Search

Over a decade ago, NASA launched the Kepler Space Telescope in order to find earth-like planets revolving around sun-like stars in the hopes of finding habitable exoplanets. The Kepler pipeline picked up data for over 9000 astronomical bodies, out of which 52% were determined to be false positives, while the remaining 48% were candidates to be classified as exoplanets. The data collected from this mission can be used to assess and automatically classify Kepler Objects of Interest (KOIs) as exoplanets or false positives. Our goal in this work is to determine if some data features are more important than others in classifying an object as an exoplanet. To this end, we built 5 Machine Learning classification models (namely, logistic regression, support vector classifier, gradient boosting classifier, random forest classifier, and multilayer perceptron) and used 15 features to train and test them. We have included Machine Learning models that are explainable to help attain our goal, Our best predictor (random forests) achieved a prediction accuracy of 99% when evaluated with k-fold cross-validation. We evaluated the feature importances of our model and found that 5 of the features (Not Transit-like Flag, Centroid Offset Flag, Stellar Eclipse Flag, Ephemeris Match Indicate Contamination Flag, and Planetary Radius) out of the 15 selected ones make up roughly 75% of the overall feature importances. We hope that our findings can guide the selection of appropriate data to accurately predict exoplanet candidacy for future missions.

External factors, such as social media and financial news, can have wide-spread effects on stock price movement. For this reason, social media is considered a useful resource for precise market predictions. In this paper, we show the effectiveness of using Twitter posts to predict stock prices. We start by training various models on the Sentiment 140 Twitter data. We found that Support Vector Machines (SVM) performed best (0.83 accuracy) in the sentimental analysis, so we used it to predict the average sentiment of tweets for each day that the market was open. Next, we use the sentimental analysis of one year’s data of tweets that contain the “stock market”, “stocktwits”, “AAPL” keywords, with the goal of predicting the corresponding stock prices of Apple Inc. (AAPL) and the US’s Dow Jones Industrial Average (DJIA) index prices. Two models, Boosted Regression Trees and Multilayer Perceptron Neural Networks were used to predict the closing price difference of AAPL and DJIA prices. We show that neural networks perform substantially better than traditional models for stocks’ price prediction.

Contiguous genes in prokaryotes are often arranged into operons. Detecting operons plays a critical role in inferring gene functionality and regulatory networks. Human experts annotate operons by visually inspecting gene neighborhoods across pileups of related genomes. These visual representations capture the inter-genic distance, strand direction, gene size, functional relatedness, and gene neighborhood conservation, which are the most prominent operon features mentioned in the literature. By studying these features, an expert can then decide whether a genomic region is part of an operon. We propose a deep learning based method named Operon Hunter that uses visual representations of genomic fragments to make operon predictions. Using transfer learning and data augmentation techniques facilitates leveraging the powerful neural networks trained on image datasets by re-training them on a more limited dataset of extensively validated operons. Our method outperforms the previously reported state-of-the-art tools, especially when it comes to predicting full operons and their boundaries accurately. Furthermore, our approach makes it possible to visually identify the features influencing the network’s decisions to be subsequently cross-checked by human experts.

The Pathosystems Resource Integration Center (PATRIC, www.patricbrc.org) is designed to provide researchers with the tools and services that they need to perform genomic and other ‘omic’ data analyses. In response to mounting concern over antimicrobial resistance (AMR), the PATRIC team has been developing new tools that help researchers understand AMR and its genetic determinants. To support comparative analyses, we have added AMR phenotype data to over 15 000 genomes in the PATRIC database, often assembling genomes from reads in public archives and collecting their associated AMR panel data from the literature to augment the collection. We have also been using this collection of AMR metadata to build machine learning-based classifiers that can predict the AMR phenotypes and the genomic regions associated with resistance for genomes being submitted to the annotation service. Likewise, we have undertaken a large AMR protein annotation effort by manually curating data from the literature and public repositories. This collection of 7370 AMR reference proteins, which contains many protein annotations (functional roles) that are unique to PATRIC and RAST, has been manually curated so that it projects stably across genomes. The collection currently projects to 1 610 744 proteins in the PATRIC database. Finally, the PATRIC Web site has been expanded to enable AMR-based custom page views so that researchers can easily explore AMR data and design experiments based on whole genomes or individual genes.

