Alzheimers Dement. 2024 Dec;20 Suppl 8:e095709. doi: 10.1002/alz.095709.

ABSTRACT

BACKGROUND: Cerebral amyloid angiopathy (CAA), the accumulation of amyloid proteins in the cerebral vasculature, increases the risk of stroke and vascular cognitive impairment and dementia (VCID). Not only is there no treatment for CAA, but the condition is also highly comorbid with Alzheimer's disease (AD), and its presence may serve as a contraindication to treating patients with anti-amyloid therapies due to an increased risk of hemorrhage and edema. Therefore, it is crucial to identify novel treatments for individuals with CAA. Epidemiological studies suggest that certain antihypertensive medications, including those that target the renin-angiotensin system (RAS), are associated with a decreased risk of dementia. This study assesses whether two FDA-approved RAS-targeting drugs: telmisartan [a moderately brain-penetrant angiotensin receptor blocker (ARB)], and lisinopril [a brain-penetrant angiotensin-converting enzyme (ACE) inhibitor]; can be repurposed for the treatment of CAA.

METHODS: At either ∼3 months (early intervention) or ∼8 months (later intervention) of age, male and female Tg-SwDI mice began treatment with either telmisartan (1 mg/kg/day) or lisinopril (15 mg/kg/day) dissolved in drinking water or received plain drinking water only. Age- and sex-matched C57BL/6J mice receiving plain drinking water served as wild-type controls. Following 4 months of treatment, mice underwent blood pressure measurement followed by behavioral testing prior to euthanasia.

RESULTS: Voluntary oral consumption delivered doses similar to the target dose for both drugs. At the doses used, telmisartan and lisinopril treatment did not significantly reduce blood pressure in Tg-SwDI mice. Our findings thus far suggest that these drug treatments, particularly lisinopril, may mitigate cognitive-behavioral deficits observed in Tg-SwDI mice.

CONCLUSIONS: Ongoing experiments are being completed to increase sample sizes and investigate the potential benefits of telmisartan and lisinopril to mitigate neuropathological and cognitive impairment in Tg-SwDI mice. If findings support our hypothesis, this will demonstrate that these drugs could be repurposed to prevent and/or treat CAA, reducing the worldwide burden of stroke and dementia.

PMID:39783163 | DOI:10.1002/alz.095709

Alzheimers Dement. 2024 Dec;20 Suppl 6:e089679. doi: 10.1002/alz.089679.

ABSTRACT

BACKGROUND: Developing drugs for treating Alzheimer's disease (AD) has been extremely challenging and costly due to limited knowledge on underlying biological mechanisms and therapeutic targets. Repurposing drugs or their combination has shown potential in accelerating drug development due to the reduced drug toxicity while targeting multiple pathologies.

METHOD: To address the challenge in AD drug development, we developed a multi-task machine learning pipeline to integrate a comprehensive knowledge graph on biological/pharmacological interactions and multi-level evidence on drug efficacy, to identify repurposable drugs and their combination candidates RESULT: Using the drug embedding from the heterogeneous graph representation model, we ranked drug candidates based on evidence from post-treatment transcriptomic patterns, mechanistic efficacy in preclinical models, population-based treatment effect, and Phase 2/3 clinical trials. We experimentally validated the top-ranked candidates in neuronal cells, identifying drug combinations with efficacy in reducing oxidative stress and safety in maintaining neuronal viability and morphology. Our neuronal response experiments confirmed several biologically efficacious drug combinations.

CONCLUSION: This methodology showed that harmonizing heterogeneous and complementary data/knowledge, including human interactome, transcriptome patterns, experimental efficacy, and real-world patient data shed light on the drug development of complex diseases.

PMID:39782643 | DOI:10.1002/alz.089679

Pediatr Pulmonol. 2025 Jan;60(1):e27473. doi: 10.1002/ppul.27473.

ABSTRACT

INTRODUCTION: Lumacaftor/ivacaftor (lum/iva) was introduced in the Netherlands in 2017. We investigated 1-year efficacy of lum/iva on lung function and small airway and structural lung disease evaluated by multiple breath nitrogen washout and CT scan. Additionally, we investigated effects of lum/iva on exacerbations, anthropometry, sweat chloride and safety in children with CF in the Netherlands.

METHODS: Children with CF aged 6-18 years and homozygous for F508del treated in one of the seven Dutch CF centers for at least 12 months were eligible. Data were extracted from the Dutch CF Registry and electronic patient records. Primary outcome was change in percent predicted FEV1 (ppFEV1) after 12 months.

