Interpreting protein abundance in Saccharomyces cerevisiae through relational learning.

MOTIVATION: Proteomic profiles reflect the functional readout of the physiological state of an organism. An increased understanding of what controls and defines protein abundances is of high scientific interest. Saccharomyces cerevisiae is a well-studied model organism, and there is a large amount of structured knowledge on yeast systems biology in databases such as the Saccharomyces Genome Database, and highly curated genome-scale metabolic models like Yeast8. These datasets, the result of decades of experiments, are abundant in information, and adhere to semantically meaningful ontologies. RESULTS: By representing this knowledge in an expressive Datalog database we generated data descriptors using relational learning that, when combined with supervised machine learning, enables us to predict protein abundances in an explainable manner. We learnt predictive relationships between protein abundances, function and phenotype; such as α-amino acid accumulations and deviations in chronological lifespan. We further demonstrate the power of this methodology on the proteins His4 and Ilv2, connecting qualitative biological concepts to quantified abundances. AVAILABILITY AND IMPLEMENTATION: All data and processing scripts are available at the following Github repository: https://github.com/DanielBrunnsaker/ProtPredict.

Protein-ligand binding affinity prediction exploiting sequence constituent homology.

MOTIVATION: Molecular docking is a commonly used approach for estimating binding conformations and their resultant binding affinities. Machine learning has been successfully deployed to enhance such affinity estimations. Many methods of varying complexity have been developed making use of some or all the spatial and categorical information available in these structures. The evaluation of such methods has mainly been carried out using datasets from PDBbind. Particularly the Comparative Assessment of Scoring Functions (CASF) 2007, 2013, and 2016 datasets with dedicated test sets. This work demonstrates that only a small number of simple descriptors is necessary to efficiently estimate binding affinity for these complexes without the need to know the exact binding conformation of a ligand. RESULTS: The developed approach of using a small number of ligand and protein descriptors in conjunction with gradient boosting trees demonstrates high performance on the CASF datasets. This includes the commonly used benchmark CASF2016 where it appears to perform better than any other approach. This methodology is also useful for datasets where the spatial relationship between the ligand and protein is unknown as demonstrated using a large ChEMBL-derived dataset. AVAILABILITY AND IMPLEMENTATION: Code and data uploaded to https://github.com/abbiAR/PLBAffinity.

Transformational machine learning: Learning how to learn from many related scientific problems.

Almost all machine learning (ML) is based on representing examples using intrinsic features. When there are multiple related ML problems (tasks), it is possible to transform these features into extrinsic features by first training ML models on other tasks and letting them each make predictions for each example of the new task, yielding a novel representation. We call this transformational ML (TML). TML is very closely related to, and synergistic with, transfer learning, multitask learning, and stacking. TML is applicable to improving any nonlinear ML method. We tested TML using the most important classes of nonlinear ML: random forests, gradient boosting machines, support vector machines, k-nearest neighbors, and neural networks. To ensure the generality and robustness of the evaluation, we utilized thousands of ML problems from three scientific domains: drug design, predicting gene expression, and ML algorithm selection. We found that TML significantly improved the predictive performance of all the ML methods in all the domains (4 to 50% average improvements) and that TML features generally outperformed intrinsic features. Use of TML also enhances scientific understanding through explainable ML. In drug design, we found that TML provided insight into drug target specificity, the relationships between drugs, and the relationships between target proteins. TML leads to an ecosystem-based approach to ML, where new tasks, examples, predictions, and so on synergistically interact to improve performance. To contribute to this ecosystem, all our data, code, and our ∼50,000 ML models have been fully annotated with metadata, linked, and openly published using Findability, Accessibility, Interoperability, and Reusability principles (∼100 Gbytes).

Romantic relationship quality and functioning for individuals with clinical and sub-clinical social anxiety: a scoping review.

