Clinical feature-related single-base substitution sequence signatures identified with an unsupervised machine learning approach

Background Mutation processes leave different signatures in genes. For single-base substitutions, previous studies have suggested that mutation signatures are not only reflected in mutation bases but also in neighboring bases. However, because of the lack of a method to identify features of long sequences next to mutation bases, the understanding of how flanking sequences influence mutation signatures is limited. Methods We constructed a long short-term memory-self organizing map (LSTM-SOM) unsupervised neural network. By extracting mutated sequence features via LSTM and clustering similar features with the SOM, single-base substitutions in The Cancer Genome Atlas database were clustered according to both their mutation site and flanking sequences. The relationship between mutation sequence signatures and clinical features was then analyzed. Finally, we clustered patients into different classes according to the composition of the mutation sequence signatures by the K-means method and then studied the differences in clinical features and survival between classes. Results Ten classes of mutant sequence signatures (mutation blots, MBs) were obtained from 2,141,527 single-base substitutions via LSTM-SOM machine learning approach. Different features in mutation bases and flanking sequences were revealed among MBs. MBs reflect both the site and pathological features of cancers. MBs were related to clinical features, including age, sex, and cancer stage. The class of an MB in a given gene was associated with survival. Finally, patients were clustered into 7 classes according to the MB composition. Significant differences in survival and clinical features were observed among different patient classes. Conclusions We provided a method for analyzing the characteristics of mutant sequences. Result of this study showed that flanking sequences, together with mutation bases, shape the signatures of SBSs. MBs were shown related to clinical features and survival of cancer patients. Composition of MBs is a feasible predictive factor of clinical prognosis. Further study of the mechanism of MBs related to cancer characteristics is suggested.

Matching sensor ontologies with unsupervised neural network with competitive learning

Sensor ontologies formally model the core concepts in the sensor domain and their relationships, which facilitates the trusted communication and collaboration of Artificial Intelligence of Things (AIoT). However, due to the subjectivity of the ontology building process, sensor ontologies might be defined by different terms, leading to the problem of heterogeneity. In order to integrate the knowledge of two heterogeneous sensor ontologies, it is necessary to determine the correspondence between two heterogeneous concepts, which is the so-called ontology matching. Recently, more and more neural networks have been considered as an effective approach to address the ontology heterogeneity problem, but they require a large number of manually labelled training samples to train the network, which poses an open challenge. In order to improve the quality of the sensor ontology alignment, an unsupervised neural network model is proposed in this work. It first models the ontology matching problem as a binary classification problem, and then uses a competitive learning strategy to efficiently cluster the ontologies to be matched, which does not require the labelled training samples. The experiment utilizes the benchmark track provided by the Ontology Alignment Evaluation Initiative (OAEI) and multiple real sensor ontology alignment tasks to test our proposal’s performance. The experimental results show that the proposed approach is able to determine higher quality alignment results compared to other matching strategies under different domain knowledge such as bibliographic and real sensor ontologies.

A computational study on the optimization of transcranial temporal interfering stimulation with high-definition electrode using unsupervised neural network

Transcranial temporal interfering stimulation (tTIS) can focally stimulate deep parts of the brain, which are related to specific functions, by using beats at two high AC frequencies that do not affect the human brain. However, it has limitations in terms of calculation time and precision for optimization because of its complexity and non-linearity. We aimed to propose a method using an unsupervised neural network (USNN) for tTIS to optimize quickly the interfering current value of high-definition electrodes, which can finely stimulate the deep part of the brain, and analyze the performance and characteristics of tTIS. A computational study was conducted using 16 realistic head models. This method generated the strongest stimulation on the target, even when targeting deep areas or multi-target stimulation. The tTIS was robust with target depth compared with transcranial alternating current stimulation, and mis-stimulation could be reduced compared with the case of using two-pair inferential stimulation. Optimization of a target could be performed in 3 min. By proposing the USNN for tTIS, we showed that the electrode currents of tTIS can be optimized quickly and accurately, and the possibility of stimulating the deep part of the brain precisely with transcranial electrical stimulation was confirmed.

A Computational Study On The Optimization of Transcranial Temporal Interfering Stimulation With High-Definition Electrode Using Unsupervised Neural Network

Transcranial temporal interfering stimulation (tTIS) can focally stimulate deep parts of the brain, which are related to specific functions, by using beats at two high AC frequencies that do not affect the human brain. However, it has limitations in terms of calculation time and precision for optimization because of its complexity and non-linearity. We aimed to propose a method using an unsupervised neural network (USNN) for tTIS to optimize quickly the interfering current value of high-definition electrodes, which can finely stimulate the deep part of the brain, and analyze the performance and characteristics of tTIS. A computational study was conducted using 16 realistic head models. This method generated the strongest stimulation on the target, even when targeting deep areas or multi-target stimulation. The tTIS was robust with target depth compared with transcranial alternating current stimulation, and mis-stimulation could be reduced compared with the case of using two-pair inferential stimulation. Optimization of a target could be performed in 3 min. By proposing the USNN for tTIS, we showed that the electrode currents of tTIS can be optimized quickly and accurately, and the possibility of stimulating the deep part of the brain precisely with transcranial electrical stimulation was confirmed.

