RESUMEN
BACKGROUND: Low back pain (LBP) is a significant public health problem that can result in physical disability and financial burden for the individual and society. Physical therapy is effective for managing LBP and includes evaluation of posture and movement, interventions directed at modifying posture and movement, and prescription of exercises. However, physical therapists have limited tools for objective evaluation of low back posture and movement and monitoring of exercises, and this evaluation is limited to the time frame of a clinical encounter. There is a need for a valid tool that can be used to evaluate low back posture and movement and monitor exercises outside the clinic. To address this need, a fabric-based, wearable sensor, Motion Tape (MT), was developed and adapted for a low back use case. MT is a low-profile, disposable, self-adhesive, skin-strain sensor developed by spray coating piezoresistive graphene nanocomposites directly onto commercial kinesiology tape. OBJECTIVE: The objectives of this study were to (1) validate MT for measuring low back posture and movement and (2) assess the acceptability of MT for users. METHODS: A total of 10 participants without LBP were tested. A 3D optical motion capture system was used as a reference standard to measure low back kinematics. Retroreflective markers and a matrix of MTs were placed on the low back to measure kinematics (motion capture) and strain (MT) simultaneously during low back movements in the sagittal, frontal, and axial planes. Cross-correlation coefficients were calculated to evaluate the concurrent validity of MT strain in reference motion capture kinematics during each movement. The acceptability of MT was assessed using semistructured interviews conducted with each participant after laboratory testing. Interview data were analyzed using rapid qualitative analysis to identify themes and subthemes of user acceptability. RESULTS: Visual inspection of concurrent MT strain and kinematics of the low back indicated that MT can distinguish between different movement directions. Cross-correlation coefficients between MT strain and motion capture kinematics ranged from -0.915 to 0.983, and the strength of the correlations varied across MT placements and low back movement directions. Regarding user acceptability, participants expressed enthusiasm toward MT and believed that it would be helpful for remote interventions for LBP but provided suggestions for improvement. CONCLUSIONS: MT was able to distinguish between different low back movements, and most MTs demonstrated moderate to high correlation with motion capture kinematics. This preliminary laboratory validation of MT provides a basis for future device improvements, which will also involve testing in a free-living environment. Overall, users found MT acceptable for use in physical therapy for managing LBP.
RESUMEN
Predicting the activities of new compounds against biophysical or phenotypic assays based on the known activities of one or a few existing compounds is a common goal in early stage drug discovery. This problem can be cast as a "few-shot learning" challenge, and prior studies have developed few-shot learning methods to classify compounds as active versus inactive. However, the ability to go beyond classification and rank compounds by expected affinity is more valuable. We describe Few-Shot Compound Activity Prediction (FS-CAP), a novel neural architecture trained on a large bioactivity data set to predict compound activities against an assay outside the training set, based on only the activities of a few known compounds against the same assay. Our model aggregates encodings generated from the known compounds and their activities to capture assay information and uses a separate encoder for the new compound whose activity is to be predicted. The new method provides encouraging results relative to traditional chemical-similarity-based techniques as well as other state-of-the-art few-shot learning methods in tests on a variety of ligand-based drug discovery settings and data sets. The code for FS-CAP is available at https://github.com/Rose-STL-Lab/FS-CAP.
Asunto(s)
Descubrimiento de Drogas , Ligandos , Descubrimiento de Drogas/métodos , Aprendizaje Automático , Redes Neurales de la ComputaciónRESUMEN
Numerous studies have demonstrated that endostatin (ES), a potent angiostatic peptide derived from collagen type XVIII alpha 1 chain and encoded by COL18A1, is elevated in pulmonary arterial hypertension (PAH). Importantly, elevated ES has consistently been associated with altered hemodynamics, poor functional status, and adverse outcomes in adult and pediatric PAH. This study used serum samples from patients with Group I PAH and plasma and tissue samples derived from the Sugen/Chronic hypoxic (SuHx) rat pulmonary hypertension (PH) model to define associations between COL18A1/ES and disease development, including hemodynamics, right ventricular (RV) remodeling, and RV dysfunction. Using cardiac magnetic resonance (CMR) imaging and advanced hemodynamic assessments with pressure-volume (PV) loops in patients with PAH to assess RV-pulmonary arterial (PA) coupling, we observed a strong relationship between circulating ES levels and metrics of RV structure and function. Specifically, RV mass and the ventricular mass index (VMI) were positively associated with ES while RV ejection fraction and RV-PA coupling were inversely associated with ES levels. Our animal data demonstrates that the development of PH is associated with increased COL18A1/ES in the heart as well as the lungs. Disease-associated increases in COL18A1 mRNA and protein were most pronounced in the RV compared to the left ventricle (LV) and lung. COL18A1 expression in the RV was strongly associated with disease-associated changes in RV mass, fibrosis, and myocardial capillary density. These findings indicate that COL18A1/ES increase early in disease development in the RV and implicate COL18A1/ES in pathologic RV dysfunction in PAH.
