Med Phys. 2024 Nov 13. doi: 10.1002/mp.17493. Online ahead of print.

ABSTRACT

BACKGROUND: Automatic primary gross tumor volume (GTVp) segmentation for nasopharyngeal carcinoma (NPC) is a quite challenging task because of the existence of similar visual characteristics between tumors and their surroundings, especially on computed tomography (CT) images with severe low contrast resolution. Therefore, most recently proposed methods based on radiomics or deep learning (DL) is difficult to achieve good results on CT datasets.

PURPOSE: A peritumoral radiomics-guided generative adversarial network (PRG-GAN) was proposed to address this challenge.

METHODS: A total of 157 NPC patients with CT images was collected and divided into training, validation, and testing cohorts of 108, 9, and 30 patients, respectively. The proposed model was based on a standard GAN consisting of a generator network and a discriminator network. Morphological dilation on the initial segmentation results from GAN was first conducted to delineate annular peritumoral region, in which radiomics features were extracted as priori guide knowledge. Then, radiomics features were fused with semantic features by the discriminator's fully connected layer to achieve the voxel-level classification and segmentation. The dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD) were used to evaluate the segmentation performance using a paired samples t-test with Bonferroni correction and Cohen's d (d) effect sizes. A two-sided p-value of less than 0.05 was considered statistically significant.

RESULTS: The model-generated predictions had a high overlap ratio with the ground truth. The average DSC, HD95, and ASSD were significantly improved from 0.80 ± 0.12, 4.65 ± 4.71 mm, and 1.35 ± 1.15 mm of GAN to 0.85 ± 0.18 (p = 0.001, d = 0.71), 4.15 ± 7.56 mm (p = 0.002, d = 0.67), and 1.11 ± 1.65 mm (p < 0.001, d = 0.46) of PRG-GAN, respectively.

CONCLUSION: Integrating radiomics features into GAN is promising to solve unclear border limitations and increase the delineation accuracy of GTVp for patients with NPC.

PMID:39535436 | DOI:10.1002/mp.17493

Int J Med Robot. 2024 Dec;20(6):e70004. doi: 10.1002/rcs.70004.

ABSTRACT

BACKGROUND: Accurately annotated CT images of liver tumours can effectively assist doctors in diagnosing and treating liver cancer. However, due to the relatively low density of the liver, its tumours, and surrounding tissues, as well as the existence of multi-scale problems, accurate automatic segmentation still faces challenges.

METHODS: We propose a segmentation network DSA-Former that combines convolutional kernels and attention. By combining the morphological and edge features of liver tumour images, capture global/local features and key inter-layer information, and integrate attention mechanisms obtaining detailed information to improve segmentation accuracy.

RESULTS: Compared to other methods, our approach demonstrates significant advantages in evaluation metrics such as the Dice coefficient, IOU, VOE, and HD95. Specifically, we achieve Dice coefficients of 96.8% for liver segmentation and 72.2% for liver tumour segmentation.

CONCLUSION: Our method offers enhanced precision in segmenting liver and liver tumour images, laying a robust foundation for liver cancer diagnosis and treatment.

PMID:39535347 | DOI:10.1002/rcs.70004

Harefuah. 2024 Nov;163(10):668-672.

