IEEE Trans Neural Netw Learn Syst. 2024 Aug 2;PP. doi: 10.1109/TNNLS.2024.3432877. Online ahead of print.

ABSTRACT

Segmentation of complex medical images such as vascular network and pulmonary tracheal network requires segmentation of many tiny targets on each tomographic section of the 3-D medical image volume. Although semantic segmentation of medical images based on deep learning has made great progress, fully supervised models require a great amount of annotations, making such complex medical image segmentation a difficult problem. In this article, we propose a semi-supervised model for complex medical image segmentation, which innovatively proposes a bidirectional self-training paradigm, through dynamically exchanging the roles of teacher and student by estimating the reliability at the model level. The direction of information and knowledge transfer between the two networks can be controlled, and the probability distribution of the roles of teacher and student in the next stage will be jointly determined by the model's uncertainty and instability in the training process. We also resolve the problem that loosely coupled networks are prone to collapse when training on small-scale annotated data by proposing asymmetric supervision (AS) strategy and hierarchical dual student (HDS) structure. In particular, a bidirectional distillation loss combined with the role exchange (RE) strategy and a global-local-aware consistency loss are introduced to obtain stable mutual promotion and achieve matching of global and local features, respectively. We conduct detailed experiments on two public datasets and one private dataset and lead existing semi-supervised methods by a large margin, while achieving fully supervised performance at a labeling cost of 5%.

PMID:39093682 | DOI:10.1109/TNNLS.2024.3432877

Int J Comput Assist Radiol Surg. 2024 Aug 2. doi: 10.1007/s11548-024-03238-4. Online ahead of print.

ABSTRACT

PURPOSE: Automated glioblastoma segmentation from magnetic resonance imaging is generally performed on a four-modality input, including T1, contrast T1, T2 and FLAIR. We hypothesize that information redundancy is present within these image combinations, which can possibly reduce a model's performance. Moreover, for clinical applications, the risk of encountering missing data rises as the number of required input modalities increases. Therefore, this study aimed to explore the relevance and influence of the different modalities used for MRI-based glioblastoma segmentation.

METHODS: After the training of multiple segmentation models based on nnU-Net and SwinUNETR architectures, differing only in their amount and combinations of input modalities, each model was evaluated with regard to segmentation accuracy and epistemic uncertainty.

RESULTS: Results show that T1CE-based segmentation (for enhanced tumor and tumor core) and T1CE-FLAIR-based segmentation (for whole tumor and overall segmentation) can reach segmentation accuracies comparable to the full-input version. Notably, the highest segmentation accuracy for nnU-Net was found for a three-input configuration of T1CE-FLAIR-T1, suggesting the confounding effect of redundant input modalities. The SwinUNETR architecture appears to suffer less from this, where said three-input and the full-input model yielded statistically equal results.

CONCLUSION: The T1CE-FLAIR-based model can therefore be considered as a minimal-input alternative to the full-input configuration. Addition of modalities beyond this does not statistically improve and can even deteriorate accuracy, but does lower the segmentation uncertainty.

PMID:39093499 | DOI:10.1007/s11548-024-03238-4

Surg Endosc. 2024 Aug 2. doi: 10.1007/s00464-024-11117-x. Online ahead of print.

ABSTRACT

BACKGROUND: Postoperative pancreatic fistula (POPF) is a critical complication of laparoscopic gastrectomy (LG). However, there are no widely recognized anatomical landmarks to prevent POPF during LG. This study aimed to identify anatomical landmarks related to POPF occurrence during LG for gastric cancer and to develop an artificial intelligence (AI) navigation system for indicating these landmarks.

METHODS: Dimpling lines (DLs)-depressions formed between the pancreas and surrounding organs-were defined as anatomical landmarks related to POPF. The DLs for the mesogastrium, intestine, and transverse mesocolon were named DMP, DIP, and DTP, respectively. We included 50 LG cases to develop the AI system (45/50 were used for training and 5/50 for adjusting the hyperparameters of the employed system). Regarding the validation of the AI system, DLs were assessed by an external evaluation committee using a Likert scale, and the pancreas was assessed using the Dice coefficient, with 10 prospectively registered cases.

