Semi-supervised Machine Learning Methods Research Articles

Aerial photography and machine learning for estimating extremely high flamingo numbers on the Makgadikgadi Pans, Botswana

Monitoring biodiversity over time and space is essential for effective conservation of habitats, processes, and dependent organisms. Estimating large abundances of individuals can be challenging (e.g. birds and mammals), demanding efficient and effective methods. The Makgadikgadi Pans in north-eastern Botswana have high concentrations of breeding and feeding flamingos (Phoenicopterus roseus and Phoeniconaias minor), among the world’s most important breeding sites. No published estimates of flamingos exist since 2009, with historical estimates providing limited details on methods. We developed a semi-supervised machine learning method for counting a large feeding concentration of flamingos (2 June 2019) in aerial photographs from northern Sua Pan of the Makgadikgadi Pans. We also analysed rainfall and flooding frequency and extent, using satellite imagery, estimating likely frequency of these flamingo concentrations. Lastly, we reviewed the site’s global importance as flamingo breeding habitat. Our analysis successfully provided an estimate of 372,172 to 689,473 flamingos, with methods producing over 97 % test accuracy. Uncertainty related primarily to data coverage and collection rather than methodology. This estimate underlined the Makgadikgadi Pans’ significance for flamingos, supported by a high frequency of flooding (>5:10 years). Sua Pan ranked in the top ten breeding sites for the lesser and greater flamingos in the world. These methods can be applied to other large concentrations of flamingos and other animals. Our techniques provide considerable promise for tracking flamingo populations to ensure their protection. We provide code, for use in Google Earth Engine.

Semi-Supervised Machine Learning Method for Predicting Observed Individual Risk Preference Using Gallup Data

Risk and uncertainty play a vital role in almost every significant economic decision, and an individual’s propensity to make riskier decisions also depends on various circumstances. This article aims to investigate the effects of social and economic covariates on an individual’s willingness to take general risks and extends the scope of existing works by using quantitative measures of risk-taking from the GPS and Gallup datasets (in addition to the qualitative measures used in the literature). Based on the available observed risk-taking data for one year, this article proposes a semi-supervised machine learning-based approach that can efficiently predict the observed risk index for those countries/individuals for years when the observed risk-taking index was not collected. We find that linear models are insufficient to capture certain patterns among risk-taking factors, and non-linear models, such as random forest regression, can obtain better root mean squared values than those reported in past literature. In addition to finding factors that agree with past studies, we also find that subjective well-being influences risk-taking behavior.

IFLAS: positive-unlabeled learning facilitates full-length transcriptome-based identification and functional exploration of alternatively spliced isoforms in maize.

The advent of full-length transcriptome sequencing technologies has accelerated the discovery of novel splicing isoforms. However, existing alternative splicing (AS) tools are either tailored for short-read RNA-Seq data or designed for human and animal studies. The disparities in AS patterns between plants and animals still pose a challenge to the reliable identification and functional exploration of novel isoforms in plants. Here, we developed integrated full-length alternative splicing analysis (iFLAS), a plant-optimized AS toolkit that introduced a semi-supervised machine learning method known as positive-unlabeled (PU) learning to accurately identify novel isoforms. iFLAS also enables the investigation of AS functions from various perspectives, such as differential AS, poly(A) tail length, and allele-specific AS (ASAS) analyses. By applying iFLAS to three full-length transcriptome sequencing datasets, we systematically identified and functionally characterized maize (Zea mays) AS patterns. We found intron retention not only introduces premature termination codons, resulting in lower expression levels of isoforms, but may also regulate the length of 3'UTR and poly(A) tail, thereby affecting the functional differentiation of isoforms. Moreover, we observed distinct ASAS patterns in two genes within heterosis offspring, highlighting their potential value in breeding. These results underscore the broad applicability of iFLAS in plant full-length transcriptome-based AS research.

