The xCELLigence technology is a real-time cellular biosensor, which measures the net adhesion of cells to high-density gold electrode arrays printed on custom-designed E-plates. The strength of cellular adhesion is influenced by a myriad of factors that include cell type, cell viability, growth, migration, spreading and proliferation. We therefore hypothesised that xCELLigence biosensor technology would provide a valuable platform for the measurement of drug responses in a multitude of different experimental, clinical or pharmacological contexts. In this manuscript, we demonstrate how xCELLigence technology has been invaluable in the identification of (1) not only if cells respond to a particular drug, but (2) the window of drug responsiveness. The latter aspect is often left to educated guess work in classical end-point assays, whereas biosensor technology reveals the temporal profile of the response in real time, which enables both acute responses and longer term responses to be profiled within the same assay. In our experience, the xCELLigence biosensor technology is suitable for highly targeted drug assessment and also low to medium throughput drug screening, which produces high content temporal data in real time.

Anomaly detection is a significant task in sensors’ signal processing since interpreting an abnormal signal can lead to making a high-risk decision in terms of sensors’ applications. Deep learning algorithms are effective tools for anomaly detection due to their capability to address imbalanced datasets. In this study, we took a semi-supervised learning approach, utilizing normal data for training the deep learning neural networks, in order to address the diverse and unknown features of anomalies. We developed autoencoder-based prediction models to automatically detect anomalous data recorded by three electrochemical aptasensors, with variations in the signals’ lengths for particular concentrations, analytes, and bioreceptors. Prediction models employed autoencoder networks and the kernel density estimation (KDE) method for finding the threshold to detect anomalies. Moreover, the autoencoder networks were vanilla, unidirectional long short-term memory (ULSTM), and bidirectional LSTM (BLSTM) autoencoders for the training stage of the prediction models. However, the decision-making was based on the result of these three networks and the integration of vanilla and LSTM networks’ results. The accuracy as a performance metric of anomaly prediction models showed that the performance of vanilla and integrated models were comparable, while the LSTM-based autoencoder models showed the least accuracy. Considering the integrated model of ULSTM and vanilla autoencoder, the accuracy for the dataset with the lengthier signals was approximately 80%, while it was 65% and 40% for the other datasets. The lowest accuracy belonged to the dataset with the least normal data in its dataset. These results demonstrate that the proposed vanilla and integrated models can automatically detect abnormal data when there is sufficient normal data for training the models.

The timing of hypoxia-ischemia (HI) in preterm infants is often uncertain and there are few biomarkers to determine whether infants are in a treatable stage of injury. We evaluated whether epileptiform sharp waves recorded from the parietal cortex could provide early prediction of neuronal loss after HI. Preterm fetal sheep (0.7 gestation) underwent acute HI induced by complete umbilical cord occlusion for 25 minutes (n = 6) or sham occlusion (control, n = 6). Neuronal survival was assessed 7 days after HI by immunohistochemistry. Sharp waves were quantified manually and using a wavelet-type-2-fuzzy-logic-system during the first 4 hours of recovery. HI resulted in significant subcortical neuronal loss. Sharp waves counted by the automated classifier in the first 30 minutes after HI were associated with greater neuronal survival in the caudate nucleus (r = 0.80), whereas sharp waves between 2–4 hours after HI were associated with reduced neuronal survival (r = −0.83). Manual and automated counts were closely correlated. This study suggests that automated quantification of sharp waves may be useful for early assessment of HI injury in preterm infants. However, the pattern of evolution of sharp waves after HI was markedly affected by the severity of neuronal loss, and therefore early, continuous monitoring is essential.

Nanomaterial-based aptasensors serve as useful instruments for detecting small biological entities. This work utilizes data gathered from three electrochemical aptamer-based sensors varying in receptors, analytes of interest, and lengths of signals. Our ultimate objective was the automatic detection and quantification of target analytes from a segment of the signal recorded by these sensors. Initially, we proposed a data augmentation method using conditional variational autoencoders to address data scarcity. Secondly, we employed recurrent-based networks for signal extrapolation, ensuring uniform signal lengths. In the third step, we developed seven deep learning classification models (GRU, unidirectional LSTM (ULSTM), bidirectional LSTM (BLSTM), ConvGRU, ConvULSTM, ConvBLSTM, and CNN) to identify and quantify specific analyte concentrations for six distinct classes, ranging from the absence of analyte to 10 μM. Finally, the second classification model was created to distinguish between abnormal and normal data segments, detect the presence or absence of analytes in the sample, and, if detected, identify the specific analyte and quantify its concentration. Evaluating the time series forecasting showed that the GRU-based network outperformed two other ULSTM and BLSTM networks. Regarding classification models, it turned out signal extrapolation was not effective in improving the classification performance. Comparing the role of the network architectures in classification performance, the result showed that hybrid networks, including both convolutional and recurrent layers and CNN networks, achieved 82% to 99% accuracy across all three datasets. Utilizing short-term Fourier transform (STFT) as the preprocessing technique improved the performance of all datasets with accuracies from 84% to 99%. These findings underscore the effectiveness of suitable data preprocessing methods in enhancing neural network performance, enabling automatic analyte identification and quantification from electrochemical aptasensor signals.