RESULTS: Six expert surgeons confirmed the efficacy of DLs as anatomical landmarks related to POPF in LG. An AI system was developed using a semantic segmentation model that indicated DLs in real-time when this system was synchronized during surgery. Additionally, the distribution of scores for DMP was significantly higher than that of the other DLs (p < 0.001), indicating the relatively high accuracy of this landmark. In addition, the Dice coefficient of the pancreas was 0.70.

CONCLUSIONS: The DLs may be used as anatomical landmarks related to POPF occurrence. The developed AI navigation system can help visualize the DLs in real-time during LG.

PMID:39093411 | DOI:10.1007/s00464-024-11117-x

J Am Dent Assoc. 2024 Jul 31:S0002-8177(24)00312-X. doi: 10.1016/j.adaj.2024.05.013. Online ahead of print.

ABSTRACT

BACKGROUND: The aim of this study was to understand the trends regarding the use of artificial intelligence in dentistry through a bibliometric review.

TYPES OF STUDIES REVIEWED: The authors performed a literature search on Web of Science. They collected the following data: articles-number and density of citations, year, key words, language, document type, study design, and theme (main objective, diagnostic method, and specialties); journals-impact factor; authors-country, continent, and institution. The authors used Visualization of Similarities Viewer software (Leiden University) to analyze the data and Spearman test for correlation analysis.

RESULTS: After selection, 1,478 articles were included. The number of citations ranged from 0 through 327. The articles were published from 1984 through 2024. Most articles were characterized as proof of concept (979). Definition and classification of structures and diseases was the most common theme (550 articles). There was an emphasis on radiology (333 articles) and radiographic-based diagnostic methods (715 articles). China was the country with the most articles (251), and Asia was the continent with the most articles (871). The Charité-University of Medicine Berlin was the institution with the most articles (42), and the author with the most articles was Schwendicke (53).

PRACTICAL IMPLICATIONS: Artificial intelligence is an important clinical tool to facilitate diagnosis and provide automation in various processes.

PMID:39093229 | DOI:10.1016/j.adaj.2024.05.013

Technol Health Care. 2024 Jul 5. doi: 10.3233/THC-232043. Online ahead of print.

ABSTRACT

BACKGROUND: Schwann cell sheaths are the source of benign, slowly expanding tumours known as acoustic neuromas (AN). The diagnostic and treatment approaches for AN must be patient-centered, taking into account unique factors and preferences.

OBJECTIVE: The purpose of this study is to investigate how machine learning and artificial intelligence (AI) can revolutionise AN management and diagnostic procedures.

METHODS: A thorough systematic review that included peer-reviewed material from public databases was carried out. Publications on AN, AI, and deep learning up until December 2023 were included in the review's purview.

RESULTS: Based on our analysis, AI models for volume estimation, segmentation, tumour type differentiation, and separation from healthy tissues have been developed successfully. Developments in computational biology imply that AI can be used effectively in a variety of fields, including quality of life evaluations, monitoring, robotic-assisted surgery, feature extraction, radiomics, image analysis, clinical decision support systems, and treatment planning.

CONCLUSION: For better AN diagnosis and treatment, a variety of imaging modalities require the development of strong, flexible AI models that can handle heterogeneous imaging data. Subsequent investigations ought to concentrate on reproducing findings in order to standardise AI approaches, which could transform their use in medical environments.

PMID:39093085 | DOI:10.3233/THC-232043

Anal Chem. 2024 Aug 2. doi: 10.1021/acs.analchem.4c02617. Online ahead of print.

