Characterisation of RNA in milk and prediction of microRNA functions

 Milk is considered on of the world’s most ‘complete’ food. To characterise milk composition, Amit investigated RNA present of milk form 8 different species ranging from platypus to human. By applying latest RNA sequencing and bioinformatic techniques, his work led to uncover hundreds of novel milk RNAs.

Reasoned versus reactive prediction of behaviour: a meta-analysis of the prototype willingness model

The prototype willingness model (PWM) was designed to extend expectancy-value models of health behaviour by also including a heuristic, or social reactive pathway, to better explain health-risk behaviours in adolescents and young adults. The pathway includes prototype, i.e., images of a typical person who engages in a behaviour, and willingness to engage in behaviour. The current study describes a meta-analysis of predictive research using the PWM and explores the role of the heuristic pathway and intentions in predicting behaviour. Eighty-one studies met inclusion criteria. Overall, the PWM was supported and explained 20.5% of the variance in behaviour. Willingness explained 4.9% of the variance in behaviour over and above intention, although intention tended to be more strongly related to behaviour than was willingness. The strength of the PWM relationships tended to vary according to the behaviour being tested, with alcohol consumption being the behaviour best explained. Age was also an important moderator, and, as expected, PWM behaviour was best accounted for within adolescent samples. Results were heterogeneous even after moderators were taken into consideration. This meta-analysis provides support for the PWM and may be used to inform future interventions that can be tailored for at-risk populations.

Optimizing prediction of binge eating episodes : a comparison approach to test alternative conceptualizations of the affect regulation model

Background : Although a wealth of studies have tested the link between negative mood states and likelihood of a subsequent binge eating episode, the assumption that this relationship follows a typical linear dose–response pattern (i.e., that risk of a binge episode increases in proportion to level of negative mood) has not been challenged. The present study demonstrates the applicability of an alternative, non-linear conceptualization of this relationship, in which the strength of association between negative mood and probability of a binge episode increases above a threshold value for the mood variable relative to the slope below this threshold value (threshold dose response model).

Methods : A sample of 93 women aged 18 to 40 completed an online survey at random intervals seven times per day for a period of one week. Participants self-reported their current mood state and whether they had recently engaged in an eating episode symptomatic of a binge.

Results : As hypothesized, the threshold approach was a better predictor than the linear dose–response modeling of likelihood of a binge episode. The superiority of the threshold approach was found even at low levels of negative mood (3 out of 10, with higher scores reflecting more  negative mood). Additionally, severity of negative mood beyond this threshold value appears to be useful for predicting time to onset of a binge episode.

Conclusions : Present findings suggest that simple dose–response formulations for the association between  negative mood and onset of binge episodes miss vital aspects of this relationship. Most  notably, the impact of mood on binge eating appears to depend on whether a threshold value  of negative mood has been breached, and elevation in mood beyond this point may be useful  for clinicians and researchers to identify time to onset.

Incremental criterion prediction of personality facets over factors: obtaining unbiased estimates and confidence intervals

 Many researchers have argued that higher order models of personality such as the Five Factor Model are insufficient, and that facet-level analysis is required to better understand criteria such as well-being, job performance, and personality disorders. However, common methods in the extant literature used to estimate the incremental prediction of facets over factors have several shortcomings. This paper delineates these shortcomings by evaluating alternative methods using statistical theory, simulation, and an empirical example. We recommend using differences between Olkin-Pratt adjusted r-squared for factor versus facet regression models to estimate the incremental prediction of facets and present a method for obtaining confidence intervals for such estimates using double adjusted-. r-squared bootstrapping. We also provide an R package that implements the proposed methods.

Machine-learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry

Using the prediction of cancer outcome as a model, we have tested the hypothesis that through analysing routinely collected digital data contained in an electronic administrative record (EAR), using machine-learning techniques, we could enhance conventional methods in predicting clinical outcomes.

Microstructure modeling and prediction of the mechanical properties of advanced high strength steels

Dual phase (DP) steels were modeled using 2D and 3D representative volume elements (RVE). Both the 2D and 3D models were generated using the Monte-Carlo-Potts method to represent the realistic microstructural details. In the 2D model, a balance between computational efficiency and required accuracy in truly representing heterogeneous microstructure was achieved. In the 3D model, a stochastic template was used to generate a model with high spatial fidelity. The 2D model proved to be efficient for characterization of the mechanical properties of a DP steel where the effect of phase distribution, morphology and strain partitioning was studied. In contrast, the current 3D modeling technique was inefficient and impractical due to significant time cost. It is shown that the newly proposed 2D model generation technique is versatile and sufficiently accurate to capture mechanical properties of steels with heterogeneous microstructure.

Characterization and prediction of issue-related risks in software projects

Identifying risks relevant to a software project and planning measures to deal with them are critical to the success of the project. Current practices in risk assessment mostly rely on high-level, generic guidance or the subjective judgements of experts. In this paper, we propose a novel approach to risk assessment using historical data associated with a software project. Specifically, our approach identifies patterns of past events that caused project delays, and uses this knowledge to identify risks in the current state of the project. A set of risk factors characterizing “risky” software tasks (in the form of issues) were extracted from five open source projects: Apache, Duraspace, JBoss, Moodle, and Spring. In addition, we performed feature selection using a sparse logistic regression model to select risk factors with good discriminative power. Based on these risk factors, we built predictive models to predict if an issue will cause a project delay. Our predictive models are able to predict both the risk impact (i.e. the extend of the delay) and the likelihood of a risk occurring. The evaluation results demonstrate the effectiveness of our predictive models, achieving on average 48%-81% precision, 23%-90% recall, 29%-71% F-measure, and 70%-92% Area Under the ROC Curve. Our predictive models also have low error rates: 0.39-0.75 for Macro-averaged Mean Cost-Error and 0.7-1.2 for Macro-averaged Mean Absolute Error.