ABSTRACT

For millennia, the ethos of "First, Do No Harm", attributed to Hippocrates, has been a cornerstone of medicine. This principle emphasizes the responsibility and ethical commitment of the clinician to the benefit of their patient. Recently, the rapid development of artificial intelligence (AI) is transforming the medical world, significantly affecting not only diagnosis, treatment plans, research, medical education, and medical ethics, but also the way we think. To maximize the benefits of AI, understand its limitations, and prevent potential harm to patients, clinicians should be aware of the principles underlying artificial intelligence. Such familiarity will enable the clinician to correctly assess outputs generated by AI tools; from medical recommendations proposed by targeted systems (such as a decision-support system for the interpretation of chest radiography) to diagnoses and treatment plans proposed by non-specific AI tools such as large language models. Developments in computing power, algorithms, and data storage have enabled significant progress in the world of AI, including the emergence of generative AI. This review bridges fundamental medical research concepts with stages of AI development, encompassing neural networks, and deep learning principles. It offers a glossary of commonly used AI terms and provides insights into the development and functioning of large language models. The potential influence of AI on the patient-physician relationship is also discussed. Several proposals are presented for actionable items that may improve the integration of AI into clinical work while maintaining the basic ethical principles of beneficence, non-maleficence, justice, and autonomy. They include proper model training, regulation, and involvement of the medical community in the development and integration of these models into clinical practice. Such involvement will ensure that the ethical principles of medicine remain at the forefront, and are not compromised by the interests of the developing entities. Disclosures: Prof. Sharon Einav and Or Degany are employed by Medint Medical Intelligence.

PMID:39535019

Cogn Neurodyn. 2024 Jun;18(3):1135-1151. doi: 10.1007/s11571-023-09967-7. Epub 2023 May 5.

ABSTRACT

In this work, we propose a dual path deep learning architecture for the application of visual brain decoding. The inputs to the proposed network are the electroencephalogram (EEG) signals which are evoked due to the external stimuli, specifically, images in this case. The objective is to classify the EEG signals based on the image categories under which they were evoked. Our approach involves the combinations of convolution neural networks (CNN) on the time axis and the channel axis. Importantly, for the purpose of learning subject-invariant features, we also make use of the gradient reversal layer (GRL). This addition to our network boosts the performance of our system. In addition, we also propose to use guided back-propagation for the selection of more informative EEG channels, and finally, with the reduced number of channels, we estimate the performance of the proposed network which is almost similar to the version when considering all EEG channels.

PMID:39534363 | PMC:PMC11551094 | DOI:10.1007/s11571-023-09967-7

JTCVS Open. 2024 Aug 17;21:290-303. doi: 10.1016/j.xjon.2024.07.018. eCollection 2024 Oct.

ABSTRACT

OBJECTIVES: To develop computed tomography (CT)-based models to increase the prediction accuracy of spread through air spaces (STAS) in clinical-stage T1N0 lung adenocarcinoma.

METHODS: Three cohorts of patients with stage T1N0 lung adenocarcinoma (n = 1258) were analyzed retrospectively. Two models using radiomics and deep neural networks (DNNs) were established to predict the lung adenocarcinoma STAS status. For the radiomic models, features were extracted using PyRadiomics, and 10 features with nonzero coefficients were selected using least absolute shrinkage and selection operator regression to construct the models. For the DNN models, a 2-stage (supervised contrastive learning and fine-tuning) deep-learning model, MultiCL, was constructed using CT images and the STAS status as training data. The area under the curve (AUC) was used to verify the predictive ability of both model types for the STAS status.

RESULTS: Among the radiomic models, the linear discriminant analysis model exhibited the best performance, with AUC values of 0.8944 (95% confidence interval [CI], 0.8241-0.9502) and 0.7796 (95% CI, 0.7089-0.8448) for predicting the STAS status on the test and external validation cohorts, respectively. Among the DNN models, MultiCL exhibited the best performance, with AUC values of 0.8434 (95% CI, 0.7580-0.9154) for the test cohort and 0.7686 (95% CI, 0.6991-0.8316) for the external validation cohort.

CONCLUSIONS: CT-based imaging models (radiomics and DNNs) can accurately identify the STAS status of clinical-stage T1N0 lung adenocarcinoma, potentially guiding surgical decision making and improving patient outcomes.

PMID:39534334 | PMC:PMC11551290 | DOI:10.1016/j.xjon.2024.07.018

Proc SPIE Int Soc Opt Eng. 2024 Feb;12925:129251D. doi: 10.1117/12.3005368. Epub 2024 Apr 1.

