Meet the authors: Georgios Rizos, Jenna L. Lawson, and Björn W. Schuller.

In their recent publication in Patterns, the authors proposed a methodology based on sample-free Bayesian neural networks and label smoothing to improve both predictive and calibration performance on animal call detection. Such approaches have the potential to foster trust in algorithmic decision making and enhance policy making in applications about conservation using recordings made by on-site passive acoustic monitoring equipment. This interview is a companion to these authors' recent paper, "Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing".

Propagating variational model uncertainty for bioacoustic call label smoothing.

Along with propagating the input toward making a prediction, Bayesian neural networks also propagate uncertainty. This has the potential to guide the training process by rejecting predictions of low confidence, and recent variational Bayesian methods can do so without Monte Carlo sampling of weights. Here, we apply sample-free methods for wildlife call detection on recordings made via passive acoustic monitoring equipment in the animals' natural habitats. We further propose uncertainty-aware label smoothing, where the smoothing probability is dependent on sample-free predictive uncertainty, in order to downweigh data samples that should contribute less to the loss value. We introduce a bioacoustic dataset recorded in Malaysian Borneo, containing overlapping calls from 30 species. On that dataset, our proposed method achieves an absolute percentage improvement of around 1.5 points on area under the receiver operating characteristic (AU-ROC), 13 points in F1, and 19.5 points in expected calibration error (ECE) compared to the point-estimate network baseline averaged across all target classes.

Assessing the Feasibility of a Text-Based Conversational Agent for Asthma Support: Protocol for a Mixed Methods Observational Study.

BACKGROUND: Despite efforts, the UK death rate from asthma is the highest in Europe, and 65% of people with asthma in the United Kingdom do not receive the professional care they are entitled to. Experts have recommended the use of digital innovations to help address the issues of poor outcomes and lack of care access. An automated SMS text messaging-based conversational agent (ie, chatbot) created to provide access to asthma support in a familiar format via a mobile phone has the potential to help people with asthma across demographics and at scale. Such a chatbot could help improve the accuracy of self-assessed risk, improve asthma self-management, increase access to professional care, and ultimately reduce asthma attacks and emergencies. OBJECTIVE: The aims of this study are to determine the feasibility and usability of a text-based conversational agent that processes a patient's text responses and short sample voice recordings to calculate an estimate of their risk for an asthma exacerbation and then offers follow-up information for lowering risk and improving asthma control; assess the levels of engagement for different groups of users, particularly those who do not access professional services and those with poor asthma control; and assess the extent to which users of the chatbot perceive it as helpful for improving their understanding and self-management of their condition. METHODS: We will recruit 300 adults through four channels for broad reach: Facebook, YouGov, Asthma + Lung UK social media, and the website Healthily (a health self-management app). Participants will be screened, and those who meet inclusion criteria (adults diagnosed with asthma and who use WhatsApp) will be provided with a link to access the conversational agent through WhatsApp on their mobile phones. Participants will be sent scheduled and randomly timed messages to invite them to engage in dialogue about their asthma risk during the period of study. After a data collection period (28 days), participants will respond to questionnaire items related to the quality of the interaction. A pre- and postquestionnaire will measure asthma control before and after the intervention. RESULTS: This study was funded in March 2021 and started in January 2022. We developed a prototype conversational agent, which was iteratively improved with feedback from people with asthma, asthma nurses, and specialist doctors. Fortnightly reviews of iterations by the clinical team began in September 2022 and are ongoing. This feasibility study will start recruitment in January 2023. The anticipated completion of the study is July 2023. A future randomized controlled trial will depend on the outcomes of this study and funding. CONCLUSIONS: This feasibility study will inform a follow-up pilot and larger randomized controlled trial to assess the impact of a conversational agent on asthma outcomes, self-management, behavior change, and access to care. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/42965.

Multilabel user classification using the community structure of online networks.

We study the problem of semi-supervised, multi-label user classification of networked data in the online social platform setting. We propose a framework that combines unsupervised community extraction and supervised, community-based feature weighting before training a classifier. We introduce Approximate Regularized Commute-Time Embedding (ARCTE), an algorithm that projects the users of a social graph onto a latent space, but instead of packing the global structure into a matrix of predefined rank, as many spectral and neural representation learning methods do, it extracts local communities for all users in the graph in order to learn a sparse embedding. To this end, we employ an improvement of personalized PageRank algorithms for searching locally in each user's graph structure. Then, we perform supervised community feature weighting in order to boost the importance of highly predictive communities. We assess our method performance on the problem of user classification by performing an extensive comparative study among various recent methods based on graph embeddings. The comparison shows that ARCTE significantly outperforms the competition in almost all cases, achieving up to 35% relative improvement compared to the second best competing method in terms of F1-score.

The K⁺-dependent GTPase Nug1 is implicated in the association of the helicase Dbp10 to the immature peptidyl transferase centre during ribosome maturation.

Ribosome synthesis employs a number of energy-consuming enzymes in both eukaryotes and prokaryotes. One such enzyme is the conserved circularly permuted GTPase Nug1 (nucleostemin in human). Nug1 is essential for 60S subunit assembly and nuclear export, but its role and time of action during maturation remained unclear. Based on in vitro enzymatic assays using the Chaetomium thermophilum (Ct) orthologue, we show that Nug1 exhibits a low intrinsic GTPase activity that is stimulated by potassium ions, rendering Nug1 a cation-dependent GTPase. In vivo we observe 60S biogenesis defects upon depletion of yeast Nug1 or expression of a Nug1 nucleotide-binding mutant. Most prominently, the RNA helicase Dbp10 was lost from early pre-60S particles, which suggested a physical interaction that could be reconstituted in vitro using CtNug1 and CtDbp10. In vivo rRNA-protein crosslinking revealed that Nug1 and Dbp10 bind at proximal and partially overlapping sites on the 60S pre-ribosome, most prominently to H89 that will constitute part of the peptidyl transferase center (PTC). The binding sites of Dbp10 are the same as those identified for the prokaryotic helicase DbpA bound to the 50S subunit. We suggest that Dbp10 and DbpA are performing a conserved role during PTC formation in all organisms.

Coupled GTPase and remodelling ATPase activities form a checkpoint for ribosome export.

Eukaryotic ribosomes are assembled by a complex pathway that extends from the nucleolus to the cytoplasm and is powered by many energy-consuming enzymes. Nuclear export is a key, irreversible step in pre-ribosome maturation, but mechanisms underlying the timely acquisition of export competence remain poorly understood. Here we show that a conserved Saccharomyces cerevisiae GTPase Nug2 (also known as Nog2, and as NGP-1, GNL2 or nucleostemin 2 in human) has a key role in the timing of export competence. Nug2 binds the inter-subunit face of maturing, nucleoplasmic pre-60S particles, and the location clashes with the position of Nmd3, a key pre-60S export adaptor. Nug2 and Nmd3 are not present on the same pre-60S particles, with Nug2 binding before Nmd3. Depletion of Nug2 causes premature Nmd3 binding to the pre-60S particles, whereas mutations in the G-domain of Nug2 block Nmd3 recruitment, resulting in severe 60S export defects. Two pre-60S remodelling factors, the Rea1 ATPase and its co-substrate Rsa4, are present on Nug2-associated particles, and both show synthetic lethal interactions with nug2 mutants. Release of Nug2 from pre-60S particles requires both its K(+)-dependent GTPase activity and the remodelling ATPase activity of Rea1. We conclude that Nug2 is a regulatory GTPase that monitors pre-60S maturation, with release from its placeholder site linked to recruitment of the nuclear export machinery.