Prediction of perinatal depression from adolescence and before conception (VIHCS): 20-year prospective cohort study

BACKGROUND: Perinatal depression is a neglected global health priority, affecting 10-15% of women in high-income countries and a greater proportion in low-income countries. Outcomes for children include cognitive, behavioural, and emotional difficulties and, in low-income settings, perinatal depression is associated with stunting and physical illness. In the Victorian Intergenerational Health Cohort Study (VIHCS), we aimed to assess the extent to which women with perinatal depressive symptoms had a history of mental health problems before conception. METHODS: VIHCS is a follow-up study of participants in the Victorian Adolescent Health Cohort Study (VAHCS), which was initiated in August, 1992, in the state of Victoria, Australia. In VAHCS, participants were assessed for health outcomes at nine timepoints (waves) from age 14 years to age 29 years. Depressive symptoms were measured with the Revised Clinical Interview Schedule and the General Health Questionnaire. Enrolment to VIHCS began in September, 2006, during the ninth wave of VAHCS; depressive symptoms at this timepoint were measured with the Composite International Diagnostic Interview. We contacted women every 6 months (from age 29 years to age 35 years) to identify any pregnancies. We assessed perinatal depressive symptoms with the Edinburgh Postnatal Depression Scale (EPDS) by computer-assisted telephone interview at 32 weeks of gestation, 8 weeks after birth, and 12 months after birth. We defined perinatal depression as an EPDS score of 10 or more. FINDINGS: From a stratified random sample of 1000 female participants in VAHCS, we enrolled 384 women with 564 pregnancies. 253 (66%) of these women had a previous history of mental health problems at some point in adolescence or young adulthood. 117 women with a history of mental health problems in both adolescence and young adulthood had 168 pregnancies, and perinatal depressive symptoms were reported for 57 (34%) of these pregnancies, compared with 16 (8%) of 201 pregnancies in 131 women with no preconception history of mental health problems (adjusted odds ratio 8·36, 95% CI 3·34-20·87). Perinatal depressive symptoms were reported at one or more assessment points in 109 pregnancies; a preconception history of mental health problems was reported in 93 (85%) of these pregnancies. INTERPRETATION: Perinatal depressive symptoms are mostly preceded by mental health problems that begin before pregnancy, in adolescence or young adulthood. Women with a history of persisting common mental disorders before pregnancy are an identifiable high-risk group, deserving of clinical support throughout the childbearing years. Furthermore, the window for considering preventive intervention for perinatal depression should extend to the time before conception. FUNDING: National Health and Medical Research Council (Australia), Victorian Health Promotion Foundation, Colonial Foundation, Australian Rotary Health Research and Perpetual Trustees.

BacHbpred: support vector machine methods for the prediction of bacterial hemoglobin-like proteins

The recent upsurge in microbial genome data has revealed that hemoglobin-like (HbL) proteins may be widely distributed among bacteria and that some organisms may carry more than one HbL encoding gene. However, the discovery of HbL proteins has been limited to a small number of bacteria only. This study describes the prediction of HbL proteins and their domain classification using a machine learning approach. Support vector machine (SVM) models were developed for predicting HbL proteins based upon amino acid composition (AC), dipeptide composition (DC), hybrid method (AC + DC), and position specific scoring matrix (PSSM). In addition, we introduce for the first time a new prediction method based on max to min amino acid residue (MM) profiles. The average accuracy, standard deviation (SD), false positive rate (FPR), confusion matrix, and receiver operating characteristic (ROC) were analyzed. We also compared the performance of our proposed models in homology detection databases. The performance of the different approaches was estimated using fivefold cross-validation techniques. Prediction accuracy was further investigated through confusion matrix and ROC curve analysis. All experimental results indicate that the proposed BacHbpred can be a perspective predictor for determination of HbL related proteins. BacHbpred, a web tool, has been developed for HbL prediction.

Analysis and prediction of major blood proteins based on their amino acid and dipeptide composition

A method has been developed for predicting blood proteins using the SVM based machine learning approach. In this prediction method a two-step strategy was deployed to predict blood proteins and their subclasses. We have developed models of blood proteins and achieved the maximum accuracies of 90.57% and 91.39% with Matthews correlation coefficient (MCC) of 0.89 and 0.90 using single amino acid and dipeptide composition respectively. Furthermore, the method is able to predict major subclasses of blood proteins; developed based on amino acid (AC) and dipeptide composition (DC) with a maximum accuracy 90.38%, 92.83%, 87.41%, 92.52% and 85.27%, 89.07%, 94.82%, 86.31 for albumin, globulin, fibrinogen, and regulatory proteins respectively. All modules were trained, tested, and evaluated using the five-fold cross-validation technique.