ABSTRACT

We proposed a deep learning-based method for single-heartbeat 4D cardiac CT reconstruction, where a single cardiac cycle was split into multiple phases for reconstruction. First, we pre-reconstruct each phase using the projection data from itself and the neighboring phases. The pre-reconstructions are fed into a supervised registration network to generate the deformation fields between different phases. The deformation fields are trained so that it can match the ground truth images from the corresponding phases. The deformation fields are then used in the FBP-and-wrap method for motion-compensated reconstruction, where a subsequent network is used to remove residual artifacts. The proposed method was validated with simulation data from 40 4D cardiac CT scans and demonstrated improved RMSE and SSIM and less blurring compared to FBP and PICCS.

PMID:39534279 | PMC:PMC11555688 | DOI:10.1117/12.3005368

ACS Appl Mater Interfaces. 2024 Nov 6. doi: 10.1021/acsami.4c12852. Online ahead of print.

ABSTRACT

Conductive organohydrogels-based flexible pressure sensors have gained considerable attention in health monitoring, artificial skin, and human-computer interaction due to their excellent biocompatibility, wearability, and versatility. However, hydrogels' unsatisfactory mechanical and unstable electrical properties hinder their comprehensive application. Herein, an elastic, fatigue-resistant, and antifreezing poly(vinyl alcohol) (PVA)/lipoic acid (LA) organohydrogel with a double-network structure and reversible cross-linking interactions has been designed, and MXene as a conductive filler is functionalized into organohydrogel to further enhance the diverse sensing performance of flexible pressure sensors. The as-fabricated MXene-based PVA/LA organohydrogels (PLBM) exhibit stable fatigue resistance for over 450 cycles under 40% compressive strain, excellent elasticity, antifreezing properties (<-20 °C), and degradability. Furthermore, the pressure sensors based on the PLBM organohydrogels show a fast response time (62 ms), high sensitivity (S = 0.0402 kPa-1), and excellent stability (over 1000 cycles). The exceptional performance enables the sensors to monitor human movements, such as joint flexion and throat swallowing. Moreover, the sensors integrating with the one-dimensional convolutional neural networks and the long-short-term memory networks deep learning algorithms have been developed to recognize letters with a 93.75% accuracy, representing enormous potential in monitoring human motion and human-computer interaction.

PMID:39506450 | DOI:10.1021/acsami.4c12852

Comput Methods Biomech Biomed Engin. 2024 Nov 7:1-15. doi: 10.1080/10255842.2024.2404149. Online ahead of print.

ABSTRACT

The SARS-CoV-2 virus reportedly originated in Wuhan in 2019, causing the coronavirus outbreak (COVID-19), which was technically designated as a global epidemic. Numerous studies have been carried out to diagnose and treat COVID-19 throughout the midst of the disease's spread. However, the genetic similarity between COVID-19 and other types of coronaviruses makes it challenging to differentiate between them. Therefore it's essential to swiftly identify if an epidemic is brought on by a brand-new virus or a well-known disease. In the present article, the DeepCoV deep-learning (DL) approach utilizes layered convolutional neural networks (CNNs) to classify viral serious acute respiratory syndrome coronavirus 2 (SARS-CoV-2) besides other viral diseases. Additionally, various motifs linked with SARS-CoV-2 can be located by examining the computational filter processes. In identifying these important motifs, DeepCoV reveals the transparency of CNNs. Experiments were conducted using the 2019nCoVR datasets, and the results indicate that DeepCoV performed more accurately than several benchmark ML models. Additionally, DeepCoV scored its maximum area under the precision-recall curve (AUCPR) and receiver operating characteristic curve (AUC-ROC) at 98.62% and 98.58%, respectively. Overall, these investigations provide strong knowledge of the employment of deep learning (DL) algorithms as a crucial alternative to identifying SARS-CoV-2 and identifying patterns of disease in the SARS-CoV-2 genes.