ABSTRACT

Abnormal expression in long noncoding RNAs (lncRNAs) is closely associated with cancers. Herein, a novel CRISPR/Cas13a-enhanced photocurrent-polarity-switching photoelectrochemical (PEC) biosensor was engineered for the joint detection of dual lncRNAs, using deep learning (DL) to assist in cancer diagnosis. After target lncRNA-activated CRISPR/Cas13a cleaves to induce DNAzyme bidirectional walkers with the help of cofactor Mg2+, nitrogen-doped carbon-Cu/Cu2O octahedra are introduced into the biosensor, producing a photocurrent in the opposite direction of CdS quantum dots (QDs). The developed PEC biosensor shows high specificity and sensitivity with limits of detection down to 25.5 aM for lncRNA HOTAIR and 53.1 aM for lncRNA MALAT1. More importantly, this platform for the lncRNA joint assay in whole blood can successfully differentiate cancers from healthy people. Furthermore, the DL model is applied to explore the potential pattern hidden in data of the established technology, and the accuracy of DL cancer diagnosis can acquire 93.3%. Consequently, the developed platform offers a new avenue for lncRNA joint detection and early intelligent diagnosis of cancer.

PMID:39092917 | DOI:10.1021/acs.analchem.4c02617

Curr Med Chem. 2024 Aug 1. doi: 10.2174/0109298673307315240730042209. Online ahead of print.

ABSTRACT

BACKGROUND: Computational assessment of the energetics of protein-ligand complexes is a challenge in the early stages of drug discovery. Previous comparative studies on computational methods to calculate the binding affinity showed that targeted scoring functions outperform universal models.

OBJECTIVE: The goal here is to review the application of a simple physics-based model to estimate the binding. The focus is on a mass-spring system developed to predict binding affinity against cyclin-dependent kinase.

METHOD: Publications in PubMed were searched to find mass-spring models to predict binding affinity. Crystal structures of cyclin-dependent kinases found in the protein data bank and two web servers to calculate affinity based on the atomic coordinates were employed.

RESULTS: One recent study showed how a simple physics-based scoring function (named Taba) could contribute to the analysis of protein-ligand interactions. Taba methodology outperforms robust physics-based models implemented in docking programs such as AutoDock4 and Molegro Virtual Docker. Predictive metrics of 27 scoring functions and energy terms highlight the superior performance of the Taba scoring function for cyclin- dependent kinase.

CONCLUSION: The recent progress of machine learning methods and the availability of these techniques through free libraries boosted the development of more accurate models to address protein-ligand interactions. Combining a naïve mass-spring system with machine-learning techniques generated a targeted scoring function with superior predictive performance to estimate pKi.

PMID:39092736 | DOI:10.2174/0109298673307315240730042209

J Microsc. 2024 Aug 2. doi: 10.1111/jmi.13349. Online ahead of print.

ABSTRACT

Single Molecule Localisation Microscopy (SMLM) is becoming a widely used technique in cell biology. After processing the images, the molecular localisations are typically stored in a table as xy (or xyz) coordinates, with additional information, such as number of photons, etc. This set of coordinates can be used to generate an image to visualise the molecular distribution, for example, a 2D or 3D histogram of localisations. Many different methods have been devised to analyse SMLM data, among which cluster analysis of the localisations is popular. However, it can be useful to first segment the data, to extract the localisations in a specific region of a cell or in individual cells, prior to downstream analysis. Here we describe a pipeline for annotating localisations in an SMLM dataset in which we compared membrane segmentation approaches, including Otsu thresholding and machine learning models, and subsequent cell segmentation. We used an SMLM dataset derived from dSTORM images of sectioned cell pellets, stained for the membrane proteins EGFR (epidermal growth factor receptor) and EREG (epiregulin) as a test dataset. We found that a Cellpose model retrained on our data performed the best in the membrane segmentation task, allowing us to perform downstream cluster analysis of membrane versus cell interior localisations. We anticipate this will be generally useful for SMLM analysis.

PMID:39092628 | DOI:10.1111/jmi.13349

J Biophotonics. 2024 Aug 2:e202400197. doi: 10.1002/jbio.202400197. Online ahead of print.

