Front Med (Lausanne). 2024 Nov 14;11:1501652. doi: 10.3389/fmed.2024.1501652. eCollection 2024.

ABSTRACT

BACKGROUND: Radiomics, which involves the conversion of digital images into high-dimensional data, has been used in oncological studies since 2012. We analyzed the publications that had been conducted on this subject using bibliometric and visual methods to expound the hotpots and future trends regarding radiomics in evaluating lymph node status in oncology.

METHODS: Documents published between 2012 and 2023, updated to August 1, 2024, were searched using the Scopus database. VOSviewer, R Package, and Microsoft Excel were used for visualization.

RESULTS: A total of 898 original articles and reviews written in English and be related to radiomics for evaluating lymph node status in oncology, published between 2015 and 2023, were retrieved. A significant increase in the number of publications was observed, with an annual growth rate of 100.77%. The publications predominantly originated from three countries, with China leading in the number of publications and citations. Fudan University was the most contributing affiliation, followed by Sun Yat-sen University and Southern Medical University, all of which were from China. Tian J. from the Chinese Academy of Sciences contributed the most within 5885 authors. In addition, Frontiers in Oncology had the most publications and transcended other journals in recent 4 years. Moreover, the keywords co-occurrence suggested that the interplay of "radiomics" and "lymph node metastasis," as well as "major clinical study" were the predominant topics, furthermore, the focused topics shifted from revealing the diagnosis of cancers to exploring the deep learning-based prediction of lymph node metastasis, suggesting the combination of artificial intelligence research would develop in the future.

CONCLUSION: The present bibliometric and visual analysis described an approximately continuous trend of increasing publications related to radiomics in evaluating lymph node status in oncology and revealed that it could serve as an efficient tool for personalized diagnosis and treatment guidance in clinical patients, and combined artificial intelligence should be further considered in the future.

PMID:39610679 | PMC:PMC11602298 | DOI:10.3389/fmed.2024.1501652

Knowl Based Syst. 2024 Dec 3;305:112638. doi: 10.1016/j.knosys.2024.112638. Epub 2024 Oct 19.

ABSTRACT

The process of developing new drugs is both time-consuming and costly, often taking over a decade and billions of dollars to obtain regulatory approval. Additionally, the complexity of patent protection for novel compounds presents challenges for pharmaceutical innovation. Drug repositioning offers an alternative strategy to uncover new therapeutic uses for existing medicines. Previous repositioning models have been limited by their reliance on homogeneous data sources, failing to leverage the rich information available in heterogeneous biomedical knowledge graphs. We propose HeteroKGRep, a novel drug repositioning model that utilizes heterogeneous graphs to address these limitations. HeteroKGRep is a multi-step framework that first generates a similarity graph from hierarchical concept relations. It then applies SMOTE over-sampling to address class imbalance before generating node sequences using a heterogeneous graph neural network. Drug and disease embeddings are extracted from the network and used for prediction. We evaluated HeteroKGRep on a graph containing biomedical concepts and relations from ontologies, pathways and literature. It achieved state-of-the-art performance with 99% accuracy, 95% AUC ROC and 94% average precision on predicting repurposing opportunities. Compared to existing homogeneous approaches, HeteroKGRep leverages diverse knowledge sources to enrich representation learning. Based on heterogeneous graphs, HeteroKGRep can discover new drug-desease associations, leveraging de novo drug development. This work establishes a promising new paradigm for knowledge-guided drug repositioning using multimodal biomedical data.

PMID:39610660 | PMC:PMC11600970 | DOI:10.1016/j.knosys.2024.112638

J Diabetes Metab Disord. 2024 Sep 20;23(2):2289-2314. doi: 10.1007/s40200-024-01497-1. eCollection 2024 Dec.

ABSTRACT

OBJECTIVE: Diabetic retinopathy (DR) is a common problem of diabetes, and it is the cause of blindness worldwide. Detection of diabetic radiology disease in the early detection stage is crucial for preventing vision loss. In this work, a deep learning-based binary classification of DR images has been proposed to classify DR images into healthy and unhealthy. Transfer learning-based 20 pre-trained networks have been fine-tuned using a robust dataset of diabetic radiology images. The combined dataset has been collected from three robust databases of diabetic patients annotated by experienced ophthalmologists indicating healthy or non-healthy diabetic retina images.

