EJNMMI Phys. 2025 May 6;12(1):43. doi: 10.1186/s40658-025-00756-1.

ABSTRACT

PURPOSE: Dopamine transporter (DAT) SPECT is an effective tool for early Parkinson's disease (PD) detection and heavily hampered by attenuation. Attenuation correction (AC) is the most important correction among other corrections. Transfer learning (TL) with fine-tuning (FT) a pre-trained model has shown potential in enhancing deep learning (DL)-based AC methods. In this study, we investigate leveraging realistic Monte Carlo (MC) simulation data to create a pre-trained model for TL-based AC (TLAC) to improve AC performance for DAT SPECT.

METHODS: A total number of 200 digital brain phantoms with realistic 99mTc-TRODAT-1 distribution was used to generate realistic noisy SPECT projections using MC SIMIND program and an analytical projector. One hundred real clinical 99mTc-TRODAT-1 brain SPECT data were also retrospectively analyzed. All projections were reconstructed with and without CT-based attenuation correction (CTAC/NAC). A 3D conditional generative adversarial network (cGAN) was pre-trained using 200 pairs of simulated NAC and CTAC SPECT data. Subsequently, 8, 24, and 80 pairs of clinical NAC and CTAC DAT SPECT data were employed to fine-tune the pre-trained U-Net generator of cGAN (TLAC-MC). Comparisons were made against without FT (DLAC-MC), training on purely limited clinical data (DLAC-CLI), clinical data with data augmentation (DLAC-AUG), mixed MC and clinical data (DLAC-MIX), TL using analytical simulation data (TLAC-ANA), and Chang's AC (ChangAC). All datasets used for DL-based methods were split to 7/8 for training and 1/8 for validation, and a 1-/2-/5-fold cross-validation were applied to test all 100 clinical datasets, depending on the numbers of clinical data used in the training model.

RESULTS: With 8 available clinical datasets, TLAC-MC achieved the best result in Normalized Mean Squared Error (NMSE) and Structural Similarity Index Measure (SSIM) (TLAC-MC; NMSE = 0.0143 ± 0.0082/SSIM = 0.9355 ± 0.0203), followed by DLAC-AUG, DLAC-MIX, TLAC-ANA, DLAC-CLI, DLAC-MC, ChangAC and NAC. Similar trends exist when increasing the number of clinical datasets. For TL-based AC methods, the fewer clinical datasets available for FT, the greater the improvement as compared to DLAC-CLI using the same number of clinical datasets for training. Joint histograms analysis and Bland-Altman plots of SBR results also demonstrate consistent findings.

CONCLUSION: TLAC is feasible for DAT SPECT with a pre-trained model generated purely based on simulation data. TLAC-MC demonstrates superior performance over other DL-based AC methods, particularly when limited clinical datasets are available. The closer the pre-training data is to the target domain, the better the performance of the TLAC model.

PMID:40327202 | DOI:10.1186/s40658-025-00756-1

Eur Spine J. 2025 May 6. doi: 10.1007/s00586-025-08895-w. Online ahead of print.

ABSTRACT

PURPOSE: Scoliosis is a prevalent spine deformity that impacts millions of children globally. The Cobb angle, a crucial and widely-accepted metric, serves as the "gold standard" for assessing scoliosis in patients. However, the traditional manual measurement of spine curvature is time-consuming and labor-intensive. It also comes with issues like intra - and inter-observer variations. Moreover, accurately and robustly evaluating Cobb angles is extremely challenging. This is because it necessitates the correct identification of all the required vertebrae in both the anterior-posterior (AP) and lateral (LAT) views of full-spine digital radiography (DR).

METHODS: To solve these challenges, a deep learning-based framework is developed to fully automatically measure patient Cobb angels from full-spine DR of both AP and LAT views. First, a deep learning network was used to distinguish AP and LAT views. Then the region of interest (ROI) of the whole spine was located and extracted. Subsequently, a detection network was applied to detect and identify the boundaries and locations, the types, and the four corner points of each spinal vertebra. Finally, the Cobb angles was measured automatically. When taking into account the location, recognition, and key points detection of spinal vertebrae, YOLOv8 architecture with CBAM module was adopted as the backbone.

