Citations

SUMMARY Artificial intelligence (AI)-based methods are increasingly critical in peptide drug discovery, but their applications are limited in a narrow scope such as antimicrobial peptides. For indications where peptide therapy inherently excels, such as metabolism, endocrinology, and tissue regeneration, AI-based pipeline for therapeutic peptide discovery is long awaited but still unmet. Here, we propose a deep learning-based pipeline, Deepeptide, capable of identifying therapeutic oligopeptides for various metabolism-related indications. Leveraging the intrinsical relationship of ‘disease indication — biological processes — molecular functions’, Deepeptide discovers oligopeptides with indication-ameliorating-related molecular functions as lead candidates for indication of interest. Deepeptide was applied in five representative indications of metabolism, endocrinology, and tissue regeneration: angiogenesis, lipid metabolism, osteogenesis, glucose metabolism, and anti-angiogenesis. Overall, 62% of the identified oligopeptide candidates demonstrated significant bioactivity in vitro, with most of them showing comparable potency to the first-line drugs. Notably, the heptapeptide AP7 exhibited angiogenic potency comparable to VEGF in excisional wound splinting mouse model by promoting cell migration rather than proliferation, and hexapeptide TP6 showed significant dual-efficacy against hyperlipidemia and obesity in high-fat diet mice by inhibiting lipid synthesis and regulating gut microbiota. These findings highlight the potential and generalizability of Deepeptide in therapeutic oligopeptide discovery for metabolic diseases.

Parkinson’s Disease (PD) is a neurodegenerative disorder in which gait abnormalities serve as key indicators of motor impairment and disease progression. Although wearable sensor-based gait analysis has advanced, existing methods still face challenges in modeling multi-sensor spatial relationships, extracting adaptive multi-scale temporal features, and effectively integrating time–frequency information. To address these issues, this paper proposes a multi-sensor gait neural network that integrates biomechanical priors with time–frequency collaborative learning for the automatic assessment of PD gait severity. The framework consists of three core modules: (1) BGS-GAT (Biomechanics-Guided Graph Attention Network), which constructs a sensor graph based on plantar anatomy and explicitly models inter-regional force dependencies via graph attention; (2) AMS-Inception1D (Adaptive Multi-Scale Inception-1D), which employs dilated convolutions and channel attention to extract multi-scale temporal features adaptively; and (3) TF-Branch (Time–Frequency Branch), which applies Real-valued Fast Fourier Transform (RFFT) and frequency-domain convolution to capture rhythmic and high-frequency components, enabling complementary time–frequency representation. Experiments on the PhysioNet multi-channel foot pressure dataset demonstrate that the proposed model achieves 0.930 in accuracy and 0.925 in F1-score for four-class severity classification, outperforming state-of-the-art deep learning models.

Abstract Background and Aims Celiac disease (CeD) is a chronic digestive autoimmune disorder affecting approximately 1% of the worldwide population. It is driven by T cells activated by specific HLA-DQ2 or HLA-DQ8 molecules leading to the destruction of intestinal villi. We aimed to characterize shared CeD-specific T cells in patients on and off a gluten-free diet (GFD) from a large cohort of cases and controls. Methods We performed bulk TCRβ immune sequencing of the peripheral blood of 1,604 biopsy-confirmed CeD patients (1,339 on GFD, 265 on normal diet) and 1,100 controls. We identified over 300 TCRβs enriched in CeD cases versus controls in an HLA-aware manner, controlling for CeD risk alleles. Results CeD-associated TCRβs were found to be more predictive of disease than previously characterized gliadin and glutenin-binding TCRs in a validation cohort. Furthermore, the clonal breadth of these TCRβs was associated with increased intestinal damage. Immune sequencing of the peripheral blood also uncovered repertoire-level differences between CeD patients and controls. CeD patients displayed significantly higher productive clonality compared to age-matched controls as well as expansion of TCRβs specific to cytomegalovirus (CMV) and Epstein-Barr Virus (EBV). Conclusions These findings underscore the value of unbiased immune repertoire sequencing to identify novel biomarkers for autoimmune disease and to discover new disease mechanisms which can improve both diagnosis and treatment of disease.

