Sci Rep. 2024 May 25;14(1):11963. doi: 10.1038/s41598-024-62174-0.

ABSTRACT

Due to the challenge of collecting a substantial amount of production-quality data in real-world industrial settings, the implementation of production quality prediction models based on deep learning is not effective. To achieve the goal of predicting production quality with limited data and address the issue of model degradation in the training process of deep learning networks, we propose Meta-Learning based on Residual Network (MLRN) models for production quality prediction with limited data. Firstly, the MLRN model is trained on a variety of learning tasks to acquire knowledge for predicting production quality. Furthermore, to obtain more features with limited data and avoid the issues of gradient disappearing or exploding in deep network training, the enhanced residual network with the effective channel attention (ECA) mechanism is chosen as the basic network structure of MLRN. Additionally, a multi-batch and multi-task data input approach is implemented to prevent overfitting. Finally, the availability of the MLRN model is demonstrated by comparing it with other models using both numerical and graphical datasets.

PMID:38796529 | DOI:10.1038/s41598-024-62174-0

Sci Rep. 2024 May 25;14(1):11987. doi: 10.1038/s41598-024-62887-2.

ABSTRACT

Unenhanced CT scans exhibit high specificity in detecting moderate-to-severe hepatic steatosis. Even though many CTs are scanned from health screening and various diagnostic contexts, their potential for hepatic steatosis detection has largely remained unexplored. The accuracy of previous methodologies has been limited by the inclusion of non-parenchymal liver regions. To overcome this limitation, we present a novel deep-learning (DL) based method tailored for the automatic selection of parenchymal portions in CT images. This innovative method automatically delineates circular regions for effectively detecting hepatic steatosis. We use 1,014 multinational CT images to develop a DL model for segmenting liver and selecting the parenchymal regions. The results demonstrate outstanding performance in both tasks. By excluding non-parenchymal portions, our DL-based method surpasses previous limitations, achieving radiologist-level accuracy in liver attenuation measurements and hepatic steatosis detection. To ensure the reproducibility, we have openly shared 1014 annotated CT images and the DL system codes. Our novel research contributes to the refinement the automated detection methodologies of hepatic steatosis on CT images, enhancing the accuracy and efficiency of healthcare screening processes.

PMID:38796521 | DOI:10.1038/s41598-024-62887-2

BioData Min. 2024 May 25;17(1):14. doi: 10.1186/s13040-024-00366-0.

ABSTRACT

BACKGROUND: Supervised machine learning models have been widely used to predict and get insight into diseases by classifying patients based on personal health records. However, a class imbalance is an obstacle that disrupts the training of the models. In this study, we aimed to address class imbalance with a conditional normalizing flow model, one of the deep-learning-based semi-supervised models for anomaly detection. It is the first introduction of the normalizing flow algorithm for tabular biomedical data.

METHODS: We collected personal health records from South Korean citizens (n = 706), featuring genetic data obtained from direct-to-customer service (microarray chip), medical health check-ups, and lifestyle log data. Based on the health check-up data, six chronic diseases were labeled (obesity, diabetes, hypertriglyceridemia, dyslipidemia, liver dysfunction, and hypertension). After preprocessing, supervised classification models and semi-supervised anomaly detection models, including conditional normalizing flow, were evaluated for the classification of diabetes, which had extreme target imbalance (about 2%), based on AUROC and AUPRC. In addition, we evaluated their performance under the assumption of insufficient collection for patients with other chronic diseases by undersampling disease-affected samples.

RESULTS: While LightGBM (the best-performing model among supervised classification models) showed AUPRC 0.16 and AUROC 0.82, conditional normalizing flow achieved AUPRC 0.34 and AUROC 0.83 during fifty evaluations of the classification of diabetes, whose base rate was very low, at 0.02. Moreover, conditional normalizing flow performed better than the supervised model under a few disease-affected data numbers for the other five chronic diseases - obesity, hypertriglyceridemia, dyslipidemia, liver dysfunction, and hypertension. For example, while LightGBM performed AUPRC 0.20 and AUROC 0.75, conditional normalizing flow showed AUPRC 0.30 and AUROC 0.74 when predicting obesity, while undersampling disease-affected samples (positive undersampling) lowered the base rate to 0.02.