Analysis of SARS-CoV-2 transmission in airports based on real human close contact behaviors

The COVID-19 pandemic has significantly impacted people's daily lives for over three years. Airports, with their dense population and frequent close contact, pose a higher risk of respiratory infectious diseases compared to many other indoor environments. However, limited availability of data on close contact behavior has resulted in a gap in indoor exposure analysis. This study conducted depth sensor measurements and video data collection across nine areas of a northern (airport A) and a southern (airport B) airports in China by 11 participants. The data, comprising more than 44 h of close contact behaviors, including interpersonal distance, relative facial orientation, and the relative position of individuals, were analyzed using a semi-supervised machine learning method. Based on this analysis, a close contact transmission model for COVID-19 was developed, which considers the aforementioned close contact behaviors to assess the risk of exposure and the efficacy of interventions. The average close contact ratio in 9 airport's areas is 25.4 % (ranging from 6.1 % to 55.0 %), with passengers having the highest frequency of close contact in manual check-in areas. During close contacts, the average interpersonal distance in airports is 1.2 m (ranging from 1.1 to 1.4 m), being shortest in boarding areas. Face-to-face close contact is highest in charging areas, with a percentage of 46.9 %. If people maintain a distance of over 1.0 m in all areas, the total virus exposure could be reduced by 6.9 %–22.0 % compared to the actual situation. Dining areas have the highest virus exposure risk for both short-range inhalation and mucosal deposition, followed by manual check-in areas. This study provides a data support for the scientific epidemic prevention and control in airports from the viewpoint of close contact behaviors.

EPCO-34. IMAGE-BASED PHENOTYPIC HIGH-CONTENT CRISPR-CAS9 SCREEN FOR CHARACTERIZING CANCER DRIVERS IN PEDIATRIC HIGH-GRADE GLIOMA

Abstract The genomic landscape of pediatric high-grade glioma is characterized by a high level of aneuploidy but few focal amplifications or homozygous deletions. Cancer aneuploidies are the principal source of tumor heterogeneity driving tumor growth and therapy resistance. Here, we deployed an image-based phenotypic high-content CRISPR-Cas9 screen to identify aneuploidy-associated pediatric glioma driver genes. Through integrated computational analyses combining whole-genome sequencing datasets from 106 pediatric gliomas and 81 canine gliomas, we identified a set of 460 genes present in regions of aneuploidy in both diseases. We designed a custom guideRNA library to systemically knockout the 460 gene set using an arrayed CRISPR-Cas9 knockout screen in two pediatric high-grade glioma cell lines. By deploying 72 of 384-well plates on automated confocal Opera Phenix High-Content Screening System and dyes staining cell membrane, nucleus, and apoptotic cells, we established 5 million live-cell images across three timepoints (day 7, 8, 9 post-transduction). Each gene was randomized to 32 randomized wells across four 384-well plates to gather robust morphological profiles. Through image-based nucleus and cell segmentation workflow, we characterized 50 million single cells across 27,648 wells over three time points. Using semi-supervised machine learning methods, we derived 1,050 cell morphological features to characterize knockout phenotypes, e.g., viability, growth, and morphology (size, shape, texture of nucleus and cells) across cells. The top ranked genes were then linked to oncogenes and tumor suppressors based on pathway and ontology analysis as well as functional in vitro and in silico validation using Pediatric Cancer Dependency Map. We find convergence of the most impactful molecular abnormalities - based on their knockout phenotypes - on candidate signaling pathways for the development of new drugs and repurposing of existing drugs for pediatric high-grade glioma.

Decoding structure-spectrum relationships with physically organized latent spaces

A new semi-supervised machine learning method for the discovery of structure-spectrum relationships is developed and demonstrated using the specific example of interpreting X-ray absorption near-edge structure (XANES) spectra. This method constructs a one-to-one mapping between individual structure descriptors and spectral trends. Specifically, an adversarial autoencoder is augmented with a novel rank constraint (RankAAE). The RankAAE methodology produces a continuous and interpretable latent space, where each dimension can track an individual structure descriptor. As a part of this process, the model provides a robust and quantitative measure of the structure-spectrum relationship by decoupling intertwined spectral contributions from multiple structural characteristics. This makes it ideal for spectral interpretation and the discovery of new descriptors. The capability of this procedure is showcased by considering five local structure descriptors and a database of over fifty thousand simulated XANES spectra across eight first-row transition metal oxide families. The resulting structure-spectrum relationships not only reproduce known trends in the literature, but also reveal unintuitive ones that are visually indiscernible in large data sets. The results suggest that the RankAAE methodology has great potential to assist researchers to interpret complex scientific data, test physical hypotheses, and reveal new patterns that extend scientific insight.