METHOD: This work has improved robust models by pre-processing the DR images by applying a denoising algorithm, normalization, and data augmentation. In this work, three rubout datasets of diabetic retinopathy images have been selected, named DRD- EyePACS, IDRiD, and APTOS-2019, for the extensive experiments, and a combined diabetic retinopathy image dataset has been generated for the exhaustive experiments. The datasets have been divided into training, testing, and validation sets, and the models use classification accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC to assess the model's efficiency for evaluating network performance. The present work has selected 20 different pre-trained networks based on three categories: Series, DAG, and lightweight.

RESULTS: This study uses pre-processed data augmentation and normalization of data to solve overfitting problems. From the exhaustive experiments, the three best pre-trained have been selected based on the best classification accuracy from each category. It is concluded that the trained model ResNet101 based on the DAG category effectively identifies diabetic retinopathy disease accurately from radiological images from all cases. It is noted that 97.33% accuracy has been achieved using ResNet101 in the category of DAG network.

CONCLUSION: Based on the experiment results, the proposed model ResNet101 helps healthcare professionals detect retina diseases early and provides practical solutions to diabetes patients. It also gives patients and experts a second opinion for early detection of diabetic retinopathy.

PMID:39610484 | PMC:PMC11599653 | DOI:10.1007/s40200-024-01497-1

Artif Intell Med. 2024 Nov 20;159:103031. doi: 10.1016/j.artmed.2024.103031. Online ahead of print.

ABSTRACT

Antinuclear Antibody (ANA) testing is pivotal to help diagnose patients with a suspected autoimmune disease. The Indirect Immunofluorescence (IIF) microscopy performed with human epithelial type 2 (HEp-2) cells as the substrate is the reference method for ANA screening. It allows for the detection of antibodies binding to specific intracellular targets, resulting in various staining patterns that should be identified for diagnosis purposes. In recent years, there has been an increasing interest in devising deep learning methods for automated cell segmentation and classification of staining patterns, as well as for other tasks related to this diagnostic technique (such as intensity classification). However, little attention has been devoted to architectures aimed at simultaneously managing multiple interrelated tasks, via a shared representation. In this paper, we propose a deep neural network model that extends U-Net in a Multi-Task Learning (MTL) fashion, thus offering an end-to-end approach to tackle three fundamental tasks of the diagnostic procedure, i.e., HEp-2 cell specimen intensity classification, specimen segmentation, and pattern classification. The experiments were conducted on one of the largest publicly available datasets of HEp-2 images. The results showed that the proposed approach significantly outperformed the competing state-of-the-art methods for all the considered tasks.

PMID:39608042 | DOI:10.1016/j.artmed.2024.103031

Artif Intell Med. 2024 Nov 23;159:103025. doi: 10.1016/j.artmed.2024.103025. Online ahead of print.

ABSTRACT

The global burden of infectious diseases significantly affects mortality rates, with their varying symptoms making it challenging to assess and determine the severity of infections. Different countries face unique challenges related to these diseases. This study introduces innovative Artificial Intelligence (AI) based methodologies to enhance diagnostic accuracy through the analysis of medical imagery. It achieves this by developing a mathematical model capable of identifying potential infectious diseases from images, utilizing a Multi-Criteria Decision-Making (MCDM) framework. This cutting-edge approach combines Hypersoft Set (HSS) within a fuzzy context, pioneering in AI-driven diagnostic processes. The decision-making process might suggest actions such as isolation, quarantine in either domestic settings or specialized facilities, or admission to a hospital for further treatment. The use of visual aids in this research not only improves understanding but also highlights the effectiveness and significance of the proposed methods. The foundational theory and the results from this novel approach demonstrate its potential for widespread application in fields like machine learning, deep learning, and pattern recognition, indicating a significant stride in the fight against infectious diseases through advanced diagnostic techniques.