CONCLUSIONS: Our research suggests the utility of conditional normalizing flow, particularly when the available cases are limited, for predicting chronic diseases using personal health records. This approach offers an effective solution to deal with sparse data and extreme class imbalances commonly encountered in the biomedical context.

PMID:38796471 | DOI:10.1186/s13040-024-00366-0

Surgery. 2024 May 24:S0039-6060(24)00219-8. doi: 10.1016/j.surg.2024.03.054. Online ahead of print.

ABSTRACT

BACKGROUND: To combat the opioid epidemic, several strategies were implemented to limit the unnecessary prescription of opioids in the postoperative period. However, this leaves a subset of patients who genuinely require additional opioids with inadequate pain control. Deep learning models are powerful tools with great potential of optimizing health care delivery through a patient-centered focus. We sought to investigate whether deep learning models can be used to predict patients who would require additional opioid prescription refills in the postoperative period after elective surgery.

METHODS: This is a retrospective study of patients who received elective surgical intervention at the Mayo Clinic. Adult English-speaking patients ≥18 years old, who underwent an elective surgical procedure between 2013 and 2019, were eligible for inclusion. Machine learning models, including deep learning, random forest, and eXtreme Gradient Boosting, were designed to predict patients who require opioid refills after discharge from hospital.

RESULTS: A total of 9,731 patients with mean age of 62.1 years (51.4% female) were included in the study. Deep learning and random forest models predicted patients who required opioid refills with high accuracy, 0.79 ± 0.07 and 0.78 ± 0.08, respectively. Procedure performed, highest pain score recorded during hospitalization, and total oral morphine milligram equivalents prescribed at discharge were the top 3 predictors for requiring opioid refills after discharge.

CONCLUSION: Deep learning models can be used to predict patients who require postoperative opioid prescription refills with high accuracy. Other machine learning models, such as random forest, can perform equal to deep learning, increasing the applicability of machine learning for combating the opioid epidemic.

PMID:38796387 | DOI:10.1016/j.surg.2024.03.054

Clin Radiol. 2024 May 3:S0009-9260(24)00237-X. doi: 10.1016/j.crad.2024.04.017. Online ahead of print.

ABSTRACT

AIM: This study aimed to develop highly precise radiomics and deep learning models to accurately detect acute lymphoblastic leukemia (ALL) using a T1WI image.

MATERIALS AND METHODS: A total of 604 brain magnetic resonance data of ALL group and normal children (NC) group. Two radiologists independently retrieved radiomics features after manually delineating the area of interest along the clivus at the median sagittal position of T1WI. According to the 9:1 ratio, all samples were randomly divided into the training cohort and the testing cohort. support vector machine was then used to classify the radiomics model using the features that had a correlation coefficient of greater than 0.99 in the training cohort. The Efficientnet-B3 network model received the training set images to create a deep learning model. The sensitivity, specificity, and area under the ROC curve were calculated in order to evaluate the diagnostic efficacy of the different models after the validation of two aforementioned models in the testing cohort.

RESULTS: The deep learning model had a higher AUC value of 0.981 than the radiomics model's value of 0.962 in the testing cohort. Delong's test showed no statistical difference between the two models (P>0.05). The accuracy/sensitivity/specificity/negative predictive value/positive predictive value achieved 0.9180/0.9565/0.8947/0.9714/0.8462 for the radiomics model and 0.9344/0.8696/0.9737/0.9250/0.9524 for deep learning model.

CONCLUSIONS: The deep learning and radiomics models showed high AUC values in the training and test cohorts. They also exhibited good diagnostic efficacy for predicting ALL.