RESULTS: Nationwide, 247 children with CF were eligible for lum/iva. Eight patients discontinued lum/iva due to side effects. In total, 223/247 children (90.3%) were evaluated. Mean (range) age at baseline was 11.0 (6.0-17.1) years. There was no change in FEV1 after 12 months of lum/iva. In a subgroup, markers of small airway function and structural lung disease, such as LCI (n = 28), mean change (SD) -10.0% (15.8), and bronchus-artery (BA) analysis on CT scan (n = 81), showed significant improvement (p < 0.01). Moreover, BMI (n = 192), exacerbations (n = 219) and sweat chloride measurements (n = 105) improved.

CONCLUSION: Lum/iva was generally well tolerated in a real-life, nationwide pediatric cohort. The efficacy of lum/iva was comparable to phase 3 studies in children. LCI and BA analysis as markers of small airway and structural lung disease showed significant improvement which indicates the importance of these parameters to evaluate treatment effects of CF modulators in children.

PMID:39785291 | DOI:10.1002/ppul.27473

Pediatr Pulmonol. 2025 Jan;60(1):e27475. doi: 10.1002/ppul.27475.

ABSTRACT

BACKGROUND: People with cystic fibrosis (CF) may not expectorate sputum at young ages or after they receive CFTR modulators. While oropharyngeal swabs are commonly used to test for lower airway pathogens, it is unknown whether Staphylococcus aureus from the oropharynx matches the strain(s) infecting the lungs. Our goal was to determine whether oropharyngeal and sputum isolates of S. aureus are genetically distinct in a cohort of patients with CF.

METHODS: We obtained historical S. aureus isolates from patients who intermittently expectorated sputum in 2018, and we prospectively cultured S. aureus from oropharyngeal swabs and sputum from subjects with CF between August 2020 and February 2022. We performed short-read whole genome sequencing, determined sequence type, and performed phylogenetic analysis using S. aureus core genome single nucleotide polymorphisms (SNPs). We assigned isolates from a patient to the same strain if they had the same sequence type and differed by ≤ 60 SNPs or the isolates were not disturbed by clade breaker analysis.

RESULTS: 36 subjects had S. aureus in ≥ 1 oropharyngeal swab and ≥ 1 sputum in 2018. In the prospective collection, 31 subjects had synchronous oropharyngeal swab and sputum collections. Although polyclonal infections were detected, sputum and oropharyngeal isolates of S. aureus typically matched the same strain within study subjects, both over the span of 2018 (31/36 patients) and when collected simultaneously from 2020 to 2022 (29/31 patients).

CONCLUSIONS: In patients with CF who intermittently produce sputum, oropharyngeal swabs identify S. aureus with genetic and phenotypic similarity to those cultured from sputum.

PMID:39785222 | DOI:10.1002/ppul.27475

Monaldi Arch Chest Dis. 2025 Jan 9. doi: 10.4081/monaldi.2025.3068. Online ahead of print.

ABSTRACT

With the increasing use of highly effective modulator therapy (HEMT) in adults with cystic fibrosis (awCF), it is necessary to determine the evolution of the most dynamic physiological markers of this disease, such as the 6-minute walk test (6MWT) and the Glittre-activities of daily living test (TGlittre). The present study aimed to evaluate the 1-year changes in the 6- minute walking distance (6MWD), TGlittre time, and quality of life (QoL) in awCF before the initiation of HEMT and to determine the impact of habitual physical activity (HPA) and chest physiotherapy (CP). This longitudinal study enrolled 24 awCF who completed the 6MWT and TGlittre. Pulmonary function tests, handgrip strength (HGS), and the Cystic Fibrosis Questionnaire-Revised (CFQ-R) were conducted. Measurements were collected at baseline (T1) and 1 year later (T2). The median body mass index increased between T1 and T2 [19.8 (18-24) vs. 21.4 (19-24) kg/m2, p=0.038]. TGlittre time decreased both in relation to the absolute values [3.10 (2.52-3.39) vs. 2.40 (2.00-3.00) minutes, p=0.001] and in relation to the predicted values [127 (116-150) vs. 108 (102-140) % predicted, p=0.001]. Although there was no increase in 6MWD relative to the predicted values, it increased relative to the absolute values [545 (463-654) vs. 617 (540-658) meters, p=0.041]. In relation to the group that did not engage in HPA, individuals who had HPA showed an increase in HGS between T1 and T2 [7.1 (0-20) vs. 0 (-12-3) kgf, p=0.031]. In relation to the group that did not undergo CP, individuals undergoing CP showed an increase in the 'treatment burden'-CFQ-R between T1 and T2 [16.1 (-3-18) vs. -11.2 (-28-1) points, p=0.049]. In conclusion, awCF performed better on TGlittre than on 6MWT. They experienced an improvement in body composition. HPA was correlated with peripheral muscle strength, as were CP and QoL.

