António Farinhas, Nuno M. Guerreiro, José Pombal
et al.
Large language models are increasingly used for mental health support, yet their conversational coherence alone does not ensure clinical appropriateness. Existing general-purpose safeguards often fail to distinguish between therapeutic disclosures and genuine clinical crises, leading to safety failures. To address this gap, we introduce a clinically grounded risk taxonomy, developed in collaboration with PhD-level psychologists, that identifies actionable harm (e.g., self-harm and harm to others) while preserving space for safe, non-crisis therapeutic content. We release MindGuard-testset, a dataset of real-world multi-turn conversations annotated at the turn level by clinical experts. Using synthetic dialogues generated via a controlled two-agent setup, we train MindGuard, a family of lightweight safety classifiers (with 4B and 8B parameters). Our classifiers reduce false positives at high-recall operating points and, when paired with clinician language models, help achieve lower attack success and harmful engagement rates in adversarial multi-turn interactions compared to general-purpose safeguards. We release all models and human evaluation data.
Magnetic Resonance Imaging (MRI) is a well-established modality for pre-operative planning and is also explored for intra-operative guidance of procedures such as intravascular interventions. Among the experimental robot-assisted technologies, the magnetic field gradients of the MRI scanner are used to power and maneuver ferromagnetic applicators for accessing sites in the patient's body via the vascular network. In this work, we propose a computational platform for preoperative planning and modeling of MRI-powered applicators inside blood vessels. This platform was implemented as a two-way data and command pipeline that links the MRI scanner, the computational core, and the operator. The platform first processes multi-slice MR data to extract the vascular bed and then fits a virtual corridor inside the vessel. This corridor serves as a virtual fixture (VF), a forbidden region for the applicators to avoid vessel perforation or collision. The geometric features of the vessel centerline, the VF, and MRI safety compliance (dB/dt, max available gradient) are then used to generate magnetic field gradient waveforms. Different blood flow profiles can be user-selected, and those parameters are used for modeling the applicator's maneuvering. The modeling module further generates cues about whether the selected vascular path can be safely maneuvered. Given future experimental studies that require a real-time operation, the platform was implemented on the Qt framework (C/C++) with software modules performing specific tasks running on dedicated threads: PID controller, generation of VF, generation of MR gradient waveforms.
Historical prescriptions and selected candidate drugs relevant to the current visit serve as important references for medication recommendation. However, in the absence of explicit intrinsic principles for semantic composition, existing methods treat synergistic drugs as independent entities and fail to capture their collective therapeutic effects, resulting in a mismatch between medication-level references and longitudinal patient representations. In this paper, we propose MSAM, a novel medication recommendation model that bridges the gap via multi-level medication abstraction. The model introduces a multi-head graph reasoning mechanism to organize flat daily medication sets into clinically meaningful semantic units, serving as intermediate abstraction results to propagate features from individual drugs to higher-level representations. Building on these units, MSAM performs two-stage abstraction over historical prescriptions and selected candidates via intra- and inter-level feature propagation across heterogeneous clinical structures, capturing collective therapeutic effects aligned with patient conditions. Experiments on two real-world clinical datasets show that MSAM consistently outperforms state-of-the-art methods, validating the effectiveness of structural medication abstraction for recommendation.
