Prediction of protein continuum secondary structure with probabilistic models based on NMR solved structures

Background: The structure of proteins may change as a result of the inherent flexibility of some protein regions. We develop and explore probabilistic machine learning methods for predicting a continuum secondary structure, i.e. assigning probabilities to the conformational states of a residue. We train our methods using data derived from high-quality NMR models. Results: Several probabilistic models not only successfully estimate the continuum secondary structure, but also provide a categorical output on par with models directly trained on categorical data. Importantly, models trained on the continuum secondary structure are also better than their categorical counterparts at identifying the conformational state for structurally ambivalent residues. Conclusion: Cascaded probabilistic neural networks trained on the continuum secondary structure exhibit better accuracy in structurally ambivalent regions of proteins, while sustaining an overall classification accuracy on par with standard, categorical prediction methods.

Diastolic dysfunction is a manifestation of ventricular-vascular interaction in patients with type 2 diabetes mellitus

Vascular disease is accelerated in patients with Type 2 diabetes mellitus (T2DM). Since the systemic vasculature plays a pivotal role in myocardial loading, this study aimed to determine the effect of arterial characteristics on left ventricular (LV) morphology and function in patients with T2DM. Conventional echocardiography and tissue Doppler imaging were performed in 172 T2DM patients (95 men; aged 55±11y) with preserved ejection fraction (62±5%). Patients were stratified into groups based on LV geometric pattern (normal [n = 79], concentric remodeling [n = 33], concentric hypertrophy [n = 29], eccentric hypertrophy [n = 31]). Total arterial compliance (TAC) was recorded by simultaneous radial tonometry and aortic outflow pulsed wave Doppler. Arterial (brachial and carotid) structure and function were determined by standard ultrasound methods. There were no significant differences between the LV geometric groups in demographic or clinical parameters. The concentric hypertrophy group had significantly increased carotid artery diameter (6.0±0.7mm versus 6.5±0.7mm; p < 0.05) and stiffness (1912±1203 dynes/cm2mm versus 2976±2695 dynes/cm2mm×10−6; p < 0.05) compared to those with normal geometry. However, TAC did not differ between groups. LV diastolic function, as determined by the ratio of diastolic mitral inflow velocity to mitral annulus tissue velocity (E/E_), was significantly associated with carotid artery relative wall thickness and intima media thickness (p < 0.05). Moreover, E/E_ was independently predicted by carotid artery relative wall thickness (β = 22.9; p = 0.007). We conclude that structural characteristics of the carotid artery are associated with abnormal LV structure and function in patients with T2DM. The LV functional irregularities may be a downstream consequence of amplified pressure wave reflections effecting sub-optimal ventricular-vascular interaction.