Ultrahigh-field 7-T MRI offers superior resolution and contrast, which enable improved detection of subtle neuroanatomic abnormalities and disease-specific imaging biomarkers, with established clinical applications across a broad range of neurologic disorders.

Autoantibodies contribute to many autoimmune diseases, yet there is no approved therapy to neutralize them selectively. A popular mouse model, experimental autoimmune encephalomyelitis (EAE), could serve to develop such a therapy, provided we can better understand the nature and importance of the autoantibodies involved. Here, we report the finding of autoantibody-secreting extrafollicular plasmablasts in EAE induced with specific myelin oligodendrocyte glycoprotein (MOG) antigens. Single-cell RNA sequencing reveals that these cells produce nonaffinity-matured IgG antibodies. These include pathogenic antibodies competing for shared binding space on MOG’s extracellular domain. Interestingly, the synthetic anti-MOG antibody 8-18C5 can prevent the binding of pathogenic antibodies from either EAE mice or people with MOG antibody disease. Moreover, an 8-18C5 variant carrying the NNAS mutation, which inactivates its effector functions, can reduce EAE severity and promote functional recovery. In brief, this study provides not only a comprehensive characterization of the humoral response in EAE models but also a proof of concept for a therapy to antagonize pathogenic anti-MOG antibodies.

Background Cardiovascular disease (CVD) is a leading cause of death in cancer survivors. Predicting CVD risk in this population remains challenging. Risk prediction models that use machine learning algorithms could provide an objective method for accurate risk prediction to facilitate the prevention and management of CVD in cancer survivors. We evaluated previously tested machine learning algorithms and logistic regression (regularized by machine learning methods), in addition to testing and validating newer, more complex machine learning algorithms, for CVD prediction in cancer survivors. Methods This multicenter study used a database of 3835 multiracial cancer survivors with 89 clinical, laboratory, and echocardiographic features over 20 years. Models were trained using repeated random and time‐split samples and tested on a separate cohort of 329 patients. Model performance was assessed using the area under the receiver operating characteristic curve. Results Regularized logistic regression achieved an area under the receiver operating characteristic curve of 0.845 (heart failure), 0.783 (atrial fibrillation), 0.792 (coronary artery disease), and 0.806 (composite CVD). These are comparable to 0.837 and 0.848 for heart failure, using Bayesian additive regression tree and random forest as more advanced machine learning models, respectively. De novo composite CVD (post‐cancer diagnosis) was also predicted with an area under the receiver operating characteristic curve of 0.826 using regularized logistic regression, compared with 0.735 and 0.802 using decision tree and random forest, respectively. Conclusions Regularized logistic regression and advanced machine learning models demonstrated similar predictive performance, with institutional transferability. These tools may support risk stratification and prevention strategies in cardio‐oncology using longitudinal data. Registration URL: https://www.clinicaltrials.gov ; Unique identifier: NCT05377320.

Abstract Background The purpose of this study was to develop a series of benchmarks specifically for large language model (LLM) performance in the identification of drug-drug interactions (DDIs). Methods We evaluated six LLMs using a clinician-designed dataset of 750 DDI scenarios. Tasks included: (1) a pointwise two-drug classification task (2) a pairwise three-drug discrimination task and (3) a listwise 4–6 drug selection task. Zero-shot prompting was applied and performance was assessed using precision, recall, F1 score, accuracy, and self-consistency. Results Model performance varied by task structure and interaction severity. GPT-5-Chat demonstrated the highest recall and F1 score in the pointwise task (80.7% and 80.2%), whereas DrugGPT achieved superior accuracy in the pairwise (93.7%) and listwise task (92.6%). All models had improved performance with more severe compared to less severe DDIs (accuracy 72.0-99.2% vs. 58.3-86.7%). All models tended to have higher self-consistency in the pairwise and listwise experiments compared to the pointwise experiment (68.8-93.6% vs. 31.0-74.2%). No model exhibited uniformly high reliability across all tasks. Conclusions Current LLMs show inconsistent capabilities in identifying DDIs. Performance degrades as reasoning space expands with limited stability. These findings emphasize the need for multi-format evaluation frameworks and reliability-aware assessment when considering LLMs for medication-safety applications.