PMID:38796378 | DOI:10.1016/j.crad.2024.04.017

HPB (Oxford). 2024 May 16:S1365-182X(24)01722-2. doi: 10.1016/j.hpb.2024.05.006. Online ahead of print.

ABSTRACT

OBJECTIVE: We sought to develop Artificial Intelligence (AI) based models to predict non-transplantable recurrence (NTR) of hepatocellular carcinoma (HCC) following hepatic resection (HR).

METHODS: HCC patients who underwent HR between 2000-2020 were identified from a multi-institutional database. NTR was defined as recurrence beyond Milan Criteria. Different machine learning (ML) and deep learning (DL) techniques were used to develop and validate two prediction models for NTR, one using only preoperative factors and a second using both preoperative and postoperative factors.

RESULTS: Overall, 1763 HCC patients were included. Among 877 patients with recurrence, 364 (41.5%) patients developed NTR. An ensemble AI model demonstrated the highest area under ROC curves (AUC) of 0.751 (95% CI: 0.719-0.782) and 0.717 (95% CI:0.653-0.782) in the training and testing cohorts, respectively which improved to 0.858 (95% CI: 0.835-0.884) and 0.764 (95% CI: 0.704-0.826), respectively after incorporation of postoperative pathologic factors. Radiologic tumor burden score and pathological microvascular invasion were the most important preoperative and postoperative factors, respectively to predict NTR. Patients predicted to develop NTR had overall 1- and 5-year survival of 75.6% and 28.2%, versus 93.4% and 55.9%, respectively, among patients predicted to not develop NTR (p < 0.0001).

CONCLUSION: The AI preoperative model may help inform decision of HR versus LT for HCC, while the combined AI model can frame individualized postoperative care (https://altaf-pawlik-hcc-ntr-calculator.streamlit.app/).

PMID:38796346 | DOI:10.1016/j.hpb.2024.05.006

J Chem Theory Comput. 2024 May 25. doi: 10.1021/acs.jctc.4c00432. Online ahead of print.

ABSTRACT

Toxicity is a roadblock that prevents an inordinate number of drugs from being used in potentially life-saving applications. Deep learning provides a promising solution to finding ideal drug candidates; however, the vastness of chemical space coupled with the underlying O(n3) matrix multiplication means these efforts quickly become computationally demanding. To remedy this, we present a hybrid quantum-classical neural network for predicting drug toxicity utilizing a quantum circuit design that mimics classical neural behavior by explicitly calculating matrix products with complexity O(n2). Leveraging the Hadamard test for efficient inner product estimation rather than the conventionally used swap test, we reduce the number of qubits by half and remove the need for quantum phase estimation. Directly computing matrix products quantum mechanically allows for learnable weights to be transferred from a quantum to a classical device for further training. We apply our framework to the Tox21 data set and show that it achieves commensurate predictive accuracy to the model's fully classical O(n3) analogue. Additionally, we demonstrate that the model continues to learn, without disruption, once transferred to a fully classical architecture. We believe that combining the quantum advantage of reduced complexity and the classical advantage of noise-free calculation will pave the way for more scalable machine learning models.

PMID:38795030 | DOI:10.1021/acs.jctc.4c00432

Plants (Basel). 2024 May 15;13(10):1377. doi: 10.3390/plants13101377.

