Resolving genomic structural variation: Many human genomes have been reported using short-read technology, but it is difficult to resolve structural variants (SVs) using these data. These genomes thus lack comprehensive comparisons among individuals and populations. Ebertet al.used long-read structural variation calling across 64 human genomes representing diverse populations and developed new methods for variant discovery. This approach allowed the authors to increase the number of confirmed SVs and to describe the patterns of variation across populations. From this dataset, they identified quantitative trait loci affected by these SVs and determined how they may affect gene expression and potentially explain genome-wide association study hits. This information provides insights into patterns of normal human genetic variation and generates reference genomes that better represent the diversity of our species.Science, this issue p.eabf7117

Protein remote homology detection plays a vital role in studies of protein structures and functions. Almost all of the traditional machine leaning methods require fixed length features to represent the protein sequences. However, it is never an easy task to extract the discriminative features with limited knowledge of proteins. On the other hand, deep learning technique has demonstrated its advantage in automatically learning representations. It is worthwhile to explore the applications of deep learning techniques to the protein remote homology detection. In this study, we employ the Bidirectional Long Short-Term Memory (BLSTM) to learn effective features from pseudo proteins, also propose a predictor called ProDec-BLSTM: it includes input layer, bidirectional LSTM, time distributed dense layer and output layer. This neural network can automatically extract the discriminative features by using bidirectional LSTM and the time distributed dense layer. Experimental results on a widely-used benchmark dataset show that ProDec-BLSTM outperforms other related methods in terms of both the mean ROC and mean ROC50 scores. This promising result shows that ProDec-BLSTM is a useful tool for protein remote homology detection. Furthermore, the hidden patterns learnt by ProDec-BLSTM can be interpreted and visualized, and therefore, additional useful information can be obtained.

Genotype imputation, where missing genotypes can be computationally imputed, is an essential tool in genomic analysis ranging from genome wide associations to phenotype prediction. Traditional genotype imputation methods are typically based on haplotype-clustering algorithms, hidden Markov models (HMMs), and statistical inference. Deep learning-based methods have been recently reported to suitably address the missing data problems in various fields. To explore the performance of deep learning for genotype imputation, in this study, we propose a deep model called a sparse convolutional denoising autoencoder (SCDA) to impute missing genotypes. We constructed the SCDA model using a convolutional layer that can extract various correlation or linkage patterns in the genotype data and applying a sparse weight matrix resulted from the L₁ regularization to handle high dimensional data. We comprehensively evaluated the performance of the SCDA model in different scenarios for genotype imputation on the yeast and human genotype data, respectively. Our results showed that SCDA has strong robustness and significantly outperforms popular reference-free imputation methods. This study thus points to another novel application of deep learning models for missing data imputation in genomic studies.

Background: Electronic medical records (EMRs) are usually stored in relational databases that require SQL queries to retrieve information of interest. Effectively completing such queries can be a challenging task for medical experts due to the barriers in expertise. Existing text-to-SQL generation studies have not been fully embraced in the medical domain. Objective: The objective of this study was to propose a neural generation model that can jointly consider the characteristics of medical text and the SQL structure to automatically transform medical texts to SQL queries for EMRs. Methods: We proposed a medical text–to-SQL model (MedTS), which employed a pretrained Bidirectional Encoder Representations From Transformers model as the encoder and leveraged a grammar-based long short-term memory network as the decoder to predict the intermediate representation that can easily be transformed into the final SQL query. We adopted the syntax tree as the intermediate representation rather than directly regarding the SQL query as an ordinary word sequence, which is more in line with the tree-structure nature of SQL and can also effectively reduce the search space during generation. Experiments were conducted on the MIMICSQL dataset, and 5 competitor methods were compared. Results: Experimental results demonstrated that MedTS achieved the accuracy of 0.784 and 0.899 on the test set in terms of logic form and execution, respectively, which significantly outperformed the existing state-of-the-art methods. Further analyses proved that the performance on each component of the generated SQL was relatively balanced and offered substantial improvements. Conclusions: The proposed MedTS was effective and robust for improving the performance of medical text–to-SQL generation, indicating strong potential to be applied in the real medical scenario.

Motivation: Protein function annotation is fundamental to understanding biological mechanisms. The abundant genome-scale protein–protein interaction (PPI) networks, together with other protein biological attributes, provide rich information for annotating protein functions. As PPI networks and biological attributes describe protein functions from different perspectives, it is highly challenging to cross-fuse them for protein function prediction. Recently, several methods combine the PPI networks and protein attributes via the graph neural networks (GNNs). However, GNNs may inherit or even magnify the bias caused by noisy edges in PPI networks. Besides, GNNs with stacking of many layers may cause the over-smoothing problem of node representations.Results: We develop a novel protein function prediction method, CFAGO, to integrate single-species PPI networks and protein biological attributes via a multi-head attention mechanism. CFAGO is first pre-trained with an encoder–decoder architecture to capture the universal protein representation of the two sources. It is then fine-tuned to learn more effective protein representations for protein function prediction. Benchmark experiments on human and mouse datasets show CFAGO outperforms state-of-the-art single-species network-based methods by at least 7.59%, 6.90%, 11.68% in terms of m-AUPR, M-AUPR, and Fmax, respectively, demonstrating cross-fusion by multi-head attention mechanism can greatly improve the protein function prediction. We further evaluate the quality of captured protein representations in terms of Davies Bouldin Score, whose results show that cross-fused protein representations by multi-head attention mechanism are at least 2.7% better than that of original and concatenated representations. We believe CFAGO is an effective tool for protein function prediction.Availability and implementation: The source code of CFAGO and experiments data are available at: http://bliulab.net/CFAGO/.

Enhancers are important cis-regulatory elements that regulate a wide range of biological functions and enhance the transcription of target genes. Although many feature extraction methods have been proposed to improve the performance of enhancer identification, they cannot learn position-related multiscale contextual information from raw DNA sequences. In this article, we propose a novel enhancer identification method (iEnhancer-ELM) based on BERT-like enhancer language models. iEnhancer-ELM tokenizes DNA sequences with multi-scale k-mers and extracts contextual information of different scale k-mers related with their positions via an multi-head attention mechanism. We first evaluate the performance of different scale k-mers, then ensemble them to improve the performance of enhancer identification. The experimental results on two popular benchmark datasets show that our model outperforms state-of-the-art methods. We further illustrate the interpretability of iEnhancer-ELM. For a case study, we discover 30 enhancer motifs via a 3-mer-based model, where 12 of motifs are verified by STREME and JASPAR, demonstrating our model has a potential ability to unveil the biological mechanism of enhancer. The models and associated code are available at https://github.com/chen-bioinfo/iEnhancer-ELM Supplementary data are available at Bioinformatics Advances online.