Fleet Management IoT

The Internet of Things (IoT) and big data have become popular subjects in recent years. New applications, like predictive maintenance, are possible with all this data being created. For a fleet of public transportation buses, consensus self-organized models approach (COSMO) is an illustration of a predictive maintenance system that aims to identify malfunctioning buses that diverge from the rest of the fleet. The current work suggests an innovative IoT architecture for preventative maintenance and a semi-supervised machine learning method that aims to enhance the COSMO sensor selection process. Fleet maintenance is a crucial exposure to improve availability in fleet management. One such important factor that is taken into account regardless of the actual flaws sets up the need for repair and replacement costs as well as the time associated with them. This is periodic and preventative maintenance. As technology has advanced, IOT and big data have been discussed. With all the data being generated, this system can be used for predictive maintenance. Through better maintenance planning and the elimination of pointless maintenance jobs, IOT-based predictive maintenance can improve fleet availability, stability, and efficiency.

Assessment of Neuroanatomical Endophenotypes of Autism Spectrum Disorder and Association With Characteristics of Individuals With Schizophrenia and the General Population

Autism spectrum disorder (ASD) is associated with significant clinical, neuroanatomical, and genetic heterogeneity that limits precision diagnostics and treatment. To assess distinct neuroanatomical dimensions of ASD using novel semisupervised machine learning methods and to test whether the dimensions can serve as endophenotypes also in non-ASD populations. This cross-sectional study used imaging data from the publicly available Autism Brain Imaging Data Exchange (ABIDE) repositories as the discovery cohort. The ABIDE sample included individuals diagnosed with ASD aged between 16 and 64 years and age- and sex-match typically developing individuals. Validation cohorts included individuals with schizophrenia from the Psychosis Heterogeneity Evaluated via Dimensional Neuroimaging (PHENOM) consortium and individuals from the UK Biobank to represent the general population. The multisite discovery cohort included 16 internationally distributed imaging sites. Analyses were performed between March 2021 and March 2022. The trained semisupervised heterogeneity through discriminative analysis models were tested for reproducibility using extensive cross-validations. It was then applied to individuals from the PHENOM and the UK Biobank. It was hypothesized that neuroanatomical dimensions of ASD would display distinct clinical and genetic profiles and would be prominent also in non-ASD populations. Heterogeneity through discriminative analysis models trained on T1-weighted brain magnetic resonance images of 307 individuals with ASD (mean [SD] age, 25.4 [9.8] years; 273 [88.9%] male) and 362 typically developing control individuals (mean [SD] age, 25.8 [8.9] years; 309 [85.4%] male) revealed that a 3-dimensional scheme was optimal to capture the ASD neuroanatomy. The first dimension (A1: aginglike) was associated with smaller brain volume, lower cognitive function, and aging-related genetic variants (FOXO3; Z = 4.65; P = 1.62 × 10-6). The second dimension (A2: schizophrenialike) was characterized by enlarged subcortical volumes, antipsychotic medication use (Cohen d = 0.65; false discovery rate-adjusted P = .048), partially overlapping genetic, neuroanatomical characteristics to schizophrenia (n = 307), and significant genetic heritability estimates in the general population (n = 14 786; mean [SD] h2, 0.71 [0.04]; P < 1 × 10-4). The third dimension (A3: typical ASD) was distinguished by enlarged cortical volumes, high nonverbal cognitive performance, and biological pathways implicating brain development and abnormal apoptosis (mean [SD] β, 0.83 [0.02]; P = 4.22 × 10-6). This cross-sectional study discovered 3-dimensional endophenotypic representation that may elucidate the heterogeneous neurobiological underpinnings of ASD to support precision diagnostics. The significant correspondence between A2 and schizophrenia indicates a possibility of identifying common biological mechanisms across the 2 mental health diagnoses.