ABSTRACT

In response to the challenge of low recognition rates for similar phenotypic symptoms of tea diseases in low-light environments and the difficulty in detecting small lesions, a novel adaptive method for tea disease severity detection is proposed. This method integrates an image enhancement algorithm based on an improved EnlightenGAN network and an enhanced version of YOLO v8. The approach involves first enhancing the EnlightenGAN network through non-paired training on low-light-intensity images of various tea diseases, guiding the generation of high-quality disease images. This step aims to expand the dataset and improve lesion characteristics and texture details in low-light conditions. Subsequently, the YOLO v8 network incorporates ResNet50 as its backbone, integrating channel and spatial attention modules to extract key features from disease feature maps effectively. The introduction of adaptive spatial feature fusion in the Neck part of the YOLOv8 module further enhances detection accuracy, particularly for small disease targets in complex backgrounds. Additionally, the model architecture is optimized by replacing traditional Conv blocks with ODConv blocks and introducing a new ODC2f block to reduce parameters, improve performance, and switch the loss function from CIOU to EIOU for a faster and more accurate recognition of small targets. Experimental results demonstrate that YOLOv8-ASFF achieves a tea disease detection accuracy of 87.47% and a mean average precision (mAP) of 95.26%. These results show a 2.47 percentage point improvement over YOLOv8, and a significant lead of 9.11, 9.55, and 7.08 percentage points over CornerNet, SSD, YOLOv5, and other models, respectively. The ability to swiftly and accurately detect tea diseases can offer robust theoretical support for assessing tea disease severity and managing tea growth. Moreover, its compatibility with edge computing devices and practical application in agriculture further enhance its value.

PMID:38794447 | DOI:10.3390/plants13101377

Pharmaceutics. 2024 May 16;16(5):673. doi: 10.3390/pharmaceutics16050673.

ABSTRACT

Photodynamic therapy (PDT) shows promise in tumor treatment, particularly when combined with nanotechnology. This study examines the impact of deep learning, particularly the Cellpose algorithm, on the comprehension of cancer cell responses to PDT. The Cellpose algorithm enables robust morphological analysis of cancer cells, while logistic growth modelling predicts cellular behavior post-PDT. Rigorous model validation ensures the accuracy of the findings. Cellpose demonstrates significant morphological changes after PDT, affecting cellular proliferation and survival. The reliability of the findings is confirmed by model validation. This deep learning tool enhances our understanding of cancer cell dynamics after PDT. Advanced analytical techniques, such as morphological analysis and growth modeling, provide insights into the effects of PDT on hepatocellular carcinoma (HCC) cells, which could potentially improve cancer treatment efficacy. In summary, the research examines the role of deep learning in optimizing PDT parameters to personalize oncology treatment and improve efficacy.

PMID:38794335 | DOI:10.3390/pharmaceutics16050673

Sensors (Basel). 2024 May 20;24(10):3258. doi: 10.3390/s24103258.

ABSTRACT

To effectively solve the increasingly complex problems experienced by human beings, the latest development trend is to apply a large number of different types of sensors to collect data in order to establish effective solutions based on deep learning and artificial intelligence [...].

PMID:38794112 | DOI:10.3390/s24103258

Sensors (Basel). 2024 May 20;24(10):3247. doi: 10.3390/s24103247.

ABSTRACT

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

PMID:38794102 | DOI:10.3390/s24103247

Sensors (Basel). 2024 May 20;24(10):3246. doi: 10.3390/s24103246.

ABSTRACT

The field of computer vision has been focusing on achieving accurate three-dimensional (3D) object representations from a single two-dimensional (2D) image through deep artificial neural networks. Recent advancements in 3D shape reconstruction techniques that combine structured light and deep learning show promise in acquiring high-quality geometric information about object surfaces. This paper introduces a new single-shot 3D shape reconstruction method that uses a nonlinear fringe transformation approach through both supervised and unsupervised learning networks. In this method, a deep learning network learns to convert a grayscale fringe input into multiple phase-shifted fringe outputs with different frequencies, which act as an intermediate result for the subsequent 3D reconstruction process using the structured-light fringe projection profilometry technique. Experiments have been conducted to validate the practicality and robustness of the proposed technique. The experimental results demonstrate that the unsupervised learning approach using a deep convolutional generative adversarial network (DCGAN) is superior to the supervised learning approach using UNet in image-to-image generation. The proposed technique's ability to accurately reconstruct 3D shapes of objects using only a single fringe image opens up vast opportunities for its application across diverse real-world scenarios.

PMID:38794100 | DOI:10.3390/s24103246

Sensors (Basel). 2024 May 18;24(10):3221. doi: 10.3390/s24103221.