Unravel Carbonate Reservoir Heterogeneities Through 3D Seismic Neural Network Application: A Machine Learning Based Approach and Workflow

The availability of 3D seismic data undoubtedly plays an important role in reservoir characterization. Currently seismic technology continues to advance at a rapid pace not only in the acquisition but also in processing and interpretation domain. The advance on this is well supported by the digitalization era which urges everything to run reliably fast, effective and efficient. Thanks to continuous development of IT peripherals we now have luxury to process and handle big data through the application of machine learning. Some debates on the effectiveness and threats that this process may automating certain task and later will decrease human workforce are still going on in many forums but still like it or not this machine learning is already embraced in almost every aspect of our life including in oil & gas industry. Carbonate reservoir on the other hand has been long known for its uniqueness compared to siliciclastic reservoir. The term heterogeneous properties are quite common for carbonate due to its complex multi-story depositional and diagenetic facies. In this paper, we bring up our case where we try to unravel carbonate heterogeneity from a massive tight gas reservoir through our machine learning application using the workflow of supervised and unsupervised neural network. In this study, we incorporate 3D PSTM seismic data and its stratigraphic interpretation coupled with the core study result, BHI (borehole image) log interpretation, and our regional understanding of the area to develop a meaningful carbonate facies model through seismic neural network exercises. As the result, we successfully derive geological consistent carbonate facies classification and distribution honoring all the supporting data above though the limitation of well penetration in the area. This result then proved to be beneficial to build integrated 3D geomodel which later can explain the issue on different gas compositions happens in the area. The result on unsupervised neural network also able to serves as a quick look for further sweetspot analysis to support full-field development.

Unsupervised Neural Networks for Identification of Aging Conditions in Li-Ion Batteries

This paper explores a new methodology based on data-driven approaches to identify and track degradation processes in Li-ion batteries. Our goal is to study if it is possible to differentiate the state of degradation of cells that present similar aging in terms of overall parameters (similar remaining capacity, state of health or internal resistance), but that have had different applications or conditions of use (different discharge currents, depth of discharges, temperatures, etc.). For this purpose, this study proposed to analyze voltage waveforms of cells obtained in cycling tests by using an unsupervised neural network, the Self-Organizing Map (SOM). In this work, a laboratory dataset of real Li-ion cells was used, and the SOM algorithm processed battery cell features, thus carrying out smart sensing of the battery. It was shown that our methodology differentiates the previous conditions of use (history) of a cell, complementing conventional metrics such as the state of health, which could be useful for the growing second-life market because it allows for determining more precisely the state of disease of a battery and assesses its suitability for a specific application.

Species information in whistle frequency modulation patterns of common dolphins

The most flexible communication systems are those of open-ended vocal learners that can acquire new signals throughout their lifetimes. While acoustic signals carry information in general voice features that affect all of an individual's vocalizations, vocal learners can also introduce novel call types to their repertoires. Delphinids are known for using such learned call types in individual recognition, but their role in other contexts is less clear. We investigated the whistles of two closely related, sympatric common dolphin species, Delphinus delphis and Delphinus bairdii , to evaluate species differences in whistle contours. Acoustic recordings of single-species groups were obtained from the Southern California Bight. We used an unsupervised neural network to categorize whistles and compared the resulting whistle types between species. Of the whistle types recorded in more than one encounter, 169 were shared between species and 60 were species-specific (32 D. delphis types, 28 D. bairdii types). Delphinus delphis used 15 whistle types with an oscillatory frequency contour while only one such type was found in D. bairdii . Given the role of vocal learning in delphinid vocalizations, we argue that these differences in whistle production are probably culturally driven and could help facilitate species recognition between Delphinus species. This article is part of the theme issue ‘Vocal learning in animals and humans’.

Bearing Defect Detection with Unsupervised Neural Networks

Bearings always suffer from surface defects, such as scratches, black spots, and pits. Those surface defects have great effects on the quality and service life of bearings. Therefore, the defect detection of the bearing has always been the focus of the bearing quality control. Deep learning has been successfully applied to the objection detection due to its excellent performance. However, it is difficult to realize automatic detection of bearing surface defects based on data-driven-based deep learning due to few samples data of bearing defects on the actual production line. Sample preprocessing algorithm based on normalized sample symmetry of bearing is adopted to greatly increase the number of samples. Two different convolutional neural networks, supervised networks and unsupervised networks, are tested separately for the bearing defect detection. The first experiment adopts the supervised networks, and ResNet neural networks are selected as the supervised networks in this experiment. The experiment result shows that the AUC of the model is 0.8567, which is low for the actual use. Also, the positive and negative samples should be labelled manually. To improve the AUC of the model and the flexibility of the samples labelling, a new unsupervised neural network based on autoencoder networks is proposed. Gradients of the unlabeled data are used as labels, and autoencoder networks are created with U-net to predict the output. In the second experiment, positive samples of the supervised experiment are used as the training set. The experiment of the unsupervised neural networks shows that the AUC of the model is 0.9721. In this experiment, the AUC is higher than the first experiment, but the positive samples must be selected. To overcome this shortage, the dataset of the third experiment is the same as the supervised experiment, where all the positive and negative samples are mixed together, which means that there is no need to label the samples. This experiment shows that the AUC of the model is 0.9623. Although the AUC is slightly lower than that of the second experiment, the AUC is high enough for actual use. The experiment results demonstrate the feasibility and superiority of the proposed unsupervised networks.