RESUMEN
Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expensive numerical integration, requiring significant computational resources and domain expertise. While deep learning (DL) provides efficient alternatives for modeling complex dynamics, they require a large amount of labeled training data. Furthermore, its predictions may disobey the governing physical laws and are difficult to interpret. Physics-guided DL aims to integrate first-principled physical knowledge into data-driven methods. It has the best of both worlds and is well equipped to better solve scientific problems. Recently, this field has gained great progress and has drawn considerable interest across discipline Here, we introduce the framework of physics-guided DL with a special emphasis on learning dynamical systems. We describe the learning pipeline and categorize state-of-the-art methods under this framework. We also offer our perspectives on the open challenges and emerging opportunities.
RESUMEN
Predicting the activities of compounds against protein-based or phenotypic assays using only a few known compounds and their activities is a common task in target-free drug discovery. Existing few-shot learning approaches are limited to predicting binary labels (active/inactive). However, in real-world drug discovery, degrees of compound activity are highly relevant. We study Few-Shot Compound Activity Prediction (FS-CAP) and design a novel neural architecture to meta-learn continuous compound activities across large bioactivity datasets. Our model aggregates encodings generated from the known compounds and their activities to capture assay information. We also introduce a separate encoder for the unknown compound. We show that FS-CAP surpasses traditional similarity-based techniques as well as other state of the art few-shot learning methods on a variety of target-free drug discovery settings and datasets.
RESUMEN
Identifying novel drug-target interactions is a critical and rate-limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, here we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Here we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training to improve binding predictions for novel proteins and ligands. We validate AI-Bind predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. AI-Bind is a high-throughput approach to identify drug-target combinations with the potential of becoming a powerful tool in drug discovery.
Asunto(s)
Proteínas , Ligandos , Proteínas/metabolismo , Unión Proteica , Sitios de Unión , Secuencia de AminoácidosRESUMEN
Graph layout algorithms used in network visualization represent the first and the most widely used tool to unveil the inner structure and the behavior of complex networks. Current network visualization software relies on the force-directed layout (FDL) algorithm, whose high computational complexity makes the visualization of large real networks computationally prohibitive and traps large graphs into high energy configurations, resulting in hard-to-interpret "hairball" layouts. Here we use Graph Neural Networks (GNN) to accelerate FDL, showing that deep learning can address both limitations of FDL: it offers a 10 to 100 fold improvement in speed while also yielding layouts which are more informative. We analytically derive the speedup offered by GNN, relating it to the number of outliers in the eigenspectrum of the adjacency matrix, predicting that GNNs are particularly effective for networks with communities and local regularities. Finally, we use GNN to generate a three-dimensional layout of the Internet, and introduce additional measures to assess the layout quality and its interpretability, exploring the algorithm's ability to separate communities and the link-length distribution. The novel use of deep neural networks can help accelerate other network-based optimization problems as well, with applications from reaction-diffusion systems to epidemics.
RESUMEN
Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, Smiles, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, Smiles has several shortcomings-most pertinently, most combinations of symbols lead to invalid results with no valid chemical interpretation. To overcome this issue, a new language for molecules was introduced in 2020 that guarantees 100% robustness: SELF-referencing embedded string (Selfies). Selfies has since simplified and enabled numerous new applications in chemistry. In this perspective, we look to the future and discuss molecular string representations, along with their respective opportunities and challenges. We propose 16 concrete future projects for robust molecular representations. These involve the extension toward new chemical domains, exciting questions at the interface of AI and robust languages, and interpretability for both humans and machines. We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.