RESULTS: A total of 1,163 AP view and 1,378 LAT view DR images were used to train and evaluate the models. Experimental results in the evaluation testing showed a mean Cobb angle error of 2.56° for AP view and 2.498° for LAT view DR images. The intra-class correlation coefficient (ICC) with 95% confidence interval (CI) was 0.956 (0.932, 0.972) for AP view and 0.925 (0.888, 0.952) for LAT view. The Pearson correlation coefficient was 0.961 for AP view and 0.930 for LAT view. In the comprehensive reader study, for the major curve, a mean Cobb angle error of 3.918°, an ICC of 0.943 (0.912, 0.965), and a high correlation coefficient of 0.960 were obtained.

CONCLUSION: The results showed that the proposed framework had a significant accuracy and consistency advantage in measuring Cobb angle, which not only validated the effectiveness of the algorithm, but also provided strong support for the diagnosis of clinicians.

PMID:40327070 | DOI:10.1007/s00586-025-08895-w

Radiology. 2025 May;315(2):e240714. doi: 10.1148/radiol.240714.

ABSTRACT

Background Four-dimensional (4D) flow MRI provides assessment of thoracic aorta hemodynamic measures that are increasingly recognized as important biomarkers for risk assessment. However, long acquisition times and cumbersome data analysis limit widespread availability. Purpose To evaluate the feasibility and accuracy of a generative artificial intelligence (AI) approach (fluid physics-informed cycle generative adversarial network [FPI-CycleGAN]) in quantifying aorta hemodynamics directly from anatomic input as an alternative to 4D flow MRI. Materials and Methods Patients were retrospectively identified from a dataset of clinical cardiothoracic MRI examinations performed between November 2011 and July 2020. All patients underwent aortic 4D flow MRI, which served as a reference standard for training and testing of FPI-CycleGANs. A three-dimensional (3D) segmentation of the aortic geometry was used as the only input to predict systolic aortic hemodynamics, with separate networks for bicuspid aortic valve (BAV) (994 in the training set and 248 in the test set) and tricuspid aortic valve (TAV) (419 in the training set and 104 in the test set). Voxel-by-voxel and regional analyses were used to quantify and compare (AI vs the reference standard, 4D flow) systolic velocity vector fields, peak velocity, wall shear stress (WSS), and classification of aortic valve stenosis. Results In total, 1765 patients (median age, 53 years [IQR, 41-63 years]; 1242 patients had BAV and 523 had TAV) were included. Mean AI computation time was 0.15 second ± 0.11 (SD), and total training was 1500 and 3600 minutes for the TAV and BAV networks, respectively. The FPI-CycleGAN predicted systolic 3D velocity vector fields accurately, with low bias (<0.01 m/sec) and excellent limits of agreements (±0.06-0.08 m/sec). For peak velocities and WSS, there was strong agreement between FPI-CycleGAN and 4D flow (r2 = 0.930-0.957 [P < .001], with relative differences of 6.2%-9.8%). AI accurately classified aortic valve stenosis severity in 85.8% of patients (302 of 352) (κ = 0.80 [95% CI: 0.71, 0.89]). The FPI-CycleGAN was robust to one- and two-voxel dilation and erosion (bias, -0.05 to 0.1 m/sec) and ±5° rotation (bias, -0.02 to 0.03 m/sec) of the input data. The application of the trained FPI-CycleGAN in an external test set with contrast-enhanced MR angiography (n = 60 patients) as AI input data demonstrated strong to excellent performance for peak velocities and WSS (r2 = 0.944-0.965 [P < .001], with relative differences of 6.2%-9.2%). Conclusion Aorta 3D hemodynamics can be derived from anatomic input in less than 1 second using an FPI-CycleGAN and demonstrate strong agreement with in vivo 4D flow MRI systolic hemodynamics. © RSNA, 2025 Supplemental material is available for this article.

PMID:40326877 | DOI:10.1148/radiol.240714

J Acoust Soc Am. 2025 May 1;157(5):3508-3523. doi: 10.1121/10.0036456.