Cervical spondylotic myelopathy (CSM) and parkinsonian syndromes (PS) present similar motor symptoms, often causing misdiagnosis due to current clinical diagnostic limitations. Misdiagnosis can exacerbate patient conditions or result in unnecessary surgical interventions, thereby increasing surgical risks and the likelihood of serious postoperative complications. This study aims to develop a mixed dual-branch network for classifying CSM patients, PS patients, and healthy individuals using gait data. This study recruits 51 CSM patients, 49 PS patients, and 33 healthy controls. The kinematic data are collected and used to calculate the time series of angle, angular velocity, and angular acceleration for the hip, knee, and ankle joints. From each time series, 20 features are extracted, including the time domain, frequency domain, time-frequency domain, and nonlinear features. A dual-branch model named DCDM-Net is proposed to classify subjects through collaborative decision making (CDM) method, with one branch using ResNet with convolutional block attention module (CBAM) and evidential deep learning (EDL) loss for analyzing time series, and the other employing multilayer perceptron (MLP) for dealing with multi-domain features. DCDM-Net achieves an ACC of 92.35% <inline-formula> <tex-math notation="LaTeX">$\pm ~0.76$ </tex-math></inline-formula>% and an AUC of 96.70% <inline-formula> <tex-math notation="LaTeX">$\pm ~0.47$ </tex-math></inline-formula>% in the three-class classification task. Additionally, in binary classification scenarios, the model demonstrates robust performance with an average ACC of 93.13% and AUC of 98.34%. Furthermore, comparative evaluations show that the integrated EDL module surpasses Softmax, MC-Dropout, and Deep Ensembles in uncertainty estimation, yielding the lowest Expected Calibration Error (ECE of 0.0304) and lower Brier score (0.1074), indicating superior reliability. However, cross-dataset OOD validation yielded an AUROC of <inline-formula> <tex-math notation="LaTeX">$0.4022~\pm ~0.2481$ </tex-math></inline-formula> and an AUPR of <inline-formula> <tex-math notation="LaTeX">$0.9699~\pm ~0.0162$ </tex-math></inline-formula>, revealing that restricting features to joint angles leads to significant distribution overlap; this conversely validates that angular velocity and acceleration are indispensable for preventing model overconfidence. Interpretable results obtained through the SHapley Additive exPlanations (SHAP) method and the integrated gradients (IG) method are confirmed by clinical findings. Our method provides a promising tool for diagnosing CSM and PS, with the potential to reduce misdiagnosis. The code implementation of this study is available at <uri>https://github.com/AImedcinesdu212/DCDM-Net</uri>
BackgroundTraditional Chinese medicine (TCM) formulations are increasingly used in combination with mesalazine to treat mild-to-moderate active ulcerative colitis (UC). However, direct comparisons between various TCM regimens are limited.MethodsWe performed a frequentist network meta-analysis of 34 randomized controlled trials (n = 2,854) comparing oral mesalazine (1.0–4.0 g/day) alone versus mesalazine plus one of eight TCM formulations: Kangfuxin solution, Shaoyao decoction, Glycyrrhizae decoction, Scutellaria decoction (Huangqin granules), Baitouweng decoction (Pulsatilla; retention enema), Shenling Baizhu Powder, CurQD formula, or Fufangkushen capsules. Outcomes included clinical efficacy, adverse events, Mayo score, serum interleukin-6 (IL-6) and tumor necrosis factor-α (TNF-α), and intestinal Bifidobacteria, Lactobacilli, and Escherichia coli. Risk ratios (RRs) were calculated for dichotomous outcomes and mean differences (MDs) for continuous outcomes. Treatments were ranked using surface under the cumulative ranking curve (SUCRA).ResultsMost TCM–mesalazine combinations improved clinical efficacy versus mesalazine alone. CurQD and Kangfuxin had the highest probabilities of being most effective for symptom improvement (SUCRA 96.7% and 72.7%, respectively); the direct CurQD–mesalazine comparison showed RR = 2.67 (95% CI 1.16–6.14). Adverse-event rates were similar across regimens, with lower incidence of adverse events. Mayo score reductions were greatest with Glycyrrhizae decoction (MD = −1.40), Baitouweng decoction via retention enema (MD = −1.09), and Kangfuxin solution (MD = −1.07). Scutellaria granules produced the largest IL-6 decrease (MD = −53.28 pg/mL) and ranked highest for TNF-α reduction, followed by Kangfuxin. For gut microbiota, Shaoyao decoction ranked highest for increasing Bifidobacteria, Glycyrrhizae decoction for increasing Lactobacilli, and Glycyrrhizae also reduced E. coli (MD = −1.93).ConclusionCombining mesalazine with selected TCM formulations can enhance clinical response, reduce inflammatory cytokines, and beneficially modulate gut microbiota without increasing adverse events. CurQD or Kangfuxin may be prioritized for symptomatic improvement, Glycyrrhizae or Baitouweng for Mayo score reduction, Scutellaria for cytokine control, and Shaoyao or Glycyrrhizae for microbiota modulation. High-quality multicenter RCTs are warranted to confirm these comparative rankings.