ABSTRACT

Stress is a natural yet potentially harmful aspect of human life, necessitating effective management, particularly during overwhelming experiences. This paper presents a scoping review of personalized stress detection models using wearable technology. Employing the PRISMA-ScR framework for rigorous methodological structuring, we systematically analyzed literature from key databases including Scopus, IEEE Xplore, and PubMed. Our focus was on biosignals, AI methodologies, datasets, wearable devices, and real-world implementation challenges. The review presents an overview of stress and its biological mechanisms, details the methodology for the literature search, and synthesizes the findings. It shows that biosignals, especially EDA and PPG, are frequently utilized for stress detection and demonstrate potential reliability in multimodal settings. Evidence for a trend towards deep learning models was found, although the limited comparison with traditional methods calls for further research. Concerns arise regarding the representativeness of datasets and practical challenges in deploying wearable technologies, which include issues related to data quality and privacy. Future research should aim to develop comprehensive datasets and explore AI techniques that are not only accurate but also computationally efficient and user-centric, thereby closing the gap between theoretical models and practical applications to improve the effectiveness of stress detection systems in real scenarios.

PMID:38794074 | DOI:10.3390/s24103221

Sensors (Basel). 2024 May 18;24(10):3215. doi: 10.3390/s24103215.

ABSTRACT

The production of multivariate time-series data facilitates the continuous monitoring of production assets. The modelling approach of multivariate time series can reveal the ways in which parameters evolve as well as the influences amongst themselves. These data can be used in tandem with artificial intelligence methods to create insight on the condition of production equipment, hence potentially increasing the sustainability of existing manufacturing and production systems, by optimizing resource utilization, waste, and production downtime. In this context, a predictive maintenance method is proposed based on the combination of LSTM-Autoencoders and a Transformer encoder in order to enable the forecasting of asset failures through spatial and temporal time series. These neural networks are implemented into a software prototype. The dataset used for training and testing the models is derived from a metal processing industry case study. Ultimately, the goal is to train a remaining useful life (RUL) estimation model.

PMID:38794070 | DOI:10.3390/s24103215

Sensors (Basel). 2024 May 18;24(10):3208. doi: 10.3390/s24103208.

ABSTRACT

Transient Luminous Events (TLEs) are short-lived, upper-atmospheric optical phenomena associated with thunderstorms. Their rapid and random occurrence makes manual classification laborious and time-consuming. This study presents an effective approach to automating the classification of TLEs using state-of-the-art Convolutional Neural Networks (CNNs) and a Vision Transformer (ViT). The ViT architecture and four different CNN architectures, namely, ResNet50, ResNet18, GoogLeNet, and SqueezeNet, are employed and their performance is evaluated based on their accuracy and execution time. The models are trained on a dataset that was augmented using rotation, translation, and flipping techniques to increase its size and diversity. Additionally, the images are preprocessed using bilateral filtering to enhance their quality. The results show high classification accuracy across all models, with ResNet50 achieving the highest accuracy. However, a trade-off is observed between accuracy and execution time, which should be considered based on the specific requirements of the task. This study demonstrates the feasibility and effectiveness of using transfer learning and pre-trained CNNs for the automated classification of TLEs.

PMID:38794062 | DOI:10.3390/s24103208

Sensors (Basel). 2024 May 17;24(10):3198. doi: 10.3390/s24103198.