Semi-Supervised Behavior Labeling Using Multimodal Data during Virtual Teamwork-Based Collaborative Activities

Adaptive human-computer systems require the recognition of human behavior states to provide real-time feedback to scaffold skill learning. These systems are being researched extensively for intervention and training in individuals with autism spectrum disorder (ASD). Autistic individuals are prone to social communication and behavioral differences that contribute to their high rate of unemployment. Teamwork training, which is beneficial for all people, can be a pivotal step in securing employment for these individuals. To broaden the reach of the training, virtual reality is a good option. However, adaptive virtual reality systems require real-time detection of behavior. Manual labeling of data is time-consuming and resource-intensive, making automated data annotation essential. In this paper, we propose a semi-supervised machine learning method to supplement manual data labeling of multimodal data in a collaborative virtual environment (CVE) used to train teamwork skills. With as little as 2.5% of the data manually labeled, the proposed semi-supervised learning model predicted labels for the remaining unlabeled data with an average accuracy of 81.3%, validating the use of semi-supervised learning to predict human behavior.

AI-based dimensional neuroimaging system for characterizing heterogeneity in brain structure and function in major depressive disorder: COORDINATE-MDD consortium design and rationale

BackgroundEfforts to develop neuroimaging-based biomarkers in major depressive disorder (MDD), at the individual level, have been limited to date. As diagnostic criteria are currently symptom-based, MDD is conceptualized as a disorder rather than a disease with a known etiology; further, neural measures are often confounded by medication status and heterogeneous symptom states.MethodsWe describe a consortium to quantify neuroanatomical and neurofunctional heterogeneity via the dimensions of novel multivariate coordinate system (COORDINATE-MDD). Utilizing imaging harmonization and machine learning methods in a large cohort of medication-free, deeply phenotyped MDD participants, patterns of brain alteration are defined in replicable and neurobiologically-based dimensions and offer the potential to predict treatment response at the individual level.International datasets are being shared from multi-ethnic community populations, first episode and recurrent MDD, which are medication-free, in a current depressive episode with prospective longitudinal treatment outcomes and in remission. Neuroimaging data consist of de-identified, individual, structural MRI and resting-state functional MRI with additional positron emission tomography (PET) data at specific sites. State-of-the-art analytic methods include automated image processing for extraction of anatomical and functional imaging variables, statistical harmonization of imaging variables to account for site and scanner variations, and semi-supervised machine learning methods that identify dominant patterns associated with MDD from neural structure and function in healthy participants.ResultsWe are applying an iterative process by defining the neural dimensions that characterise deeply phenotyped samples and then testing the dimensions in novel samples to assess specificity and reliability. Crucially, we aim to use machine learning methods to identify novel predictors of treatment response based on prospective longitudinal treatment outcome data, and we can externally validate the dimensions in fully independent sites.ConclusionWe describe the consortium, imaging protocols and analytics using preliminary results. Our findings thus far demonstrate how datasets across many sites can be harmonized and constructively pooled to enable execution of this large-scale project.

Recently Emerged Genome Wide Computational Enhancer Target Prediction Tools: A Brief Survey

Enhancers are non-coding genomic regulatory elements capable of elevating gene transcription in various biological as well as developmental stages in the host organism. Discovered since 1981, the enhancers play major roles in genetic disease onset and development, orchestrating gene regulation patterns even across the same species via the sequence variations. To date, predicting enhancers and their targets remain a daunting task as universal enhancer markers are yet to be discovered. Computational enhancer target prediction involves three major approaches: supervised, unsupervised and semi-supervised machine learning methods which work on enhancer target features such as enhancer-promoter distance, closest promoter, co-conservation and correlation of molecular signals. In this review, we introduced some recently emerged enhancer target prediction tools as well as their modus operandi, in hope that we can provide future directions towards the development of a more robust tool to aid in the advancement of enhancer targeted treatment researches.

Anomaly detection of communication link of mobile internet of things based on EM algorithm

The abnormality of communication link of mobile Internet of Things will threaten the security of communication of mobile Internet of Things, and the existing abnormality detection method is limited due to low accuracy, long time consumption and high energy consumption. To this end, the anomaly detection method of communication link of mobile Internet of Things based on EM algorithm is proposed in this study. Firstly, the anomaly range of the Internet of Things is located according to the communication node information of the data changes. Then the abnormal link of the target is judged and the anomaly feature of the communication link of the Internet of Things based on twin neural network is extracted. Finally, EM algorithm is improved with semi-supervised machine learning method to detect abnormal communication links of mobile Internet of Things. The experimental results show that the proposed method has the advantages of high precision, short time consumption and low energy consumption in the anomaly detection of communication links in the Internet of Things.