PMID:39783834 | DOI:10.4081/monaldi.2025.3068

Expert Rev Respir Med. 2025 Jan 9. doi: 10.1080/17476348.2025.2451960. Online ahead of print.

ABSTRACT

INTRODUCTION: Sickle cell disease (SCD) is an inherited hemoglobinopathy characterized by the production of sickle hemoglobin, leading to red blood cells sickling and hemolysis in hypoxic conditions. The resulting acute and chronic endothelial inflammation leads to chronic organ damage. Respiratory manifestations in SCD usually start from childhood and represent the leading causes of morbidity and mortality. Nevertheless, they are generally poorly addressed or recognized later in life, often contributing to a more severe course and complications.

AREAS COVERED: This narrative review aims to outline the significant acute and chronic respiratory manifestations in children with SCD, focusing on prevention and clinical management. Compelling issues that need to be addressed in the future are also discussed. We searched the PubMed database for original papers written in English. Age restrictions were set for children (birth to 18 years). No limitations were set for the date and study country.

EXPERT OPINION: Early detection and treatment of respiratory manifestations in SCD should be central to follow-up with patients affected by SCD. Nonetheless, studies are lacking, especially in pediatric age, and there is still no consensus on their management. Further research is strongly needed to accomplish universally accepted guidelines to guarantee patients the best care possible.

PMID:39783770 | DOI:10.1080/17476348.2025.2451960

Sci Diabetes Self Manag Care. 2025 Jan 9:26350106241306058. doi: 10.1177/26350106241306058. Online ahead of print.

ABSTRACT

PURPOSE: The purpose of the study was to identify the most common reasons for and timing of continuous glucose monitoring (CGM) attrition in youth with type 1 diabetes (T1DM).

METHODS: This single center retrospective chart review included youth with T1DM <22 years seen between November 1, 2021, and October 31, 2022. Data were gathered from CGM cloud-based software and the electronic medical record.

RESULTS: Among 2663 youth, 88.3% (n = 2351) actively used CGM, and 5.9% (n = 311) had CGM attrition. Those who discontinued CGM were older (17.0 vs 14.9 years, P = .0001), had a longer T1DM duration (7.4 vs 5.1 years), higher A1C (9% vs 7.4%), and were non-Hispanic Black (NHB; 34.0% vs 11.5%). The odds of CGM attrition were 5.0 and 2.8 times higher in NHB and Latine youth, respectively, compared to non-Hispanic White youth. Median time to CGM discontinuation was 4 months, 21 days after initiation; 57% of youth who discontinued did so in the first 6 months of use. The most common reasons for CGM attrition were problems with device adhesion (18.4%), dislike device on the body (10.8%), insurance problems (9.5%), pain with device use (8.3%), and system mistrust due to inaccurate readings (8.2%). NHB and Latine youth were more likely to discontinue CGM due to insurance problems (3.2% vs 15.1% vs 16.7%).

CONCLUSIONS: To support equitable, uninterrupted CGM use, education at CGM initiation should address practical approaches to improve adhesion and wearability and provide a clear pathway to obtaining supplies. Interventions to support sustained CGM use should occur within the first 6 months of initiation.

PMID:39783011 | DOI:10.1177/26350106241306058

Bioinformatics. 2025 Jan 9:btae762. doi: 10.1093/bioinformatics/btae762. Online ahead of print.

ABSTRACT

MOTIVATION: Transcription factors (TFs) are DNA-binding proteins that regulate gene expression. Traditional methods predict a protein as a TF if the protein contains any DNA-binding domains (DBDs) of known TFs. However, this approach fails to identify a novel TF that does not contain any known DBDs. Recently proposed TF prediction methods do not rely on DBDs. Such methods use features of protein sequences to train a machine learning model, and then use the trained model to predict whether a protein is a TF or not. Because the 3-dimensional (3D) structure of a protein captures more information than its sequence, using 3D protein structures will likely allow for more accurate prediction of novel TFs.