ABSTRACT

Underwater passive acoustic recognition, which focuses on classifying targets based on ship-radiated noise, is a key challenge in underwater acoustics. Deep learning-based methods have gained popularity in recent years because of their strong performance. However, these methods often fail to generalize well in real-world scenarios. This work reveals one underlying challenge: the characteristics of ship-radiated noise are influenced by factors such as vessel structures and propulsion systems. Although vessels of the same type may exhibit different patterns in these aspects, vessels of different categories share similarities. As a result, data-driven models often tend to overemphasize individual-specific features, leading to "overfitting" and poor generalization. The momentum-based adversarial training (MBAT) framework is proposed to mitigate this challenge. MBAT leverages a momentum adversarial strategy to use category information and individual vessel relationships, helping extract class-discriminative features. A homoscedastic uncertainty algorithm is employed to balance the optimization objectives of category-related and vessel-specific features. These strategies allow the model to capture category-discriminative patterns more effectively and generalize to unseen targets. Experiments on DeepShip and ShipsEar demonstrate that MBAT significantly improves generalization capability on unseen individual vessels, outperforming existing state-of-the-art methods. Visualizations further confirm the efficacy and necessity of the proposed approach.

PMID:40326792 | DOI:10.1121/10.0036456

Bioinformatics. 2025 May 6:btaf277. doi: 10.1093/bioinformatics/btaf277. Online ahead of print.

ABSTRACT

MOTIVATION: The availability of very large numbers of protein structures from accurate computational methods poses new challenges in storing, searching and detecting relationships between these structures. In particular, the new-found abundance of multi-domain structures in the AlphaFold structure database introduces challenges for traditional structure comparison methods.

RESULTS: We address these challenges using a fast, embedding-based structure comparison method called Foldclass which detects structural similarity between protein domains. We demonstrate the accuracy of Foldclass embeddings for homology detection. In combination with a recently developed deep learning-based automatic domain segmentation tool Merizo, we develop Merizo-search, which first segments multi-domain query structures into domains, and then searches a Foldclass embedding database to determine the top matches for each constituent domain. Combining the ability of Merizo to accurately segment complete chains into domains, and Foldclass to embed and detect similar domains, the Merizo-search tool can be used to rapidly detect per-domain similarities for complete chains, taking as little as 2 minutes to search all 365 million domains from the Encyclopedia of Domains. We anticipate that these tools will enable many analyses using the wealth of predicted structural data now available.

AVAILABILITY: Foldclass and Merizo-search are available at https://github.com/psipred/merizo_search. The version used in this publication is archived at https://doi.org/10.5281/zenodo.15120830. Merizo-search is also available on the PSIPRED web server at http://bioinf.cs.ucl.ac.uk/psipred.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:40326701 | DOI:10.1093/bioinformatics/btaf277

Gen Physiol Biophys. 2025 May;44(3):187-200. doi: 10.4149/gpb_2025008.

ABSTRACT

The abnormal proliferation and activation of fibroblasts have been implicated in idiopathic pulmonary fibrosis. Herein, the present research explored the impacts of the relationship between hydroxysafflor yellow A (HSYA) and a disintegrin and metalloproteinase 17 (ADAM17) on fibroblast activation, which can provide novel insight into the treatment and management of idiopathic pulmonary fibrosis. MRC-5 fibroblasts were firstly activated with TGF-β1, followed by measurement of ADAM17 expression through qRT-PCR and Western blot. Fibrosis-related gene and protein expression levels, cell viability, proliferation, migration, and fibroblast-to-myofibroblast transdifferentiation were determined by qRT-PCR and Western blot, MTS, EdU, Transwell, and immunofluorescence assays, respectively. Moreover, the regulatory relationships among HSYA, ADAM17, and the NF-κB/STAT3 pathway in MRC-5 cells were analyzed by bioinformatics analysis, qRT-PCR, and Western blot. The results show that HSYA treatment could diminish the fibrosis-related gene and protein expression patterns, proliferation, migration, and fibroblast-to-myofibroblast transdifferentiation in TGF-β1-stimulated MRC-5 cells. Moreover, HSYA could repress the TGF-β1-triggered ADAM17 up-regulation, thereby suppressing the NF-κB/STAT3 pathway. Furthermore, over-expression of ADAM17 negated the inhibitory effect of HSYA on fibroblast activation induced by TGF-β1. The findings revealed that HSYA blocked the NF-κB/STAT3 pathway activation by down-regulating ADAM17, thereby inhibiting TGF-β1-induced fibroblast activation.

PMID:40326971 | DOI:10.4149/gpb_2025008

ACS Synth Biol. 2025 May 6. doi: 10.1021/acssynbio.5c00077. Online ahead of print.