BACKGROUND: Social Anxiety Disorder (SAD) is associated with pervasive functional impairments and chronicity. Romantic relationship functioning and quality for individuals with SAD has been previously explored but existing studies have not been synthesised. AIMS: This scoping review charted existing literature regarding the quality and functioning of romantic relationships for people with SAD and high sub-clinical social anxiety (SA). METHODS: The review used a scoping approach to explore the current evidence base relating to SA, romantic relationship quality and functioning. Articles published in English after 1980 that reported either clinical or high sub-clinical SA were eligible. Double screening, data extraction, quality assessment, and thematic analysis of studies was conducted. RESULTS: 50 studies from 46 articles were identified, involving a range of community, college, adolescent, and clinical samples. Thematic analysis identified four themes; Relationship Quality, Satisfaction and Commitment; Communication and Self-Disclosure; Conflict, Social Support and Trust; Intimacy, Closeness and Sexual Satisfaction. CONCLUSIONS: The review highlights that evidence relating to romantic relationship functioning for individuals with SAD and high sub-clinical SA is heterogeneous, with relationship initiation in particular relatively under-explored. Further research is required to elucidate key constructs and interpersonal processes related to relationship functioning, and to inform treatment approaches with this group.

Improved prediction of gene expression through integrating cell signalling models with machine learning.

BACKGROUND: A key problem in bioinformatics is that of predicting gene expression levels. There are two broad approaches: use of mechanistic models that aim to directly simulate the underlying biology, and use of machine learning (ML) to empirically predict expression levels from descriptors of the experiments. There are advantages and disadvantages to both approaches: mechanistic models more directly reflect the underlying biological causation, but do not directly utilize the available empirical data; while ML methods do not fully utilize existing biological knowledge. RESULTS: Here, we investigate overcoming these disadvantages by integrating mechanistic cell signalling models with ML. Our approach to integration is to augment ML with similarity features (attributes) computed from cell signalling models. Seven sets of different similarity feature were generated using graph theory. Each set of features was in turn used to learn multi-target regression models. All the features have significantly improved accuracy over the baseline model - without the similarity features. Finally, the seven multi-target regression models were stacked together to form an overall prediction model that was significantly better than the baseline on 95% of genes on an independent test set. The similarity features enable this stacking model to provide interpretable knowledge about cancer, e.g. the role of ERBB3 in the MCF7 breast cancer cell line. CONCLUSION: Integrating mechanistic models as graphs helps to both improve the predictive results of machine learning models, and to provide biological knowledge about genes that can help in building state-of-the-art mechanistic models.

Batched Bayesian Optimization for Drug Design in Noisy Environments.

The early stages of the drug design process involve identifying compounds with suitable bioactivities via noisy assays. As databases of possible drugs are often very large, assays can only be performed on a subset of the candidates. Selecting which assays to perform is best done within an active learning process, such as batched Bayesian optimization, and aims to reduce the number of assays that must be performed. We compare how noise affects different batched Bayesian optimization techniques and introduce a retest policy to mitigate the effect of noise. Our experiments show that batched Bayesian optimization remains effective, even when large amounts of noise are present, and that the retest policy enables more active compounds to be identified in the same number of experiments.

Circulating BMP9 Protects the Pulmonary Endothelium during Inflammation-induced Lung Injury in Mice.

