Social anxiety (SA) is a prevalent mental health challenge that significantly impacts daily social interactions. Imaginal Exposure (IE), a Cognitive Behavioral Therapy (CBT) technique involving imagined anxiety-provoking scenarios, is effective but underutilized, in part because traditional IE homework requires clients to construct and sustain clinically relevant fear narratives. In this work, we explore the feasibility of an LLM-enabled tool that supports IE by generating vivid, personalized exposure scripts. We first co-designed ImaginalExpoBot with mental health professionals, followed by a formative evaluation with five therapists and a user study involving 19 individuals experiencing SA symptoms. Our findings show that LLM-enabled support can facilitate preparation for anxiety-inducing situations while enabling immediate, user-specific adaptation, with scenarios remaining within a therapeutically beneficial "window of tolerance". Our participants and MHPs also identified limitations in continuity and customization, pointing to the need for deeper adaptivity in future designs. These findings offer preliminary design insights for integrating LLMs into structured therapeutic practices in accessible, scalable ways.
Abstract The dose-response effect refers to the relationship between the dose (e.g., length, frequency) of treatment and the subsequent probability of improvement. This systematic review aimed to synthesize the literature on the dose-response effect in routine psychological therapies delivered to adult patients with mental health problems. Twenty-six studies were eligible for inclusion. Different methodological approaches have been used to examine the dose-response effect; including survival analysis, multilevel modelling and descriptive cluster analyses. Replicated and consistent support was found for a curvilinear (log-linear or cubic) relationship between treatment length and outcomes, with few exceptions such as eating disorders and severe psychiatric populations. Optimal doses of psychotherapy in routine settings range between 4 and 26 sessions (4–6 for low intensity guided self-help) and vary according to setting, clinical population and outcome measures. Weekly therapy appears to accelerate the rate of improvement compared to less frequent schedules. Most of the reviewed evidence is from university counselling centres and outpatient psychotherapy clinics for common mental health problems. There is scarce and inconclusive evidence in clinical samples with chronic and severe mental disorders.
Nur Fadhilah Umar, Arifin Manggau, Muhammad Hasim
et al.
This study aims to investigate the direct and indirect relationship between experience as a victim, observation, and microaggression statements with Bugis regional microaggression behavior moderated by aspects of understanding microaggression in South Sulawesi. The study population was all Bugis students in South Sulawesi enrolled in the 2019/2020 academic year at public and private universities. The purposive sampling method was used to select 207 students who met the inclusion criteria. The instruments used consisted of adaptations of the Racial Microaggression Scale (RMAS) and the Bugis-South Sulawesi Regional Microaggression Scale. The results of data analysis using path analysis showed that experience as a victim of microaggression has a significant direct influence on Bugis regional microaggression behavior. Observation of microaggression also acts as a significant factor in reinforcing microaggression behavior. However, microaggression statements do not have a significant direct influence on microaggression behavior. Understanding of microaggression did not play a significant moderating role in the relationship between exogenous variables and microaggression behavior. These results demonstrate the complexity of the microaggression behavior phenomenon and suggest that there is a cycle to microaggression behavior that is similar to bullying. This cycle involves the roles of perpetrator, victim, bystander. Microaggression and bullying behaviors, although having different forms and expressions of behavior, have in common the impact of demeaning, harming, or discriminating against the victim and tend to occur repeatedly and consistently against the victim, reinforcing the cycle of microaggression behavior.
Assertive behavior plays a crucial role for bullying victims in authentically expressing themselves and maintaining self-respect, while a positive school climate fosters identity development and reduces bullying. This study aims to examine the relationships between self-esteem, school climate, and assertive behavior in adolescents. The research employs a systematic literature review with a scoping review approach based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol. Sources include journal articles and books published within the last ten years, retrieved from databases such as Google Scholar, Semantic Scholar, ScienceDirect, and Wiley Online Library. Analysis of 30 sources reveals that self-esteem influences assertive behavior, while a research gap exists regarding the correlation between school climate and assertive behavior in adolescents. This study holds significance for adolescents and schools in reducing bullying by emphasizing the role of both personal and contextual factors.