Geostatistical semi-supervised learning for spatial prediction

Geoscientists are increasingly tasked with spatially predicting a target variable in the presence of auxiliary information using supervised machine learning algorithms. Typically, the target variable is observed at a few sampling locations due to the relatively time-consuming and costly process of obtaining measurements. In contrast, auxiliary variables are often exhaustively observed within the region under study through the increasing development of remote sensing platforms and sensor networks. Supervised machine learning methods do not fully leverage this large amount of auxiliary spatial data. Indeed, in these methods, the training dataset includes only labeled data locations (where both target and auxiliary variables were measured). At the same time, unlabeled data locations (where auxiliary variables were measured but not the target variable) are not considered during the model training phase. Consequently, only a limited amount of auxiliary spatial data is utilized during the model training stage. As an alternative to supervised learning, semi-supervised learning, which learns from labeled as well as unlabeled data, can be used to address this problem. However, conventional semi-supervised learning techniques do not account for the specificities of spatial data. This paper introduces a spatial semi-supervised learning framework where geostatistics and machine learning are combined to harness a large amount of unlabeled spatial data in combination with typically a smaller set of labeled spatial data. The main idea consists of leveraging the target variable’s spatial autocorrelation to generate pseudo labels at unlabeled data points that are geographically close to labeled data points. This is achieved through geostatistical conditional simulation, where an ensemble of pseudo labels is generated to account for the uncertainty in the pseudo labeling process. The observed labels are augmented by this ensemble of pseudo labels to create an ensemble of pseudo training datasets. A supervised machine learning model is then trained on each pseudo training dataset, followed by an aggregation of trained models. The proposed geostatistical semi-supervised learning method is applied to synthetic and real-world spatial datasets. Its predictive performance is compared with some classical supervised and semi-supervised machine learning methods. It appears that it can effectively leverage a large amount of unlabeled spatial data to improve the target variable’s spatial prediction.

Machine learning-based direct solver for one-to-many problems on temporal shaping of relativistic electron beams

To control the temporal profile of a relativistic electron beam to meet requirements of various advanced scientific applications like free-electron-laser and plasma wakefield acceleration, a widely-used technique is to manipulate the dispersion terms which turns out to be one-to-many problems. Due to their intrinsic one-to-many property, current popular stochastic optimization approaches on temporal shaping may face the problems of long computing time or sometimes suggesting only one solution. Here we propose a real-time solver for one-to-many problems of temporal shaping, with the aid of a semi-supervised machine learning method, the conditional generative adversarial network (CGAN). We demonstrate that the CGAN solver can learn the one-to-many dynamics and is able to accurately and quickly predict the required dispersion terms for different custom temporal profiles. This machine learning-based solver is expected to have the potential for wide applications to one-to-many problems in other scientific fields.

Abstract 3106: Identifying drivers in the converging syntenic aneuploidies of spontaneous canine and pediatric high-grade glioma using imaging-based an arrayed CRISPR-Cas9 phenotypic screen