RESULTS: We propose a deep learning-based TF prediction method (StrucTFactor), which is the first method to utilize 3D secondary structural information of proteins. We compare StrucTFactor with recent state-of-the-art TF prediction methods based on ∼525 000 proteins across 12 datasets, capturing different aspects of data bias (including sequence redundancy) possibly influencing a method's performance. We find that StrucTFactor significantly (p-value<0.001) outperforms the existing TF prediction methods, improving the performance over its closest competitor by up to 17% based on Matthews correlation coefficient.

AVAILABILITY: Data and source code are available at https://github.com/lieboldj/StrucTFactor and on our website at https://apps.cosy.bio/StrucTFactor/.

SUPPLEMENTARY INFORMATION: Included.

PMID:39786868 | DOI:10.1093/bioinformatics/btae762

Can J Exp Psychol. 2025 Jan 9. doi: 10.1037/cep0000360. Online ahead of print.

ABSTRACT

Working memory is associated with general intelligence and is crucial for performing complex cognitive tasks. Neuroimaging investigations have recognized that working memory is supported by a distribution of activity in regions across the entire brain. Identification of these regions has come primarily from general linear model analyses of statistical parametric maps to reveal brain regions whose activation is linearly related to working memory task conditions. This approach can fail to detect nonlinear task differences or differences reflected in distributed patterns of activity. In this study, we take advantage of the increased sensitivity of multivariate pattern analysis in a multiple-constraint deep learning classifier to analyze patterns of whole-brain blood oxygen level dependent (BOLD) activity in children performing two different conditions of the emotional n-back task. Regional (supervoxel) whole-brain activation patterns from functional imaging runs of 20 children were used to train a set of neural network classifiers to identify task category (0-back vs. 2-back) and activation co-occurrence probability, which encoded functional connectivity. These simultaneous constraints promote the discovery of coherent networks that contribute towards task performance in each memory load condition. Permutation analyses discovered the global activation patterns and interregional coactivations that distinguish memory load. Examination of model weights identified the brain regions most predictive of memory load and the functional networks integrating these regions. Community detection analyses identified functional networks integrating task-predictive regions and found distinct patterns of network activation for each task type. Comparisons to functional network literature suggest more focused attentional network activation during the 2-back task. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

PMID:39786863 | DOI:10.1037/cep0000360

Bioinformatics. 2025 Jan 9:btaf010. doi: 10.1093/bioinformatics/btaf010. Online ahead of print.

ABSTRACT

MOTIVATION: Accurate prediction of protein side-chain conformations is necessary to understand protein folding, protein-protein interactions and facilitate de novo protein design.

RESULTS: Here we apply torsional flow matching and equivariant graph attention to develop FlowPacker, a fast and performant model to predict protein side-chain conformations conditioned on the protein sequence and backbone. We show that FlowPacker outperforms previous state-of-the-art baselines across most metrics with improved runtime. We further show that FlowPacker can be used to inpaint missing side-chain coordinates and also for multimeric targets, and exhibits strong performance on a test set of antibody-antigen complexes.

AVAILABILITY: Code is available at https://gitlab.com/mjslee0921/flowpacker.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39786861 | DOI:10.1093/bioinformatics/btaf010

Int J Cardiovasc Imaging. 2025 Jan 9. doi: 10.1007/s10554-025-03322-z. Online ahead of print.

ABSTRACT

Amid an aging global population, heart failure has become a leading cause of hospitalization among older people. Its high prevalence and mortality rates underscore the importance of accurate mortality prediction for swift disease progression assessment and better patient outcomes. The evolution of artificial intelligence (AI) presents new avenues for predicting heart failure mortality. Yet current research has predominantly leveraged structured data and unstructured clinical notes from electronic health records (EHR), underutilizing the prognostic value of chest X-rays (CXRs). This study aims to harness deep learning methodologies to explore the feasibility of enhancing the precision of predicting in-hospital all-cause mortality in heart failure patients using CXRs data. We propose a novel multimodal deep learning network based on the spatially and temporally decoupled Transformer (MN-STDT) for in-hospital mortality prediction in heart failure by integrating longitudinal CXRs and structured EHR data. The MN-STDT captures spatial and temporal information from CXRs through a Hybrid Spatial Encoder and a Distance-Aware Temporal Encoder, ultimately fusing features from both modalities for predictive modeling. Initial pre-training of the spatial encoder was conducted on CheXpert, followed by full model training and evaluation on the MIMIC-IV and MIMIC-CXR datasets for mortality prediction tasks. In a comprehensive view, the MN-STDT demonstrated the best performance, with an AUC-ROC of 0.8620, surpassing all baseline models. Comparative analysis revealed that the AUC-ROC of the multimodal model (0.8620) was significantly higher than that of models using only structured data (0.8166) or chest X-ray data alone (0.7479). This study demonstrates the value of CXRs in the prognosis of heart failure, showing that the combination of longitudinal CXRs with structured EHR data can significantly improve the accuracy of mortality prediction in heart failure. Feature importance analysis based on SHAP provides interpretable decision support, paving the way for potential clinical applications.

