bioRxiv [Preprint]. 2024 Jun 28:2024.06.28.599394. doi: 10.1101/2024.06.28.599394.

ABSTRACT

The Per-Arnt-Sim (PAS) domains are characterized by diverse sequences and feature tandemly arranged PAS and PAS-associated C-terminal (PAC) motifs that fold seamlessly to generate the metabolite-sensing PAS domain. Here, using evolutionary scale sequence, domain mapping, and deep learning-based protein structure analysis, we deconstructed the sequence-structure relationship to unearth a novel example of signal-regulated assembly of PAS and PAC subdomains in metazoan PAS domain-regulated kinase (PASK). By comparing protein sequence, domain architecture, and computational protein models between fish, bird, and mammalian PASK orthologs, we propose the existence of previously unrecognized third PAS domain of PASK (PAS-C) formed through long-range intramolecular interactions between the N-terminal PAS fold and the C-terminal PAC fold. We experimentally validated this novel structural design using residue-level cross-linking assays and showed that the PAS-C domain assembly is nutrient-responsive. Furthermore, by combining structural phylogeny approaches with residue-level cross-linking, we revealed that the PAS-C domain assembly links nutrient sensing with quaternary structure reorganization in PASK, stabilizing the kinase catalytic core of PASK. Thus, PAS-C domain assembly likely integrates environmental signals, thereby relaying sensory information for catalytic control of the PASK kinase domain. In conclusion, we theorize that during their horizontal transfer from bacteria to multicellular organisms, PAS domains gained the capacity to integrate environmental signals through dynamic modulation of PAS and PAC motif interaction, adding a new regulatory layer suited for multicellular systems. We propose that metazoan PAS domains are likely to be more dynamic in integrating sensory information than previously considered, and their structural assembly could be targeted by regulatory signals and exploited to develop therapeutic strategies.

PMID:38979257 | PMC:PMC11230368 | DOI:10.1101/2024.06.28.599394

bioRxiv [Preprint]. 2024 Jun 28:2024.06.25.600585. doi: 10.1101/2024.06.25.600585.

ABSTRACT

Cancer cells show remarkable plasticity and can switch lineages in response to the tumor microenvironment. Cellular plasticity drives invasiveness and metastasis and helps cancer cells to evade therapy by developing resistance to radiation and cytotoxic chemotherapy. Increased understanding of cell fate determination through epigenetic reprogramming is critical to discover how cancer cells achieve transcriptomic and phenotypic plasticity. Glioblastoma is a perfect example of cancer evolution where cells retain an inherent level of plasticity through activation or maintenance of progenitor developmental programs. However, the principles governing epigenetic drivers of cellular plasticity in glioblastoma remain poorly understood. Here, using machine learning (ML) we employ cross-patient prediction of transcript expression using a combination of epigenetic features (ATAC-seq, CTCF ChIP-seq, RNAPII ChIP-seq, H3K27Ac ChIP-seq, and RNA-seq) of glioblastoma stem cells (GSCs). We investigate different ML and deep learning (DL) models for this task and build our final pipeline using XGBoost. The model trained on one patient generalizes to another one suggesting that the epigenetic signals governing gene transcription are consistent across patients even if GSCs can be very different. We demonstrate that H3K27Ac is the epigenetic feature providing the most significant contribution to cross-patient prediction of gene expression. In addition, using H3K27Ac signals from patients-derived GSCs, we can predict gene expression of human neural crest stem cells suggesting a shared developmental epigenetic trajectory between subpopulations of these malignant and benign stem cells. Our cross-patient ML/DL models determine weighted patterns of influence of epigenetic marks on gene expression across patients with glioblastoma and between GSCs and neural crest stem cells. We propose that broader application of this analysis could reshape our view of glioblastoma tumor evolution and inform the design of new epigenetic targeting therapies.