Abstract Gliomas occur in companion dogs at rates comparable to humans, with short-snouted breeds such as boxers being more susceptible than others. The natural progression of cancer in the immuno-competent host allows companion dogs diagnosed with sporadic glioma as an optimal model for preclinical testing of therapeutic approaches with human relevance, including immunotherapies. We have recently performed comprehensive genomic and epigenetic characterization of glioma in dogs to their human counterparts and found strong convergent evolution - shared somatic mutations and aneuploidies - among syntenic regions, including those of known pediatric glioma drivers, e.g., PDGFRA, MYC, PIK3CA. Here, using arrayed CRISPR-Cas9 imaging based phenotypic screen, we will probe potential oncogenic drivers and tumor suppressor genes within syntenic aneuploidies and thus outline functional versus non-functional heterogeneity of cancer aneuploidy. Specifically, we are conducting arrayed knockout screen (one gene per well) of 400+ genes within syntenic aneuploidies across primary cultured cells of canine glioma (n=2) and pediatric high-grade glioma cell lines (n=2). We will first capture images by high-speed confocal imaging system at three time points post-transduction of single guide RNAs (2 per gene) targeting each of 400+ genes in their separate wells. Then, using high-throughput image analysis and semi-supervised machine learning methods, we will measure well-based phenotypic features (viability, growth, and morphology) from these images. Genes will be ranked per cross-validated predicted probability in yielding either proliferating or slow-growing cell type based on learned phenotypic features using image data of knockout cells from and across wells. The top ranked genes will then be linked to oncogenes and tumor suppressors based on pathway and ontology analysis as well as further functional in vitro and in vivo (PDX) validation. We expect to find convergence of the most impactful molecular abnormalities (based on their knockout phenotypes) on candidate signaling pathways for the development of new drugs and repurposing of existing drugs for children and dogs with high-grade glioma. Citation Format: Samirkumar B. Amin, Amit Gujar, Eunhee Yi, Wonyeong Kang, Megan Costa, Greg Sjogren, Paul Gabriel, Leigh Maher, Peter Dickinson, Rebecca Packer, Elise Courtois, Paul Robson, Charles Lee, Roel Verhaak. Identifying drivers in the converging syntenic aneuploidies of spontaneous canine and pediatric high-grade glioma using imaging-based an arrayed CRISPR-Cas9 phenotypic screen [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 3106.

Machine learning-assisted high-throughput exploration of interface energy space in multi-phase-field model with CALPHAD potential

Computational methods are increasingly being incorporated into the exploitation of microstructure–property relationships for microstructure-sensitive design of materials. In the present work, we propose non-intrusive materials informatics methods for the high-throughput exploration and analysis of a synthetic microstructure space using a machine learning-reinforced multi-phase-field modeling scheme. We specifically study the interface energy space as one of the most uncertain inputs in phase-field modeling and its impact on the shape and contact angle of a growing phase during heterogeneous solidification of secondary phase between solid and liquid phases. We evaluate and discuss methods for the study of sensitivity and propagation of uncertainty in these input parameters as reflected on the shape of the Cu6Sn5 intermetallic during growth over the Cu substrate inside the liquid Sn solder due to uncertain interface energies. The sensitivity results rank σSI,σIL, and σIL, respectively, as the most influential parameters on the shape of the intermetallic. Furthermore, we use variational autoencoder, a deep generative neural network method, and label spreading, a semi-supervised machine learning method for establishing correlations between inputs of outputs of the computational model. We clustered the microstructures into three categories (“wetting”, “dewetting”, and “invariant”) using the label spreading method and compared it with the trend observed in the Young-Laplace equation. On the other hand, a structure map in the interface energy space is developed that shows σSI and σSL alter the shape of the intermetallic synchronously where an increase in the latter and decrease in the former changes the shape from dewetting structures to wetting structures. The study shows that the machine learning-reinforced phase-field method is a convenient approach to analyze microstructure design space in the framework of the ICME.

TMOD-13. IDENTIFYING DRIVERS IN THE CONVERGING SYNTENIC REGIONS OF SPONTANEOUS CANINE AND PEDIATRIC HIGH-GRADE GLIOMA USING IMAGING BASED CRISPR-CAS9 ARRAY SCREEN

Abstract Gliomas occur in companion dogs at rates comparable to humans, with short-snouted breeds such as boxers being more susceptible than others. The natural progression of cancer in the immuno-competent host allows companion dogs diagnosed with sporadic glioma as an optimal model for preclinical testing of therapeutic approaches with human relevance, including immunotherapies. We have recently performed comprehensive genomic and epigenetic characterization of glioma in dogs to their human counterparts and found strong convergent evolution – shared somatic mutations and aneuploidies - among syntenic regions, including those of known pediatric glioma drivers, e.g., PDGFRA, MYC, PIK3CA. Here, using arrayed CRISPR-Cas9 imaging based phenotypic screen, we will probe potential oncogenic drivers and tumor suppressor genes within syntenic aneuploidies and thus outline functional versus non-functional heterogeneity of cancer aneuploidy. Specifically, we are conducting arrayed knockout screen (one gene per well) of 400+ genes within syntenic aneuploidies across canine (n=2) and pediatric (n=2) high-grade glioma cell lines. We will first capture images by high-speed confocal imaging system at three time points post-transduction of single guide RNAs (2 per gene) targeting each of 400+ genes in their separate wells. Then, using high-throughput image analysis and semi-supervised machine learning methods, we will measure well-based phenotypic features (viability, growth, and morphology) from these images. Genes will be ranked per cross-validated predicted probability in yielding either proliferating or slow-growing cell type based on learned phenotypic features using image data of knockout cells from and across wells. The top ranked genes will then be linked to oncogenes and tumor suppressors based on pathway and ontology analysis. We expect that we will see convergence of the most impactful molecular abnormalities (based on their knockout phenotypes) on mechanisms or candidate signaling pathways for the development of new drugs and repurposing of existing drugs for kids and dogs with high-grade glioma.