ABSTRACT

Photoacoustic computed tomography (PACT) has centimeter-level imaging ability and can be used to detect the human body. However, strong photoacoustic signals from skin cover deep tissue information, hindering the frontal display and analysis of photoacoustic images of deep regions of interest. Therefore, we propose a 2.5 D deep learning model based on feature pyramid structure and single-type skin annotation to extract the skin region, and design a mask generation algorithm to remove skin automatically. PACT imaging experiments on the human periphery blood vessel verified the correctness our proposed skin-removal method. Compared with previous studies, our method exhibits high robustness to the uneven illumination, irregular skin boundary, and reconstruction artifacts in the images, and the reconstruction errors of PACT images decreased by 20% ~ 90% with a 1.65 dB improvement in the signal-to-noise ratio at the same time. This study may provide a promising way for high-definition PACT imaging of deep tissues.

PMID:39092484 | DOI:10.1002/jbio.202400197

Cureus. 2024 Jul 2;16(7):e63646. doi: 10.7759/cureus.63646. eCollection 2024 Jul.

ABSTRACT

Google DeepMind Technologies Limited (London, United Kingdom) recently released its new version of the biomolecular structure predictor artificial intelligence (AI) model named AlphaFold 3. Superior in accuracy and more powerful than its predecessor AlphaFold 2, this innovation has astonished the world with its capacity and speed. It takes humans years to determine the structure of various proteins and how the shape works with the receptors but AlphaFold 3 predicts the same structure in seconds. The version's utility is unimaginable in the field of drug discoveries, vaccines, enzymatic processes, and determining the rate and effect of different biological processes. AlphaFold 3 uses similar machine learning and deep learning models such as Gemini (Google DeepMind Technologies Limited). AlphaFold 3 has already established itself as a turning point in the field of computational biochemistry and drug development along with receptor modulation and biomolecular development. With the help of AlphaFold 3 and models similar to this, researchers will gain unparalleled insights into the structural dynamics of proteins and their interactions, opening up new avenues for scientists and doctors to exploit for the benefit of the patient. The integration of AI models like AlphaFold 3, bolstered by rigorous validation against high-standard research publications, is set to catalyze further innovations and offer a glimpse into the future of biomedicine.

PMID:39092344 | PMC:PMC11292590 | DOI:10.7759/cureus.63646

MethodsX. 2024 Jul 3;13:102845. doi: 10.1016/j.mex.2024.102845. eCollection 2024 Dec.

ABSTRACT

This study introduces a simulation of biological reinforcement learning to explore the behavior of natural enemies in the presence of host pests, aiming to analyze the population dynamics between natural enemies and insect pests within an ecological context. The simulation leverages on Q-learning, a reinforcement learning algorithm, to model the decision-making processes of both parasitoids/predators and pests, thereby assessing the impact of varying parasitism and predation rates on pest population growth. Simulation parameters, such as episode count, duration in months, steps, learning rate, and discount factor, were set arbitrarily. Environmental and reward matrices, representing climatic conditions, crop availability, and the rewards for different actions, were established for each month. Initial Q-tables for parasitoids/predators and pests, along with population arrays, were used to track population dynamics.•The simulation, illustrated through the Aphid-Ladybird beetle interaction case study over multiple episodes, includes a sensitivity analysis to evaluate the effects of different predation rates.•Findings reveal detailed population dynamics, phase relationships between predator and pest populations, and the significant influence of predation rates.•These insights contribute to a deeper understanding of ecological systems and inform potential pest management strategies.

PMID:39092273 | PMC:PMC11292350 | DOI:10.1016/j.mex.2024.102845

Heliyon. 2024 Jul 6;10(14):e33945. doi: 10.1016/j.heliyon.2024.e33945. eCollection 2024 Jul 30.