Abstract Over 100 million children worldwide suffer from mental distress, with incidence rates steadily increasing. However, the combined impacts of air pollution and non-optimal temperature on schoolchildren’s mental health, as well as the disparities across urban and rural schools and between genders, remain insufficiently explored. Utilizing 95,658 mental distress records from school children in eastern China, we developed nine composite exposure scenarios to evaluate the mental health impacts of short-term (0–14 days) exposure to particulate matter (PM) air pollution (i.e., PM1, PM2.5, PM10), average temperature, and temperature variability (including both intra-day and inter-day temperature fluctuations). We found that children’s mental distress was significantly associated with PM pollution, particularly in urban schools, with rising risk trends and intensified hazards for finer particles (PM10 < PM2.5 < PM1). For each 10 μg/m³ increase, the relative risks of mental distress absenteeism for PM1, PM2.5, and PM10 were 1.017, 1.011, and 1.008, respectively. Polluted days coupled with warming temperature >10 °C and large intra-day (>10 °C) and inter-day fluctuations (<−2.5 or >0 °C) consistently exhibited higher and increasing risks, with relative risks ranging from 1.031 to 1.534 (p < 0.05). Girls, constituting 61.4% of the cases examined, exhibited greater vulnerability than boys, with higher threats and rising trends across all scenarios. Among the affected children, 77.9% didn’t receive medical assistance. Given the global warming trend, it’s crucial to address the combined impacts of extreme weather and PM pollution on schoolchildren’s mental health, particularly for girls and in rapidly urbanizing areas.
Wenrui Fan, L. M. Riza Rizky, Jiayang Zhang
et al.
Neuropathic pain, affecting up to 10% of adults, remains difficult to treat due to limited therapeutic efficacy and tolerability. Although resting-state functional MRI (rs-fMRI) is a promising non-invasive measurement of brain biomarkers to predict drug response in therapeutic development, the complexity of fMRI demands machine learning models with substantial capacity. However, extreme data scarcity in neuropathic pain research limits the application of high-capacity models. To address the challenge of data scarcity, we propose FMM$_{TC}$, a Foundation-Model-boosted Multimodal learning framework for fMRI-based neuropathic pain drug response prediction, which leverages both internal multimodal information in pain-specific data and external knowledge from large pain-agnostic data. Specifically, to maximize the value of limited pain-specific data, FMM$_{TC}$ integrates complementary information from two rs-fMRI modalities: Time series and functional Connectivity. FMM$_{TC}$ is further boosted by an fMRI foundation model with its external knowledge from extensive pain-agnostic fMRI datasets enriching limited pain-specific information. Evaluations with an in-house dataset and a public dataset from OpenNeuro demonstrate FMM$_{TC}$'s superior representation ability, generalizability, and cross-dataset adaptability over existing unimodal fMRI models that only consider one of the rs-fMRI modalities. The ablation study validates the effectiveness of multimodal learning and foundation-model-powered external knowledge transfer in FMM$_{TC}$. An integrated gradient-based interpretation study explains how FMM$_{TC}$'s cross-dataset dynamic behaviors enhance its adaptability. In conclusion, FMM$_{TC}$ boosts clinical trials in neuropathic pain therapeutic development by accurately predicting drug responses to improve the participant stratification efficiency.
Duncan F. Muir, Parker Grosjean, Margaux M. Pinney
et al.
Accurate prediction of enzymatic activity from amino acid sequences could drastically accelerate enzyme engineering for applications such as bioremediation and therapeutics development. In recent years, Protein Language Model (PLM) embeddings have been increasingly leveraged as the input into sequence-to-function models. Here, we use consistently collected catalytic turnover observations for 175 orthologs of the enzyme Adenylate Kinase (ADK) as a test case to assess the use of PLMs and their embeddings in enzyme kinetic prediction tasks. In this study, we show that nonlinear probing of PLM embeddings outperforms baseline embeddings (one-hot-encoding) and the specialized $k_{cat}$ (catalytic turnover number) prediction models DLKcat and CatPred. We also compared fixed and learnable aggregation of PLM embeddings for $k_{cat}$ prediction and found that transformer-based learnable aggregation of amino-acid PLM embeddings is generally the most performant. Additionally, we found that ESMC 600M embeddings marginally outperform other PLM embeddings for $k_{cat}$ prediction. We explored Low-Rank Adaptation (LoRA) masked language model fine-tuning and direct fine-tuning for sequence-to-$k_{cat}$ mapping, where we found no difference or a drop in performance compared to zero-shot embeddings, respectively. And we investigated the distinct hidden representations in PLM encoders and found that earlier layer embeddings perform comparable to or worse than the final layer. Overall, this study assesses the state of the field for leveraging PLMs for sequence-to-$k_{cat}$ prediction on a set of diverse ADK orthologs.