PMID:39608041 | DOI:10.1016/j.artmed.2024.103025

Comput Biol Med. 2024 Nov 27;184:109448. doi: 10.1016/j.compbiomed.2024.109448. Online ahead of print.

ABSTRACT

Cardiotocography (CTG) is the main tool available to detect neonatal acidemia during delivery. Presently, obstetricians and midwives primarily rely on visual interpretation, leading to a significant intra-observer variability. In this paper, we build and evaluate a convolutional neural network to detect neonatal acidemia from the CTG signals during delivery on a multicenter database with 27662 cases in five centers, including 3457 and 464 cases of moderate and severe neonatal acidemia respectively (defined by a fetal pH at birth between 7.05 and 7.20, and lower than 7.05 respectively). To use all the available records, the convolutional layers are pretrained on a task which consists in predicting several features known to be associated with neonatal acidemia from the raw CTG signals. In a cross-center evaluation, the AUC varies from 0.74 to 0.83 between the centers for the detection of severe acidemia, showing the ability of deep learning models to generalize from one dataset to the other and paving the way for more accurate models trained on larger databases. The model can still be significantly improved, by adding clinical variables to account for risk factors of acidemia that may not appear in the CTG signals. Further research will also be led to integrate the model in a tool that could assist humans in the interpretation of CTG.

PMID:39608037 | DOI:10.1016/j.compbiomed.2024.109448

Comput Biol Med. 2024 Nov 27;184:109447. doi: 10.1016/j.compbiomed.2024.109447. Online ahead of print.

ABSTRACT

Pharmaceutical companies increasingly use medicinal plants because they are cheaper and have fewer side effects than conventional drugs. Accurate identification and classification of medicinal plants is critical for guaranteeing scientific evidence-based usage of herbal treatments in traditional medicine, upholding pharmaceutical safety requirements, and contributing to biodiversity conservation efforts. However, conventional manual classification methods are time-consuming, error-prone, and necessitate specialized knowledge. As a result, many researchers are very interested in studying the automatic classification of therapeutic plants. Current state-of-the-art techniques rely primarily on leaf or plant imagery, restricting their application to certain scenarios. This study combines a large dataset of medicinal plants and their accompanying leaves to create a more generalizable approach for classifying medicinal plants efficiently. The first phase uses contrast-limited adaptive histogram equalization (CLAHE) to highlight important features in medicinal plant and leaf images. The proposed deep learning architecture, Attention-based Enhanced Local and Global Features Network (AELGNet), utilizes these images to extract and classify prominent features. Three MBConv modules in the AELGNet extract base features, subsequently dividing them into four non-overlapping patches for local feature extraction. Additionally, the AELGNet examines base features for global feature extraction. We simultaneously apply residual channel-wise and spatial attention to each patch and global feature to extract more conspicuous information pertinent to the medicinal plant or leaves. The experiment employs a dataset of Indian medicinal plants to assess the efficacy of ALEGNet. AELGNet has a 99.71% accuracy, a 99.80% precision, a 99.75% recall, and a 99.77% F1 score. The suggested AELGNet outperforms 14 current methods with an accuracy range of 2%-10%. The findings confirm AELGNet in medical and industrial settings, providing a strong tool for accurately and quickly identifying medicinal plants and leaves.

PMID:39608035 | DOI:10.1016/j.compbiomed.2024.109447

Comput Biol Med. 2024 Nov 27;184:109442. doi: 10.1016/j.compbiomed.2024.109442. Online ahead of print.