Matthew W. Cotton, Alain Goriely, David Klenerman
et al.
Neurodegenerative diseases are driven by the accumulation of protein aggregates in the brain of affected individuals. The aggregation behaviour in vitro is well understood and driven by the equilibration of a super-saturated protein solution to its aggregated equilibrium state. However, the situation is altered fundamentally in living systems where active processes consume energy to remove aggregates. It remains unclear how and why cells transition from a state with predominantly monomeric protein, which is stable over decades, to one dominated by aggregates. Here, we develop a simple but universal theoretical framework to describe cellular systems that include both aggregate formation and removal. Using a two-dimensional phase-plane representation, we show that the interplay of aggregate formation and removal generates cell-level bistability, with a bifurcation structure that explains both the emergence of disease and the effects of therapeutic interventions. We explore a wide range of aggregate formation and removal mechanisms and show that phenomena such as seeding arise robustly when a minimal set of requirements on the mechanism are satisfied. By connecting in vitro aggregation mechanisms to changes in cell state, our framework provides a general conceptual link between molecular-level therapeutic interventions and their impact on disease progression.
Moringa oleifera, known for its medicinal properties, contains bioactive compounds such as polyphenols and flavonoids with diverse therapeutic potentials, including anti-cancer effects. This study investigates the efficacy of M. oleifera leaf phytochemicals in inhibiting BCL-2, a critical protein involved in cancer cell survival. For the first time, multi-ligand simultaneous docking (MLSD) has been employed to understand the anti-cancer properties of M. oleifera leaf extract. Molecular docking techniques, including single-ligand and MLSD, were used to assess binding interactions with BCL-2. Single-ligand docking revealed strong binding affinities for compounds such as niazinin, alpha carotene, hesperetin, apigenin, niaziminin B, and niazimicin A, with some compounds even surpassing Venetoclax, a commercial BCL-2 inhibitor. MLSD highlighted inter-ligand interactions among apigenin, hesperetin, and niazimicin A, exhibiting a binding affinity of -14.96 kcal/mol, indicating a synergistic effect. These results shed light on the potential synergistic effects of phytochemicals when using multi-ligand simultaneous docking, underscoring the importance of considering compound interactions in the development of therapeutic strategies.
In the last decade, researchers have increasingly explored using biosensing technologies for music-based affective regulation and stress management interventions in laboratory and real-world settings. These systems -- including interactive music applications, brain-computer interfaces, and biofeedback devices -- aim to provide engaging, personalized experiences that improve therapeutic outcomes. In this scoping and mapping review, we summarize and synthesize systematic reviews and empirical research on biosensing systems with potential applications in music-based affective regulation and stress management, identify gaps in the literature, and highlight promising areas for future research. We identified 28 studies involving 646 participants, with most systems utilizing prerecorded music, wearable cardiorespiratory sensors, or desktop interfaces. We categorize these systems based on their biosensing modalities, music types, computational models for affect or stress detection and music prediction, and biofeedback mechanisms. Our findings highlight the promising potential of these systems and suggest future directions, such as integrating multimodal biosensing, exploring therapeutic mechanisms of music, leveraging generative artificial intelligence for personalized music interventions, and addressing methodological, data privacy, and user control concerns.
Akshay Shendre, Naman Kumar Mehta, Anand Singh Rathore
et al.