Asal Mehradfar, Mohammad Shahab Sepehri, Jose Miguel Hernandez-Lobato
et al.
The discovery of new ionizable lipids for efficient lipid nanoparticle (LNP)-mediated RNA delivery remains a critical bottleneck for RNA-based therapeutics development. Recent advances have highlighted the potential of machine learning (ML) to predict transfection efficiency from molecular structure, enabling high-throughput virtual screening and accelerating lead identification. However, existing approaches are hindered by inadequate data quality, ineffective feature representations, low predictive accuracy, and poor generalizability. Here, we present LANTERN (Lipid nANoparticle Transfection Efficiency pRedictioN), a robust ML framework for predicting transfection efficiency based on ionizable lipid representation. We benchmarked a diverse set of ML models against AGILE, a previously published model developed for transfection prediction. Our results show that combining simpler models with chemically informative features, particularly count-based Morgan fingerprints, outperforms more complex models that rely on internally learned embeddings, such as AGILE. We also show that a multi-layer perceptron trained on a combination of Morgan fingerprints and Expert descriptors achieved the highest performance ($\text{R}^2$ = 0.8161, r = 0.9053), significantly exceeding AGILE ($\text{R}^2$ = 0.2655, r = 0.5488). We show that the models in LANTERN consistently have strong performance across multiple evaluation metrics. Thus, LANTERN offers a robust benchmarking framework for LNP transfection prediction and serves as a valuable tool for accelerating lipid-based RNA delivery systems design.
Long COVID is a multisystem condition characterized by persistent symptoms such as fatigue, cognitive impairment, and systemic inflammation, following COVID-19 infection, yet its mechanisms remain poorly understood. In this study, we applied quantum walk (QW), a computational approach leveraging quantum interference, to explore large-scale SARS-CoV-2-induced protein (SIP) networks. Compared to the conventional random walk with restart (RWR) method, QW demonstrated superior capacity to traverse deeper regions of the network, uncovering proteins and pathways implicated in Long COVID. Key findings include mitochondrial dysfunction, thromboinflammatory responses, and neuronal inflammation as central mechanisms. QW uniquely identified the CDGSH iron-sulfur domain-containing protein family and VDAC1, a mitochondrial calcium transporter, as critical regulators of these processes. VDAC1 emerged as a potential biomarker and therapeutic target, supported by FDA-approved compounds such as cannabidiol. These findings highlight QW as a powerful tool for elucidating complex biological systems and identifying novel therapeutic targets for conditions like Long COVID.
Recent technological advances have expanded the availability of high-throughput biological datasets, enabling the reliable design of digital twins of biomedical systems or patients. Such computational tools represent key reaction networks driving perturbation or drug response and can guide drug discovery and personalized therapeutics. Yet, their development still relies on laborious data integration by the human modeler, so that automated approaches are critically needed. The success of data-driven system discovery in Physics, rooted in clean datasets and well-defined governing laws, has fueled interest in applying similar techniques in Biology, which presents unique challenges. Here, we reviewed methodologies for automatically inferring digital twins from biological time series, which mostly involve symbolic or sparse regression. We evaluate algorithms according to eight biological and methodological challenges, associated to noisy/incomplete data, multiple conditions, prior knowledge integration, latent variables, high dimensionality, unobserved variable derivatives, candidate library design, and uncertainty quantification. Upon these criteria, sparse regression generally outperformed symbolic regression, particularly when using Bayesian frameworks. We further highlight the emerging role of deep learning and large language models, which enable innovative prior knowledge integration, though the reliability and consistency of such approaches must be improved. While no single method addresses all challenges, we argue that progress in learning digital twins will come from hybrid and modular frameworks combining chemical reaction network-based mechanistic grounding, Bayesian uncertainty quantification, and the generative and knowledge integration capacities of deep learning. To support their development, we further propose a benchmarking framework to evaluate methods across all challenges.
Weronika Bielska, Igor Jaszczyszyn, Pawel Dudzic
et al.
Machine learning applications in protein sciences have ushered in a new era for designing molecules in silico. Antibodies, which currently form the largest group of biologics in clinical use, stand to benefit greatly from this shift. Despite the proliferation of these protein design tools, their direct application to antibodies is often limited by the unique structural biology of these molecules. Here, we review the current computational methods for antibody design, highlighting their role in advancing computational drug discovery.