PMID:39508163 | DOI:10.1080/10255842.2024.2404149

Front Immunol. 2024 Oct 23;15:1468599. doi: 10.3389/fimmu.2024.1468599. eCollection 2024.

ABSTRACT

INTRODUCTION: Antibodies represent a specific class of proteins produced by the adaptive immune system in response to pathogens. Mining the information embedded in antibody amino acid sequences can benefit both antibody property prediction and novel therapeutic development. However, antibodies possess unique features that should be incorporated using specifically designed training methods, leaving room for improvement in pre-training models for antibody sequences.

METHODS: In this study, we present a Pre-trained model of Antibody sequences trained with a Rational Approach for antibodies (PARA). PARA employs a strategy conforming to antibody sequence patterns and an advanced natural language processing self-encoding model structure. This approach addresses the limitations of existing protein pre-training models, which primarily utilize language models without fully considering the differences between protein sequences and language sequences.

RESULTS: We demonstrate PARA's performance on several tasks by comparing it to various published pre-training models of antibodies. The results show that PARA significantly outperforms existing models on these tasks, suggesting that PARA has an advantage in capturing antibody sequence information.

DISCUSSION: The antibody latent representation provided by PARA can substantially facilitate studies in relevant areas. We believe that PARA's superior performance in capturing antibody sequence information offers significant potential for both antibody property prediction and the development of novel therapeutics. PARA is available at https://github.com/xtalpi-xic.

PMID:39507535 | PMC:PMC11537868 | DOI:10.3389/fimmu.2024.1468599

Ann Transl Med. 2024 Oct 20;12(5):89. doi: 10.21037/atm-24-73. Epub 2024 Oct 12.

ABSTRACT

BACKGROUND: The opaqueness of artificial intelligence (AI) algorithms decision processes limit their application in healthcare. Our objective was to explore discrepancies in heatmaps originated from slightly different retinal images from the same eyes of individuals with diabetes, to gain insights into the deep learning (DL) decision process.

METHODS: Pairs of retinal images from the same eyes of individuals with diabetes, composed of images obtained before and after pupil dilation, underwent automatic analysis by a convolutional neural network for the presence of diabetic retinopathy (DR), output being a score ranging from 0 to 1. Gradient-based Class Activation Maps (GradCam) allowed visualization of activated areas. Pairs of images with discordant DL scores or outputs within the pair were objectively compared to the concordant pairs, regarding the sum of activations of Class Activation Mapping (CAM), the number of activated areas, and DL score differences. Heatmaps of discordant pairs were also qualitatively assessed.

RESULTS: Algorithmic performance for the detection of DR attained 89.8% sensitivity, 96.3% specificity and area under the receiver operating characteristic (ROC) curve of 0.95. Out of 210 comparable pairs of images, 20 eyes and 10 eyes were considered discordant according to DL score difference and regarding DL output, respectively. Comparison of concordant versus discordant groups showed statistically significant differences for all objective variables. Qualitative analysis pointed to subtle differences in image quality within discordant pairs.

CONCLUSIONS: The successfully established relationship among objective parameters extracted from heatmaps and DL output discrepancies reinforces the role of heatmaps for DL explainability, fostering acceptance of DL systems for clinical use.

PMID:39507460 | PMC:PMC11534741 | DOI:10.21037/atm-24-73

Eur J Radiol Open. 2024 Oct 24;13:100606. doi: 10.1016/j.ejro.2024.100606. eCollection 2024 Dec.

ABSTRACT

BACKGROUND: Chest radiographs (CXRs) are widely used to screen for infectious diseases like tuberculosis and COVID-19 among migrants. At such high-volume settings, manual CXR reporting is challenging and integrating artificial intelligence (AI) algorithms into the workflow help to rule out normal findings in minutes, allowing radiologists to focus on abnormal cases.