PMID:39786626 | DOI:10.1007/s10554-025-03322-z

Breast Cancer Res Treat. 2025 Jan 9. doi: 10.1007/s10549-024-07589-z. Online ahead of print.

ABSTRACT

PURPOSE: Traditional computer-assisted detection (CADe) algorithms were developed for 2D mammography, while modern artificial intelligence (AI) algorithms can be applied to 2D mammography and/or digital breast tomosynthesis (DBT). The objective is to compare the performance of a traditional machine learning CADe algorithm for synthetic 2D mammography to a deep learning-based AI algorithm for DBT on the same mammograms.

METHODS: Mammographic examinations from 764 patients (mean age 58 years ± 11) with 106 biopsy-proven cancers and 658 cancer-negative cases were analyzed by a CADe algorithm (ImageChecker v10.0, Hologic, Inc.) and an AI algorithm (Genius AI Detection v2.0, Hologic, Inc.). Synthetic 2D images were used for CADe analysis, and DBT images were used for AI analysis. For each algorithm, an overall case score was defined as the highest score of all lesion marks, which was used to determine the area under the receiver operating characteristic curve (AUC).

RESULTS: The overall AUC was higher for 3D AI than 2D CADe (0.873 versus 0.693, P < 0.001). Lesion-specific sensitivity of 3D AI was higher than 2D CADe (94.3 versus 72.6%, P = 0.002). Specificity of 3D AI was higher than 2D CADe (54.3 versus 16.7%, P < 0.001), and the rate of false marks on non-cancer cases was lower for 3D AI than 2D CADe (0.91 versus 3.24 per exam, P < 0.001).

CONCLUSION: A deep learning-based AI algorithm applied to DBT images significantly outperformed a traditional machine learning CADe algorithm applied to synthetic 2D mammographic images, with regard to AUC, sensitivity, and specificity.

PMID:39786500 | DOI:10.1007/s10549-024-07589-z

Drug Saf. 2025 Jan 9. doi: 10.1007/s40264-024-01505-6. Online ahead of print.

ABSTRACT

BACKGROUND: Natural language processing (NLP) and machine learning (ML) techniques may help harness unstructured free-text electronic health record (EHR) data to detect adverse drug events (ADEs) and thus improve pharmacovigilance. However, evidence of their real-world effectiveness remains unclear.

OBJECTIVE: To summarise the evidence on the effectiveness of NLP/ML in detecting ADEs from unstructured EHR data and ultimately improve pharmacovigilance in comparison to other data sources.

METHODS: A scoping review was conducted by searching six databases in July 2023. Studies leveraging NLP/ML to identify ADEs from EHR were included. Titles/abstracts were screened by two independent researchers as were full-text articles. Data extraction was conducted by one researcher and checked by another. A narrative synthesis summarises the research techniques, ADEs analysed, model performance and pharmacovigilance impacts.

RESULTS: Seven studies met the inclusion criteria covering a wide range of ADEs and medications. The utilisation of rule-based NLP, statistical models, and deep learning approaches was observed. Natural language processing/ML techniques with unstructured data improved the detection of under-reported adverse events and safety signals. However, substantial variability was noted in the techniques and evaluation methods employed across the different studies and limitations exist in integrating the findings into practice.

CONCLUSIONS: Natural language processing (NLP) and machine learning (ML) have promising possibilities in extracting valuable insights with regard to pharmacovigilance from unstructured EHR data. These approaches have demonstrated proficiency in identifying specific adverse events and uncovering previously unknown safety signals that would not have been apparent through structured data alone. Nevertheless, challenges such as the absence of standardised methodologies and validation criteria obstruct the widespread adoption of NLP/ML for pharmacovigilance leveraging of unstructured EHR data.

PMID:39786481 | DOI:10.1007/s40264-024-01505-6

J Chem Inf Model. 2025 Jan 9. doi: 10.1021/acs.jcim.4c01732. Online ahead of print.