ABSTRACT

Cardiac T1 mapping can evaluate various clinical symptoms of myocardial tissue. However, there is currently a lack of effective, robust, and efficient methods for motion correction in cardiac T1 mapping. In this paper, we propose a deep learning-based and topology-preserving image registration framework for motion correction in cardiac T1 mapping. Notably, our proposed implicit consistency constraint dubbed BLOC, to some extent preserves the image topology in registration by bidirectional consistency constraint and local anti-folding constraint. To address the contrast variation issue, we introduce a weighted image similarity metric for multimodal registration of cardiac T1-weighted images. Besides, a semi-supervised myocardium segmentation network and a dual-domain attention module are integrated into the framework to further improve the performance of the registration. Numerous comparative experiments, as well as ablation studies, demonstrated the effectiveness and high robustness of our method. The results also indicate that the proposed weighted image similarity metric, specifically crafted for our network, contributes a lot to the enhancement of the motion correction efficacy, while the bidirectional consistency constraint combined with the local anti-folding constraint ensures a more desirable topology-preserving registration mapping.

PMID:39608033 | DOI:10.1016/j.compbiomed.2024.109442

J Med Internet Res. 2024 Nov 28;26:e54557. doi: 10.2196/54557.

ABSTRACT

BACKGROUND: Accurate measurement of food and nutrient intake is crucial for nutrition research, dietary surveillance, and disease management, but traditional methods such as 24-hour dietary recalls, food diaries, and food frequency questionnaires are often prone to recall error and social desirability bias, limiting their reliability. With the advancement of artificial intelligence (AI), there is potential to overcome these limitations through automated, objective, and scalable dietary assessment techniques. However, the effectiveness and challenges of AI applications in this domain remain inadequately explored.

OBJECTIVE: This study aimed to conduct a scoping review to synthesize existing literature on the efficacy, accuracy, and challenges of using AI tools in assessing food and nutrient intakes, offering insights into their current advantages and areas of improvement.

METHODS: This review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive literature search was conducted in 4 databases-PubMed, Web of Science, Cochrane Library, and EBSCO-covering publications from the databases' inception to June 30, 2023. Studies were included if they used modern AI approaches to assess food and nutrient intakes in human subjects.

RESULTS: The 25 included studies, published between 2010 and 2023, involved sample sizes ranging from 10 to 38,415 participants. These studies used a variety of input data types, including food images (n=10), sound and jaw motion data from wearable devices (n=9), and text data (n=4), with 2 studies combining multiple input types. AI models applied included deep learning (eg, convolutional neural networks), machine learning (eg, support vector machines), and hybrid approaches. Applications were categorized into dietary intake assessment, food detection, nutrient estimation, and food intake prediction. Food detection accuracies ranged from 74% to 99.85%, and nutrient estimation errors varied between 10% and 15%. For instance, the RGB-D (Red, Green, Blue-Depth) fusion network achieved a mean absolute error of 15% in calorie estimation, and a sound-based classification model reached up to 94% accuracy in detecting food intake based on jaw motion and chewing patterns. In addition, AI-based systems provided real-time monitoring capabilities, improving the precision of dietary assessments and demonstrating the potential to reduce recall bias typically associated with traditional self-report methods.

CONCLUSIONS: While AI demonstrated significant advantages in improving accuracy, reducing labor, and enabling real-time monitoring, challenges remain in adapting to diverse food types, ensuring algorithmic fairness, and addressing data privacy concerns. The findings suggest that AI has transformative potential for dietary assessment at both individual and population levels, supporting precision nutrition and chronic disease management. Future research should focus on enhancing the robustness of AI models across diverse dietary contexts and integrating biological sensors for a holistic dietary assessment approach.

PMID:39608003 | DOI:10.2196/54557

J Neuropathol Exp Neurol. 2024 Nov 28:nlae123. doi: 10.1093/jnen/nlae123. Online ahead of print.