METHODS: In this post-deployment study, all the CXRs acquired during the visa screening process across 33 centers in United Arab Emirates from January 2021 to June 2022 (18 months) were included. The qXR v2.1 chest X-ray interpretation software was used to classify the scans into normal and abnormal, and its agreement against radiologist was evaluated. Additionally, a digital survey was conducted among 20 healthcare professionals with prior AI experience to understand real-world implementation challenges and impact.

RESULTS: The analysis of 1309,443 CXRs from 1309,431 patients (median age: 35 years; IQR [29-42]; 1030,071 males [78.7 %]) in this study revealed a Negative Predictive Value (NPV) of 99.92 % (95 % CI: 99.92, 99.93), Positive Predictive Value (PPV) of 5.06 % (95 % CI: 4.99, 5.13) and overall percent agreement of the AI with radiologists of 72.90 % (95 % CI: 72.82, 72.98). In the survey, majority (88.2 %) of the radiologists agreed to turnaround time reduction after AI integration, while 82 % suggested that the AI improved their diagnostic accuracy.

DISCUSSION: In contrast with the existing studies, this research uses a substantially large data. A high NPV and satisfactory agreement with human readers indicate that AI can reliably identify normal CXRs, making it suitable for routine applications.

PMID:39507100 | PMC:PMC11539241 | DOI:10.1016/j.ejro.2024.100606

Transl Lung Cancer Res. 2024 Oct 31;13(10):2746-2760. doi: 10.21037/tlcr-24-716. Epub 2024 Oct 17.

ABSTRACT

BACKGROUND: Glycolysis proved to have a prognostic value in lung cancer; however, to identify glycolysis-related genomic markers is expensive and challenging. This study aimed at identifying glycolysis-related computed tomography (CT) radiomics features to develop a deep-learning prognostic model for non-small cell lung cancer (NSCLC).

METHODS: The study included 274 NSCLC patients from cohorts of The Second Affiliated Hospital of Soochow University (SZ; n=64), the Cancer Genome Atlas (TCGA)-NSCLC dataset (n=74), and the Gene Expression Omnibus dataset (n=136). Initially, the glycolysis enrichment scores were evaluated using a single-sample gene set enrichment analysis, and the cut-off values were optimized to investigate the prognostic potential of glycolysis genes. Radiomic features were then extracted using LIFEx software. The least absolute reduction and selection operator (LASSO) algorithm was employed to determine the glycolytic CT radiomics features. A deep-learning prognostic model was constructed by integrating CT radiomics and clinical features. The biological functions of the model were analyzed by incorporating RNA sequencing data.

RESULTS: Kaplan-Meier curves indicated that elevated glycolysis levels were associated with poorer survival outcomes. The LASSO algorithm identified 11 radiomic features that were then selected for inclusion in the deep-learning model. They have shown significant discrimination capability in assessing glycolysis status, achieving an area under the curve value of 0.8442. The glycolysis-based radiomics deep-learning model was named the DeepGR model. This model was able to effectively predict the clinical outcomes of NSCLC patients with AUCs of 0.8760 and 0.8259 in the SZ and TCGA cohorts, respectively. High-risk DeepGR scores were strongly associated with poor overall survival, resting memory CD4+ T cells, and a high response to programmed cell death protein 1 immunotherapy.

CONCLUSIONS: The DeepGR model effectively predicted the prognosis of NSCLC patients.

PMID:39507025 | PMC:PMC11535831 | DOI:10.21037/tlcr-24-716

Heliyon. 2024 Oct 9;10(20):e38915. doi: 10.1016/j.heliyon.2024.e38915. eCollection 2024 Oct 30.