ABSTRACT

Proteolysis-targeting chimeras (PROTACs) are heterobifunctional molecules that target undruggable proteins, enhance selectivity and prevent target accumulation through catalytic activity. The unique structure of PROTACs presents challenges in structural identification and drug design. Liquid chromatography (LC), combined with mass spectrometry (MS), enhances compound annotation by providing essential retention time (RT) data, especially when MS alone is insufficient. However, predicting RT for PROTACs remains challenging. To address this, we compiled the PROTAC-RT data set from literature and evaluated the performance of four machine learning algorithms─extreme gradient boosting (XGBoost), random forest (RF), K-nearest neighbor (KNN) and support vector machines (SVM)─and a deep learning model, fully connected neural network (FCNN), using 24 molecular fingerprints and descriptors. Through screening combinations of molecular fingerprints, descriptors and chromatographic condition descriptors (CCs), we developed an optimized XGBoost model (XGBoost + moe206+Path + Charge + CCs) that achieved an R2 of 0.958 ± 0.027 and an RMSE of 0.934 ± 0.412. After hyperparameter tuning, the model's R2 improved to 0.963 ± 0.023, with an RMSE of 0.896 ± 0.374. The model showed strong predictive accuracy under new chromatographic separation conditions and was validated using six experimentally determined compounds. SHapley Additive exPlanations (SHAP) not only highlights the advantages of XGBoost but also emphasizes the importance of CCs and molecular features, such as bond variability, van der Waals surface area, and atomic charge states. The optimized XGBoost model combines moe206, path, charge descriptors, and CCs, providing a fast and precise method for predicting the RT of PROTACs compounds, thus facilitating their annotation.

PMID:39786356 | DOI:10.1021/acs.jcim.4c01732

Alzheimers Dement. 2024 Dec;20 Suppl 2:e087666. doi: 10.1002/alz.087666.

ABSTRACT

BACKGROUND: Drugs targeting Alzheimer's disease (AD) pathology are likely to be most effective in the presymptomatic stage, where individuals harbor AD pathology but have not manifested symptoms. Neuroimaging approaches can help to identify such individuals, but are costly for population-wide screening. Cost-effective screening is needed to identify those who may benefit from neuroimaging, such as those at risk of developing clinical disease. We present a deep learning algorithm that uses accelerometry recordings to predict clinically diagnosed AD in dementia-free patients.

METHOD: Participants were from The Memory and Aging Project (MAP), a longitudinal cohort study of older adults focused on aging and dementia. As part of this study, participants were asked to wear a wrist accelerometer for ten days. We designed a feedforward neural network that synthesizes clinical and accelerometric features to predict clinical AD. Clinical features were selected based on ease of collection, and included age, sex, education, social isolation and purpose in life. The dataset included participants without dementia at the time of recording, who survived for and had a known clinical AD outcome within five years of the recording.

RESULT: The training dataset consisted of 875 unique patients. The test dataset consisted of 395 unique patients (mean age 81.5, SD= 6.8). 14.4% of the test set developed clinical AD within five years. On the test set, the model achieved 89% sensitivity (SN), 70% specificity (SP), and an F1 score of 0.87 (Figure 1). This is superior to accelerometric-only (SN 67%, SP 70%, F1 0.68) and clinical-only (SN 76%, SP 80%, F1 0.78) models. Model accuracy was similar for patients both with and without mild cognitive impairment at baseline. When the binarized model output was used as a predictor for five-year AD-free survival via Cox proportional hazards (Figure 2), it achieved a C-index of 0.729 [95% CI 0.69 b-0.77], a hazard ratio of 6.90 [95% CI 4.15-11.47], and a log-likelihood ratio of 71.05. Further tuning and validation of the model are underway.

CONCLUSION: A deep learning model using wrist accelerometry and easily obtained clinical features shows promise in predicting 5-year AD outcomes in adults without dementia at baseline.

PMID:39786306 | DOI:10.1002/alz.087666

Alzheimers Dement. 2024 Dec;20 Suppl 2:e086725. doi: 10.1002/alz.086725.

ABSTRACT

BACKGROUND: The location of proposed brain MRI markers of small vessel disease (SVD) might reflect their pathogenesis and may translate into differential associations with cognition. We derived regional MRI markers of SVD and studied: (i) associations with cognitive performance, (ii) patterns most likely to reflect underlying SVD, (iii) mediating effects on the relationships of age and cardiovascular disease (CVD) risk with cognition.

