Large repositories of source code available over the Internet, or within large organizations, create new challenges and opportunities for data mining and statistical machine learning. Here we first develop Sourcerer, an infrastructure for the automated crawling, parsing, fingerprinting, and database storage of open source software on an Internet-scale. In one experiment, we gather 4,632 Java projects from SourceForge and Apache totaling over 38 million lines of code from 9,250 developers. Simple statistical analyses of the data first reveal robust power-law behavior for package, method call, and lexical containment distributions. We then develop and apply unsupervised, probabilistic, topic and author-topic (AT) models to automatically 123 Mining and searching internet-scale software repositories 301 discover the topics embedded in the code and extract topic-word, document-topic, and AT distributions. In addition to serving as a convenient summary for program function and developer activities, these and other related distributions provide a statistical and information-theoretic basis for quantifying and analyzing source file similarity, developer similarity and competence, topic scattering, and document tangling, with direct applications to software engineering an software development staffing. Finally, by combining software textual content with structural information captured by our CodeRank approach, we are able to significantly improve software retrieval performance, increasing the area under the curve (AUC) retrieval metric to 0.92-roughly 10-30% better than previous approaches based on text alone. A prototype of the system is available at: http://sourcerer.ics.uci.edu.

Implementing artificial neural networks is commonly achieved via high-level programming languages such as Python and easy-to-use deep learning libraries such as Keras. These software libraries come preloaded with a variety of network architectures, provide autodifferentiation, and support GPUs for fast and efficient computation. As a result, a deep learning practitioner will favor training a neural network model in Python, where these tools are readily available. However, many large-scale scientific computation projects are written in Fortran, making it difficult to integrate with modern deep learning methods. To alleviate this problem, we introduce a software library, the Fortran-Keras Bridge (FKB). This two-way bridge connects environments where deep learning resources are plentiful with those where they are scarce. The paper describes several unique features offered by FKB, such as customizable layers, loss functions, and network ensembles. The paper concludes with a case study that applies FKB to address open questions about the robustness of an experimental approach to global climate simulation, in which subgrid physics are outsourced to deep neural network emulators. In this context, FKB enables a hyperparameter search of one hundred plus candidate models of subgrid cloud and radiation physics, initially implemented in Keras, to be transferred and used in Fortran. Such a process allows the model’s emergent behavior to be assessed, i.e., when fit imperfections are coupled to explicit planetary-scale fluid dynamics. The results reveal a previously unrecognized strong relationship between offline validation error and online performance, in which the choice of the optimizer proves unexpectedly critical. This in turn reveals many new neural network architectures that produce considerable improvements in climate model stability including some with reduced error, for an especially challenging training dataset.

Supplementary data are available at Bioinformatics online.

Key Points Question How has opioid use in pediatric patients changed over the past 10 years, and what factors are associated with differences in opioid use? Findings A cross-sectional study of 69 152 emergency department visits found that opioid prescribing rates decreased between 2006 to 2010 (8.23%) and 2011 to 2015 (6.30%). Region, race, age, and payment method were associated with differences in opioid prescribing. Meaning Opioid rates have decreased in recent years but inconsistencies in prescribing continue, suggesting the need for further research.

Autism spectrum disorder (ASD) research has yet to leverage Bbig data^on the same scale as other fields; however, advancements in easy, affordable data collection and analysis may soon make this a reality. Indeed, there has been a notable increase in research literature evaluating the effectiveness of machine learning for diagnosing ASD, exploring its genetic underpinnings, and designing effective interventions. This paper provides a comprehensive review of 45 papers utilizing supervised machine learning in ASD, including algorithms for classification and text analysis. The goal of the paper is to identify and describe supervised machine learning trends in ASD literature as well as inform and guide researchers interested in expanding the body of clinically, computationally, and statistically sound approaches for mining ASD data.