ABSTRACT

Wind energy is becoming increasingly competitive, Accurate and reliable multi-engine wind power forecasts can reduce power system operating costs and improve wind power consumption capacity. Existing research on wind power forecasting has neglected the importance of interval forecasting using clusters of wind farms to capture spatial characteristics and the objective selection of forecasting sub-learners, leading to increased uncertainty and risk in system operation. This paper proposes a new "decomposition-aggregation-multi-model parallel prediction" method. The data set is pre-processed by a decomposition-aggregation strategy and spatial feature extraction, and then a Stacking model with multiple parallel sub-learners selected by bootstrap method is used for point and interval forecasting. Experiments and discussions are conducted based on 15-min resolution wind power data from a cluster dataset of a wind farm in northwest China. The experimental results indicate that the method achieves higher accuracy and reliability in both point prediction and interval prediction than other comparative models, with a root mean square error value of 7.47 and an average F value of 1.572, which can provide a reliable reference for power generation planning from wind farm clusters.

PMID:39092247 | PMC:PMC11292254 | DOI:10.1016/j.heliyon.2024.e33945

R Soc Open Sci. 2024 Jun 19;11(6):240042. doi: 10.1098/rsos.240042. eCollection 2024 Jun.

ABSTRACT

The seafloor is inhabited by a large number of benthic invertebrates, and their importance in mediating carbon mineralization and biogeochemical cycles is recognized. However, the majority of fauna live below the sediment surface, so most means of survey rely on destructive sampling methods that are limited to documenting species presence rather than event driven activity and functionally important aspects of species behaviour. We have developed and tested a laboratory-based three-dimensional acoustic coring system that is capable of non-invasively visualizing the presence and activity of invertebrates within the sediment matrix. Here, we present reconstructed three-dimensional acoustic images of the sediment profile, with strong backscatter revealing the presence and position of individual benthic organisms. These data were used to train a three-dimensional convolutional neural network model and, using a combination of data augmentation and data correction techniques, we were able to identify individual species with an 88% accuracy. Combining three-dimensional acoustic coring with deep learning forms an effective and non-invasive means of providing detailed mechanistic information of in situ species-sediment interactions, opening new opportunities to quantify species-specific contributions to ecosystems.

PMID:39092142 | PMC:PMC11293796 | DOI:10.1098/rsos.240042

Front Aging Neurosci. 2024 Jul 18;16:1437707. doi: 10.3389/fnagi.2024.1437707. eCollection 2024.

ABSTRACT

BACKGROUNDS: Freezing of gait (FoG) is a common and debilitating symptom of Parkinson's disease (PD) that can lead to falls and reduced quality of life. Wearable sensors have been used to detect FoG, but current methods have limitations in accuracy and practicality. In this paper, we aimed to develop a deep learning model using pressure sensor data from wearable insoles to accurately detect FoG in PD patients.

METHODS: We recruited 14 PD patients and collected data from multiple trials of a standardized walking test using the Pedar insole system. We proposed temporal convolutional neural network (TCNN) and applied rigorous data filtering and selective participant inclusion criteria to ensure the integrity of the dataset. We mapped the sensor data to a structured matrix and normalized it for input into our TCNN. We used a train-test split to evaluate the performance of the model.

RESULTS: We found that TCNN model achieved the highest accuracy, precision, sensitivity, specificity, and F1 score for FoG detection compared to other models. The TCNN model also showed good performance in detecting FoG episodes, even in various types of sensor noise situations.

CONCLUSIONS: We demonstrated the potential of using wearable pressure sensors and machine learning models for FoG detection in PD patients. The TCNN model showed promising results and could be used in future studies to develop a real-time FoG detection system to improve PD patients' safety and quality of life. Additionally, our noise impact analysis identifies critical sensor locations, suggesting potential for reducing sensor numbers.

PMID:39092074 | PMC:PMC11291202 | DOI:10.3389/fnagi.2024.1437707

Front Oncol. 2024 Jul 18;14:1400341. doi: 10.3389/fonc.2024.1400341. eCollection 2024.