PMID:38979226 | PMC:PMC11230286 | DOI:10.1101/2024.06.25.600585

bioRxiv [Preprint]. 2024 Jun 30:2024.06.26.600902. doi: 10.1101/2024.06.26.600902.

ABSTRACT

Recent advances in molecular modeling using deep learning can revolutionize our understanding of dynamic protein structures. NMR is particularly well-suited for determining dynamic features of biomolecular structures. The conventional process for determining biomolecular structures from experimental NMR data involves its representation as conformation-dependent restraints, followed by generation of structural models guided by these spatial restraints. Here we describe an alternative approach: generating a distribution of realistic protein conformational models using artificial intelligence-(AI-) based methods and then selecting the sets of conformers that best explain the experimental data. We applied this conformational selection approach to redetermine the solution NMR structure of the enzyme Gaussia luciferase. First, we generated a diverse set of conformer models using AlphaFold2 (AF2) with an enhanced sampling protocol. The models that best-fit NOESY and chemical shift data were then selected with a Bayesian scoring metric. The resulting models include features of both the published NMR structure and the standard AF2 model generated without enhanced sampling. This "AlphaFold-NMR" protocol also generated an alternative "open" conformational state that fits nearly as well to the overall NMR data but accounts for some NOESY data that is not consistent with first "closed" conformational state; while other NOESY data consistent with this second state are not consistent with the first conformational state. The structure of this "open" structural state differs from that of the "closed" state primarily by the position of a thumb-shaped loop between α-helices H5 and H6, revealing a cryptic surface pocket. These alternative conformational states of Gluc are supported by "double recall" analysis of NOESY data and AF2 models. Additional structural states are also indicated by backbone chemical shift data indicating partially-disordered conformations for the C-terminal segment. Considered as a multistate ensemble, these multiple states of Gluc together fit the NOESY and chemical shift data better than the "restraint-based" NMR structure and provide novel insights into its structure-dynamic-function relationships. This study demonstrates the potential of AI-based modeling with enhanced sampling to generate conformational ensembles followed by conformer selection with experimental data as an alternative to conventional restraint satisfaction protocols for protein NMR structure determination.

PMID:38979209 | PMC:PMC11230435 | DOI:10.1101/2024.06.26.600902

bioRxiv [Preprint]. 2024 Jun 28:2024.06.24.600378. doi: 10.1101/2024.06.24.600378.

ABSTRACT

Chronic diseases like ME/CFS and long COVID exhibit high heterogeneity with multifactorial etiology and progression, complicating diagnosis and treatment. To address this, we developed BioMapAI, an explainable Deep Learning framework using the richest longitudinal multi-'omics dataset for ME/CFS to date. This dataset includes gut metagenomics, plasma metabolome, immune profiling, blood labs, and clinical symptoms. By connecting multi-'omics to asymptom matrix, BioMapAI identified both disease- and symptom-specific biomarkers, reconstructed symptoms, and achieved state-of-the-art precision in disease classification. We also created the first connectivity map of these 'omics in both healthy and disease states and revealed how microbiome-immune-metabolome crosstalk shifted from healthy to ME/CFS. Thus, we proposed several innovative mechanistic hypotheses for ME/CFS: Disrupted microbial functions - SCFA (butyrate), BCAA (amino acid), tryptophan, benzoate - lost connection with plasma lipids and bile acids, and activated inflammatory and mucosal immune cells (MAIT, γδT cells) with INFγ and GzA secretion. These abnormal dynamics are linked to key disease symptoms, including gastrointestinal issues, fatigue, and sleep problems.

PMID:38979186 | PMC:PMC11230215 | DOI:10.1101/2024.06.24.600378

bioRxiv [Preprint]. 2024 Jun 27:2024.06.22.600179. doi: 10.1101/2024.06.22.600179.