Rationale: Pulmonary endothelial permeability contributes to the high-permeability pulmonary edema that characterizes acute respiratory distress syndrome. Circulating BMP9 (bone morphogenetic protein 9) is emerging as an important regulator of pulmonary vascular homeostasis. Objectives:To determine whether endogenous BMP9 plays a role in preserving pulmonary endothelial integrity and whether loss of endogenous BMP9 occurs during LPS challenge. Methods: A BMP9-neutralizing antibody was administrated to healthy adult mice, and lung vasculature was examined. Potential mechanisms were delineated by transcript analysis in human lung endothelial cells. The impact of BMP9 administration was evaluated in a murine acute lung injury model induced by inhaled LPS. Levels of BMP9 were measured in plasma from patients with sepsis and from endotoxemic mice. Measurements and Main Results: Subacute neutralization of endogenous BMP9 in mice (N = 12) resulted in increased lung vascular permeability (P = 0.022), interstitial edema (P = 0.0047), and neutrophil extravasation (P = 0.029) compared with IgG control treatment (N = 6). In pulmonary endothelial cells, BMP9 regulated transcriptome pathways implicated in vascular permeability and cell-membrane integrity. Augmentation of BMP9 signaling in mice (N = 8) prevented inhaled LPS-induced lung injury (P = 0.0027) and edema (P < 0.0001). In endotoxemic mice (N = 12), endogenous circulating BMP9 concentrations were markedly reduced, the causes of which include a transient reduction in hepatic BMP9 mRNA expression and increased elastase activity in plasma. In human patients with sepsis (N = 10), circulating concentratons of BMP9 were also markedly reduced (P < 0.0001). Conclusions: Endogenous circulating BMP9 is a pulmonary endothelial-protective factor, downregulated during inflammation. Exogenous BMP9 offers a potential therapy to prevent increased pulmonary endothelial permeability in lung injury.

Closed-loop cycles of experiment design, execution, and learning accelerate systems biology model development in yeast.

One of the most challenging tasks in modern science is the development of systems biology models: Existing models are often very complex but generally have low predictive performance. The construction of high-fidelity models will require hundreds/thousands of cycles of model improvement, yet few current systems biology research studies complete even a single cycle. We combined multiple software tools with integrated laboratory robotics to execute three cycles of model improvement of the prototypical eukaryotic cellular transformation, the yeast (Saccharomyces cerevisiae) diauxic shift. In the first cycle, a model outperforming the best previous diauxic shift model was developed using bioinformatic and systems biology tools. In the second cycle, the model was further improved using automatically planned experiments. In the third cycle, hypothesis-led experiments improved the model to a greater extent than achieved using high-throughput experiments. All of the experiments were formalized and communicated to a cloud laboratory automation system (Eve) for automatic execution, and the results stored on the semantic web for reuse. The final model adds a substantial amount of knowledge about the yeast diauxic shift: 92 genes (+45%), and 1,048 interactions (+147%). This knowledge is also relevant to understanding cancer, the immune system, and aging. We conclude that systems biology software tools can be combined and integrated with laboratory robots in closed-loop cycles.

The tumour immune microenvironment in oesophageal cancer.

Oesophageal cancer (OC) is an inflammation-associated malignancy linked to gastro-oesophageal reflux disease, obesity and tobacco use. Knowledge of the microenvironment of oesophageal tumours is relevant to our understanding of the development of OC and its biology, and has major implications for understanding the response to standard therapies and immunotherapies, as well as for uncovering novel targets. In this context, we discuss what is known about the TME in OC from tumour initiation to development and progression, and how this is relevant to therapy sensitivity and resistance in the two major types of OC. We provide an immunological characterisation of the OC TME and discuss its prognostic implications with specific comparison with the Immunoscore and immune-hot, -cold, altered-immunosuppressed and -altered-excluded models. Targeted therapeutics for the TME under pre-clinical and clinical investigation in OCs are also summarised. A deeper understanding of the TME will enable the development of combination approaches to concurrently target the tumour cells and TME delivering precision medicine to OC patients.

Psychological correlates of disordered eating in youth with type 1 diabetes: Results from diabetes MILES Youth-Australia.