ABSTRACT

This study delves into the intricate interplay between gender stereotypes and financial reporting through an aspect-level sentiment analysis approach. Leveraging Big Data comprising 129,251 human face images extracted from 2085 financial reports in Chile, and employing Deep Learning techniques, we uncover the underlying factors influencing the representation of women in financial reports. Our findings reveal that gender stereotypes, combined with external economic factors, significantly shape the portrayal of women in financial reports, overshadowing intentional efforts by companies to influence stakeholder perceptions of financial performance. Notably, economic expansion periods correlate with a decline in women's representation, while economic instability amplifies their portrayal. Furthermore, the financial inclusion of women positively correlates with their presence in financial report images. Our results underscore a bias in image selection within financial reports, diverging from the neutrality principles advocated by the International Accounting Standards Board (IASB). This pioneering study, combining Big Data and Deep Learning, contributes to gender stereotype literature, financial report soft information research, and business impression management research.

PMID:39506953 | PMC:PMC11538733 | DOI:10.1016/j.heliyon.2024.e38915

ACS Appl Mater Interfaces. 2024 Nov 7. doi: 10.1021/acsami.4c13193. Online ahead of print.

ABSTRACT

Classifications of fluids using miniaturized sensors are of substantial importance for various fields of application. Modified with functional nanomaterials, a moisture-enabled electricity generation (MEG) device can execute a dual-purpose operation as both a self-powered framework and a fluid detection platform. In this study, a novel intelligent self-sustained sensing approach was implemented by integrating MEG with deep learning in microfluidics. Following a multilayer design, the MEG device including three individual units for power generation/fluid classification was fabricated in this study by using nonwoven fabrics, hydroxylated carbon nanotubes, poly(vinyl alcohol)-mixed gels, and indium tin bismuth liquid alloy. A composite configuration utilizing hydrophobic microfluidic channels and hydrophilic porous substrates was conducive to self-regulation of the on-chip flow. As a generator, the MEG device was capable of maintaining a continuous and stable power output for at least 6 h. As a sensor, the on-chip units synchronously measured the voltage (V), current (C), and resistance (R) signals as functions of time, whose transitions were completed using relays. These signals can serve as straightforward indicators of a fluid presence, such as the distinctive "fingerprint". After normalization and Fourier transform of raw V/C/R signals, a lightweight deep learning model (wide-kernel deep convolutional neural network, WDCNN) was employed for classifying pure water, kiwifruit, clementine, and lemon juices. In particular, the accuracy of the sample distinction using the WDCNN model was 100% within 15 s. The proposed integration of MEG, microfluidics, and deep learning provides a novel paradigm for the development of sustainable intelligent environmental perception, as well as new prospects for innovations in analytical science and smart instruments.

PMID:39506898 | DOI:10.1021/acsami.4c13193

Anal Chem. 2024 Nov 7. doi: 10.1021/acs.analchem.4c04479. Online ahead of print.

ABSTRACT

In photoacoustic spectroscopy based multicomponent gas analysis, the overlap of the absorption spectra among different gases can affect the measurement accuracy of gas concentrations. We report a multicomponent gas analysis method based on empirical modal decomposition (EMD), convolutional neural networks (CNN), and long short-term memory (LSTM) networks that can extract the exact concentrations of mixed gases from the overlapping wavelength-modulated spectroscopy with second harmonic (WMS-2f) detection. The WMS-2f signals of 25 different concentration combinations of acetylene-ammonia mixtures are detected using a single distributed feedback laser (DFB) at 1531.5 nm. The acetylene concentrations range from 2.5 to 7.5 ppm and the ammonia concentrations from 12.5 to 37.5 ppm. The data set is enhanced by cyclic shifting and adding Gaussian noise. The classification accuracy of the test set reaches 99.89% after tuning. The mean absolute errors of the five additional sets of data measured under different conditions are 0.092 ppm for acetylene and 1.902 ppm for ammonia, within the above concentration ranges.

PMID:39506893 | DOI:10.1021/acs.analchem.4c04479

J Ovarian Res. 2024 Nov 6;17(1):219. doi: 10.1186/s13048-024-01544-8.