ABSTRACT

Innovations in protein engineering can help redesign allergenic proteins to reduce adverse reactions in sensitive individuals. To accomplish this aim, a better knowledge of the molecular properties of allergenic proteins and the molecular features that make a protein allergenic is needed. We present a novel AI-based tool, AllergenAI, to quantify the allergenic potential of a given protein. Our approach is solely based on protein sequences, differentiating it from previous tools that use some knowledge of the allergens' physicochemical and other properties in addition to sequence homology. We used the collected data on protein sequences of allergenic proteins as archived in the three well-established databases, SDAP 2.0, COMPARE, and AlgPred 2, to train a convolutional neural network and assessed its prediction performance by cross-validation. We then used Allergen AI to find novel potential proteins of the cupin family in date palm, spinach, maize, and red clover plants with a high allergenicity score that might have an adverse allergenic effect on sensitive individuals. By analyzing the feature importance scores (FIS) of vicilins, we identified a proline-alanine-rich (P-A) motif in the top 50% of FIS regions that overlapped with known IgE epitope regions of vicilin allergens. Furthermore, using∼ 1600 allergen structures in our SDAP database, we showed the potential to incorporate 3D information in a CNN model. Future, incorporating 3D information in training data should enhance the accuracy. AllergenAI is a novel foundation for identifying the critical features that distinguish allergenic proteins.

PMID:38979176 | PMC:PMC11230160 | DOI:10.1101/2024.06.22.600179

bioRxiv [Preprint]. 2024 Jun 30:2024.05.05.592587. doi: 10.1101/2024.05.05.592587.

ABSTRACT

Proteins are inherently dynamic, and their conformational ensembles are functionally important in biology. Large-scale motions may govern protein structure-function relationship, and numerous transient but stable conformations of intrinsically disordered proteins (IDPs) can play a crucial role in biological function. Investigating conformational ensembles to understand regulations and disease-related aggregations of IDPs is challenging both experimentally and computationally. In this paper we first introduced an unsupervised deep learning-based model, termed Internal Coordinate Net (ICoN), which learns the physical principles of conformational changes from molecular dynamics (MD) simulation data. Second, we selected interpolating data points in the learned latent space that rapidly identify novel synthetic conformations with sophisticated and large-scale sidechains and backbone arrangements. Third, with the highly dynamic amyloid-β 1-42 (Aβ42) monomer, our deep learning model provided a comprehensive sampling of Aβ42's conformational landscape. Analysis of these synthetic conformations revealed conformational clusters that can be used to rationalize experimental findings. Additionally, the method can identify novel conformations with important interactions in atomistic details that are not included in the training data. New synthetic conformations showed distinct sidechain rearrangements that are probed by our EPR and amino acid substitution studies. This approach is highly transferable and can be used for any available data for training. The work also demonstrated the ability for deep learning to utilize learned natural atomistic motions in protein conformation sampling.

PMID:38979147 | PMC:PMC11230202 | DOI:10.1101/2024.05.05.592587

Nan Fang Yi Ke Da Xue Xue Bao. 2024 Jun 20;44(6):1198-1208. doi: 10.12122/j.issn.1673-4254.2024.06.22.

ABSTRACT

OBJECTIVE: We propose a motion artifact correction algorithm (DMBL) for reducing motion artifacts in reconstructed dental cone-beam computed tomography (CBCT) images based on deep blur learning.

METHODS: A blur encoder was used to extract motion-related degradation features to model the degradation process caused by motion, and the obtained motion degradation features were imported in the artifact correction module for artifact removal. The artifact correction module adopts a joint learning framework for image blur removal and image blur simulation for treatment of spatially varying and random motion patterns. Comparative experiments were conducted to verify the effectiveness of the proposed method using both simulated motion data sets and clinical data sets.

RESULTS: The experimental results with the simulated dataset showed that compared with the existing methods, the PSNR of the proposed method increased by 2.88%, the SSIM increased by 0.89%, and the RMSE decreased by 10.58%. The results with the clinical dataset showed that the proposed method achieved the highest expert level with a subjective image quality score of 4.417 (in a 5-point scale), significantly higher than those of the comparison methods.

