SUMMARY: Protein language models (PLMs) have recently demonstrated potential to supplant classical protein database search methods based on sequence alignment, but are slower than common alignment-based tools and appear to be prone to a high rate of false labeling. Here, we present Neural Embeddings for Amino acid Relationships (NEAR), a method based on neural representation learning that is designed to improve both speed and accuracy of search for likely homologs in a large protein sequence database. NEAR's ResNet embedding model is trained using contrastive learning guided by trusted sequence alignments. It computes per-residue embeddings for target and query protein sequences, and identifies alignment candidates with a pipeline consisting of residue-level k-NN search and a simple neighbor aggregation scheme. Tests on a benchmark consisting of trusted remote homologs and randomly shuffled decoy sequences reveal that NEAR substantially improves accuracy relative to state-of-the-art PLMs, with lower memory requirements and faster embedding and search speed. While these results suggest that the NEAR model may be useful for standalone homology detection with increased sensitivity over standard alignment-based methods, in this manuscript, we focus on a more straightforward analysis of the model's value as a high-speed pre-filter for sensitive annotation. In that context, NEAR is at least 5x faster than the pre-filter currently used in the widely used profile hidden Markov model (pHMM) search tool HMMER3, and also outperforms the pre-filter used in our fast pHMM tool, nail. AVAILABILITY AND IMPLEMENTATION: NEAR is under an open-source license. Code and data curation instructions can be found at https://github.com/TravisWheelerLab/NEAR.

Accurate maps of irrigation are essential for understanding and managing water resources. We present a new method of mapping irrigation based on an ensemble of convolutional neural networks that use reflectance information from Landsat imagery to classify irrigated pixels. The methodology does not rely on extensive feature engineering and does not condition the classification with land use information from existing geospatial datasets. The ensemble does not need exhaustive hyperparameter tuning and the analysis pipeline is lightweight enough to be implemented on a personal computer. Furthermore, the proposed methodology provides an estimate of the uncertainty associated with classification. We evaluated our methodology and the resulting irrigation maps using a highly accurate novel spatially-explicit ground truth data set, using county-scale USDA surveys of irrigation extent, and using cadastral surveys. We demonstrate the accuracy of the method by mapping irrigation over the state of Montana from years 2000-2019. We found that our method outperforms other methods that use satellite remote sensing information in terms of overall accuracy and precision. We found that our method agrees better statewide with the USDA National Agricultural Statistics Survey estimates of irrigated area compared to other methods, and has far fewer errors of commission in rainfed agriculture areas. This methodology has the potential to be applied across the entire United States and for the complete Landsat record.