Semi-Supervised Classification of the State of Operation in Self-Lubricating Journal Bearings Using a Random Forest Classifier

For a tribological experiment involving a steel shaft sliding in a self-lubricating bronze bearing, a semi-supervised machine learning method for the classification of the state of operation is proposed. During the translatory oscillating motion, the system may undergo different states of operation from normal to critical, showing self-recovering behaviour. A Random Forest classifier was trained on individual cycles from the lateral force data from four distinct experimental runs in order to distinguish between four states of operation. The labelling of the individual cycles proved to be crucial for a high prediction accuracy of the trained RF classifier. The proposed semi-supervised approach allows choosing within a range between automatically generated labels and full manual labelling by an expert user. The algorithm was at the current state used for ex post classification of the state of operation. Considering the results from the ex post analysis and providing a sufficiently sized training dataset, online classification of the state of operation of a system will be possible. This will allow taking active countermeasures to stabilise the system or to terminate the experiment before major damage occurs.

Learning-based defect recognition for quasi-periodic HRSTEM images

Controlling crystalline material defects is crucial, as they affect properties of the material that may be detrimental or beneficial for the final performance of a device. Defect analysis on the sub-nanometer scale is enabled by high-resolution scanning transmission electron microscopy (HRSTEM), where the identification of defects is currently carried out based on human expertise. However, the process is tedious, highly time consuming and, in some cases, yields ambiguous results. Here we propose a semi-supervised machine learning method that assists in the detection of lattice defects from atomic resolution HRSTEM images. It involves a convolutional neural network that classifies image patches as defective or non-defective, a graph-based heuristic that chooses one non-defective patch as a model, and finally an automatically generated convolutional filter bank, which highlights symmetry breaking such as stacking faults, twin defects and grain boundaries. Additionally, we suggest a variance filter to segment amorphous regions and beam defects. The algorithm is tested on III–V/Si crystalline materials and successfully evaluated against different metrics and a baseline approach, showing promising results even for extremely small training data sets and for noise compromised images. By combining the data-driven classification generality, robustness and speed of deep learning with the effectiveness of image filters in segmenting faulty symmetry arrangements, we provide a valuable open-source tool to the microscopist community that can streamline future HRSTEM analyses of crystalline materials.

Spam review detection using self-organizing maps and convolutional neural networks

Online public reviews have significant influenced customers who purchase products or seek services. Fake reviews are posted online to promote or demote targeted products or reputation of the organizations and businesses. Spam review detection has been the focus of many researchers in recent years. As the online services have been growing rapidly, the importance of the issue is ever increasing and needs to be addressed properly. In this regard, there is a variety of approaches that have been introduced to distinguish truthful reviews from the fake ones. The main features engineered in the past studies typically involve two types of linguistic-based and behavioral-based characteristics of the reviews. Unsupervised, supervised and semi-supervised machine learning methods have been widely utilized to perform such a classification. This paper introduces a novel approach to detect fake reviews from the genuine ones using linguistic features. Unsupervised learning via self-organizing maps (SOM) in conjunction with a convolutional neural networks (CNN) are employed to perform classification of the reviews. We transform the reviews into images by arranging semantically-similar words around a pixel of the image or equivalently a SOM grid cell. The resulting review images are consequently fed to the CNN for supervised training and then classification. Comprehensive tests on two gold-standard datasets show the effectiveness of the proposed method on single and multi-domain contexts with accuracy of 88% and 87%, respectively.