ABSTRACT

Recently, explainability in machine and deep learning has become an important area in the field of research as well as interest, both due to the increasing use of artificial intelligence (AI) methods and understanding of the decisions made by models. The explainability of artificial intelligence (XAI) is due to the increasing consciousness in, among other things, data mining, error elimination, and learning performance by various AI algorithms. Moreover, XAI will allow the decisions made by models in problems to be more transparent as well as effective. In this study, models from the 'glass box' group of Decision Tree, among others, and the 'black box' group of Random Forest, among others, were proposed to understand the identification of selected types of currant powders. The learning process of these models was carried out to determine accuracy indicators such as accuracy, precision, recall, and F1-score. It was visualized using Local Interpretable Model Agnostic Explanations (LIMEs) to predict the effectiveness of identifying specific types of blackcurrant powders based on texture descriptors such as entropy, contrast, correlation, dissimilarity, and homogeneity. Bagging (Bagging_100), Decision Tree (DT0), and Random Forest (RF7_gini) proved to be the most effective models in the framework of currant powder interpretability. The measures of classifier performance in terms of accuracy, precision, recall, and F1-score for Bagging_100, respectively, reached values of approximately 0.979. In comparison, DT0 reached values of 0.968, 0.972, 0.968, and 0.969, and RF7_gini reached values of 0.963, 0.964, 0.963, and 0.963. These models achieved classifier performance measures of greater than 96%. In the future, XAI using agnostic models can be an additional important tool to help analyze data, including food products, even online.

PMID:38794052 | DOI:10.3390/s24103198

Sensors (Basel). 2024 May 16;24(10):3180. doi: 10.3390/s24103180.

ABSTRACT

Advances in deep learning and computer vision have overcome many challenges inherent in the field of autonomous intelligent vehicles. To improve the detection accuracy and efficiency of EdgeBoard intelligent vehicles, we proposed an optimized design of EdgeBoard based on our PP-YOLOE+ model. This model innovatively introduces a composite backbone network, incorporating deep residual networks, feature pyramid networks, and RepResBlock structures to enrich environmental perception capabilities through the advanced analysis of sensor data. The incorporation of an efficient task-aligned head (ET-head) in the PP-YOLOE+ framework marks a pivotal innovation for precise interpretation of sensor information, addressing the interplay between classification and localization tasks with high effectiveness. Subsequent refinement of target regions by detection head units significantly sharpens the system's ability to navigate and adapt to diverse driving scenarios. Our innovative hardware design, featuring a custom-designed mainboard and drive board, is specifically tailored to enhance the computational speed and data processing capabilities of intelligent vehicles. Furthermore, the optimization of our Pos-PID control algorithm allows the system to dynamically adjust to complex driving scenarios, significantly enhancing vehicle safety and reliability. Besides, our methodology leverages the latest technologies in edge computing and dynamic label assignment, enhancing intelligent vehicles' operations through seamless sensor integration. Our custom dataset, specifically designed for this study, includes 4777 images captured by intelligent vehicles under a variety of environmental and lighting conditions. The dataset features diverse scenarios and objects pertinent to autonomous driving, such as pedestrian crossings and traffic signs, ensuring a comprehensive evaluation of the model's performance. We conducted extensive testing of our model on this dataset to thoroughly assess sensor performance. Evaluated against metrics including accuracy, error rate, precision, recall, mean average precision (mAP), and F1-score, our findings reveal that the model achieves a remarkable accuracy rate of 99.113%, an mAP of 54.9%, and a real-time detection frame rate of 192 FPS, all within a compact parameter footprint of just 81 MB. These results demonstrate the superior capability of our PP-YOLOE+ model to integrate sensor data, achieving an optimal balance between detection accuracy and computational speed compared with existing algorithms.

PMID:38794034 | DOI:10.3390/s24103180

Microbiome. 2024 May 24;12(1):94. doi: 10.1186/s40168-024-01807-y.

ABSTRACT

BACKGROUND: Microbial secondary metabolites play a crucial role in the intricate interactions within the natural environment. Among these metabolites, ribosomally synthesized and post-translationally modified peptides (RiPPs) are becoming a promising source of therapeutic agents due to their structural diversity and functional versatility. However, their biosynthetic capacity and ecological functions remain largely underexplored.