ABSTRACT

Brain tumors occur due to the expansion of abnormal cell tissues and can be malignant (cancerous) or benign (not cancerous). Numerous factors such as the position, size, and progression rate are considered while detecting and diagnosing brain tumors. Detecting brain tumors in their initial phases is vital for diagnosis where MRI (magnetic resonance imaging) scans play an important role. Over the years, deep learning models have been extensively used for medical image processing. The current study primarily investigates the novel Fine-Tuned Vision Transformer models (FTVTs)-FTVT-b16, FTVT-b32, FTVT-l16, FTVT-l32-for brain tumor classification, while also comparing them with other established deep learning models such as ResNet50, MobileNet-V2, and EfficientNet - B0. A dataset with 7,023 images (MRI scans) categorized into four different classes, namely, glioma, meningioma, pituitary, and no tumor are used for classification. Further, the study presents a comparative analysis of these models including their accuracies and other evaluation metrics including recall, precision, and F1-score across each class. The deep learning models ResNet-50, EfficientNet-B0, and MobileNet-V2 obtained an accuracy of 96.5%, 95.1%, and 94.9%, respectively. Among all the FTVT models, FTVT-l16 model achieved a remarkable accuracy of 98.70% whereas other FTVT models FTVT-b16, FTVT-b32, and FTVT-132 achieved an accuracy of 98.09%, 96.87%, 98.62%, respectively, hence proving the efficacy and robustness of FTVT's in medical image processing.

PMID:39091923 | PMC:PMC11291226 | DOI:10.3389/fonc.2024.1400341

bioRxiv [Preprint]. 2024 Jul 27:2024.07.25.605164. doi: 10.1101/2024.07.25.605164.

ABSTRACT

A key challenge in understanding subcellular organization is quantifying interpretable measurements of intracellular structures with complex multi-piece morphologies in an objective, robust and generalizable manner. Here we introduce a morphology-appropriate representation learning framework that uses 3D rotation invariant autoencoders and point clouds. This framework is used to learn representations of complex multi-piece morphologies that are independent of orientation, compact, and easy to interpret. We apply our framework to intracellular structures with punctate morphologies (e.g. DNA replication foci) and polymorphic morphologies (e.g. nucleoli). We systematically compare our framework to image-based autoencoders across several intracellular structure datasets, including a synthetic dataset with pre-defined rules of organization. We explore the trade-offs in the performance of different models by performing multi-metric benchmarking across efficiency, generative capability, and representation expressivity metrics. We find that our framework, which embraces the underlying morphology of multi-piece structures, facilitates the unsupervised discovery of sub-clusters for each structure. We show how our approach can also be applied to phenotypic profiling using a dataset of nucleolar images following drug perturbations. We implement and provide all representation learning models using CytoDL, a python package for flexible and configurable deep learning experiments.

PMID:39091871 | PMC:PMC11291148 | DOI:10.1101/2024.07.25.605164

bioRxiv [Preprint]. 2024 Jul 25:2024.04.18.590141. doi: 10.1101/2024.04.18.590141.

ABSTRACT

Directed evolution has emerged as a powerful tool for engineering new biocatalysts. However, introducing new catalytic residues can be destabilizing, and it is generally beneficial to start with a stable enzyme parent. Here we show that the deep learning-based tool ProteinMPNN can be used to redesign Fe(II)/αKG superfamily enzymes for greater stability, solubility, and expression while retaining both native activity and industrially-relevant non-native functions. For the Fe(II)/αKG enzyme tP4H, we performed site-saturation mutagenesis with both the wild-type and stabilized design variant and screened for activity increases in a non-native C-H hydroxylation reaction. We observed substantially larger increases in non-native activity for variants obtained from the stabilized scaffold compared to those from the wild-type enzyme. ProteinMPNN is user-friendly and widely-accessible, and straightforward structural criteria were sufficient to obtain stabilized, catalytically-functional variants of the Fe(II)/αKG enzymes tP4H and GriE. Our work suggests that stabilization by computational sequence redesign could be routinely implemented as a first step in directed evolution campaigns for novel biocatalysts.

PMID:39091854 | PMC:PMC11290999 | DOI:10.1101/2024.04.18.590141

bioRxiv [Preprint]. 2024 Jul 23:2024.07.22.604476. doi: 10.1101/2024.07.22.604476.