METHOD: In 891 participants from The Multi-Ethnic Study of Atherosclerosis, we segmented enlarged perivascular spaces (ePVS), white matter hyperintensities (WMH) and microbleeds (MBs) using deep learning-based algorithms, and calculated white matter (WM) microstructural integrity measures of fractional anisotropy (FA), trace (TR) and free water (FW) using automated DTI-processing pipelines. Measures of global and domain-specific cognitive performance were derived from a comprehensive cognitive evaluation based on the UDS v3 neuropsychological battery.

RESULT: Mean (SD) age was 73.6 (7.9) years; 474 (53%) participants were women. In generalized linear models adjusted for demographics, vascular risk factors, and APOE ε4 carriership, higher basal ganglia ePVS count was associated with worse global, language, and attention cognitive performance (Table 1). Higher periventricular WMH volume was associated with worse global, delayed memory, language, phonemic, and attention performance. Higher WM FA was associated with better global, delayed memory, language, and attention performance. Higher WM TR was associated with worse global, delayed memory, language, phonemic, and attention performance. Exploratory factor analysis revealed that basal ganglia ePVS (standardized loading=0.51), thalamus ePVS (0.43), periventricular WMH (0.85), subcortical WMH (0.65), and WM FA (-0.73) and TR (0.84) loaded onto the same factor, likely reflecting underlying SVD. Structural equation models demonstrated that SVD mediated the effect of age on cognition (β[95%CI]= -0.071[-0.088,-0.053]) through the pathways: Age→SVD→Cognition (-0.044[-0.063,-0.026]) and Age→SVD→Brain Atrophy→Cognition (-0.006[-0.012,-0.002]) - Figure 1, and the effect of CVD risk on cognition (-0.028[-0.044,-0.012]) through the pathways: CVD Risk→SVD→Cognition (-0.021[-0.031,-0.013]) and CVD Risk→SVD→Brain Atrophy→Cognition (-0.007[-0.012,-0.003]) - Figure 2.

CONCLUSION: The location of the proposed MRI markers of SVD likely reflects distinct etiopathogenic substrates and should be considered when examining associations with cognitive or other health-related outcomes. SVD mediates the relationships of age and CVD risk with cognition via both atrophy-related and unrelated pathways.

PMID:39786253 | DOI:10.1002/alz.086725

Alzheimers Dement. 2024 Dec;20 Suppl 2:e090583. doi: 10.1002/alz.090583.

ABSTRACT

BACKGROUND: Neurodegenerative diseases are a heterogeneous group of illnesses. Differences across patients exist in the underlying biological drivers of disease. Furthermore, cross-diagnostic disease mechanisms exist, and different pathologies often co-occur in the brain. Clinical symptoms fail to capture this heterogeneity. Molecular biomarker-driven approaches are needed to improve patient identification & stratification with the aim of moving towards more targeted patient treatment strategies.

METHOD: The UK Biobank Pharma Proteomics Project has generated a proteomics dataset of unprecedented size. It consists of plasma proteomic profiles measured using the Olink 3k protein panel from over 54,000 individuals, complemented with broad phenotypic & genetic information. It is a unique resource to explore the biological correlation between neurodegenerative diseases as well as with other indications. We applied a multi-task deep learning (MTL) approach to generate models that predict disease status based on plasma proteomics profiles for a broad range of indications, including neurodegenerative diseases such as Alzheimer's and Parkinson's disease. The MTL approach first learns fundamental biological patterns by knowledge sharing between diseases in the initial segment of the network. Subsequently, understanding of a specific indication is refined with dedicated training. This improves model generalizability and statistical power. The neural network also produces low-dimensional embeddings of proteomic profiles that can be used for sample clustering and to derive insights about disease-associated processes.

RESULT: The average precision-recall area-under-the-curve (PR-AUC) of the MTL models across all diseases is 0.72 vs. 0.67 for the baseline single task logistic regression models. For Alzheimer's disease, the MTL classifier has a PR-AUC of 0.76. Feature importance scores were calculated using the SHAP method. Top features for Alzheimer's disease included several known biomarkers (e.g., GFAP, NPTXR). A UMAP projection of all diseases using the feature importance scores clusters diseases by disease category. Sample clustering revealed biologically interpretable patient subgroups, such as a Parkinson's cluster linked to lysosomal biology.

CONCLUSION: High performance of the MTL approach signifies good characterization of cross-disease biology. This is corroborated by the model's capability to produce meaningful low-dimensional representations of plasma proteomics profiles that can be used for identification of cross-diagnostic protein signatures and subtypes of neurodegenerative diseases. UKB application number 65851.

