Conectar
by Domonkos Pogány, Péter Antal
Given the prolonged timelines and high costs associated with traditional approaches, accelerating drug development is crucial. Computational methods, particularly drug-target interaction prediction, have emerged as efficient tools, yet the explainability of machine learning models remains a challenge. Our work aims to provide more interpretable interaction prediction models using similarity-based prediction in a latent space aligned to biological hierarchies. We investigated integrating drug and protein hierarchies into a joint-embedding drug-target latent space via embedding regularization by conducting a comparative analysis between models employing traditional flat Euclidean vector spaces and those utilizing hyperbolic embeddings. Besides, we provided a latent space analysis as an example to show how we can gain visual insights into the trained model with the help of dimensionality reduction. Our results demonstrate that hierarchy regularization improves interpretability without compromising predictive performance. Furthermore, integrating hyperbolic embeddings, coupled with regularization, enhances the quality of the embedded hierarchy trees. Our approach enables a more informed and insightful application of interaction prediction models in drug discovery by constructing an interpretable hyperbolic latent space, simultaneously incorporating drug and target hierarchies and pairing them with available interaction information. Moreover, compatible with pairwise methods, the approach allows for additional transparency through existing explainable AI solutions.Autism (formally autism spectrum disorder) encompasses a group of complex neurodevelopmental conditions, characterised by differences in communication and social interactions. Co-occurring chronic gastrointestinal symptoms are common among autistic individuals and can adversely affect their quality of life. This study aims to evaluate the efficacy of oral encapsulated faecal microbiome transfer (FMT) in improving gastrointestinal symptoms and well-being among autistic adolescents and adults.
This double-blind, randomised, placebo-controlled trial will recruit 100 autistic adolescents and adults aged 16–45 years, who have mild to severe gastrointestinal symptoms (Gastrointestinal Symptoms Rating Scale (GSRS) score ≥2.0). We will also recruit eight healthy donors aged 18–32 years, who will undergo extensive clinical screening. Recipients will be randomised 1:1 to receive FMT or placebo, stratified by biological sex. Capsules will be administered over two consecutive days following an overnight bowel cleanse with follow-up assessments at 6, 12 and 26 weeks post-treatment. The primary outcome is GSRS score at 6 weeks. Other assessments include anthropometry, body composition, hair cortisol concentration, gut microbiome profile, urine/plasma gut-derived metabolites, plasma markers of gut inflammation/permeability and questionnaires on general well-being, sleep quality, physical activity, food diversity and treatment tolerability. Adverse events will be recorded and reviewed by an independent data monitoring committee.
Ethics approval for the study was granted by the Central Health and Disability Ethics Committee on 24 August 2021 (reference number: 21/CEN/211). Results will be published in peer-reviewed journals and presented to both scientific and consumer group audiences.
ACTRN12622000015741.
This study aimed to develop a simulation model to support orthopaedic elective capacity planning.
An open-source, generalisable discrete-event simulation was developed, including a web-based application. The model used anonymised patient records between 2016 and 2019 of elective orthopaedic procedures from a National Health Service (NHS) Trust in England. In this paper, it is used to investigate scenarios including resourcing (beds and theatres) and productivity (lengths of stay, delayed discharges and theatre activity) to support planning for meeting new NHS targets aimed at reducing elective orthopaedic surgical backlogs in a proposed ring-fenced orthopaedic surgical facility. The simulation is interactive and intended for use by health service planners and clinicians.
A higher number of beds (65–70) than the proposed number (40 beds) will be required if lengths of stay and delayed discharge rates remain unchanged. Reducing lengths of stay in line with national benchmarks reduces bed utilisation to an estimated 60%, allowing for additional theatre activity such as weekend working. Further, reducing the proportion of patients with a delayed discharge by 75% reduces bed utilisation to below 40%, even with weekend working. A range of other scenarios can also be investigated directly by NHS planners using the interactive web app.
The simulation model is intended to support capacity planning of orthopaedic elective services by identifying a balance of capacity across theatres and beds and predicting the impact of productivity measures on capacity requirements. It is applicable beyond the study site and can be adapted for other specialties.
FreshRSS 