Explore the vast range of titles available.

Accurate lung tumor segmentation using computed tomography (CT) scans is needed for efficient tumor treatment. However, the development of deep learning models is often constrained by strict patient privacy regulations that limit direct data sharing. This work presents a system that enables multi-institutional collaboration while training high-quality lung tumor segmentation models without requiring access to sensitive patient data. The proposed framework features the AuraViT suite, which includes the standard AuraViT—a hybrid model with 136 million parameters that combines a Vision Transformer (ViT) encoder, Atrous Spatial Pyramid Pooling (ASPP), and attention-gated residual connections—and the Lightweight AuraViT (LAURA) family (Small, Tiny, and Mobile). These variants are designed for resource-constrained environments and potential edge deployment scenarios. Training is conducted on publicly available datasets (MSD Lung and NSCLC) in a simulated five-client federated learning setup that emulates collaboration among institutions while ensuring patient privacy. The framework uses a federated learning setup with FedProx, adaptive weighted aggregation, and a dynamic virtual client strategy to handle data and system differences. The framework is further evaluated through ablation studies on model architecture and feature importance. The results show that the standard AuraViT-FL achieves a global mean Dice score of 80.81%, while maintaining performance close to centralized training. Additionally, the LAURA variations show a better trade-off between accuracy and efficiency. Notably, the Mobile variant with ∼5 M parameters reduces model complexity by over 96% while maintaining competitive performance (82.96% Dice on MSD Lung).

In drug development, managing interactions such as drug–drug, drug–disease, and drug–nutrient is critical for ensuring the safety and efficacy of pharmacological treatments. These interactions often overlap, forming a complex, interconnected landscape that necessitates accurate prediction to improve patient outcomes and support evidence-based care. Recent advances in artificial intelligence (AI), powered by large-scale datasets (e.g., DrugBank, TWOSIDES, SIDER), have significantly enhanced interaction prediction. Machine learning, deep learning, and graph-based models show great promise, but challenges persist, including data imbalance, noisy sources, Limited explainability, and underrepresentation of certain types of interactions. This systematic review of 147 studies (2018–2024) is the first to comprehensively map AI applications across major interaction types. We present a detailed taxonomy of models and datasets, emphasizing the growing roles of large language models and knowledge graphs in overcoming key limitations. Their integration—alongside explainable AI tools—enhances transparency, paving the way for AI-driven systems that proactively mitigate adverse interactions. By identifying the most promising approaches and critical research gaps, this review lays the groundwork for advancing more robust, interpretable, and personalized models for drug interaction prediction.

Despite being the initial choice for treating toxoplasmosis, sulfadiazine and pyrimethamine have limited effectiveness in eliminating the infection and were linked to a variety of adverse effects. Therefore, the search for new effective therapeutic strategies against toxoplasmosis is still required. The current work is the first research to assess the efficacy of spiramycin-loaded maltodextrin nanoparticles (SPM-loaded MNPs) as a novel alternative drug therapy against toxoplasmosis in a murine model. Fifty laboratory-bred Swiss albino mice were divided into five groups: normal control group (GI, n  = 10), positive control group (GII, n  = 10), orally treated with spiramycin (SPM) alone (GIII, n  = 10), intranasal treated with SPM-loaded MNPs (GIV, n  = 10), and orally treated with SPM-loaded MNPs (GV, n  = 10). Cysts of  Toxoplasma gondii  ME-49 strain were used to infect the mice. Tested drugs were administered 2 months after the infection. Drug efficacy was assessed by counting brain cysts, histopathological examination, and measures of serum CD19 by flow cytometer. The orally treated group with SPM-loaded MNPs (GV) showed a marked reduction of brain cyst count (88.7%), histopathological improvement changes, and an increasing mean level of CD19 (80.2%) with significant differences. SPM-loaded MNPs showed potent therapeutic effects against chronic toxoplasmosis. Further research should be conducted to assess it in the treatment of human toxoplasmosis, especially during pregnancy. Graphical Abstract

