38770396 | PMC:PMC11102978 | DOI:10.3389/fnhum.2024.1348154

Gen Psychiatr. 2024 May 17;37(3):e101425. doi: 10.1136/gpsych-2023-101425. eCollection 2024.

ABSTRACT

BACKGROUND: The role of human lineage mutations (HLMs) in human evolution through post-transcriptional modification is unclear.

AIMS: To investigate the contribution of HLMs to human evolution through post-transcriptional modification.

METHODS: We applied a deep learning model Seqweaver to predict how HLMs impact RNA-binding protein affinity.

RESULTS: We found that only 0.27% of HLMs had significant impacts on RNA-binding proteins at the threshold of the top 1% of human common variations. These HLMs enriched in a set of conserved genes highly expressed in adult excitatory neurons and prenatal Purkinje neurons, and were involved in synapse organisation and the GTPase pathway. These genes also carried excess damaging coding mutations that caused neurodevelopmental disorders, ataxia and schizophrenia. Among these genes, NTRK2 and ITPR1 had the most aggregated evidence of functional importance, suggesting their essential roles in cognition and bipedalism.

CONCLUSIONS: Our findings suggest that a small subset of human-specific mutations have contributed to human speciation through impacts on post-transcriptional modification of critical brain-related genes.

PMID:38770356 | PMC:PMC11103204 | DOI:10.1136/gpsych-2023-101425

Heliyon. 2024 May 4;10(10):e30763. doi: 10.1016/j.heliyon.2024.e30763. eCollection 2024 May 30.

ABSTRACT

Accurate delineation of Gross Tumor Volume (GTV) is crucial for radiotherapy. Deep learning-driven GTV segmentation technologies excel in rapidly and accurately delineating GTV, providing a basis for radiologists in formulating radiation plans. The existing 2D and 3D segmentation models of GTV based on deep learning are limited by the loss of spatial features and anisotropy respectively, and are both affected by the variability of tumor characteristics, blurred boundaries, and background interference. All these factors seriously affect the segmentation performance. To address the above issues, a Layer-Volume Parallel Attention (LVPA)-UNet model based on 2D-3D architecture has been proposed in this study, in which three strategies are introduced. Firstly, 2D and 3D workflows are introduced in the LVPA-UNet. They work in parallel and can guide each other. Both the fine features of each slice of 2D MRI and the 3D anatomical structure and spatial features of the tumor can be extracted by them. Secondly, parallel multi-branch depth-wise strip convolutions adapt the model to tumors of varying shapes and sizes within slices and volumetric spaces, and achieve refined processing of blurred boundaries. Lastly, a Layer-Channel Attention mechanism is proposed to adaptively adjust the weights of slices and channels according to their different tumor information, and then to highlight slices and channels with tumor. The experiments by LVPA-UNet on 1010 nasopharyngeal carcinoma (NPC) MRI datasets from three centers show a DSC of 0.7907, precision of 0.7929, recall of 0.8025, and HD95 of 1.8702 mm, outperforming eight typical models. Compared to the baseline model, it improves DSC by 2.14 %, precision by 2.96 %, and recall by 1.01 %, while reducing HD95 by 0.5434 mm. Consequently, while ensuring the efficiency of segmentation through deep learning, LVPA-UNet is able to provide superior GTV delineation results for radiotherapy and offer technical support for precision medicine.

PMID:38770315 | PMC:PMC11103467 | DOI:10.1016/j.heliyon.2024.e30763