CONCLUSION: The proposed DMBL algorithm with a deep blur joint learning network structure can effectively reduce motion artifacts in dental CBCT images and achieve high-quality image restoration.

PMID:38977351 | DOI:10.12122/j.issn.1673-4254.2024.06.22

Comput Biol Med. 2024 Jul 7;179:108846. doi: 10.1016/j.compbiomed.2024.108846. Online ahead of print.

ABSTRACT

BACKGROUND: Autofluorescence imaging of the coenzyme, reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H), provides a label-free technique to assess cellular metabolism. Because NAD(P)H is localized in the cytosol and mitochondria, instance segmentation of cell cytoplasms from NAD(P)H images allows quantification of metabolism with cellular resolution. However, accurate cytoplasmic segmentation of autofluorescence images is difficult due to irregular cell shapes and cell clusters.

METHOD: Here, a cytoplasm segmentation method is presented and tested. First, autofluorescence images are segmented into cells via either hand-segmentation or Cellpose, a deep learning-based segmentation method. Then, a cytoplasmic post-processing algorithm (CPPA) is applied for cytoplasmic segmentation. CPPA uses a binarized segmentation image to remove non-segmented pixels from the NAD(P)H image and then applies an intensity-based threshold to identify nuclei regions. Errors at cell edges are removed using a distance transform algorithm. The nucleus mask is then subtracted from the cell segmented image to yield the cytoplasm mask image. CPPA was tested on five NAD(P)H images of three different cell samples, quiescent T cells, activated T cells, and MCF7 cells.

RESULTS: Using POSEA, an evaluation method tailored for instance segmentation, the CPPA yielded F-measure values of 0.89, 0.87, and 0.94 for quiescent T cells, activated T cells, and MCF7 cells, respectively, for cytoplasm identification of hand-segmented cells. CPPA achieved F-measure values of 0.84, 0.74, and 0.72 for Cellpose segmented cells.

CONCLUSION: These results exceed the F-measure value of a comparative cell segmentation method (CellProfiler, ∼0.50-0.60) and support the use of artificial intelligence and post-processing techniques for accurate segmentation of autofluorescence images for single-cell metabolic analyses.

PMID:38976959 | DOI:10.1016/j.compbiomed.2024.108846

Genome Biol. 2024 Jul 8;25(1):184. doi: 10.1186/s13059-024-03328-1.

ABSTRACT

BACKGROUND: Although disease-causal genetic variants have been found within silencer sequences, we still lack a comprehensive analysis of the association of silencers with diseases. Here, we profiled GWAS variants in 2.8 million candidate silencers across 97 human samples derived from a diverse panel of tissues and developmental time points, using deep learning models.

RESULTS: We show that candidate silencers exhibit strong enrichment in disease-associated variants, and several diseases display a much stronger association with silencer variants than enhancer variants. Close to 52% of candidate silencers cluster, forming silencer-rich loci, and, in the loci of Parkinson's-disease-hallmark genes TRIM31 and MAL, the associated SNPs densely populate clustered candidate silencers rather than enhancers displaying an overall twofold enrichment in silencers versus enhancers. The disruption of apoptosis in neuronal cells is associated with both schizophrenia and bipolar disorder and can largely be attributed to variants within candidate silencers. Our model permits a mechanistic explanation of causative SNP effects by identifying altered binding of tissue-specific repressors and activators, validated with a 70% of directional concordance using SNP-SELEX. Narrowing the focus of the analysis to individual silencer variants, experimental data confirms the role of the rs62055708 SNP in Parkinson's disease, rs2535629 in schizophrenia, and rs6207121 in type 1 diabetes.

CONCLUSIONS: In summary, our results indicate that advances in deep learning models for the discovery of disease-causal variants within candidate silencers effectively "double" the number of functionally characterized GWAS variants. This provides a basis for explaining mechanisms of action and designing novel diagnostics and therapeutics.