The potential and utility of inner speech is pivotal for developing practical, everyday Brain-Computer Interface (BCI) applications, as it represents a type of brain signal that operates independently of external stimuli however it is largely underdeveloped due to the challenges faced in deciphering its signals. In this study, we evaluated the behaviors of various Machine Learning (ML) and Deep Learning (DL) models on a publicly available dataset, employing popular preprocessing methods as feature extractors to enhance model training. We face significant challenges like subject-dependent variability, high noise levels, and overfitting. To address overfitting in particular, we propose using “BruteExtraTree”: a new classifier which relies on moderate stochasticity inherited from its base model, the ExtraTreeClassifier. This model not only matches the best DL model, ShallowFBCSPNet, in the subject-independent scenario in our experiments scoring 32% accuracy, but also surpasses the state-of-the-art by achieving 46.6% average per-subject accuracy in the subject-dependent case. Our results on the subject-dependent case show promise on the possibility of a new paradigm for using inner speech data inspired from LLM pretraining but we also highlight the crucial need for a drastic change in data recording or noise removal methods to open the way for more practical accuracies in the subject-independent case.

Purpose Resistance and adverse consequences of albendazole (ABZ) in treating trichinellosis urged demand for secure and effective new drugs. The current study aimed to assess the effect of chitosan-coated lipid nano-combination with albendazole and miltefosine (MFS) in treating experimental murine trichinellosis and evaluating pathological and immunological changes of trichinellosis. Materials and Methods One hundred twenty Swiss albino mice were divided into six groups. Each group was subdivided into a and b subgroups based on the scarification time, which was 7- and 40-days post-infection (PI), respectively. The treatment efficacy was evaluated using parasitological, histopathological, serological (interleukin (IL)-12 and IL-4 serum levels), immunohistochemical (GATA3, glutathione peroxidase1 (GPX1) and caspase-3), and scanning electron microscopy (SEM) methods. Results The most effective drug was nanostructured lipid carriers (NLCs) loaded with ABZ (G5), which showed the most significant reduction in adults and larval count (100% and 92.39%, respectively). The greatest amelioration in histopathological changes was reported in G4 treated with MFS. GATA3 and caspase-3 were significantly reduced in all treated groups. GPX1 was significantly increased in G6 treated with MFS + NLCs. The highest degenerative effects on adults and larvae by SEM were documented in G6. Conclusion Loading ABZ or MFS on chitosan-coated NLCs enhanced their efficacy against trichinellosis. Although ABZ was better than MFS, their combination should be considered as MFS caused a significant reduction in the intensity of infection. Furthermore, MFS showed anti-inflammatory (↓GATA3) and antiapoptotic effects (↓caspase-3), especially in the muscular phase. Also, when loaded with NLCS, it showed an antioxidant effect (↑GPX1). Graphical abstract

The increasing interest in automated code conversion and transcompilation—driven by the need to support multiple platforms efficiently—has raised new challenges in verifying that translated codes preserve the intended behaviors of the originals. Although it has not yet been widely adopted, transcompilation offers promising applications in software reuse and cross-platform migration. With the growing use of Large Language Models (LLMs) in code translation, where internal reasoning remains inaccessible, verifying the equivalence of their generated outputs has become increasingly essential. However, existing evaluation metrics—such as BLEU and CodeBLEU, which are commonly used as baselines in transcompiler evaluation—primarily measure syntactic similarity, even though this does not guarantee semantic correctness. This syntactic bias often leads to misleading evaluations where structurally different but semantically equivalent code is penalized. This syntactic bias often leads to misleading evaluations, where structurally different but semantically equivalent code is penalized. To address this limitation, we propose a formal verification framework based on equivalence checking using First-Order Logic (FOL). The approach models core programming constructs—such as loops, conditionals, and function calls—that function as logical axioms, enabling equivalence to be assessed at the behavioral level rather than simply by their textual similarity. We initially used the Z3 solver to manually encode Swift and Java code into FOL. To improve scalability and automation, we later integrated ANTLR to parse and translate both the source and transcompiled codes into logical representations. Although the framework is language-agnostic, we demonstrate its effectiveness through a case study of Swift-to-Java transcompilation. The experimental results demonstrated that our method effectively identifies semantic equivalence, even when syntax differs significantly. Our method achieves an average semantic accuracy of 86.1%, compared to BLEU’s syntactic accuracy of 64.45%. This framework bridges the gap between code translation and formal semantic verification. These results highlight the potential for formal equivalence checking to serve as a more reliable validation method in code translation tasks, enabling more trustworthy cross-language code conversion.