Background Horizontal gene transfer is the main source of adaptability for bacteria, through which genes are obtained from different sources including bacteria, archaea, viruses, and eukaryotes. This process promotes the rapid spread of genetic information across lineages, typically in the form of clusters of genes referred to as genomic islands (GIs). Different types of GIs exist, and are often classified by the content of their cargo genes or their means of integration and mobility. While various computational methods have been devised to detect different types of GIs, no single method is capable of detecting all types. Results We propose a method, which we call Shutter Island, that uses a deep learning model (Inception V3, widely used in computer vision) to detect genomic islands. The intrinsic value of deep learning methods lies in their ability to generalize. Via a technique called transfer learning, the model is pre-trained on a large generic dataset and then re-trained on images that we generate to represent genomic fragments. We demonstrate that this image-based approach generalizes better than the existing tools. Conclusions We used a deep neural network and an image-based approach to detect the most out of the correct GI predictions made by other tools, in addition to making novel GI predictions. The fact that the deep neural network was re-trained on only a limited number of GI datasets and then successfully generalized indicates that this approach could be applied to other problems in the field where data is still lacking or hard to curate.

The Pathosystems Resource Integration Center (PATRIC) is the bacterial Bioinformatics Resource Center (https://www.patricbrc.org). Recent changes to PATRIC include a redesign of the web interface and some new services that provide users with a platform that takes them from raw reads to an integrated analysis experience. The redesigned interface allows researchers direct access to tools and data, and the emphasis has changed to user- created genome-groups, with detailed summaries and views of the data that researchers have selected. Perhaps the biggest change has been the enhanced capability for researchers to analyze their private data and compare it to the available public data. Researchers can assemble their raw sequence reads and annotate the contigs using RASTtk. PATRIC also provides services for RNA-Seq, variation, model reconstruction and differential expression analysis, all delivered through an updated private workspace. Private data can be compared by `virtual integration' to any of PATRIC's public data. The number of genomes available for comparison in PATRIC has expanded to over 80 000, with a special emphasis on genomes with antimicrobial resistance data. PATRIC uses this data to improve both subsystem annotation and k-mer classification, and tags new genomes as having signatures that indicate susceptibility or resistance to specific antibiotics. National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services [HHSN272201400027C] PATRIC has been funded in whole or in part with Federal funds from the National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services [HHSN272201400027C]. Funding for open access charge: Federal funds from the National Institute of Allergy and Infectious Diseases, National Institutes of Health, Department of Health and Human Services [HHSN272201400027C].

The rapidly evolving CUDA environment is well suited for numerical integration of high dimensional integrals, in particular by Monte Carlo or quasi-Monte Carlo methods. With some care, near peak performance can be obtained on important applications. A basis for efficient numerical integration using using CUDA kernels on NVIDIA GPUs is presented, showing several ways to use CUDA features, provide automatic error control and prevention or detection of roundoff errors. This framework allows easy extension to multiple GPUs, clusters and clouds for addressing problems that were impractical to attack in the past, and is the basis for an update to the ParInt numerical integration package.

Feynman loop integrals appear in higher order corrections of interaction cross section calculations in perturbative quantum field theory. The integrals are computationally intensive especially in view of singularities which may occur within the integration domain. For the treatment of threshold and infrared singularities we developed techniques using iterated (repeated) adaptive integration and extrapolation. In this paper we describe a shared memory parallelization and its application to one- and two-loop problems, by multi-threading in the outer integrations of the iterated integral. The implementation is layered over OpenMP and retains the adaptive procedure of the sequential method exactly. We give performance results for loop integrals associated with various types of diagrams including one-loop box, pentagon, two-loop self-energy and two-loop vertex diagrams.