Metagenomic binning is an essential technique for genome-resolved characterization of uncultured microorganisms in various ecosystems but hampered by the low efficiency of binning tools in adequately recovering metagenome-assembled genomes (MAGs). Here, we introduce BASALT (Binning Across a Series of Assemblies Toolkit) for binning and refinement of short- and long-read sequencing data. BASALT employs multiple binners with multiple thresholds to produce initial bins, then utilizes neural networks to identify core sequences to remove redundant bins and refine non-redundant bins. Using the same assemblies generated from Critical Assessment of Metagenome Interpretation (CAMI) datasets, BASALT produces up to twice as many MAGs as VAMB, DASTool, or metaWRAP. Processing assemblies from a lake sediment dataset, BASALT produces ~30% more MAGs than metaWRAP, including 21 unique class-level prokaryotic lineages. Functional annotations reveal that BASALT can retrieve 47.6% more non-redundant opening-reading frames than metaWRAP. These results highlight the robust handling of metagenomic sequencing data of BASALT.
The alignment of long-read RNA sequencing reads is non-trivial due to high sequencing errors and complicated gene structures. We propose deSALT, a tailored two-pass alignment approach, which constructs graph-based alignment skeletons to infer exons and uses them to generate spliced reference sequences to produce refined alignments. deSALT addresses several difficult technical issues, such as small exons and sequencing errors, which break through bottlenecks of long RNA-seq read alignment. Benchmarks demonstrate that deSALT has a greater ability to produce accurate and homogeneous full-length alignments. deSALT is available at: https://github.com/hitbc/deSALT.
Motivation: In recent years, there has been a breakthrough in protein structure prediction, and the AlphaFold2 model of the DeepMind team has improved the accuracy of protein structure prediction to the atomic level. Currently, deep learning-based protein function prediction models usually extract features from protein sequences and combine them with protein–protein interaction networks to achieve good results. However, for newly sequenced proteins that are not in the protein–protein interaction network, such models cannot make effective predictions. To address this, this article proposes the Struct2GO model, which combines protein structure and sequence data to enhance the precision of protein function prediction and the generality of the model. Results: We obtain amino acid residue embeddings in protein structure through graph representation learning, utilize the graph pooling algorithm based on a self-attention mechanism to obtain the whole graph structure features, and fuse them with sequence features obtained from the protein language model. The results demonstrate that compared with the traditional protein sequence-based function prediction model, the Struct2GO model achieves better results. Availability and implementation: The data underlying this article are available at https://github.com/lyjps/Struct2GO.
11 February 2022 in Computational and Structural Biotechnology Journal
The infectious and parasitic diseases represent a major threat to public health and are among the main causes of morbidity and mortality. The complex and divergent life cycles of parasites present major difficulties associated with the diagnosis of these organisms by microscopic examination. Deep learning has shown extraordinary performance in biomedical image analysis including various parasites diagnosis in the past few years. Here we summarize advances of deep learning in the field of protozoan parasites microscopic examination, focusing on publicly available microscopic image datasets of protozoan parasites. In the end, we summarize the challenges and future trends, which deep learning faces in protozoan parasite diagnosis.
20 April 2022 in Computational and Structural Biotechnology Journal
Motivation: Microscopic images are widely used in basic biomedical research, disease diagnosis and medical discovery. Obtaining high-quality in-focus microscopy images has been a cornerstone of the microscopy. However, images obtained by microscopes are often out-of-focus, resulting in poor performance in research and diagnosis. Results: To solve the out-of-focus issue in microscopy, we developed a Cycle Generative Adversarial Network (CycleGAN) based model and a multi-component weighted loss function. We train and test our network in two self-collected datasets, namely Leishmania parasite dataset captured by a bright-field microscope, and bovine pulmonary artery endothelial cells (BPAEC) captured by a confocal fluorescence microscope. In comparison to other GAN-based deblurring methods, the proposed model reached state-of-the-art performance in correction. Another publicly available dataset, human cells dataset from the Broad Bioimage Benchmark Collection is used for evaluating the generalization abilities of the model. Our model showed excellent generalization capability, which could transfer to different types of microscopic image datasets. Availability and Implementation: Code and dataset are publicly available at: https://github.com/jiangdat/COMI .
Concurrent use of multiple drugs can lead to unexpected adverse drug reactions. The interaction between drugs can be confirmed by routine in vitro and clinical trials. However, it is difficult to test the drug–drug interactions widely and effectively before the drugs enter the market. Therefore, the prediction of drug–drug interactions has become one of the research priorities in the biomedical field. In recent years, researchers have been using deep learning to predict drug–drug interactions by exploiting drug structural features and graph theory, and have achieved a series of achievements. A drug–drug interaction prediction model SmileGNN is proposed in this paper, which can be characterized by aggregating the structural features of drugs constructed by SMILES data and the topological features of drugs in knowledge graphs obtained by graph neural networks. The experimental results show that the model proposed in this paper combines a variety of data sources and has a better prediction performance compared with existing prediction models of drug–drug interactions. Five out of the top ten predicted new drug–drug interactions are verified from the latest database, which proves the credibility of SmileGNN.