ABSTRACT

Pseudomonas aeruginosa elastase is a metalloprotease with significant industrial potential but is challenging to produce due to its pathogenic origin and folding complexities. In this study, we applied rational design to engineer nonfunctional regions of elastase within Saccharomyces cerevisiae, specifically targeting propeptide and signal peptide cleavage sites, and N-glycosylation in the propeptide. This led to the development of several improved elastase variants. Integrating the yeast protein secretory model pcSecYeast with protease production characteristics, a total of 75 targets were identified and validated, comprising both model-predicted and production-feature-based targets. Notably, overexpression of POS5 enhanced protease activity to 2.43-fold that of the control, while knockout of TES1 or VPS10 further optimized production. This work demonstrates the potential of systems biology in creating yeast cell factories for protease production and highlights S. cerevisiae as a versatile host for biotechnological applications.

PMID:40327375 | DOI:10.1021/acssynbio.5c00077

ACS Synth Biol. 2025 May 6. doi: 10.1021/acssynbio.4c00742. Online ahead of print.

ABSTRACT

Historically, studying the development of brain and central nervous system (CNS) tissues has been challenging. Human pluripotent stem cell (hPSC) technology has allowed for the in vitro reconstitution of relevant, early cell trajectories by using small molecules and recombinant proteins to guide differentiation of cells toward relevant brain and CNS phenotypes. However, many of these protocols fail to recapitulate the cell-guided differentiation programs intrinsic to embryonic development, particularly the signaling centers that emerge within the neural tube during brain formation. Located on the ventral end of the neural tube, the floor plate acts as one such signaling center to pattern the dorsal/ventral axis by secreting the morphogen Sonic Hedgehog (SHH). Here, we present a method for cell-guided differentiation using the synthetic Notch (synNotch) receptor platform to regulate SHH production and subsequent cell fate specification. We show that the widely used configuration of the orthogonal synNotch ligand green fluorescent protein (GFP) mounted on a platelet-derived growth factor receptor-β transmembrane chassis does not allow for robust artificial signaling in synNotch-hPSCs ("receivers") cocultured with ligand-presenting hPSCs ("senders"). We discovered that refined designs of membrane-bound GFP-ligand allow for efficient receptor activation in hPSC receivers. A variant of this enhanced synNotch system drives the production of SHH in hPSC sender:hPSC receiver cocultures and gives rise to floor plate-like cell types seen during neural tube development. This revised synNotch platform has the potential to pattern hPSC differentiation programs in synthetic morphogenesis studies designed to uncover key paradigms of human CNS development.

PMID:40327355 | DOI:10.1021/acssynbio.4c00742

Plant Cell Rep. 2025 May 6;44(6):113. doi: 10.1007/s00299-025-03503-z.

ABSTRACT

Cotton plants undergo a drastic transcriptional reprogramming after cotton boll weevil infestation, modulating several defense pathways to cope with the damage. The global demand for cotton fiber continues to rise, but pests and pathogens significantly hinder cotton production, causing substantial losses. Among these, the cotton boll weevil (Anthonomus grandis) is one of the most destructive pests. To investigate the molecular responses of cotton (Gossypium hirsutum) to boll weevil infestation, we evaluated the global gene expression of floral buds using mRNA-seq. Additionally, we analyzed the expression of non-coding RNAs, including microRNAs (miRNAs) and long intergenic non-coding RNAs (lincRNAs). Infestation by cotton boll weevil larvae triggered a rapid and drastic transcriptional reprogramming, with 1,656 and 1.698 genes modulated after two and twelve hours, respectively. Gene ontology enrichment analysis revealed significant regulation of defense-related and developmental processes, including photosynthesis, primary metabolism, and cell organization. Transcription factor families such as ERF, WRKY, GRAS, and NAC were strongly affected, highlighting their roles in coordinating defense responses. The jasmonate pathway showed intensive modulation, alongside secondary metabolite pathways like terpenoids and phenylpropanoids, which contribute to plant defense mechanisms. Non-coding RNAs also played a critical role in the response. We identified 921 unique known and novel miRNAs, with 36 modulated by the infestation, and predicted 98,850 putative lincRNAs, several of which were differentially expressed. Understanding the genetic and molecular mechanisms underlying cotton's defense against boll weevil, particularly during early infestation stages, is vital for developing biotechnological strategies to reduce pest damage. Our findings provide critical insights to enhance cotton resilience against herbivores.