PMID:38978133 | DOI:10.1186/s13059-024-03328-1

BMC Med Inform Decis Mak. 2024 Jul 8;24(1):191. doi: 10.1186/s12911-024-02591-3.

ABSTRACT

BACKGROUND: Recent advances in Vision Transformer (ViT)-based deep learning have significantly improved the accuracy of lung disease prediction from chest X-ray images. However, limited research exists on comparing the effectiveness of different optimizers for lung disease prediction within ViT models. This study aims to systematically evaluate and compare the performance of various optimization methods for ViT-based models in predicting lung diseases from chest X-ray images.

METHODS: This study utilized a chest X-ray image dataset comprising 19,003 images containing both normal cases and six lung diseases: COVID-19, Viral Pneumonia, Bacterial Pneumonia, Middle East Respiratory Syndrome (MERS), Severe Acute Respiratory Syndrome (SARS), and Tuberculosis. Each ViT model (ViT, FastViT, and CrossViT) was individually trained with each optimization method (Adam, AdamW, NAdam, RAdam, SGDW, and Momentum) to assess their performance in lung disease prediction.

RESULTS: When tested with ViT on the dataset with balanced-sample sized classes, RAdam demonstrated superior accuracy compared to other optimizers, achieving 95.87%. In the dataset with imbalanced sample size, FastViT with NAdam achieved the best performance with an accuracy of 97.63%.

CONCLUSIONS: We provide comprehensive optimization strategies for developing ViT-based model architectures, which can enhance the performance of these models for lung disease prediction from chest X-ray images.

PMID:38978027 | DOI:10.1186/s12911-024-02591-3

BMC Geriatr. 2024 Jul 8;24(1):586. doi: 10.1186/s12877-024-05188-7.

ABSTRACT

OBJECTIVE: Through a randomized controlled trial on older adults with sarcopenia, this study compared the training effects of an AI-based remote training group using deep learning-based 3D human pose estimation technology with those of a face-to-face traditional training group and a general remote training group.

METHODS: Seventy five older adults with sarcopenia aged 60-75 from community organizations in Changchun city were randomly divided into a face-to-face traditional training group (TRHG), a general remote training group (GTHG), and an AI-based remote training group (AITHG). All groups underwent a 3-month program consisting of 24-form Taichi exercises, with a frequency of 3 sessions per week and each session lasting 40 min. The participants underwent Appendicular Skeletal Muscle Mass Index (ASMI), grip strength, 6-meter walking pace, Timed Up and Go test (TUGT), and quality of life score (QoL) tests before the experiment, during the mid-term, and after the experiment. This study used SPSS26.0 software to perform one-way ANOVA and repeated measures ANOVA tests to compare the differences among the three groups. A significance level of p < 0.05 was defined as having significant difference, while p < 0.01 was defined as having a highly significant difference.

RESULTS: (1) The comparison between the mid-term and pre-term indicators showed that TRHG experienced significant improvements in ASMI, 6-meter walking pace, and QoL (p < 0.01), and a significant improvement in TUGT timing test (p < 0.05); GTHG experienced extremely significant improvements in 6-meter walking pace and QoL (p < 0.01); AITHG experienced extremely significant improvements in ASMI, 6-meter walking pace, and QoL (p < 0.01), and a significant improvement in TUGT timing test (p < 0.05). (2) The comparison between the post-term and pre-term indicators showed that TRHG experienced extremely significant improvements in TUGT timing test (p < 0.01); GTHG experienced significant improvements in ASMI and TUGT timing test (p < 0.05); and AITHG experienced extremely significant improvements in TUGT timing test (p < 0.01). (3) During the mid-term, there was no significant difference among the groups in all tests (p > 0.05). The same was in post-term tests (p > 0.05).

