No abstract

Most preclinical sleep studies are conducted in nocturnal rodents that have fragmented sleep in comparison to humans who are primarily diurnal, typically with a consolidated sleep period. Consequently, we sought to define basal sleep characteristics, sleep/wake architecture and electroencephalographic (EEG) activity in a diurnal non-human primate (NHP) to evaluate the utility of this species for pharmacological manipulation of the sleep/wake cycle. Adult, 9–11 y.o. male cynomolgus macaques ( n = 6) were implanted with telemetry transmitters to record EEG and electromyogram (EMG) activity and Acticals to assess locomotor activity under baseline conditions and following injections either with vehicle or the caffeine (CAF; 10 mg/kg, i.m.) prior to the 12 h dark phase. EEG/EMG recordings (12–36 h in duration) were analyzed for sleep/wake states and EEG spectral composition. Macaques exhibited a sleep state distribution and architecture similar to previous NHP and human sleep studies. Acute administration of CAF prior to light offset enhanced wakefulness nearly 4-fold during the dark phase with consequent reductions in both NREM and REM sleep, decreased slow wave activity during wakefulness, and increased higher EEG frequency activity during NREM sleep. Despite the large increase in wakefulness and profound reduction in sleep during the dark phase, no sleep rebound was observed during the 24 h light and dark phases following caffeine administration. Cynomolgus macaques show sleep characteristics, EEG spectral structure, and respond to CAF in a similar manner to humans. Consequently, monitoring EEG/EMG by telemetry in this species may be useful both for basic sleep/wake studies and for pre-clinical assessments of drug-induced effects on sleep/wake.

Several research groups have developed automated sleep-wakefulness classifiers for night wrist actigraphic (ACT) data. These classifiers tend to be unbalanced, with a tendency to overestimate the detection of sleep, at the expense of poorer detection of wakefulness. The reason for this is that the measure of success in previous works was the maximization of the overall accuracy, disregarding the balance between sensitivity and specificity. The databases were usually sleep recordings, hence the over-representation of sleep samples. In this work an Artificial Neural Network (ANN), sleep-wakefulness classifier is presented. ACT data was collected every minute. An 11-min moving window was used as observing frame for data analysis, as applied in previous sleep ACT studies. However, our feature set adds new variables such as the time of the day, the median and the median absolute deviation. Sleep and Wakefulness data were balanced to improve the system training. A comparison with previous studies can still be done, by choosing the point in the ROC curve associated with the corresponding data balance. Our results are compared with a polysomnogram-based hypnogram as golden standard, rendering an accuracy of 92.8%, a sensitivity of 97.6% and a specificity of 73.4%. Geometric mean between sensitivity and specificity is 84.9%.

The increasing integration between protein engineering and machine learning has led to many interesting results. A problem still to solve is to evaluate the likelihood that a sequence will fold into a target structure. This problem can be also viewed as sequence prediction from a known structure.In the current work, we propose improvements in the recent architecture of Geometric Vector Perceptrons in order to optimize the sampling of sequences from a known backbone structure. The proposed model differs from the original in that there is: (i) no updating in the vectorial embedding, only in the scalar one, (ii) only one layer of decoding. The first aspect improves the accuracy of the model and reduces the use of memory, the second allows for training of the model with several tasks without incurring data leakage.We treat the trained classifier as an Energy-Based Model and sample sequences by sampling amino acids in a non-autoreggresive manner in the empty positions of the sequence using energy-guided criteria and followed by Monte Carlo optimization.We improve the median identity of samples from 40.2% to 44.7%.An additional question worth investigating is whether sampled and original sequences fold into similar structures independent of their identity. We chose proteins in our test set whose sampled sequences show low identity (under 30%) but for which our model predicted favorable energies. We used trRosetta server and observed that the predicted structures for sampled sequences highly resemble the predicted structures for original sequences, with an average TM score of 0.848.

No abstract