Abstract Introduction: Adult T-cell leukemia/lymphoma (ATLL) is a rare blood disorder associated with human T-cell leukemia virus type 1 (HTLV-1) infection. It is generally categorized into four subtypes: smoldering, chronic, lymphoma, and acute. Given the heterogeneity of these subtypes, there is a significant difference in outcomes. Robust and contemporary epidemiological data are lacking for this rare disorder. We present a retrospective cohort study of patients with ATLL, utilizing the National Cancer Database (NCDB) to better characterize the epidemiology and survival trends in the United States. Methods: This is a retrospective cohort study using the NCDB to identify ATLL cases diagnosed from 2004-2020. Descriptive statistics summarized baseline characteristics, while chi-square tests assessed group differences. Overall survival (OS) was estimated using Kaplan-Meier analysis and compared using log-rank tests. Multivariable Cox proportional hazards models identified independent prognostic factors (p < 0.05 considered significant). Results: A total of 635 patients were identified with ATLL, including 344 (54%) males and 291 (46%) females, with a median age at diagnosis of 59 years (range: 19-90). Most patients came from the Middle Atlantic (NY, NJ, PA) region (33%), followed by the South Atlantic (DC, DE, FL, GA, MD, NC, SC, VA, WV) region (20%) and the East North Central (IL, IN, MI, OH, WI) region (8%). Of the 635 patients, 335 (52%) were Black, 247 (39%) White, and 26 (4%) Asian. Sixty-five (10%) patients were of Hispanic origin. Over half of patients with ATLL (54%) had a median income below $46,000. International Prognostic Index (IPI) score was only available for 16 patients: three (19%) patients were in the high-risk group, 7 (43%) in the high-intermediate group, and 6 (37.5%) in the low-intermediate group. Treatment groups included 357 (56%) patients treated with chemotherapy and 29 (4.5%) who received radiation therapy. Thirty-three (5%) patients underwent hematopoietic stem cell transplant (HSCT), including 27 autologous and 16 allogeneic transplants. The median survival time in the cohort was 9 months (95% CI 7.3-10.7). One-year OS rate in the cohort was 43%, while 2-year and 5-year OS rates were 31% and 23.5%, respectively. Patients over the age of 65 had a significantly shorter median OS than those under 65 (4 vs. 11 months, p=0.001) and were significantly less likely to undergo HSCT (p< 0.001). Black patients had significantly shorter median OS compared to White patients (7.8 months vs 13.3 months, p=0.014), despite similar treatment rates with chemotherapy and HSCT. Median OS appeared to improve over time, from 8 months in patients diagnosed between 2004-2009 to 10 months for those diagnosed between 2016-2020, although this was not statistically significant (p=0.145). Treatment with allogeneic HSCT was associated with significantly prolonged median survival, compared to those who did not receive transplant (50 months vs. 7 months, p<0.05). Additionally, receiving chemotherapy and/or radiation compared to not receiving treatment was also associated with significantly prolonged median survival (p<0.05). Patients treated in the Middle Atlantic region had a median survival of 8.8 months, compared to 23.2 months in the West South Central (AR, LA, OK, TX) region (p< 0.001). Increased education and income levels were not significantly associated with improved survival. There were no significant differences in survival between males and females. Conclusions: We provide contemporary estimates on the epidemiology of ATLL. Factors associated with improved prognosis included undergoing HSCT, radiation, or chemotherapy. We report that increased age and Black race are negative prognostic factors. Regional differences in incidence and survival persist in the US. Our study findings underscore the need for increasing access to treatment, including HSCT for those who are good candidates. Additionally, there remains work to be done to address racial disparities in the care of patients with ATLL.