CONCLUSION: Compared to the pre-experiment, there was no significant difference at the post- experiment in the recovery effects on the muscle quality, physical activity ability, and life quality of patients with sarcopenia between the AI-based remote training group and the face-to-face traditional training group. 3D pose estimation is equally as effective as traditional rehabilitation methods in enhancing muscle quality, functionality and life quality in older adults with sarcopenia.

TRIAL REGISTRATION: The trial was registered in ClinicalTrials.gov (NCT05767710).

PMID:38977995 | DOI:10.1186/s12877-024-05188-7

Br J Haematol. 2024 Jul 8. doi: 10.1111/bjh.19639. Online ahead of print.

ABSTRACT

For over a century, the need to identify malaria in the peripheral blood has been the driving force behind the development of fundamental clinical microscopy techniques. In the study by Moysis et al., artificial intelligence-based model was utilized to identify and provide quantitative morphological characteristics of red blood cells typical to severe malaria anaemia, irrespective to the actual presence of visible parasites. Commentary on: Moysis et al. Leveraging deep learning for detecting red blood cell morphological changes in blood films from children with severe malaria anaemia. Br J Haematol 2024 (Online ahead of print). doi: 10.1111/bjh.19599.

PMID:38977858 | DOI:10.1111/bjh.19639

Nat Genet. 2024 Jul 8. doi: 10.1038/s41588-024-01831-6. Online ahead of print.

ABSTRACT

Although high-dimensional clinical data (HDCD) are increasingly available in biobank-scale datasets, their use for genetic discovery remains challenging. Here we introduce an unsupervised deep learning model, Representation Learning for Genetic Discovery on Low-Dimensional Embeddings (REGLE), for discovering associations between genetic variants and HDCD. REGLE leverages variational autoencoders to compute nonlinear disentangled embeddings of HDCD, which become the inputs to genome-wide association studies (GWAS). REGLE can uncover features not captured by existing expert-defined features and enables the creation of accurate disease-specific polygenic risk scores (PRSs) in datasets with very few labeled data. We apply REGLE to perform GWAS on respiratory and circulatory HDCD-spirograms measuring lung function and photoplethysmograms measuring blood volume changes. REGLE replicates known loci while identifying others not previously detected. REGLE are predictive of overall survival, and PRSs constructed from REGLE loci improve disease prediction across multiple biobanks. Overall, REGLE contain clinically relevant information beyond that captured by existing expert-defined features, leading to improved genetic discovery and disease prediction.

PMID:38977853 | DOI:10.1038/s41588-024-01831-6

Sci Rep. 2024 Jul 8;14(1):15661. doi: 10.1038/s41598-024-66427-w.

ABSTRACT

The goal of this research is to create an ensemble deep learning model for Internet of Things (IoT) applications that specifically target remote patient monitoring (RPM) by integrating long short-term memory (LSTM) networks and convolutional neural networks (CNN). The work tackles important RPM concerns such early health issue diagnosis and accurate real-time physiological data collection and analysis using wearable IoT devices. By assessing important health factors like heart rate, blood pressure, pulse, temperature, activity level, weight management, respiration rate, medication adherence, sleep patterns, and oxygen levels, the suggested Remote Patient Monitor Model (RPMM) attains a noteworthy accuracy of 97.23%. The model's capacity to identify spatial and temporal relationships in health data is improved by novel techniques such as the use of CNN for spatial analysis and feature extraction and LSTM for temporal sequence modeling. Early intervention is made easier by this synergistic approach, which enhances trend identification and anomaly detection in vital signs. A variety of datasets are used to validate the model's robustness, highlighting its efficacy in remote patient care. This study shows how using ensemble models' advantages might improve health monitoring's precision and promptness, which would eventually benefit patients and ease the burden on healthcare systems.

PMID:38977848 | DOI:10.1038/s41598-024-66427-w

Sci Rep. 2024 Jul 8;14(1):15728. doi: 10.1038/s41598-024-66605-w.