RESUMEN
Generation of drug-like molecules with high binding affinity to target proteins remains a difficult and resource-intensive task in drug discovery. Existing approaches primarily employ reinforcement learning, Markov sampling, or deep generative models guided by Gaussian processes, which can be prohibitively slow when generating molecules with high binding affinity calculated by computationally-expensive physics-based methods. We present Latent Inceptionism on Molecules (LIMO), which significantly accelerates molecule generation with an inceptionism-like technique. LIMO employs a variational autoencoder-generated latent space and property prediction by two neural networks in sequence to enable faster gradient-based reverse-optimization of molecular properties. Comprehensive experiments show that LIMO performs competitively on benchmark tasks and markedly outperforms state-of-the-art techniques on the novel task of generating drug-like compounds with high binding affinity, reaching nanomolar range against two protein targets. We corroborate these docking-based results with more accurate molecular dynamics-based calculations of absolute binding free energy and show that one of our generated drug-like compounds has a predicted K D (a measure of binding affinity) of 6 · 10-14 M against the human estrogen receptor, well beyond the affinities of typical early-stage drug candidates and most FDA-approved drugs to their respective targets. Code is available at https://github.com/Rose-STL-Lab/LIMO.
RESUMEN
BACKGROUND: Humane education, which focuses on the cultivation of kindness and empathy towards animals, the environment, and fellow humans, helps children to be less egocentric and more sensitive to the human-animal interaction in ecology. AIM: This study aimed to evaluate an animal-assisted, school-based humane education programme that promotes a humane attitude and enhances social-emotional competence for children in Hong Kong. METHOD: A sequential mixed-methods formative evaluation was adopted in the pilot year of the programme. A controlled trial and focus groups were conducted to evaluate the preliminary outcomes and process of the programme and to identify the implementation obstacles and effective strategies. One hundred and ten primary three students from two primary schools participated in the study (55 in the intervention group and 55 in the control group with ordinary formal school extra-curricular activities). Paired sample t tests and a mixed ANOVA were conducted to explore the changes in students' social-emotional competence in our programme and two typical extra-curricular school programmes. Thematic analysis was conducted to categorise the transcriptions from the focus groups. RESULTS: Quantitative findings indicated that class-based, animal-assisted humane education increased cognitive competence (t[24] = 2.42, p = .02), empathy (t[24] = 2.94, p < .01), and reduced hyperactivity (t[23] = -2.40, p = .02). Further analysis indicated that the participant recruitment strategies moderate the impact of interventions on the development of empathy (F[2,104] = 4.11, p = .02) and cognitive competence (F[2,104] = 2.96, p = .05). Qualitative analysis suggested three major themes: enhancement of self-control, promotion of humane attitude, and improvement of reading skills. CONCLUSION: The preliminary results of this pilot study indicate positive effects of the programme. Vigorous systematic formative evaluation on the process and effective implementation should be included in future follow-up studies to ensure its sustainability and fidelity.
Asunto(s)
Emociones/fisiología , Instituciones Académicas , Animales de Servicio , Habilidades Sociales , Análisis de Varianza , Ira , Animales , Actitud , Niño , Hong Kong , Humanos , Proyectos PilotoRESUMEN
Global urbanization has given cause for a re-assessment of the nature and importance of the relationship between humans and domesticated animals. In densely-populated urban societies, where loneliness and alienation can be prevalent, the use of animals as human companions has taken on heightened importance. Hong Kong is the world's most urbanised political entity, and thus provides an ideal context for the exploration of the role of animals in the provision of companionship for human beings in cities. A web-based survey with descriptive analyses, regression, and ANOVA was conducted. Six-hundred-and-forty-seven companion animal owners and 312 non-owners completed the survey that examined their socio-demographic information, companion animal ownership status, and physical-psychosocial well-being. The statistically significant findings appear to suggest that socio-demographic variables (i.e., age, gender, housing, and education level) have stronger predictive values than companion animal ownership status with respect to the well-being of people in Hong Kong. Due the unique environmental features in Hong Kong, the positive impacts of companion animal ownership on the physical well-being of owners may be limited by the city's cramped living space and the limited number of people who own companion animals. However, results suggested that companion animals may still serve as a social lubricant between the owners and their significant others, thereby playing a heightened role significant role in enhancing general social connectedness in a metropolis. Given the importance of animals as human companions, it is suggested that relevant administrative agencies need to consider the development of policies and facilities which are conducive to both the maintenance and development of the bonds between humans and their companion animals and the physical and psychosocial health of both.