BACKGROUND: This study examined the relationship between disordered eating (DE), body dissatisfaction (BD), and psychological variables; and identified correlates of DE in youth with type 1 diabetes. METHODS: Data were from the Diabetes Management and Impact for Long-Term Empowerment and Success Youth Study-Australia, an online survey assessing the psychosocial impact of type 1 diabetes. Adolescents (N = 477; mean age 16 ± 2 years) with type 1 diabetes for at least 1 year, completed the Diabetes Eating Problem Survey-Revised, measures of BD, quality of life, well-being, depressive and anxiety symptoms, diabetes distress, and resilience. RESULTS: DE correlated positively (moderate-large) with depressive and anxiety symptoms, diabetes distress, and BD; and negatively (moderate-large) with well-being, quality of life, and resilience. In contrast, BD correlated (moderately) with all psychological variables in females only. In the stepwise regression, high diabetes distress and BD were the strongest predictors of DE. While the magnitude of BD was almost five times higher in females, the level of DE risk across genders did not differ when BD was added into the model, which overall explained 71% of the variance. CONCLUSIONS: This study explored potential risk and protective factors associated with DE. The novel finding that diabetes distress is a strong indicator of DE provides preliminary support for its inclusion into future risk models and potential target for intervention. Longitudinal studies are required to map how these factors predict changes over time with greater emphasis needed into understanding the gender-specific risks associated with BD, particularly during more difficult developmental phases, such as adolescence to young adulthood.

The relationships between socially prescribed perfectionism, in-group affect, negative urgency, and disordered eating in women.

Socially prescribed perfectionism (SPP) is often considered as a key risk factor for disordered eating (DE). However, current conceptualizations of SPP largely assume that this perfectionism pressure is non-specific (i.e., a global pressure), despite research indicating that for females experiencing DE, female-dominated groups impose this pressure (as a perceived norm). Furthermore, this relationship may be mediated by a negative reaction to this pressure, in the form of impulsivity (or negative urgency). To date, no research has investigated whether the relationship between SPP and DE is mediated by negative urgency, nor has there been research clarifying how in-group identification relates to DE, independent of SPP and negative urgency. To address these gaps, we assessed these variables in 147 female dieters (Mage  = 25.12 years, SD = 3.08) using a cross-sectional design. Consistent with our hypotheses, negative urgency fully mediated the link between female-based SPP and disordered eating, while female-based in-group affect (identification) was predictive of disordered eating (although the latter relationship was not sustained in a multiple regression model). These findings suggest that the SPP from other women may relate to DE through increasing negative urgency, and that the link between in-group (female) affect and DE may be better explained by SPP's link to DE.

Gender differences in disordered eating behaviors and body dissatisfaction among adolescents with type 1 diabetes: Results from diabetes MILES youth-Australia.

OBJECTIVE: To examine gender differences in disordered eating behaviors (DEB) and body dissatisfaction in adolescents with type 1 diabetes. While evidence shows that female youth with type 1 diabetes are more prone to DEB compared to their peers without diabetes, little is known about male adolescents. METHOD: In a national online survey, adolescents (13-19 years) with type 1 diabetes for ≥1 year completed the Diabetes Eating Problem Survey-Revised (DEPS-R), and the Body Mass Index Silhouette Matching Test (BMI-SMT) and items on binge eating and insulin omission. RESULTS: About 477 adolescents (mean age 16 years; 62% females) completed the DEPS-R and 431 the BMI-SMT. The DEPS-R total score was higher for females than males, with scores for females increasing with age. BMI, HbA1c , insulin omission, and binge-eating frequency were associated moderately with DEPS-R for both genders. On the BMI-SMT, 88% of females wanted to be thinner. Of the males, 76% reported body dissatisfaction; however, only 43% expressed a desire for thinness with the remainder desiring a larger body size. DEPS-R was positively associated with the discrepancy between perceived actual and ideal body size for both genders. DISCUSSION: A large proportion of adolescents with type 1 diabetes, particularly females reported engaging in DEB. Similarly, high rates of body dissatisfaction were reported, though ideal body shape preferences differed by gender. Given the high levels of self-reported DEB and gender-based patterns of body dissatisfaction, future research needs to examine the effectiveness of routine screening of DEB and consider implementation of stepped care approaches.

Relationships Between Self-Reported and Observed Parenting Behaviour, Adolescent Disordered Eating Attitudes and Behaviours, and the 5-HTTLPR Polymorphism: Data From the Australian Temperament Project.