Several formats, including FASTA, PIR, GenBank, EMBL, and GCG, have been developed for representing protein sequences composed of natural amino acids. Among these, FASTA remains the most widely used due to its simplicity and human readability. However, FASTA lacks the capability to represent chemically modified or non-natural residues, as well as structural annotations and mutations in protein variants. To address some of these limitations, the PEFF format was recently introduced as an extension of FASTA. Additionally, formats such as HELM and BILN have been proposed to represent amino acids and their modifications at the atomic level. Despite their advancements, these formats have not achieved widespread adoption within the bioinformatics community due to their complexity. To complement existing formats and overcome current challenges, we propose a new format called MAP (Modification and Annotation in Proteins), which enables comprehensive annotation of protein sequences. MAP introduces meta tags in the header for protein-level annotations and inline tags within the sequence for residue-level modifications. In this format, standard one-letter amino acid codes are augmented with curly-brace tags to denote various modifications, including phosphorylation, acetylation, non-natural residues, cyclization, and other residue-specific features. The header metadata also captures information such as organism, function, and sequence variants. We describe the structure, objectives, and capabilities of the MAP format and demonstrate its application in bioinformatics, particularly in the domain of protein therapeutics. To facilitate community adoption, we are developing a comprehensive suite of MAP-format resources, including a detailed manual, annotated datasets, and conversion tools, available at http://webs.iiitd.edu.in/raghava/maprepo/.
Current AI counseling systems struggle with maintaining effective long-term client engagement. Through formative research with counselors and a systematic literature review, we identified five key design considerations for AI counseling interactions. Based on these insights, we propose CA+, a Cognition Augmented counselor framework enhancing contextual understanding through three components: (1) Therapy Strategies Module: Implements hierarchical Goals-Session-Action planning with bidirectional adaptation based on client feedback; (2) Communication Form Module: Orchestrates parallel guidance and empathy pathways for balanced therapeutic progress and emotional resonance; (3) Information Management: Utilizes client profile and therapeutic knowledge databases for dynamic, context-aware interventions. A three-day longitudinal study with 24 clients demonstrates CA+'s significant improvements in client engagement, perceived empathy, and overall satisfaction compared to a baseline system. Besides, two licensed counselors confirm its high professionalism. Our research demonstrates the potential for enhancing LLM engagement in psychological counseling dialogues through cognitive theory, which may inspire further innovations in computational interaction in the future.
Erik W. Baars, Petra Weiermayer, Henrik P. Szőke
et al.
<b>Background/Objectives</b>: Given the magnitude and urgency of the global antimicrobial resistance (AMR) problem and the insufficiency of strategies to reduce antimicrobial use, there is a need for novel strategies. Traditional, Complementary, and Integrative Healthcare (TCIH) provides strategies and solutions that contribute to reducing (inappropriate) antimicrobial use, preventing or treating infections in both human and veterinary medicine, and may contribute to promoting the health/resilience of humans and animals and reducing AMR. The aims of this study were to present the core results of a global TCIH research agenda for AMR and its added value to two existing global AMR research agendas published in 2023. <b>Methods</b>: A survey, interviews, and consensus meetings among network members, as an adapted version of the nominal group technique, were executed to develop the global TCIH research agenda. A comparison of the global TCIH research agenda with the two existing global AMR research agendas was performed. The TCIH additions to these two existing global AMR research agendas were determined. <b>Results</b>: The global TCIH research agenda adds to 19 of 40 research priorities of the World Health Organization (WHO) AMR research agenda 2023 and three of the five pillars of the WHO/Food and Agriculture Organization of the United Nations (FAO)/United Nations Environment Programme (UNEP)/World Organisation for Animal Health (WOAH) research agenda 2023. In addition, the TCIH research agenda adds two new research themes with four new research priorities and three new research priorities to already existing themes of the two global AMR research agendas. <b>Conclusions</b>: The global TCIH research agenda fits with and adds to two global AMR research agendas and can be used as an additional strategy to reduce AMR and (inappropriate) use of antibiotics.