NO ABSTRACT

PMID:38977774 | DOI:10.1038/s41598-024-66605-w

Sci Rep. 2024 Jul 8;14(1):15751. doi: 10.1038/s41598-024-66481-4.

ABSTRACT

The need for intubation in methanol-poisoned patients, if not predicted in time, can lead to irreparable complications and even death. Artificial intelligence (AI) techniques like machine learning (ML) and deep learning (DL) greatly aid in accurately predicting intubation needs for methanol-poisoned patients. So, our study aims to assess Explainable Artificial Intelligence (XAI) for predicting intubation necessity in methanol-poisoned patients, comparing deep learning and machine learning models. This study analyzed a dataset of 897 patient records from Loghman Hakim Hospital in Tehran, Iran, encompassing cases of methanol poisoning, including those requiring intubation (202 cases) and those not requiring it (695 cases). Eight established ML (SVM, XGB, DT, RF) and DL (DNN, FNN, LSTM, CNN) models were used. Techniques such as tenfold cross-validation and hyperparameter tuning were applied to prevent overfitting. The study also focused on interpretability through SHAP and LIME methods. Model performance was evaluated based on accuracy, specificity, sensitivity, F1-score, and ROC curve metrics. Among DL models, LSTM showed superior performance in accuracy (94.0%), sensitivity (99.0%), specificity (94.0%), and F1-score (97.0%). CNN led in ROC with 78.0%. For ML models, RF excelled in accuracy (97.0%) and specificity (100%), followed by XGB with sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%). Overall, RF and XGB outperformed other models, with accuracy (97.0%) and specificity (100%) for RF, and sensitivity (99.37%), F1-score (98.27%), and ROC (96.08%) for XGB. ML models surpassed DL models across all metrics, with accuracies from 93.0% to 97.0% for DL and 93.0% to 99.0% for ML. Sensitivities ranged from 98.0% to 99.37% for DL and 93.0% to 99.0% for ML. DL models achieved specificities from 78.0% to 94.0%, while ML models ranged from 93.0% to 100%. F1-scores for DL were between 93.0% and 97.0%, and for ML between 96.0% and 98.27%. DL models scored ROC between 68.0% and 78.0%, while ML models ranged from 84.0% to 96.08%. Key features for predicting intubation necessity include GCS at admission, ICU admission, age, longer folic acid therapy duration, elevated BUN and AST levels, VBG_HCO3 at initial record, and hemodialysis presence. This study as the showcases XAI's effectiveness in predicting intubation necessity in methanol-poisoned patients. ML models, particularly RF and XGB, outperform DL counterparts, underscoring their potential for clinical decision-making.

PMID:38977750 | DOI:10.1038/s41598-024-66481-4

EJNMMI Phys. 2024 Jul 9;11(1):58. doi: 10.1186/s40658-024-00661-z.

ABSTRACT

BACKGROUND: Residual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) - a locally adaptive image filter - allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering.

METHODS: Altogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ( [ 18 F ] FDG, [ 18 F ] L-DOPA, [ 68 Ga ] DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the "optimal" filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs.

RESULTS: The automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal SUV max values of the unfiltered images with a low mean ± SD difference of δ SUV max CNN , STD = (-3.9 ± 5.2)% and δ SUV max BF , STD = (-4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar SUV max values in the vast majority of cases with an overall average difference of δ SUV max CNN , BF = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with δ Noise CNN , BF = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed.

CONCLUSIONS: Our results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning.

PMID:38977533 | DOI:10.1186/s40658-024-00661-z

Cardiovasc Intervent Radiol. 2024 Jul 8. doi: 10.1007/s00270-024-03805-x. Online ahead of print.

ABSTRACT

OBJECTIVES: To develop and validate a deep learning model for detecting post-endovascular aortic repair (EVAR) endoleak from non-contrast CT.