Code conversion, encompassing translation, optimization, and generation, is becoming increasingly critical in information systems and the software industry. Traditional validation methods, such as test cases and code coverage metrics, often fail to ensure the correctness, completeness, and equivalence of converted code to its original form. Formal verification emerges as a crucial methodology to address these limitations. Although numerous surveys have explored formal verification in various contexts, a significant research gap exists in pinpointing appropriate formal verification approaches to code conversion tasks. This paper provides a detailed survey of formal verification techniques applicable to code conversion. This survey identifies the strengths and limitations of contemporary adopted approaches while outlining a trajectory for future research, emphasizing the need for automated and scalable verification tools. The novel categorization of formal verification methods provided in this paper serves as a foundational guide for researchers seeking to enhance the reliability of code conversion processes.

Code-to-code translation, a critical domain in software engineering, increasingly utilizes trans-compilers to translate between high-level languages. Traditionally, the fidelity of such translations has been evaluated using the BLEU score, which predominantly measures token similarity between the generated output and the ground truth. However, this metric falls short of assessing the methodologies underlying the translation processes and only evaluates the translations that are tested. To bridge this gap, this paper introduces an innovative architecture, “TC-Verifier”, to formally employ the Uppaal Model-checker to verify trans-compiler-based code translators. We applied the proposed architecture to a trans-compiler translating between Swift and Java, providing insights into the verified and unverified aspects of the translation process. Our findings illuminate the strengths and limitations of using Model-checking for formal verification in code translation. Notably, the examined trans-compiler reached a verification success rate of 50.74% for the grammar rules and productions modeled. This study underscores the gaps in trans-compiler-based translations and suggests that these gaps could potentially be addressed by integrating Large Language Models (LLMs) in future work.

Schistosomiasis is caused by several worm species of the genus Schistosoma and afflicts up to 600 million people in 74 tropical and sub-tropical countries in the developing world. Present disease control depends on treatment with the only available drug praziquantel. No vaccine exists despite the intense search for molecular candidates and adjuvant formulations over the last three decades. Cysteine peptidases such as papain and Der p 1 are well known environmental allergens that sensitize the immune system driving potent Th2-responses. Recently, we showed that the administration of active papain to mice induced significant protection (P<0.02, 50%) against an experimental challenge infection with Schistosoma mansoni. Since schistosomes express and secrete papain-like cysteine peptidases we reasoned that these could be employed as vaccines with inbuilt adjuvanticity to protect against these parasites. Here we demonstrate that sub-cutaneous injection of functionally active S. mansoni cathepsin B1 (SmCB1), or a cathepsin L from a related parasite Fasciola hepatica (FhCL1), elicits highly significant (P<0.0001) protection (up to 73%) against an experimental challenge worm infection. Protection and reduction in worm egg burden were further increased (up to 83%) when the cysteine peptidases were combined with other S. mansoni vaccine candidates, glyceraldehyde 3-phosphate dehydrogenase (SG3PDH) and peroxiredoxin (PRX-MAP), without the need to add chemical adjuvants. These studies demonstrate the capacity of helminth cysteine peptidases to behave simultaneously as immunogens and adjuvants, and offer an innovative approach towards developing schistosomiasis vaccines.