RNA design shows growing applications in synthetic biology and therapeutics, driven by the crucial role of RNA in various biological processes. A fundamental challenge is to find functional RNA sequences that satisfy given structural constraints, known as the inverse folding problem. Computational approaches have emerged to address this problem based on secondary structures. However, designing RNA sequences directly from 3D structures is still challenging, due to the scarcity of data, the non-unique structure-sequence mapping, and the flexibility of RNA conformation. In this study, we propose RiboDiffusion, a generative diffusion model for RNA inverse folding that can learn the conditional distribution of RNA sequences given 3D backbone structures. Our model consists of a graph neural network-based structure module and a Transformer-based sequence module, which iteratively transforms random sequences into desired sequences. By tuning the sampling weight, our model allows for a trade-off between sequence recovery and diversity to explore more candidates. We split test sets based on RNA clustering with different cut-offs for sequence or structure similarity. Our model outperforms baselines in sequence recovery, with an average relative improvement of $11\%$ for sequence similarity splits and $16\%$ for structure similarity splits. Moreover, RiboDiffusion performs consistently well across various RNA length categories and RNA types. We also apply in-silico folding to validate whether the generated sequences can fold into the given 3D RNA backbones. Our method could be a powerful tool for RNA design that explores the vast sequence space and finds novel solutions to 3D structural constraints.
Protein-protein interactions are central mediators in many biological processes. Accurately predicting the effects of mutations on interactions is crucial for guiding the modulation of these interactions, thereby playing a significant role in therapeutic development and drug discovery. Mutations generally affect interactions hierarchically across three levels: mutated residues exhibit different sidechain conformations, which lead to changes in the backbone conformation, eventually affecting the binding affinity between proteins. However, existing methods typically focus only on sidechain-level interaction modeling, resulting in suboptimal predictions. In this work, we propose a self-supervised multi-level pre-training framework, ProMIM, to fully capture all three levels of interactions with well-designed pretraining objectives. Experiments show ProMIM outperforms all the baselines on the standard benchmark, especially on mutations where significant changes in backbone conformations may occur. In addition, leading results from zero-shot evaluations for SARS-CoV-2 mutational effect prediction and antibody optimization underscore the potential of ProMIM as a powerful next-generation tool for developing novel therapeutic approaches and new drugs.
Xin Yi Yeo, Soohyun Kwon, Kimberley R. Rinai
et al.
The etiology of hearing impairment is multifactorial, with contributions from both genetic and environmental factors. Although genetic studies have yielded valuable insights into the development and function of the auditory system, the contribution of gene products and their interaction with alternate environmental factors for the maintenance and development of auditory function requires further elaboration. In this review, we provide an overview of the current knowledge on the role of redox dysregulation as the converging factor between genetic and environmental factor-dependent development of hearing loss, with a focus on understanding the interaction of oxidative stress with the physical components of the peripheral auditory system in auditory disfunction. The potential involvement of molecular factors linked to auditory function in driving redox imbalance is an important promoter of the development of hearing loss over time.
ObjectiveThis study compares the relationships between five anthropometric indices, a body shape index (ABSI), body roundness index (BRI), waist circumference (WC), body mass index (BMI) and waist-to-height ratio (WHtR), and hypertension, assessing their predictive capacities. The aim is to determine the specific numerical changes in hypertension incidence, systolic blood pressure (SBP) and diastolic blood pressure (DBP) for each increase in standard deviation of these indices, and to identify the optimal predictive indicators for different populations, including the calculation of cutoff values.MethodsThis study used data from the NHANES datasets spanning 2007 to 2018. Logistic regression analysis was used to quantify the associations between these anthropometric indices and hypertension, calculating β coefficients and odds ratios (ORs). Receiver operating characteristic (ROC) analysis was used to evaluate the predictive ability of each index for hypertension.ResultsFor each increase in standard deviation in WC, BMI, WHtR, ABSI and BRI, the prevalence of hypertension increased by 33% (95% CI: 27%–40%), 32% (95% CI: 26%–38%), 35% (95% CI: 28%–42%), 9% (95% CI: 4%–16%) and 32% (95% CI: 26%–38%), respectively. The SBP correspondingly increased by 2.36 mmHg (95% CI: 2.16–2.56), 2.41 mmHg (95% CI: 2.21–2.60), 2.48 mmHg (95% CI: 2.28–2.68), 0.42 mmHg (95% CI: 0.19–0.66) and 2.46 mmHg (95% CI: 2.26–2.66), respectively. Similarly, DBP increased by 1.83 mmHg (95% CI: 1.68–1.98), 1.72 mmHg (95% CI: 1.58–1.87), 1.72 mmHg (95% CI: 1.57–1.88), 0.44 mmHg (95% CI: 0.27–0.62) and 1.64 mmHg (95% CI: 1.48–1.79). In the youth and middle-aged groups, WC had the best predictive ability, with AUCs of 0.749 and 0.603, respectively. Among the elderly group, the AUCs for all five indices ranged between 0.5 and 0.52.ConclusionIncreases in WC, BMI, WHtR and BRI are significantly associated with higher incidences of hypertension and increases in SBP and DBP, while the impact of ABSI on blood pressure is relatively weak. Stratified analysis indicates significant age-related differences in the predictive value of these indices, with the strongest associations observed in the youth group, followed by the middle age group, and the weakest in the elderly. WC demonstrates excellent predictive ability across youth populations.