ABSTRACT

Cancer of unknown primary (CUP) constitutes between 2% and 5% of human malignancies and is among the most common causes of cancer death in the United States. Brain metastases are often the first clinical presentation of CUP; despite extensive pathological and imaging studies, 20%-45% of CUP are never assigned a primary site. DNA methylation array profiling is a reliable method for tumor classification but tumor-type-specific classifier development requires many reference samples. This is difficult to accomplish for CUP as many cases are never assigned a specific diagnosis. Recent studies identified subsets of methylation quantitative trait loci (mQTLs) unique to specific organs, which could help increase classifier accuracy while requiring fewer samples. We performed a retrospective genome-wide methylation analysis of 759 carcinoma samples from formalin-fixed paraffin-embedded tissue samples using Illumina EPIC array. Utilizing mQTL specific for breast, lung, ovarian/gynecologic, colon, kidney, or testis (BLOCKT) (185k total probes), we developed a deep learning-based methylation classifier that achieved 93.12% average accuracy and 93.04% average F1-score across a 10-fold validation for BLOCKT organs. Our findings indicate that our organ-based DNA methylation classifier can assist pathologists in identifying the site of origin, providing oncologists insight on a diagnosis to administer appropriate therapy, improving patient outcomes.

PMID:39607989 | DOI:10.1093/jnen/nlae123

Gigascience. 2024 Jan 2;13:giae089. doi: 10.1093/gigascience/giae089.

ABSTRACT

BACKGROUND: Deciphering spatial domains using spatially resolved transcriptomics (SRT) is of great value for characterizing and understanding tissue architecture. However, the inherent heterogeneity and varying spatial resolutions present challenges in the joint analysis of multimodal SRT data.

RESULTS: We introduce a multimodal geometric deep learning method, named stMMR, to effectively integrate gene expression, spatial location, and histological information for accurate identifying spatial domains from SRT data. stMMR uses graph convolutional networks and a self-attention module for deep embedding of features within unimodality and incorporates similarity contrastive learning for integrating features across modalities.

CONCLUSIONS: Comprehensive benchmark analysis on various types of spatial data shows superior performance of stMMR in multiple analyses, including spatial domain identification, pseudo-spatiotemporal analysis, and domain-specific gene discovery. In chicken heart development, stMMR reconstructed the spatiotemporal lineage structures, indicating an accurate developmental sequence. In breast cancer and lung cancer, stMMR clearly delineated the tumor microenvironment and identified marker genes associated with diagnosis and prognosis. Overall, stMMR is capable of effectively utilizing the multimodal information of various SRT data to explore and characterize tissue architectures of homeostasis, development, and tumor.

PMID:39607984 | DOI:10.1093/gigascience/giae089

Gigascience. 2024 Jan 2;13:giae087. doi: 10.1093/gigascience/giae087.

ABSTRACT

BACKGROUND: Diatoms are microalgae with finely ornamented microscopic silica shells. Their taxonomic identification by light microscopy is routinely used as part of community ecological research as well as ecological status assessment of aquatic ecosystems, and a need for digitalization of these methods has long been recognized. Alongside their high taxonomic and morphological diversity, several other factors make diatoms highly challenging for deep learning-based identification using light microscopy images. These include (i) an unusually high intraclass variability combined with small between-class differences, (ii) a rather different visual appearance of specimens depending on their orientation on the microscope slide, and (iii) the limited availability of diatom experts for accurate taxonomic annotation.

FINDINGS: We present the largest diatom image dataset thus far, aimed at facilitating the application and benchmarking of innovative deep learning methods to the diatom identification problem on realistic research data, "UDE DIATOMS in the Wild 2024." The dataset contains 83,570 images of 611 diatom taxa, 101 of which are represented by at least 100 examples and 144 by at least 50 examples each. We showcase this dataset in 2 innovative analyses that address individual aspects of the above challenges using subclustering to deal with visually heterogeneous classes, out-of-distribution sample detection, and semi-supervised learning.

CONCLUSIONS: The problem of image-based identification of diatoms is both important for environmental research and challenging from the machine learning perspective. By making available the so far largest image dataset, accompanied by innovative analyses, this contribution will facilitate addressing these points by the scientific community.

PMID:39607983 | DOI:10.1093/gigascience/giae087

Med Phys. 2024 Nov 28. doi: 10.1002/mp.17501. Online ahead of print.

ABSTRACT

BACKGROUND: Recent advances in deep learning have sparked new research interests in dynamic magnetic resonance imaging (MRI) reconstruction. However, existing deep learning-based approaches suffer from insufficient reconstruction efficiency and accuracy due to the lack of time correlation modeling during the reconstruction procedure.