ABSTRACT

OBJECTIVES: The study aimed to compare the diagnostic efficacy of the machine learning models with expert subjective assessment (SA) in assessing the malignancy risk of ovarian tumors using transvaginal ultrasound (TVUS).

METHODS: The retrospective single-center diagnostic study included 1555 consecutive patients from January 2019 to May 2021. Using this dataset, Residual Network(ResNet), Densely Connected Convolutional Network(DenseNet), Vision Transformer(ViT), and Swin Transformer models were established and evaluated separately or combined with Cancer antigen 125 (CA 125). The diagnostic performance was then compared with SA.

RESULTS: Of the 1555 patients, 76.9% were benign, while 23.1% were malignant (including borderline). When differentiating the malignant from ovarian tumors, the SA had an AUC of 0.97 (95% CI, 0.93-0.99), sensitivity of 87.2%, and specificity of 98.4%. Except for Vision Transformer, other machine learning models had diagnostic performance comparable to that of the expert. The DenseNet model had an AUC of 0.91 (95% CI, 0.86-0.95), sensitivity of 84.6%, and specificity of 95.1%. The ResNet50 model had an AUC of 0.91 (0.85-0.95). The Swin Transformer model had an AUC of 0.92 (0.87-0.96), sensitivity of 87.2%, and specificity of 94.3%. There was a statistically significant difference between the Vision Transformer and SA, and between the Vision Transformer and Swin Transformer models (AUC: 0.87 vs. 0.97, P = 0.01; AUC: 0.87 vs. 0.92, P = 0.04). Adding CA125 did not improve the diagnostic performance of the models in distinguishing benign and malignant ovarian tumors.

CONCLUSION: The deep learning model of TVUS can be used in ovarian cancer evaluation, and its diagnostic performance is comparable to that of expert assessment.

PMID:39506832 | DOI:10.1186/s13048-024-01544-8

BMC Bioinformatics. 2024 Nov 6;25(1):348. doi: 10.1186/s12859-024-05961-w.

ABSTRACT

BACKGROUND: Antibodies play a crucial role in disease treatment, leveraging their ability to selectively interact with the specific antigen. However, screening antibody gene sequences for target antigens via biological experiments is extremely time-consuming and labor-intensive. Several computational methods have been developed to predict antibody-antigen interaction while suffering from the lack of characterizing the underlying structure of the antibody.

RESULTS: Beneficial from the recent breakthroughs in deep learning for antibody structure prediction, we propose a novel neural network architecture to predict antibody-antigen interaction. We first introduce AbAgIPA: an antibody structure prediction network to obtain the antibody backbone structure, where the structural features of antibodies and antigens are encoded into representation vectors according to the amino acid physicochemical features and Invariant Point Attention (IPA) computation methods. Finally, the antibody-antigen interaction is predicted by global max pooling, feature concatenation, and a fully connected layer. We evaluated our method on antigen diversity and antigen-specific antibody-antigen interaction datasets. Additionally, our model exhibits a commendable level of interpretability, essential for understanding underlying interaction mechanisms.

CONCLUSIONS: Quantitative experimental results demonstrate that the new neural network architecture significantly outperforms the best sequence-based methods as well as the methods based on residue contact maps and graph convolution networks (GCNs). The source code is freely available on GitHub at https://github.com/gmthu66/AbAgIPA .

PMID:39506679 | DOI:10.1186/s12859-024-05961-w

Neuropsychopharmacology. 2024 Nov 6. doi: 10.1038/s41386-024-02021-y. Online ahead of print.