RESULTS: Here, we aim to explore the biosynthetic profile of RiPPs and their potential roles in the interactions between microbes and viruses in the ocean, which encompasses a vast diversity of unique biomes that are rich in interactions and remains chemically underexplored. We first developed TrRiPP to identify RiPPs from ocean metagenomes, a deep learning method that detects RiPP precursors in a hallmark gene-independent manner to overcome the limitations of classic methods in processing highly fragmented metagenomic data. Applying this method to metagenomes from the global ocean microbiome, we uncover a diverse array of previously uncharacterized putative RiPP families with great novelty and diversity. Through correlation analysis based on metatranscriptomic data, we observed a high prevalence of antiphage defense-related and phage-related protein families that were co-expressed with RiPP families. Based on this putative association between RiPPs and phage infection, we constructed an Ocean Virus Database (OVD) and established a RiPP-involving host-phage interaction network through host prediction and co-expression analysis, revealing complex connectivities linking RiPP-encoding prokaryotes, RiPP families, viral protein families, and phages. These findings highlight the potential of RiPP families involved in prokaryote-phage interactions and coevolution, providing insights into their ecological functions in the ocean microbiome.

CONCLUSIONS: This study provides a systematic investigation of the biosynthetic potential of RiPPs from the ocean microbiome at a global scale, shedding light on the essential insights into the ecological functions of RiPPs in prokaryote-phage interactions through the integration of deep learning approaches, metatranscriptomic data, and host-phage connectivity. This study serves as a valuable example of exploring the ecological functions of bacterial secondary metabolites, particularly their associations with unexplored microbial interactions. Video Abstract.

PMID:38790030 | DOI:10.1186/s40168-024-01807-y

J Cheminform. 2024 May 24;16(1):59. doi: 10.1186/s13321-024-00845-w.

ABSTRACT

De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. SCIENTIFIC CONTRIBUTION: The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria-including target specificity, synthetic accessibility, solubility, and metabolic stability-within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries.

PMID:38790018 | DOI:10.1186/s13321-024-00845-w

Breast Cancer Res. 2024 May 24;26(1):82. doi: 10.1186/s13058-024-01830-9.

ABSTRACT

BACKGROUND: Patients with a Breast Imaging Reporting and Data System (BI-RADS) 4 mammogram are currently recommended for biopsy. However, 70-80% of the biopsies are negative/benign. In this study, we developed a deep learning classification algorithm on mammogram images to classify BI-RADS 4 suspicious lesions aiming to reduce unnecessary breast biopsies.

MATERIALS AND METHODS: This retrospective study included 847 patients with a BI-RADS 4 breast lesion that underwent biopsy at a single institution and included 200 invasive breast cancers, 200 ductal carcinoma in-situ (DCIS), 198 pure atypias, 194 benign, and 55 atypias upstaged to malignancy after excisional biopsy. We employed convolutional neural networks to perform 4 binary classification tasks: (I) benign vs. all atypia + invasive + DCIS, aiming to identify the benign cases for whom biopsy may be avoided; (II) benign + pure atypia vs. atypia-upstaged + invasive + DCIS, aiming to reduce excision of atypia that is not upgraded to cancer at surgery; (III) benign vs. each of the other 3 classes individually (atypia, DCIS, invasive), aiming for a precise diagnosis; and (IV) pure atypia vs. atypia-upstaged, aiming to reduce unnecessary excisional biopsies on atypia patients.

RESULTS: A 95% sensitivity for the "higher stage disease" class was ensured for all tasks. The specificity value was 33% in Task I, and 25% in Task II, respectively. In Task III, the respective specificity value was 30% (vs. atypia), 30% (vs. DCIS), and 46% (vs. invasive tumor). In Task IV, the specificity was 35%. The AUC values for the 4 tasks were 0.72, 0.67, 0.70/0.73/0.72, and 0.67, respectively.

CONCLUSION: Deep learning of digital mammograms containing BI-RADS 4 findings can identify lesions that may not need breast biopsy, leading to potential reduction of unnecessary procedures and the attendant costs and stress.

PMID:38790005 | DOI:10.1186/s13058-024-01830-9