PURPOSE: Inappropriate tensor processing steps and deep learning models may lead to not only a lack of modeling in the time dimension but also an increase in the overall size of the network. Therefore, this study aims to find suitable tensor processing methods and deep learning models to achieve better reconstruction results and a smaller network size.

METHODS: We propose a novel unrolling network method that enhances the reconstruction quality and reduces the parameter redundancy by introducing time correlation modeling into MRI reconstruction with low-rank core matrix and convolutional long short-term memory (ConvLSTM) unit.

RESULTS: We conduct extensive experiments on AMRG Cardiac MRI dataset to evaluate our proposed approach. The results demonstrate that compared to other state-of-the-art approaches, our approach achieves higher peak signal-to-noise ratios and structural similarity indices at different accelerator factors with significantly fewer parameters.

CONCLUSIONS: The improved reconstruction performance demonstrates that our proposed time correlation modeling is simple and effective for accelerating MRI reconstruction. We hope our approach can serve as a reference for future research in dynamic MRI reconstruction.

PMID:39607945 | DOI:10.1002/mp.17501

Elife. 2024 Nov 28;13:RP96017. doi: 10.7554/eLife.96017.

ABSTRACT

Memory deficits are a hallmark of many different neurological and psychiatric conditions. The Rey-Osterrieth complex figure (ROCF) is the state-of-the-art assessment tool for neuropsychologists across the globe to assess the degree of non-verbal visual memory deterioration. To obtain a score, a trained clinician inspects a patient's ROCF drawing and quantifies deviations from the original figure. This manual procedure is time-consuming, slow and scores vary depending on the clinician's experience, motivation, and tiredness. Here, we leverage novel deep learning architectures to automatize the rating of memory deficits. For this, we collected more than 20k hand-drawn ROCF drawings from patients with various neurological and psychiatric disorders as well as healthy participants. Unbiased ground truth ROCF scores were obtained from crowdsourced human intelligence. This dataset was used to train and evaluate a multihead convolutional neural network. The model performs highly unbiased as it yielded predictions very close to the ground truth and the error was similarly distributed around zero. The neural network outperforms both online raters and clinicians. The scoring system can reliably identify and accurately score individual figure elements in previously unseen ROCF drawings, which facilitates explainability of the AI-scoring system. To ensure generalizability and clinical utility, the model performance was successfully replicated in a large independent prospective validation study that was pre-registered prior to data collection. Our AI-powered scoring system provides healthcare institutions worldwide with a digital tool to assess objectively, reliably, and time-efficiently the performance in the ROCF test from hand-drawn images.

PMID:39607424 | DOI:10.7554/eLife.96017

Med Phys. 2024 Nov 28. doi: 10.1002/mp.17549. Online ahead of print.

ABSTRACT

BACKGROUND: The electronic portal imaging device (EPID) can be used in vivo, to detect on-treatment errors by evaluating radiation exiting a patient. To detect deviations from the planning intent, image predictions need to be modeled based on the patient's anatomy and plan information. To date in vivo transit images have been predicted using Monte Carlo (MC) algorithms. A deep learning approach can make predictions faster than MC and only requires patient information for training.

PURPOSE: To test the feasibility and reliability of creating a deep-learning model with patient data for predicting in vivo EPID images for IMRT treatments.

METHODS: In our approach, the in vivo EPID image was separated into contributions from primary and scattered photons. A primary photon attenuation function was determined by measuring attenuation factors for various thicknesses of solid water. The scatter component of in vivo EPID images was estimated using a convolutional neural network (CNN). The CNN input was a 3-channel image comprised of the non-transit EPID image and ray tracing projections through a pretreatment CBCT. The predicted scatter component was added to the primary attenuation component to give the full predicted in vivo EPID image. We acquired 193 IMRT fields/images from 93 patients treated on the Varian Halcyon. Model training:validation:test dataset ratios were 133:20:40 images. Additional patient plans were delivered to anthropomorphic phantoms, yielding 75 images for further validation. We assessed model accuracy by comparing model-calculated and measured in vivo images with a gamma comparison.