PMID:40327114 | DOI:10.1007/s00299-025-03503-z

J Exp Med. 2025 Aug 4;222(8):e20241133. doi: 10.1084/jem.20241133. Epub 2025 May 6.

ABSTRACT

In chronic viral infections, sustained CD8+ T cell response relies on TCF1+ precursor-exhausted T cells (TPEX) exhibiting stem-like properties. TPEX self-renew and respond to PD-1 blockade, underscoring their paramount importance. However, strategies for effectively augmenting TPEX remain limited. Here, we demonstrate that ZC3H12A deficiency initiates a stemness program in TPEX but also increases cell death, whereas BCOR deficiency predominantly promotes TPEX proliferation. Consequently, co-targeting of both BCOR and ZC3H12A imparts exceptional stemness and functionality to TPEX, thereby enhancing viral control. Mechanistically, BCOR and ZC3H12A collaboratively suppress a core stemness program in TPEX characterized by heightened expression of ∼216 factors. While TCF1 plays a role, this core stemness program relies on novel factors, including PDZK1IP1, IFIT3, PIM2, LTB, and POU2F2. Crucially, overexpressing POU2F2 robustly boosts TPEX and enhances antiviral immunity. Thus, a core stemness program exists in exhausted T cells, jointly repressed by BCOR and ZC3H12A, robustly controlling TPEX differentiation and providing new targets for addressing T cell exhaustion.

PMID:40327039 | DOI:10.1084/jem.20241133

Elife. 2025 May 6;14:RP101299. doi: 10.7554/eLife.101299.

ABSTRACT

3D cellular-specific epigenetic and transcriptomic reprogramming is critical to organogenesis and tumorigenesis. Here, we dissect the distinct cell fitness in 2D (normoxia vs. chronic hypoxia) vs 3D (normoxia) culture conditions for an MYC-driven murine liver cancer model. We identify over 600 shared essential genes and additional context-specific fitness genes and pathways. Knockout of the VHL-HIF1 pathway results in incompatible fitness defects under normoxia vs. 1% oxygen or 3D culture conditions. Moreover, deletion of each of the mitochondrial respiratory electron transport chain complex has distinct fitness outcomes. Notably, multicellular organogenesis signaling pathways including TGFβ-SMAD, which is upregulated in 3D culture, specifically constrict the uncontrolled cell proliferation in 3D while inactivation of epigenetic modifiers (Bcor, Kmt2d, Mettl3, and Mettl14) has opposite outcomes in 2D vs. 3D. We further identify a 3D-dependent synthetic lethality with partial loss of Prmt5 due to a reduction of Mtap expression resulting from 3D-specific epigenetic reprogramming. Our study highlights unique epigenetic, metabolic, and organogenesis signaling dependencies under different cellular settings.

PMID:40326560 | DOI:10.7554/eLife.101299

Anal Chem. 2025 May 6. doi: 10.1021/acs.analchem.5c00390. Online ahead of print.

ABSTRACT

The interpretation of proteomics data often relies on functional enrichment analysis, such as Gene Ontology (GO) enrichment, to uncover the biological functions of proteins, as well as the examination of protein expression patterns across data sets like the Clinical Proteomic Tumor Analysis Consortium (CPTAC) database. However, conventional approaches to functional enrichment frequently produce extensive and redundant term lists, complicating interpretation and synthesis. Moreover, the absence of specialized tools tailored to proteomics researchers limits the efficient exploration of protein expression within specific biological contexts. To address these challenges, we developed Ontolomics-P, a user-friendly web-based tool designed to advance proteomics data interpretation. Ontolomics-P integrates topic modeling using latent Dirichlet allocation (LDA) with GO semantic similarity analysis, enabling the consolidation of redundant terms into coherent topics. These topics are further refined and reannotated using the GPT-4o language model, creating a novel topics database that provides precise and interpretable insights into shared biological functions. Additionally, Ontolomics-P incorporates quantitative proteomic data from 10 diverse cancer types archived in the CPTAC database, allowing for a comprehensive exploration of protein expression profiles from a data-driven perspective. Through detailed case studies, we demonstrate the tool's capacity to streamline workflows, simplify interpretation, and provide actionable biological insights. Ontolomics-P represents a significant advancement in proteomics data analysis, offering innovative solutions for functional annotation, quantitative exploration, and visualization, ultimately empowering researchers to accelerate discoveries in systems biology and beyond.

