Search

The discovery of therapeutic peptides is often accelerated by means of virtual screening supported by machine learning-based predictive models. The predictive performance of such models is sensitive to the choice of data and its representation scheme. While the peptide physicochemical and compositional representations fail to distinguish sequence permutations, the amino acid arrangement within the sequence lacks the important information contained in physicochemical, conformational, topological, and geometrical properties. In this paper, we propose a solution to the identified information gap by implementing a hybrid scheme that complements the best traits from both approaches with the aim of predicting antimicrobial and antiviral activities based on experimental data from DRAMP 2.0, AVPdb, and Uniprot data repositories. Using the Friedman test of statistical significance, we compared our hybrid, sequential properties approach to peptide properties, one-hot vector encoding, and word embedding schemes in the 10-fold cross-validation setting, with respect to the F1 score, Matthews correlation coefficient, geometric mean, recall, and precision evaluation metrics. Moreover, the sequence modeling neural network was employed to gain insight into the synergic effect of both properties- and amino acid order-based predictions. The results suggest that sequential properties significantly (P < 0.01) surpasses the aforementioned state-of-the-art representation schemes. This makes it a strong candidate for increasing the predictive power of screening methods based on machine learning, applicable to any category of peptides.

The analysis of non-stationary signals is often performed on raw waveform data or on Fourier transformations of those data, i.e., spectrograms. However, the possibility of alternative time-frequency representations being more informative than spectrograms or the original data remains unstudied. In this study, we tested if alternative time-frequency representations could be more informative for machine learning classification of seismic signals. This hypothesis was assessed by training three well-established convolutional neural networks, using nine different time-frequency representations, to classify seismic waveforms as earthquake or noise. The results were compared to the base model, which was trained on the raw waveform data. The signals used in the experiment were seismogram instances from the LEN-DB seismological dataset (Magrini et al. 2020). The results demonstrate that Pseudo Wigner-Ville and Wigner-Ville time-frequency representations yield significantly better results than the base model, while Margenau-Hill performs significantly worse (P < .01). Interestingly, the spectrogram, which is often used in non-stationary signal analysis, did not yield statistically significant improvements. This research could have a notable impact in the field of seismology because the data that were previously hidden in the seismic noise are now classified more accurately. Moreover, the results might suggest that alternative time-frequency representations could be used in other fields which use non-stationary time series to extract more valuable information from the original data. The potential fields encompass different fields of geophysics, speech recognition, EEG and ECG signals, gravitational waves and so on. This, however, requires further research.

In this study, we compared the performance of machine learning models trained using transfer learning and those that were trained from scratch - on time series data. Four machine learning models were used for the experiment. Two models were taken from the field of seismology, and the other two are general-purpose models for working with time series data. The accuracy of selected models was systematically observed and analyzed when switching within the same domain of application (seismology), as well as between mutually different domains of application (seismology, speech, medicine, finance). In seismology, we used two databases of local earthquakes (one in counts, and the other with the instrument response removed) and a database of global earthquakes for predicting earthquake magnitude; other datasets targeted classifying spoken words (speech), predicting stock prices (finance) and classifying muscle movement from EMG signals (medicine).In practice, it is very demanding and sometimes impossible to collect datasets of tagged data large enough to successfully train a machine learning model. Therefore, in our experiment, we use reduced data sets of 1,500 and 9,000 data instances to mimic such conditions. Using the same scaled-down datasets, we trained two sets of machine learning models: those that used transfer learning for training and those that were trained from scratch. We compared the performances between pairs of models in order to draw conclusions about the utility of transfer learning. In order to confirm the validity of the obtained results, we repeated the experiments several times and applied statistical tests to confirm the significance of the results. The study shows when, within the set experimental framework, the transfer of knowledge brought improvements in terms of model accuracy and in terms of model convergence rate.Our results show that it is possible to achieve better performance and faster convergence by transferring knowledge from the domain of global earthquakes to the domain of local earthquakes; sometimes also vice versa. However, improvements in seismology can sometimes also be achieved by transferring knowledge from medical and audio domains. The results show that the transfer of knowledge between other domains brought even more significant improvements, compared to those within the field of seismology. For example, it has been shown that models in the field of sound recognition have achieved much better performance compared to classical models and that the domain of sound recognition is very compatible with knowledge from other domains. We came to similar conclusions for the domains of medicine and finance. Ultimately, the paper offers suggestions when transfer learning is useful, and the explanations offered can provide a good starting point for knowledge transfer using time series data.

Chemical space is vast and its exploration by hand-picking chemical compounds with desirable features can appear slow and demanding. With the advancement in the field of search based algorithms such exploration can be rationally controlled. Our goal was to construct a genetic algorithm that searches through chemical space of short peptides in intelligent and fast manner. We achieved our goal by adapting the multi-objective NSGA-II algorithm through the implementation of the early stopping criterion and mitigation of possible memory issues by using simulated annealing. The contribution of this paper is the design strategy for multiple peptide libraries that cover greater area of search space in exploration of new active peptides.

In practice, it is very demanding and sometimes impossible to collect datasets of tagged data large enough to successfully train a machine learning model, and one possible solution to this problem is transfer learning. This study aims to assess how transferable are the features between different domains of time series data and under which conditions. The effects of transfer learning are observed in terms of predictive performance of the models and their convergence rate during training. In our experiment, we use reduced data sets of 1,500 and 9,000 data instances to mimic real world conditions. Using the same scaled-down datasets, we trained two sets of machine learning models: those that were trained with transfer learning and those that were trained from scratch. Four machine learning models were used for the experiment. Transfer of knowledge was performed within the same domain of application (seismology), as well as between mutually different domains of application (seismology, speech, medicine, finance). We observe the predictive performance of the models and the convergence rate during the training. In order to confirm the validity of the obtained results, we repeated the experiments seven times and applied statistical tests to confirm the significance of the results. The general conclusion of our study is that transfer learning is very likely to either increase or not negatively affect the predictive performance of the model or its convergence rate. The collected data is analysed in more details to determine which source and target domains are compatible for transfer of knowledge. We also analyse the effect of target dataset size and the selection of model and its hyperparameters on the effects of transfer learning.

Range of motion measurement is often performed in physiotherapy. It is important for both initial patient’s joint health status evaluation, and later on for tracking progress of a rehabilitation therapy. Standard goniometers are often cumbersome to use and many therapists resort to approximative by eye angle assessment. In this paper, we investigate a modern smartphone application goniometer, based on an inertial measurement unit (IMU). We analyze IMU properties and their influence on angle measurement accuracy. The application is tested in a controlled environment and later on in real-life situations. The same set of measurements is performed by experienced physiotherapist using both the smartphone application and traditional goniometers. Shoulder abduction and elbow pronation and supination were examined. The results obtained clearly show that the smartphone application is comparable in accuracy to traditional ways of measurement. There was no statistically significant difference between the measurements made with traditional instruments and the mobile application. It was shown that for some ROM measurements it was efficient and easy to use and can be considered to be a viable and a better alternative to traditional goniometers.