This study examined whether self-reported and observationally measured parental behaviours were associated with disordered eating, and investigated possible moderation by a serotonin-transporter polymorphism (5-HTTLPR). Study 1 included 650 adolescents from the Australian Temperament Project who completed the Eating Disorder Inventory-2 Drive for Thinness and Bulimia scales at 15/16 years and were genotyped for 5-HTTLPR. Parents completed an Australian Temperament Project-devised measure of parental warmth and harsh punishment. Study 2 included a subgroup of 304 participants who also engaged in a video-recorded family interaction, with observed parental warmth and hostility coded by the Iowa Family Interaction Rating Scale. Greater self-reported parental warmth was associated with lower bulimia scores. Conversely, observationally measured parental warmth was associated with lower drive for thinness, but not bulimia. Self-reported parental harsh punishment was associated with bulimia only, with observed parental hostility associated with neither outcome. 5-HTTLPR genotype did not moderate the relationship between parent behaviours and adolescent disordered eating. Copyright © 2017 John Wiley & Sons, Ltd and Eating Disorders Association.

The effect of low parental warmth and low monitoring on disordered eating in mid-adolescence: Findings from the Australian Temperament Project.

OBJECTIVE: To investigate the interactions between low parental warmth and monitoring at age 13-14 years and disordered eating attitudes and behaviours at age 15-16 years. METHOD: Data on 1300 (667 females) adolescents and their parents were drawn from The Australian Temperament Project (ATP), a 30 year (15 wave) population based longitudinal study of social-emotional development. Parent participants completed surveys on parenting practices in late childhood, and adolescent participants reported disordered eating using the drive for thinness and bulimia subscales of the Eating Disorder Inventory (EDI) and an additional body dissatisfaction scale. Interaction was examined on the additive scale by estimating super-additive risk; i.e., risk in excess of the sum of individual risks. RESULTS: For boys, neither parental warmth or monitoring, nor their interaction, was related to disordered eating. For girls, low parental warmth (alone) was associated with bulimic behaviours. In contrast, exposure to both low monitoring and warmth was associated with ∼3½-fold, ∼4-fold and ∼5-fold increases in the odds of reporting body dissatisfaction, drive for thinness and bulimia, respectively. For body dissatisfaction and drive for thinness, risk associated with joint exposure exceeded the sum of individual risks, suggesting an additive interaction between parenting styles. CONCLUSION: Further investment in family-level interventions that focus on promoting parental monitoring behaviour and a warm parent-child relationship remain important strategies for preventing a range of disordered eating behaviours in adolescents.

EXACT2: the semantics of biomedical protocols.

BACKGROUND: The reliability and reproducibility of experimental procedures is a cornerstone of scientific practice. There is a pressing technological need for the better representation of biomedical protocols to enable other agents (human or machine) to better reproduce results. A framework that ensures that all information required for the replication of experimental protocols is essential to achieve reproducibility. To construct EXACT2 we manually inspected hundreds of published and commercial biomedical protocols from several areas of biomedicine. After establishing a clear pattern for extracting the required information we utilized text-mining tools to translate the protocols into a machine amenable format. We have verified the utility of EXACT2 through the successful processing of previously 'unseen' (not used for the construction of EXACT2)protocols. METHODS: We have developed the ontology EXACT2 (EXperimental ACTions) that is designed to capture the full semantics of biomedical protocols required for their reproducibility. RESULTS: The paper reports on a fundamentally new version EXACT2 that supports the semantically-defined representation of biomedical protocols. The ability of EXACT2 to capture the semantics of biomedical procedures was verified through a text mining use case. In this EXACT2 is used as a reference model for text mining tools to identify terms pertinent to experimental actions, and their properties, in biomedical protocols expressed in natural language. An EXACT2-based framework for the translation of biomedical protocols to a machine amenable format is proposed. CONCLUSIONS: The EXACT2 ontology is sufficient to record, in a machine processable form, the essential information about biomedical protocols. EXACT2 defines explicit semantics of experimental actions, and can be used by various computer applications. It can serve as a reference model for for the translation of biomedical protocols in natural language into a semantically-defined format.