PMID:40326493 | DOI:10.1021/acs.analchem.5c00390

J Chem Inf Model. 2025 May 6. doi: 10.1021/acs.jcim.5c00136. Online ahead of print.

ABSTRACT

Computational prediction of potential drug side effects plays a crucial role in reducing health risks for clinical patients and accelerating drug development. Recent methods have constructed heterogeneous graphs that represent drugs and their side effects, utilizing graph learning strategies such as graph convolutional networks to predict associations between them. However, existing approaches fail to fully exploit the diverse topologies and semantics present in multiple knowledge graphs. We propose MVDSA, a novel multi-view drug-side effect association prediction model. Our approach integrates multiple relationship semantics, local topologies of knowledge graphs, and multi-view features of drug-side effect entity pairs. First, we constructed two knowledge graphs based on drug functional and structural similarity, side effect similarity, and drug-side effect associations. These knowledge graphs capture the topological and semantic connections between drug and side effect entities from diverse perspectives. Second, considering the diverse similarities and associations between entities, we designed a space-sensitive learning strategy where a relation-gated semantic encoder is constructed for each type of relationship. This encoder adaptively adjusts the contribution of each entity feature to the relational semantic representation, facilitating the learning of entity-specific semantic features within each relational space. Third, for the two knowledge graphs, given the multiple types of connections between head and tail entities, we propose a connection-sensitive tail entity attention mechanism to integrate these diverse semantic relationships. To capture the contribution of different knowledge graphs to entity feature learning, we designed a knowledge graph-level attention mechanism to adaptively fuse the enhanced features from multiple knowledge graphs. Finally, we propose a multi-view enhanced multi-layer perceptron (MLP) strategy to encode the features of drug-side effect pairs from three perspectives and capture the potential associations between entities. Extensive experiments demonstrate that MVDSA outperforms 10 state-of-the-art methods in predicting drug-side effect associations. Ablation studies validate the contributions of the proposed innovations to improved prediction performance. Additionally, case studies on candidate side effects for five drugs highlight MVDSA's capability to discover potential drug-side effect associations.

PMID:40326886 | DOI:10.1021/acs.jcim.5c00136

ACS Infect Dis. 2025 May 6. doi: 10.1021/acsinfecdis.4c00962. Online ahead of print.

ABSTRACT

The emergence of drug-resistant malarial parasites has been a growing challenge to medical science to safeguard public health in the malaria-endemic regions of the globe. With time, the parasite develops newer resistance mechanisms to defunct the drug's action one after another. Genetic mutation is the prime weapon parasites rely upon to initiate the resistance mechanism in a case-specific manner, following various strategies such as structural changes in the target protein, metabolic alterations, and tweaking the drug-transported channels. In order to combat these resistances, different approaches have evolved among these developing inhibitors against critical parasite enzymes and metabolic pathways, combinatorial/hybrid drug therapies, exploring new drug targets and analogues of existing drugs, use of resistance-reversal agents, drug-repurposing, gene blocking/altering using RNA interference and CRISPR/Cas systems are prominent. However, the effectiveness of these approaches needs to be earnestly monitored for better management of the disease, which demands the development of a reliable diagnosis technique. Several methodologies have been investigated in search of a suitable diagnosis technique, such as in vivo, in vitro, ex vivo drug efficacy studies, and molecular techniques. A parallel effort to transform the efficient method into an inexpensive and portable diagnosis tool for rapid screening of drug resistance malaria among masses in the societal landscape is advocated. This review gives an insight into the historical perspectives of drug-resistant malaria and the recent developments in malaria diagnosis and antimalarial drug discovery. Efforts have been made to update recent strategies formulated to combat and diagnose drug-resistant malaria. Finally, a concluding remark with a future perspective on the subject has been forwarded.

PMID:40326084 | DOI:10.1021/acsinfecdis.4c00962

Clin Pharmacol Ther. 2025 May 5. doi: 10.1002/cpt.3704. Online ahead of print.

