No abstract

No abstract

A major challenge for food security worldwide is the large inter-annual variability of crop yield, and climate change is expected to further exacerbate this volatility. Accurate prediction of the crop response to climate variability and change is critical for short-term management and long-term planning in multiple sectors. In this study, using maize in the U.S. Corn Belt as an example, we train and validate multiple machine learning (ML) models predicting crop yield based on meteorological variables and soil properties using the leaving-one-year-out approach, and compare their performance with that of a widely used process-based crop model (PBM). Our proposed Long Short-Term Memory model with attention (LSTMatt) outperforms other ML models (including other variations of LSTM developed in this study), and explains 73% of the spatiotemporal variance of the observed maize yield, in contrast to 16% explained by the regionally calibrated PBM; the magnitude of yield prediction errors in LSTMatt is about one-third of that in the PBM. When applied to the extreme drought year 2012 that has no counterpart in the training data, the LSTMatt performance drops but still shows advantage over the PBM. Findings from this study suggest a great potential for out-of-sample application of the 𝐿𝑆𝑇𝑀𝑎𝑡𝑡 model to predict crop yieldunder a changing climate.

Surface modification techniques are often used to enhance the properties of Ti‐based materials as hard‐tissue replacements. While the microstructure of the coating and the quality of the interface between the substrate and coating are essential to evaluate the reliability and applicability of the surface modification. In this study, both a hydroxyapatite (HA) coating and a collagen‐hydroxyapatite (Col‐HA) composite coating were deposited onto a Ti‐6Al‐4V substrate using a biomimetic coating process. Importantly, a gradient cross‐sectional structure with a porous coating toward the surface, while a dense layer adjacent to the interface between the coating and substrate was observed in three‐dimensional (3D) from both the HA and Col‐HA coatings via a dual‐beam focused ion beam‐scanning electron microscope (FIB‐SEM). Moreover, the pore distributions within the entire coatings were reconstructed in 3D using Avizo, and the pores size distributions along the coating depth were calculated using RStudio. By evaluating the mechanical property and biocompatibility of these materials and closely observing the cross‐sectional cell‐coating‐substrate interfaces using FIB‐SEM, it was revealed that the porous surface created by both coatings well supports osteoblast cell adhesion while the dense inner layer facilitates a good bonding between the coating and the substrate. Although the mechanical property of the coating decreased with the addition of collagen, it is still strong enough for implant handling and the biocompatibility was promoted.

Structurally similar analogues of given query compounds can be rapidly retrieved from chemical databases by the molecular similarity search approaches. However, the computational cost associated with the exhaustive similarity search of a large compound database will be quite high. Although the latest indexing algorithms can greatly speed up the search process, they cannot be readily applicable to molecular similarity search problems due to the lack of Tanimoto similarity metric implementation. In this paper, we first implement Python or C++ codes to enable the Tanimoto similarity search via several recent indexing algorithms, such as Hnsw and Onng. Moreover, there are increasing interests in computational communities to develop robust benchmarking systems to access the performance of various computational algorithms. Here, we provide a benchmark to evaluate the molecular similarity searching performance of these recent indexing algorithms. To avoid the potential package dependency issues, two separate benchmarks are built based on currently popular container technologies, Docker and Singularity. The Singularity container is a rather new container framework specifically designed for the high-performance computing (HPC) platform and does not need the privileged permissions or the separated daemon process. Both benchmarking methods are extensible to incorporate other new indexing algorithms, benchmarking data sets, and different customized parameter settings. Our results demonstrate that the graph-based methods, such as Hnsw and Onng, consistently achieve the best trade-off between searching effectiveness and searching efficiencies. The source code of the entire benchmark systems can be downloaded from https://github.uconn.edu/mldrugdiscovery/MssBenchmark.