METHODS: This retrospective study involved 245 patients who underwent EVAR between September 2016 and December 2022. All patients underwent both non-enhanced and enhanced follow-up CT. The presence of endoleak was evaluated based on computed tomography angiography (CTA) and radiology reports. First, the aneurysm sac was segmented, and radiomic features were extracted on non-contrast CT. Statistical analysis was conducted to investigate differences in shape and density characteristics between aneurysm sacs with and without endoleak. Subsequently, a deep learning model was trained to generate predicted segmentation of the endoleak. A binary decision was made based on whether the model produced a segmentation to detect the presence of endoleak. The absence of a predicted segmentation indicated no endoleak, while the presence of a predicted segmentation indicated endoleak. Finally, the performance of the model was evaluated by comparing the predicted segmentation with the reference segmentation obtained from CTA. Model performance was assessed using metrics such as dice similarity coefficient, sensitivity, specificity, and the area under the curve (AUC).

RESULTS: This study finally included 85 patients with endoleak and 82 patients without endoleak. Compared to patients without endoleak, patients with endoleak had higher CT values and greater dispersion. The AUC in validation group was 0.951, dice similarity coefficient was 0.814, sensitivity was 0.877, and specificity was 0.884.

CONCLUSION: This deep learning model based on non-contrast CT can detect endoleak after EVAR with high sensitivity.

PMID:38977447 | DOI:10.1007/s00270-024-03805-x

J Chem Inf Model. 2024 Jul 8. doi: 10.1021/acs.jcim.4c00403. Online ahead of print.

ABSTRACT

Predicting drug-target interactions (DTIs) is one of the crucial tasks in drug discovery, but traditional wet-lab experiments are costly and time-consuming. Recently, deep learning has emerged as a promising tool for accelerating DTI prediction due to its powerful performance. However, the models trained on limited known DTI data struggle to generalize effectively to novel drug-target pairs. In this work, we propose a strategy to train an ensemble of models by capturing both domain-generic and domain-specific features (E-DIS) to learn diverse domain features and adapt them to out-of-distribution data. Multiple experts were trained on different domains to capture and align domain-specific information from various distributions without accessing any data from unseen domains. E-DIS provides a comprehensive representation of proteins and ligands by capturing diverse features. Experimental results on four benchmark data sets in both in-domain and cross-domain settings demonstrated that E-DIS significantly improved model performance and domain generalization compared to existing methods. Our approach presents a significant advancement in DTI prediction by combining domain-generic and domain-specific features, enhancing the generalization ability of the DTI prediction model.

PMID:38976879 | DOI:10.1021/acs.jcim.4c00403

PLoS One. 2024 Jul 8;19(7):e0302413. doi: 10.1371/journal.pone.0302413. eCollection 2024.

ABSTRACT

During the COVID-19 pandemic, pneumonia was the leading cause of respiratory failure and death. In addition to SARS-COV-2, it can be caused by several other bacterial and viral agents. Even today, variants of SARS-COV-2 are endemic and COVID-19 cases are common in many places. The symptoms of COVID-19 are highly diverse and robust, ranging from invisible to severe respiratory failure. Current detection methods for the disease are time-consuming and expensive with low accuracy and precision. To address such situations, we have designed a framework for COVID-19 and Pneumonia detection using multiple deep learning algorithms further accompanied by a deployment scheme. In this study, we have utilized four prominent deep learning models, which are VGG-19, ResNet-50, Inception V3 and Xception, on two separate datasets of CT scan and X-ray images (COVID/Non-COVID) to identify the best models for the detection of COVID-19. We achieved accuracies ranging from 86% to 99% depending on the model and dataset. To further validate our findings, we have applied the four distinct models on two more supplementary datasets of X-ray images of bacterial pneumonia and viral pneumonia. Additionally, we have implemented a flask app to visualize the outcome of our framework to show the identified COVID and Non-COVID images. The findings of this study will be helpful to develop an AI-driven automated tool for the cost effective and faster detection and better management of COVID-19 patients.

PMID:38976703 | DOI:10.1371/journal.pone.0302413