ABSTRACT

Chemical and conformational changes underlie the functional cycles of proteins. Comparative crystallography can reveal these changes over time, over ligands, and over chemical and physical perturbations in atomic detail. A key difficulty, however, is that the resulting observations must be placed on the same scale by correcting for experimental factors. We recently introduced a Bayesian framework for correcting (scaling) X-ray diffraction data by combining deep learning with statistical priors informed by crystallographic theory. To scale comparative crystallography data, we here combine this framework with a multivariate statistical theory of comparative crystallography. By doing so, we find strong improvements in the detection of protein dynamics, element-specific anomalous signal, and the binding of drug fragments.

PMID:39091831 | PMC:PMC11291090 | DOI:10.1101/2024.07.22.604476

Sci Rep. 2024 Aug 1;14(1):17785. doi: 10.1038/s41598-024-68749-1.

ABSTRACT

Skin cancer is a lethal disease, and its early detection plays a pivotal role in preventing its spread to other body organs and tissues. Artificial Intelligence (AI)-based automated methods can play a significant role in its early detection. This study presents an AI-based novel approach, termed 'DualAutoELM' for the effective identification of various types of skin cancers. The proposed method leverages a network of autoencoders, comprising two distinct autoencoders: the spatial autoencoder and the FFT (Fast Fourier Transform)-autoencoder. The spatial-autoencoder specializes in learning spatial features within input lesion images whereas the FFT-autoencoder learns to capture textural and distinguishing frequency patterns within transformed input skin lesion images through the reconstruction process. The use of attention modules at various levels within the encoder part of these autoencoders significantly improves their discriminative feature learning capabilities. An Extreme Learning Machine (ELM) with a single layer of feedforward is trained to classify skin malignancies using the characteristics that were recovered from the bottleneck layers of these autoencoders. The 'HAM10000' and 'ISIC-2017' are two publicly available datasets used to thoroughly assess the suggested approach. The experimental findings demonstrate the accuracy and robustness of the proposed technique, with AUC, precision, and accuracy values for the 'HAM10000' dataset being 0.98, 97.68% and 97.66%, and for the 'ISIC-2017' dataset being 0.95, 86.75% and 86.68%, respectively. This study highlights the possibility of the suggested approach for accurate detection of skin cancer.

PMID:39090261 | DOI:10.1038/s41598-024-68749-1

Clin Transl Med. 2024 Aug;14(8):e1789. doi: 10.1002/ctm2.1789.

ABSTRACT

Recent advancements in artificial intelligence (AI) have accelerated the prediction of unknown protein structures. However, accurately predicting the three-dimensional (3D) structures of fusion proteins remains a difficult task because the current AI-based protein structure predictions are focused on the WT proteins rather than on the newly fused proteins in nature. Following the central dogma of biology, fusion proteins are translated from fusion transcripts, which are made by transcribing the fusion genes between two different loci through the chromosomal rearrangements in cancer. Accurately predicting the 3D structures of fusion proteins is important for understanding the functional roles and mechanisms of action of new chimeric proteins. However, predicting their 3D structure using a template-based model is challenging because known template structures are often unavailable in databases. Deep learning (DL) models that utilize multi-level protein information have revolutionized the prediction of protein 3D structures. In this review paper, we highlighted the latest advancements and ongoing challenges in predicting the 3D structure of fusion proteins using DL models. We aim to explore both the advantages and challenges of employing AlphaFold2, RoseTTAFold, tr-Rosetta and D-I-TASSER for modelling the 3D structures. HIGHLIGHTS: This review provides the overall pipeline and landscape of the prediction of the 3D structure of fusion protein. This review provides the factors that should be considered in predicting the 3D structures of fusion proteins using AI approaches in each step. This review highlights the latest advancements and ongoing challenges in predicting the 3D structure of fusion proteins using deep learning models. This review explores the advantages and challenges of employing AlphaFold2, RoseTTAFold, tr-Rosetta, and D-I-TASSER to model 3D structures.

PMID:39090739 | DOI:10.1002/ctm2.1789