ABSTRACT

There is increasing attention on the clinical utility and value of pharmacogenetic (PGx) testing to individualize medication management. Most clinical practice guidelines from medical professional societies do not recommend routine PGx testing, with a few key exceptions. Inconsistent recommendations across clinical practice guidelines, FDA product labeling, and payer reimbursement policies have hampered widespread adoption of testing. Multiple resources exist to aid in the adoption and use of actionable PGx test results in clinical practice; however, most of these resources do not provide guidance on who should receive PGx testing and when-a critical question the clinical community continues to struggle with. There are multiple considerations when answering this question beyond the clinical validity of the drug-gene interaction itself, such as the actionable result frequency, severity of the adverse clinical outcome, predictive power of the PGx test, suitability of alternative treatments, cost, and turnaround time of test results. This perspective discusses these considerations and models for testing including preemptive screening, pretreatment testing, and reactive testing, highlighting advantages and disadvantages of each approach. The authors provide their perspectives on identifying candidates for PGx testing in the current real-world environment and how that differs from a clinically ideal scenario.

PMID:40325943 | DOI:10.1002/cpt.3704

Pediatr Pulmonol. 2025 May;60(5):e71102. doi: 10.1002/ppul.71102.

ABSTRACT

BACKGROUND: Cystic fibrosis (CF) is a chronic genetic disorder requiring regimented visits for maintenance of care. The COVID-19 pandemic accelerated the accessibility of telehealth (TH) and forced a trial of incorporating remote care into routine CF care. The CF Learning Network (CFLN) organized for data sharing into a telehealth innovation lab (TH-iLab) to improve access to the interdisciplinary care team and co-produced shared agenda-setting.

METHODS: All persons with CF (PwCF) with a CF diagnosis in the CF Foundation Registry (CFFPR) from 1/2020-12/2021 were included and categorized into CFLN TH-iLab, CFLN TH-iLab non-participants, and non-CFLN programs.

HYPOTHESIS: standardized TH implementation in the CFLN TH-iLab is associated with increased access to the CF care model and results in similar lung function and nutrition health outcomes.

RESULTS: In 2020 and 2021, the average number of TH visits per person per year and the percentage of PwCF with one or more TH visits per year were higher in the CFLN TH-iLab than in the other groups. Lung function was highest in PwCF, followed by a program that was part of the CFLN TH-iLab in 2020 and 2021. Anthropometric measurements, spirometry, and attainment of microbiology cultures were similar among all three groups. Access to interdisciplinary care was highest in the CFLN non-TH-iLab group.

CONCLUSION: Integrating TH into CF care in the CFLN TH-iLab provided access to care during the COVID-19 pandemic without compromising clinical outcomes. Further research on optimizing the telehealth experience for PwCF can help better understand TH's long-term impact on CF care.

PMID:40325945 | DOI:10.1002/ppul.71102

Pediatr Pulmonol. 2025 May;60(5):e71101. doi: 10.1002/ppul.71101.

ABSTRACT

BACKGROUND: Cystic fibrosis (CF) is a genetic disorder that necessitates high-calorie, protein-rich diets, leading to nutritional deficiencies. Food insecurity (FI) poses a significant challenge for people with CF (pwCF), impacting their ability to maintain the necessary dietary intake. This study aims to explore FI and dietary patterns among pwCF in Turkey.

METHODS: A cross-sectional study involving 290 pwCF from the Marmara University Selim Çöremen Cystic Fibrosis Center was conducted between April 2023 and February 2024. The "US Household Food Security Survey Module" and the "Your Current Life Situation" survey were used to assess FI and socioeconomic status among the participants. Nutritional data, including BMI, FEV1 values, and dietary intake, were recorded.

RESULTS: Among the participants, 52.7% were female, with a mean age of 13.3 ± 8.1 years. FI was detected in 46.8% of pwCF, with 18% facing very low food security. Higher income levels were associated with better food security (p = 0.008). Nutritional inadequacies were observed even among food-secure individuals, particularly in the consumption of legumes, nuts, and fish. BMI and BMI percentile values were significantly lower in the very low FS group compared to the high FS group (p = 0.03 and p = 0.02, respectively).

CONCLUSION: Ensuring adequate nutrition and calorie intake is crucial for pwCF. Our study highlights significant FI among pwCF in Turkey, with income levels influencing food security status. Nutritional inadequacies persist even among those classified as food secure. Based on these findings, targeted nutritional support will be provided to those in need to improve overall health and well-being.