Shame is a key emotion requiring understanding in therapeutic practice, not only from the perspective of a client but also from that of a practitioner. Shame may be outside or on the edge of awareness manifesting itself in different ways. This study explored shame as understood and experienced by person-centred counsellors and psychotherapists. Semi-structured interviews were undertaken with five person-centred therapists and data analysed using interpretative phenomenological analysis (IPA) which identified two themes: Framing Shame and Transforming Shame. Shame impacts on the efficacy of therapeutic work and supervision. Therefore, approaching shame from a place of principled non-directivity may be helpful for transforming shame in therapeutic work because it supports the therapist to empathically attune to the client, so clients can explore these experiences at their own pace. This paper considers these themes through the lens of person-centred theory, recognising the importance of understanding this master emotion from its source in past events and experiences.
Sobre la obra de Beatriz González.
Beatriz González (1932)
Beatriz González es un referente en el arte colombiano. Como artista se ha dedicado a examinar con una mirada incisiva la historia y memoria de Colombia. Ha tenido además un importante trayecto como investigadora y curadora, enfocándose en particular en la caricatura y el siglo XIX en Colombia. En una trayectoria de más de 50 años ha expuesto nacional e internacionalmente; entrado a conformar colecciones públicas como el Museo de Arte Moderno de Nueva York, la TATE Modern, y el Museo del Banco de la República entre otras, y trabajado en más de 15 publicaciones como catálogos, artículos y libros.
Agradecemos la colaboración de "Sextante galería. Arte Dos Gráfico Taller", del "Catálogo razonado Beatriz González - BADAC" de la Universidad de los Andes y, de manera especial, a la maestra Beatriz González y a Natalia Gutiérrez por permitirnos dialogar con su obra.
Sextante galería. Arte Dos Gráfico Taller
Catálogo razonado Beatriz González - BADAC
Paul Pereira, Hervé Minoux, Aleksandra M. Walczak
et al.
Since the approval of the first antibody drug in 1986, a total of 162 antibodies have been approved for a wide range of therapeutic areas, including cancer, autoimmune, infectious, or cardiovascular diseases. Despite advances in biotechnology that accelerated the development of antibody drugs, the drug discovery process for this modality remains lengthy and costly, requiring multiple rounds of optimizations before a drug candidate can progress to preclinical and clinical trials. This multi-optimization problem involves increasing the affinity of the antibody to the target antigen while refining additional biophysical properties that are essential to drug development such as solubility, thermostability or aggregation propensity. Additionally, antibodies that resemble natural human antibodies are particularly desirable, as they are likely to offer improved profiles in terms of safety, efficacy, and reduced immunogenicity, further supporting their therapeutic potential. In this article, we explore the use of energy-based generative models to optimize a candidate monoclonal antibody. We identify tradeoffs when optimizing for multiple properties, concentrating on solubility, humanness and affinity and use the generative model we develop to generate candidate antibodies that lie on an optimal Pareto front that satisfies these constraints.
Lamia Berriche, Maha Driss, Areej Ahmed Almuntashri
et al.
This paper introduces a new application named ArPA for Arabic kids who have trouble with pronunciation. Our application comprises two key components: the diagnostic module and the therapeutic module. The diagnostic process involves capturing the child's speech signal, preprocessing, and analyzing it using different machine learning classifiers like K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Decision Trees as well as deep neural network classifiers like ResNet18. The therapeutic module offers eye-catching gamified interfaces in which each correctly spoken letter earns a higher avatar level, providing positive reinforcement for the child's pronunciation improvement. Two datasets were used for experimental evaluation: one from a childcare centre and the other including Arabic alphabet pronunciation recordings. Our work uses a novel technique for speech recognition using Melspectrogram and MFCC images. The results show that the ResNet18 classifier on speech-to-image converted data effectively identifies mispronunciations in Arabic speech with an accuracy of 99.015\% with Mel-Spectrogram images outperforming ResNet18 with MFCC images.
Drug repurposing is an unconventional approach that is used to investigate new therapeutic aids of existing and shelved drugs. Recent advancement in technologies and the availability of the data of genomics, proteomics, transcriptomics, etc., and with the accessibility of large and reliable database resources, there are abundantly of opportunities to discover drugs by drug repurposing in an efficient manner. The recent pandemic of SARS-COV-2, that caused the death of 6,245,750 human beings to date, has tremendously increase the exceptional usage of bioinformatics tools in interpreting the molecular characterizations of viral infections. In this paper, we have employed various bioinformatics tools such as AutoDock-Vina, PyMol etc. We have found a leading drug candidate Cepharanthine that has shown better results and effectiveness than recently used antiviral drug candidates such as Favipiravir, IDX184, Remedesivir, Ribavirin and etc. This paper has analyzed Cepharanthine potential therapeutic importance as a drug of choice in managing COVID-19 cases. It is anticipated that proposed study would be beneficial for researchers and medical practitioners in handling SARS-CoV-2 and its variant related diseases.