PMID:39786064 | DOI:10.1002/alz.090583

Allergol Immunopathol (Madr). 2025 Jan 1;53(1):153-169. doi: 10.15586/aei.v53i1.1234. eCollection 2025.

ABSTRACT

Common variable immunodeficiency (CVID) is the most common symptomatic and heterogeneous type of inborn errors of immunity (IEI). However, the pathogenesis process of this disease is often unknown. Epigenetic modifications may be involved in unresolved patients. MiR-142 and miR-155 were identified as immune system modulators and dysregulated in autoimmune and inflammatory diseases. We assessed hsa-miR-142-3p and hsa-miR-155-5p expression in a selected cohort of unresolved CVID cases and identified experimentally validated targets of these miRNAs. We constructed a protein-protein interaction (PPI) network from the common targets of two miRNAs and determined the hub genes. The hub genes' expression was investigated in GEO datasets. Gene ontology (GO) and pathway enrichment analysis were done for target genes. Hsa-miR-142-3p and hsa-miR-155-5p expression were significantly reduced in CVID patients. Evaluation of the PPI network demonstrated some hub genes in which pathogenic mutations have been reported in IEI, and other hub genes directly contribute to immune responses and the pathophysiology of IEI. Expression analysis of hub genes showed that they were significantly dysregulated in validating the CVID cohort. The pathway enrichment analysis indicated the involvement of the FOXO-mediated signaling pathway, TGFβ receptor complex, and VEGFR2-mediated vascular permeability. Considering the dysregulation of hsa-miR-142-3p and hsa-miR-155-5p in CVID and the known role of their target genes in the immune system, their involvement in the pathogenesis of CVID can be suggested.

PMID:39786889 | DOI:10.15586/aei.v53i1.1234

Bioinformatics. 2025 Jan 9:btae762. doi: 10.1093/bioinformatics/btae762. Online ahead of print.

ABSTRACT

MOTIVATION: Transcription factors (TFs) are DNA-binding proteins that regulate gene expression. Traditional methods predict a protein as a TF if the protein contains any DNA-binding domains (DBDs) of known TFs. However, this approach fails to identify a novel TF that does not contain any known DBDs. Recently proposed TF prediction methods do not rely on DBDs. Such methods use features of protein sequences to train a machine learning model, and then use the trained model to predict whether a protein is a TF or not. Because the 3-dimensional (3D) structure of a protein captures more information than its sequence, using 3D protein structures will likely allow for more accurate prediction of novel TFs.

RESULTS: We propose a deep learning-based TF prediction method (StrucTFactor), which is the first method to utilize 3D secondary structural information of proteins. We compare StrucTFactor with recent state-of-the-art TF prediction methods based on ∼525 000 proteins across 12 datasets, capturing different aspects of data bias (including sequence redundancy) possibly influencing a method's performance. We find that StrucTFactor significantly (p-value<0.001) outperforms the existing TF prediction methods, improving the performance over its closest competitor by up to 17% based on Matthews correlation coefficient.

AVAILABILITY: Data and source code are available at https://github.com/lieboldj/StrucTFactor and on our website at https://apps.cosy.bio/StrucTFactor/.

SUPPLEMENTARY INFORMATION: Included.

PMID:39786868 | DOI:10.1093/bioinformatics/btae762

Elife. 2025 Jan 9;12:RP88833. doi: 10.7554/eLife.88833.

ABSTRACT

Transcription factor partners can cooperatively bind to DNA composite elements to augment gene transcription. Here, we report a novel protein-DNA binding screening pipeline, termed Spacing Preference Identification of Composite Elements (SPICE), that can systematically predict protein binding partners and DNA motif spacing preferences. Using SPICE, we successfully identified known composite elements, such as AP1-IRF composite elements (AICEs) and STAT5 tetramers, and also uncovered several novel binding partners, including JUN-IKZF1 composite elements. One such novel interaction was identified at CNS9, an upstream conserved noncoding region in the human IL10 gene, which harbors a non-canonical IKZF1 binding site. We confirmed the cooperative binding of JUN and IKZF1 and showed that the activity of an IL10-luciferase reporter construct in primary B and T cells depended on both this site and the AP1 binding site within this composite element. Overall, our findings reveal an unappreciated global association of IKZF1 and AP1 and establish SPICE as a valuable new pipeline for predicting novel transcription binding complexes.

PMID:39786853 | DOI:10.7554/eLife.88833