RESULTS: Comparing the model-calculated and measured in vivo images gives a mean gamma pass rate for the training:validation:test datasets of 95.4%:94.1%:92.9% for 3%/3 mm and 98.4%:98.4%:96.8% for 5%/3 mm. For images delivered to phantom data sets the average gamma pass rate was 96.4% (3%/3 mm criteria). In all data sets, the lower passing rates of some images were due to CBCT artifacts and patient motion that occurred between the time of CBCT and treatment. CONCLUSIONS: The developed deep-learning-based model can generate in vivo EPID images with a mean gamma pass rate greater than 92% (3%/3 mm criteria). This approach provides an alternative to MC prediction algorithms. Image predictions can be made in 30 ms on a standard GPU. In future work, image predictions from this model can be used to detect in vivo treatment errors and on-treatment changes in patient anatomy, providing an additional layer of patient-specific quality assurance.

PMID:39607282 | DOI:10.1002/mp.17549

Mol Pharm. 2024 Nov 28. doi: 10.1021/acs.molpharmaceut.4c00804. Online ahead of print.

ABSTRACT

Monoclonal antibodies (mAbs) have found extensive applications and development in treating various diseases. From the pharmaceutical industry's perspective, the journey from the design and development of mAbs to clinical testing and large-scale production is a highly time-consuming and resource-intensive process. During the research and development phase, assessing and optimizing the developability of mAbs is of paramount importance to ensure their success as candidates for therapeutic drugs. The critical factors influencing mAb development are their biophysical properties, such as aggregation propensity, solubility, and viscosity. This study utilized a data set comprising 12 biophysical properties of 137 antibodies from a previous study (Proc Natl Acad Sci USA. 114(5):944-949, 2017). We employed full-length antibody molecular dynamics simulations and machine learning techniques to predict experimental data for these 12 biophysical properties. Additionally, we utilized a newly developed deep learning model called DeepSP, which directly predicts the dynamical and structural properties of spatial aggregation propensity and spatial charge map in different antibody regions from sequences. Our research findings indicate that the machine learning models we developed outperform previous methods in predicting most biophysical properties. Furthermore, the DeepSP model yields similar predictive results compared to molecular dynamic simulations while significantly reducing computational time. The code and parameters are freely available at https://github.com/Lailabcode/AbDev. Also, the webapp, AbDev, for 12 biophysical properties prediction has been developed and provided at https://devpred.onrender.com/AbDev.

PMID:39606945 | DOI:10.1021/acs.molpharmaceut.4c00804

ArXiv [Preprint]. 2024 Nov 14:arXiv:2411.09820v1.

ABSTRACT

While deep learning has revolutionized computer-aided drug discovery, the AI community has predominantly focused on model innovation and placed less emphasis on establishing best benchmarking practices. We posit that without a sound model evaluation framework, the AI community's efforts cannot reach their full potential, thereby slowing the progress and transfer of innovation into real-world drug discovery. Thus, in this paper, we seek to establish a new gold standard for small molecule drug discovery benchmarking, WelQrate. Specifically, our contributions are threefold: WelQrate Dataset Collection - we introduce a meticulously curated collection of 9 datasets spanning 5 therapeutic target classes. Our hierarchical curation pipelines, designed by drug discovery experts, go beyond the primary high-throughput screen by leveraging additional confirmatory and counter screens along with rigorous domain-driven preprocessing, such as Pan-Assay Interference Compounds (PAINS) filtering, to ensure the high-quality data in the datasets; WelQrate Evaluation Framework - we propose a standardized model evaluation framework considering high-quality datasets, featurization, 3D conformation generation, evaluation metrics, and data splits, which provides a reliable benchmarking for drug discovery experts conducting real-world virtual screening; Benchmarking - we evaluate model performance through various research questions using the WelQrate dataset collection, exploring the effects of different models, dataset quality, featurization methods, and data splitting strategies on the results. In summary, we recommend adopting our proposed WelQrate as the gold standard in small molecule drug discovery benchmarking. The WelQrate dataset collection, along with the curation codes, and experimental scripts are all publicly available at WelQrate.org.