Di indonesia, alat ukur untuk melihat sikap mencari bantuan Kesehatan mental masih terbatas selain itu kesadaran para remaja dalam menyikapi mencari bantuan kesehatan mental masih rendah. Hal ini juga di dasari oleh ketidaktahuan para remaja tentang layanan kesehatan mental dan pentingnya menjaga kesehatan mental. Meskipun sudah ada beberapa penelitian tentang pentingnya menjaga kesehatan mental, akan tetapi penelitian tersebut tidak menyertakan alat ukur yang terstandarisasi untuk mendiagnosa sikap mencari bantuan kesehatan mental. Berdasarkan latar belakang dan tujuan yang disebut sebelumnya, dalam artikel ini penulis menyertakan skala yang dapat digunakan untuk menjadi alat ukur sikap remaja dalam mencari bantuan kesehatan mental. Dalam artikel ini penulis mengadaptasi skala mencari bantuan Kesehatan mental menggunakan pendekatan kuantitatif. Hasil penelitian menunjukan bahwa adaptasi skala sikap dalam mencari bantuan kesahatan mental kedalam bahasa indonesia, menurut penilaian ahli Bahasa dan pengguna, dapat dikatakan valid secara kebahasaan dan dapat dilanjutkan untuk pengujian lebih lanjut mengenai validitas internal dan reliabilitasnya sebelum digunakan secara luas.
Protein-protein interactions (PPIs) are essentials for many biological processes where two or more proteins physically bind together to achieve their functions. Modeling PPIs is useful for many biomedical applications, such as vaccine design, antibody therapeutics, and peptide drug discovery. Pre-training a protein model to learn effective representation is critical for PPIs. Most pre-training models for PPIs are sequence-based, which naively adopt the language models used in natural language processing to amino acid sequences. More advanced works utilize the structure-aware pre-training technique, taking advantage of the contact maps of known protein structures. However, neither sequences nor contact maps can fully characterize structures and functions of the proteins, which are closely related to the PPI problem. Inspired by this insight, we propose a multimodal protein pre-training model with three modalities: sequence, structure, and function (S2F). Notably, instead of using contact maps to learn the amino acid-level rigid structures, we encode the structure feature with the topology complex of point clouds of heavy atoms. It allows our model to learn structural information about not only the backbones but also the side chains. Moreover, our model incorporates the knowledge from the functional description of proteins extracted from literature or manual annotations. Our experiments show that the S2F learns protein embeddings that achieve good performances on a variety of PPIs tasks, including cross-species PPI, antibody-antigen affinity prediction, antibody neutralization prediction for SARS-CoV-2, and mutation-driven binding affinity change prediction.
Warfarin, a commonly prescribed drug to prevent blood clots, has a highly variable individual response. Determining a maintenance warfarin dose that achieves a therapeutic blood clotting time, as measured by the international normalized ratio (INR), is crucial in preventing complications. Machine learning algorithms are increasingly being used for warfarin dosing; usually, an initial dose is predicted with clinical and genotype factors, and this dose is revised after a few days based on previous doses and current INR. Since a sequence of prior doses and INR better capture the variability in individual warfarin response, we hypothesized that longitudinal dose response data will improve maintenance dose predictions. To test this hypothesis, we analyzed a dataset from the COAG warfarin dosing study, which includes clinical data, warfarin doses and INR measurements over the study period, and maintenance dose when therapeutic INR was achieved. Various machine learning regression models to predict maintenance warfarin dose were trained with clinical factors and dosing history and INR data as features. Overall, dose revision algorithms with a single dose and INR achieved comparable performance as the baseline dose revision algorithm. In contrast, dose revision algorithms with longitudinal dose and INR data provided maintenance dose predictions that were statistically significantly much closer to the true maintenance dose. Focusing on the best performing model, gradient boosting (GB), the proportion of ideal estimated dose, i.e., defined as within $\pm$20% of the true dose, increased from the baseline (54.92%) to the GB model with the single (63.11%) and longitudinal (75.41%) INR. More accurate maintenance dose predictions with longitudinal dose response data can potentially achieve therapeutic INR faster, reduce drug-related complications and improve patient outcomes with warfarin therapy.