Accurate prediction of crop yield supported by scientific and domain-relevant insights, is useful to improve agricultural breeding, provide monitoring across diverse climatic conditions and thereby protect against climatic challenges to crop production. We used performance records from Uniform Soybean Tests (UST) in North America to build a Long Short Term Memory (LSTM)—Recurrent Neural Network based model that leveraged pedigree relatedness measures along with weekly weather parameters to dissect and predict genotype response in multiple-environments. Our proposed models outperformed other competing machine learning models such as Support Vector Regression with Radial Basis Function kernel (SVR-RBF), least absolute shrinkage and selection operator (LASSO) regression and the data-driven USDA model for yield prediction. Additionally, for providing interpretability of the important time-windows in the growing season, we developed a temporal attention mechanism for LSTM models. The outputs of such interpretable models could provide valuable insights to plant breeders.

No abstract

BackgroundShort read DNA sequencing technologies have revolutionized genome assembly by providing high accuracy and throughput data at low cost. But it remains challenging to assemble short read data, particularly for large, complex and polyploid genomes. The linked read strategy has the potential to enhance the value of short reads for genome assembly because all reads originating from a single long molecule of DNA share a common barcode. However, the majority of studies to date that have employed linked reads were focused on human haplotype phasing and genome assembly.ResultsHere we describe a de novo maize B73 genome assembly generated via linked read technology which contains ~ 172,000 scaffolds with an N50 of 89 kb that cover 50% of the genome. Based on comparisons to the B73 reference genome, 91% of linked read contigs are accurately assembled. Because it was possible to identify errors with > 76% accuracy using machine learning, it may be possible to identify and potentially correct systematic errors. Complex polyploids represent one of the last grand challenges in genome assembly. Linked read technology was able to successfully resolve the two subgenomes of the recent allopolyploid, proso millet (Panicum miliaceum). Our assembly covers ~ 83% of the 1 Gb genome and consists of 30,819 scaffolds with an N50 of 912 kb.ConclusionsOur analysis provides a framework for future de novo genome assemblies using linked reads, and we suggest computational strategies that if implemented have the potential to further improve linked read assemblies, particularly for repetitive genomes.Electronic supplementary materialThe online version of this article (10.1186/s12864-018-5040-z) contains supplementary material, which is available to authorized users.

Accurate traffic sensor data is essential for traffic operation management systems and acquisition of real-time traffic surveillance data depends heavily on the reliability of the traffic sensors (e.g., wide range detector, automatic traffic recorder). Therefore, detecting the health status of the sensors in a traffic sensor network is critical for the departments of transportation as well as other public and private entities, especially in the circumstances where real-time decision is required. With the purpose of efficiently determining the sensor health status and identifying the failed sensor(s) in a timely manner, this paper proposes a graphical modeling approach called spatiotemporal pattern network (STPN). Traffic speed and volume measurement sensors are used in this paper to formulate and analyze the proposed sensor health monitoring system and historical time-series data from a network of traffic sensors on the Interstate 35 (I-35) within the state of Iowa is used for validation. Based on the validation results, we demonstrate that the proposed approach can: (i) extract spatiotemporal dependencies among the different sensors which leads to an efficient graphical representation of the sensor network in the information space, and (ii) distinguish and quantify a sensor issue by leveraging the extracted spatiotemporal relationship of the candidate sensor(s) to the other sensors in the network.