We conduct an extensive study on using near-term quantum computers for a task in the domain of computational biology. By constructing quantum models based on parameterised quantum circuits we perform sequence classification on a task relevant to the design of therapeutic proteins, and find competitive performance with classical baselines of similar scale. To study the effect of noise, we run some of the best-performing quantum models with favourable resource requirements on emulators of state-of-the-art noisy quantum processors. We then apply error mitigation methods to improve the signal. We further execute these quantum models on the Quantinuum H1-1 trapped-ion quantum processor and observe very close agreement with noiseless exact simulation. Finally, we perform feature attribution methods and find that the quantum models indeed identify sensible relationships, at least as well as the classical baselines. This work constitutes the first proof-of-concept application of near-term quantum computing to a task critical to the design of therapeutic proteins, opening the route toward larger-scale applications in this and related fields, in line with the hardware development roadmaps of near-term quantum technologies.
Investigators, funders, and the public desire knowledge on topics and trends in publicly funded research but current efforts in manual categorization are limited in scale and understanding. We developed a semi-automated approach to extract and name research topics, and applied this to \$1.9B of NCI funding over 21 years in the radiological sciences to determine micro- and macro-scale research topics and funding trends. Our method relies on sequential clustering of existing biomedical-based word embeddings, naming using subject matter experts, and visualization to discover trends at a macroscopic scale above individual topics. We present results using 15 and 60 cluster topics, where we found that 2D projection of grant embeddings reveals two dominant axes: physics-biology and therapeutic-diagnostic. For our dataset, we found that funding for therapeutics- and physics-based research have outpaced diagnostics- and biology-based research, respectively. We hope these results may (1) give insight to funders on the appropriateness of their funding allocation, (2) assist investigators in contextualizing their work and explore neighboring research domains, and (3) allow the public to review where their tax dollars are being allocated.
Marina Pereira Rocha, Lyandra Maciel Cabral da Silva, Laura Paulino Maia Silva
et al.
This study investigated the similarities between <i>Echinodorus macrophyllus</i> and <i>Echinodorus grandiflorus</i>, plant species that are traditionally used in Brazil to treat rheumatism and arthritis, whose anti-inflammatory effects are supported by scientific evidence. The contents of <i>cis</i>- and <i>trans</i>-aconitic acid, homoorientin, chicoric acid, swertisin, caffeoyl-feruloyl-tartaric acid, and di-feruloyl-tartaric acid were quantified by UPLC-DAD in various hydroethanolic extracts from the leaves, whereas their anti-oxidant activity and their effect on TNF release by LPS-stimulated THP-1 cells were assessed to evaluate potential anti-inflammatory effects. The 50% and 70% ethanol extracts showed higher concentrations of the analyzed markers in two commercial samples and a cultivated specimen of <i>E. macrophyllus</i>, as well as in a commercial lot of <i>E. grandiflorus</i>. However, distinguishing between the species based on marker concentrations was not feasible. The 50% and 70% ethanol extracts also exhibited higher biological activity, yet they did not allow differentiation between the species, indicating similar chemical composition and biological effects. Principal component analysis highlighted comparable chemical composition and biological activity among the commercial samples of <i>E. macrophyllus</i>, while successfully distinguishing the cultivated specimen from the commercial lots. In summary, no differences were observed between the two species in terms of the evaluated chemical markers and biological activities.