PMID:40325925 | DOI:10.1002/ppul.71101

Curr Opin Pulm Med. 2025 May 6. doi: 10.1097/MCP.0000000000001179. Online ahead of print.

ABSTRACT

PURPOSE OF REVIEW: This review evaluates the role of artificial intelligence (AI) in diagnosing solitary pulmonary nodules (SPNs), focusing on clinical applications and limitations in pulmonary medicine. It explores AI's utility in imaging and blood/tissue-based diagnostics, emphasizing practical challenges over technical details of deep learning methods.

RECENT FINDINGS: AI enhances computed tomography (CT)-based computer-aided diagnosis (CAD) through steps like nodule detection, false positive reduction, segmentation, and classification, leveraging convolutional neural networks and machine learning. Segmentation achieves Dice similarity coefficients of 0.70-0.92, while malignancy classification yields areas under the curve of 0.86-0.97. AI-driven blood tests, incorporating RNA sequencing and clinical data, report AUCs up to 0.907 for distinguishing benign from malignant nodules. However, most models lack prospective, multiinstitutional validation, risking overfitting and limited generalizability. The "black box" nature of AI, coupled with overlapping inputs (e.g., nodule size, smoking history) with physician assessments, complicates integration into clinical workflows and precludes standard Bayesian analysis.

SUMMARY: AI shows promise for SPN diagnosis but requires rigorous validation in diverse populations and better clinician training for effective use. Rather than replacing judgment, AI should serve as a second opinion, with its reported performance metrics understood as study-specific, not directly applicable at the bedside due to double-counting issues.

PMID:40326426 | DOI:10.1097/MCP.0000000000001179

Circ Cardiovasc Imaging. 2025 May 6:e018291. doi: 10.1161/CIRCIMAGING.125.018291. Online ahead of print.

NO ABSTRACT

PMID:40326361 | DOI:10.1161/CIRCIMAGING.125.018291

Brain. 2025 May 6:awaf172. doi: 10.1093/brain/awaf172. Online ahead of print.

ABSTRACT

Migraine has an assumed polygenic basis, but the genetic risk variants identified in genome-wide association studies only explain a proportion of the heritability. We aimed to develop machine learning models, capturing non-additive and interactive effects, to address the missing heritability. This was a cross-sectional population-based study of participants in the second and third Trøndelag Health Study. Individuals underwent genome-wide genotyping and were phenotyped based on validated modified criteria of the International Classification of Headache Disorders. Four datasets of increasing number of genetic variants were created using different thresholds of linkage disequilibrium and univariate genome-wide associated p-values. A series of machine learning and deep learning methods were optimized and evaluated. The genotype tools PLINK and LDPred2 were used for polygenic risk scoring. Models were trained on a partition of the dataset and tested in a hold-out set. The area under the receiver operating characteristics curve was used as the primary scoring metric. Classification by machine learning was statistically compared to that of polygenic risk scoring. Finally, we explored the biological functions of the variants unique to the machine learning approach. 43,197 individuals (51% women), with a mean age of 54.6 years, were included in the modelling. A light gradient boosting machine performed best for the three smallest datasets (108, 7,771 and 7,840 variants), all with hold-out test set area under curve at 0.63. A multinomial naïve Bayes model performed best in the largest dataset (140,467 variants) with a hold-out test set area under curve of 0.62. The models were statistically significantly superior to polygenic risk scoring (area under curve 0.52 to 0.59) for all the datasets (p<0.001 to p=0.02). Machine learning identified many of the same genes and pathways identified in genome-wide association studies, but also several unique pathways, mainly related to signal transduction and neurological function. Interestingly, pathways related to botulinum toxins, and pathways related to the calcitonin gene-related peptide receptor also emerged. This study suggests that migraine may follow a non-additive and interactive genetic causal structure, potentially best captured by complex machine learning models. Such structure may be concealed where the data dimensionality (high number of genetic variants) is insufficiently supported by the scale of available data, leaving a misleading impression of purely additive effects. Future machine learning models using substantially larger sample sizes could harness both the additive and the interactive effects, enhancing precision and offering deeper understanding of genetic interactions underlying migraine.

PMID:40326299 | DOI:10.1093/brain/awaf172