AutonoMS: Automated Ion Mobility Metabolomic Fingerprinting.

Automation is dramatically changing the nature of laboratory life science. Robotic lab hardware that can perform manual operations with greater speed, endurance, and reproducibility opens an avenue for faster scientific discovery with less time spent on laborious repetitive tasks. A major bottleneck remains in integrating cutting-edge laboratory equipment into automated workflows, notably specialized analytical equipment, which is designed for human usage. Here we present AutonoMS, a platform for automatically running, processing, and analyzing high-throughput mass spectrometry experiments. AutonoMS is currently written around an ion mobility mass spectrometry (IM-MS) platform and can be adapted to additional analytical instruments and data processing flows. AutonoMS enables automated software agent-controlled end-to-end measurement and analysis runs from experimental specification files that can be produced by human users or upstream software processes. We demonstrate the use and abilities of AutonoMS in a high-throughput flow-injection ion mobility configuration with 5 s sample analysis time, processing robotically prepared chemical standards and cultured yeast samples in targeted and untargeted metabolomics applications. The platform exhibited consistency, reliability, and ease of use while eliminating the need for human intervention in the process of sample injection, data processing, and analysis. The platform paves the way toward a more fully automated mass spectrometry analysis and ultimately closed-loop laboratory workflows involving automated experimentation and analysis coupled to AI-driven experimentation utilizing cutting-edge analytical instrumentation. AutonoMS documentation is available at https://autonoms.readthedocs.io.

Collaborative Care Skills Training workshops: helping carers cope with eating disorders from the UK to Australia.

PURPOSE: The Collaborative Care Skills Training workshops, developed by Treasure and associates aim to improve the well-being, coping strategies and problem-solving skills of carers of someone with an eating disorder. Evidence has demonstrated the effectiveness of the workshops in the UK where it was developed. The aim of this pilot study was to examine whether conducting the workshops in different contexts by facilitators trained in its delivery could lead to similar impact. METHODS: The workshops were conducted with 15 carers in VIC, Australia and delivered by experienced health professionals trained in its content and delivery. A non-experimental research design with repeated measures was implemented. Quantitative data were collected at pre-and post-intervention and 8 weeks after completion of the workshops. RESULTS: Participation led to significant reductions in carers' reported expressed emotion, dysfunctional coping, distress, burden and accommodation and enabling of the eating disorder behaviour, which were maintained at the 8-week follow-up. CONCLUSION: Results suggest the workshops are effective in reducing carer distress and burden as well as modifying unhelpful emotional interactional styles when caring for family members with an eating disorder. The content of the workshops and its delivery, once experienced facilitators have received training, are transferable to other contexts.

A longitudinal examination of burden and psychological distress in carers of people with an eating disorder.

PURPOSE: Eating disorders are chronic conditions that require ongoing, high level care. Despite the chronic nature of eating disorders, to date, previous research examining eating disorder carer burden and psychological distress has been cross-sectional only. Therefore, the current study aimed to conduct a preliminary longitudinal examination of the predictors of carer burden and psychological distress for carers of those with an eating disorder. METHODS: A self-report, quantitative questionnaire approach was utilised. Forty-two carers completed three self-report questionnaires over a period of 9 months (initial, 4½ and 9 months) assessing carer burden, psychological distress, carer needs, expressed emotion, coping strategies and social support. RESULTS: Maladaptive coping, expressed emotion and carer needs were significant longitudinal predictors of carer burden. Carer psychological distress could not be predicted longitudinally. CONCLUSIONS: In order to reduce carer burden, interventions should test whether reducing maladaptive coping strategies, expressed emotion and addressing carer needs lead to lower carer burden and distress.