PMID:39606732 | PMC:PMC11601797

ArXiv [Preprint]. 2024 Nov 21:arXiv:2411.14630v1.

ABSTRACT

Spatiotemporal magnetic field variations from B0-inhomogeneity and diffusion-encoding-induced eddy-currents can be detrimental to rapid image-encoding schemes such as spiral, EPI and 3D-cones, resulting in undesirable image artifacts. In this work, a data driven approach for automatic estimation of these field imperfections is developed by combining autofocus metrics with deep learning, and by leveraging a compact basis representation of the expected field imperfections. The method was applied to single-shot spiral diffusion MRI at high b-values where accurate estimation of B0 and eddy were obtained, resulting in high quality image reconstruction without need for additional external calibrations.

PMID:39606720 | PMC:PMC11601784

ArXiv [Preprint]. 2024 Nov 19:arXiv:2411.12370v1.

ABSTRACT

The fast evolution of SARS-CoV-2 and other infectious viruses poses a grand challenge to the rapid response in terms of viral tracking, diagnostics, and design and manufacture of monoclonal antibodies (mAbs) and vaccines, which are both time-consuming and costly. This underscores the need for efficient computational approaches. Recent advancements, like topological deep learning (TDL), have introduced powerful tools for forecasting emerging dominant variants, yet they require deep mutational scanning (DMS) of viral surface proteins and associated three-dimensional (3D) protein-protein interaction (PPI) complex structures. We propose an AlphaFold 3 (AF3)-assisted multi-task topological Laplacian (MT-TopLap) strategy to address this need. MT-TopLap combines deep learning with topological data analysis (TDA) models, such as persistent Laplacians (PL) to extract detailed topological and geometric characteristics of PPIs, thereby enhancing the prediction of DMS and binding free energy (BFE) changes upon virus mutations. Validation with four experimental DMS datasets of SARS-CoV-2 spike receptor-binding domain (RBD) and the human angiotensin-converting enzyme-2 (ACE2) complexes indicates that our AF3 assisted MT-TopLap strategy maintains robust performance, with only an average 1.1% decrease in Pearson correlation coefficients (PCC) and an average 9.3% increase in root mean square errors (RMSE), compared with the use of experimental structures. Additionally, AF3-assisted MT-TopLap achieved a PCC of 0.81 when tested with a SARS-CoV-2 HK.3 variant DMS dataset, confirming its capability to accurately predict BFE changes and adapt to new experimental data, thereby showcasing its potential for rapid and effective response to fast viral evolution.

PMID:39606716 | PMC:PMC11601794

ArXiv [Preprint]. 2024 Nov 13:arXiv:2411.06635v2.

ABSTRACT

Single-cell RNA sequencing (scRNA-seq) data are often confounded by technical or biological batch effects. Existing deep learning models mitigate these effects but often discard batch-specific information, potentially losing valuable biological insights. We propose a Mixed Effects Deep Learning (MEDL) autoencoder framework that separately models batch-invariant (fixed effects) and batch-specific (random effects) components. By decoupling batch-invariant biological states from batch variations, our framework integrates both into predictive models. Our approach also generates 2D visualizations of how the same cell appears across batches, enhancing interpretability. Retaining both fixed and random effect latent spaces improves classification accuracy. We applied our framework to three datasets spanning the cardiovascular system (Healthy Heart), Autism Spectrum Disorder (ASD), and Acute Myeloid Leukemia (AML). With 147 batches in the Healthy Heart dataset, far exceeding typical numbers, we tested our framework's ability to handle many batches. In the ASD dataset, our approach captured donor heterogeneity between autistic and healthy individuals. In the AML dataset, it distinguished donor heterogeneity despite missing cell types and diseased donors exhibiting both healthy and malignant cells. These results highlight our framework's ability to characterize fixed and random effects, enhance batch effect visualization, and improve prediction accuracy across diverse datasets.

PMID:39606715 | PMC:PMC11601787