ABSTRACT

Brain alterations associated with illness severity in schizophrenia remain poorly understood. Establishing linkages between imaging biomarkers and symptom expression may enhance mechanistic understanding of acute psychotic illness. Constructing models using MRI and clinical features together to maximize model validity may be particularly useful for these purposes. A multi-task deep learning model for standard case/control recognition incorporated with psychosis symptom severity regression was constructed with anatomic MRI collected from 286 patients with drug-naïve first-episode schizophrenia and 330 healthy controls from two datasets, and validated with an independent dataset including 40 first-episode schizophrenia. To evaluate the contribution of regression to the case/control recognition, a single-task classification model was constructed. Performance of unprocessed anatomical images and of predefined imaging features obtained using voxel-based morphometry (VBM) and surface-based morphometry (SBM), were examined and compared. Brain regions contributing to the symptom severity regression and illness identification were identified. Models developed with unprocessed images achieved greater group separation than either VBM or SBM measurements, differentiating schizophrenia patients from healthy controls with a balanced accuracy of 83.0% with sensitivity = 76.1% and specificity = 89.0%. The multi-task model also showed superior performance to single-task classification model without considering clinical symptoms. These findings showed high replication in the site-split validation and external validation analyses. Measurements in parietal, occipital and medial frontal cortex and bilateral cerebellum had the greatest contribution to the multi-task model. Incorporating illness severity regression in pattern recognition algorithms, our study developed an MRI-based model that was of high diagnostic value in acutely ill schizophrenia patients, highlighting clinical relevance of the model.

PMID:39506100 | DOI:10.1038/s41386-024-02021-y

Nat Comput Sci. 2024 Nov 6. doi: 10.1038/s43588-024-00720-6. Online ahead of print.

ABSTRACT

RNAs represent a class of programmable biomolecules capable of performing diverse biological functions. Recent studies have developed accurate RNA three-dimensional structure prediction methods, which may enable new RNAs to be designed in a structure-guided manner. Here, we develop a structure-to-sequence deep learning platform for the de novo generative design of RNA aptamers. We show that our approach can design RNA aptamers that are predicted to be structurally similar, yet sequence dissimilar, to known light-up aptamers that fluoresce in the presence of small molecules. We experimentally validate several generated RNA aptamers to have fluorescent activity, show that these aptamers can be optimized for activity in silico, and find that they exhibit a mechanism of fluorescence similar to that of known light-up aptamers. Our results demonstrate how structural predictions can guide the targeted and resource-efficient design of new RNA sequences.

PMID:39506080 | DOI:10.1038/s43588-024-00720-6

Sci Rep. 2024 Nov 6;14(1):27000. doi: 10.1038/s41598-024-78557-2.

ABSTRACT

Traditional English corpora mainly collect information from a single modality, but lack information from multimodal information, resulting in low quality of corpus information and certain problems with recognition accuracy. To solve the above problems, this paper proposes to introduce depth information into multimodal corpora, and studies the construction method of English multimodal corpora that integrates electronic images and depth information, as well as the speech recognition method of the corpus. The multimodal fusion strategy adopted integrates speech signals and image information, including key visual information such as the speaker's lip movements and facial expressions, and uses deep learning technology to mine acoustic and visual features. The acoustic model in the Kaldi toolkit is used for experimental research.Through experimental research, the following conclusions were drawn: Under 15-dimensional lip features, the accuracy of corpus A under monophone model was 2.4% higher than that of corpus B under monophone model when the SNR (signal-to-noise ratio) was 10dB, and the accuracy of corpus A under the triphone model at the signal-to-noise ratio of 10dB was 1.7% higher than that of corpus B under the triphone model at the signal-to-noise ratio of 10dB. Under the 32-dimensional lip features, the speech recognition effect of corpus A under the monophone model at the SNR of 10dB was 1.4% higher than that of corpus B under the monophone model at the SNR of 10dB, and the accuracy of corpus A under the triphone model at the SNR of 10dB was 2.6% higher than that of corpus B under the triphone model at the SNR of 10dB. The English multimodal corpus with image and depth information has a high accuracy, and the depth information helps to improve the accuracy of the corpus.

PMID:39506055 | DOI:10.1038/s41598-024-78557-2