Finding known homologs of newly predicted proteins is essential for understanding their functions and mechanisms. It is a highly complex task because proteins undergo various changes during evolution. Traditional methods based on sequence or structure alignment either have low accuracy or take a long time. Recent deep learning-based methods primarily focus on structural information, yet they can’t fully exploiting protein information. To solve this problem, in this paper, we propose a novel general-purpose protein embedding model that can be used for homology search. It first employs a protein language pre-trained model to extract protein sequence embeddings, capturing intricate biological patterns. Subsequently, a Transformer integrating protein structural information generates the high-level representations. By combining protein sequence and structural features, the model can effectively exploit the rich contextual and spatial information inherent in proteins. We applied the model to the SCOP dataset for protein superfamily classification, achieving a classification accuracy of 86.97%, outperforming state-of-the-art method by 7.91%. The source code has been published on GitHub (https://github.com/CMACH508/PEST).

Protein binding site prediction is an important prerequisite for the discovery of new drugs. Usually, natural 3D U-Net is adopted as the standard site prediction framework to do per-voxel binary mask classification. However, this scheme only performs feature extraction for single-scale samples, which may bring the loss of global or local information, resulting in incomplete, artifacted or even missed predictions. To tackle this issue, we propose a network called GLPocket, which is based on the Lmser (Least mean square error reconstruction) network and utilizes multi-scale representation to predict binding sites. Firstly, GLPocket uses Target Cropping Block (TCB) for targeted prediction. TCB selects the local interested feature from the global representations to perform concentrated prediction, and reduces the volume of feature maps to be calculated by 82% without adding additional parameters. It integrates global distribution information into local regions, making prediction more concentrated on decoding stage. Secondly, GLPocket establishes long-range relationship of patches within the local region with Transformer Block (TB), to enrich local context semantic information. Experiments show that GLPocket improves by 0.5%-4% on DCA Top-n prediction compared with previous state-of-the-art methods on four datasets. Our code has been released in https://github.com/CMACH508/GLPocket.

Protein binding site prediction is an important prerequisite task of drug discovery and design. While binding sites are very small, irregular and varied in shape, making the prediction very challenging. Standard 3D U-Net has been adopted to predict binding sites but got stuck with unsatisfactory prediction results, incomplete, out-of-bounds, or even failed. The reason is that this scheme is less capable of extracting the chemical interactions of the entire region and hardly takes into account the difficulty of segmenting complex shapes. In this paper, we propose a refined U-Net architecture, called RefinePocket, consisting of an attention-enhanced encoder and a mask-guided decoder. During encoding, taking binding site proposal as input, we employ Dual Attention Block (DAB) hierarchically to capture rich global information, exploring residue relationship and chemical correlations in spatial and channel dimensions respectively. Then, based on the enhanced representation extracted by the encoder, we devise Refine Block (RB) in the decoder to enable self-guided refinement of uncertain regions gradually, resulting in more precise segmentation. Experiments show that DAB and RB complement and promote each other, making RefinePocket has an average improvement of 10.02% on DCC and 4.26% on DVO compared with the state-of-the-art method on four test sets.

It is an essential step to locate the binding sites or pockets of drug molecules on protein structure in drug design. This is challenging because the 3D protein structures are usually in complicated, irregular shape and the pockets are relatively small. Existing deep learning methods for this task are U-Net models, and they have forward skip connections to efficiently transfer features of different levels of 3D structure from encoder to decoder for improving pocket prediction. However, there is still room to improve prediction accuracy. In this paper, we propose RecurPocket, a recurrent Lmser (Least mean square error reconstruction) network for pocket detection. A gated recurrent refinement is devised in RecurPocket to enhance the representation learning on the 3D protein structures. This is fulfilled by feedback connections in RecurPocket network from decoder to encoder, recurrently and progressively improving the feature embedding for accurate prediction. Moreover, a 3D gate mechanism filters out irrelevant information through the feedback links that interfere with detection, making the prediction more precise and clear. Experiments show that RecurPocket improves by 3%-9% on top-n prediction compared with previous state-of-the-art on five benchmark data sets. The source code and trained model are available at https://github.con CMACH508/RecurPocket.

Developing an efficient system for automated detection and segmentation of intracranial aneurysms (IAs) became an active research topic recently. However, existing methods are poor in detecting small IA with high false positives. In this paper, we present a feature enrichment (FE) based deep learning method for robust IA detection and segmentation. The FE technique is featured by reconstructing a 3D model from all computed tomography angiography (CTA) images and then projecting 3D information into the so-called projection images of different slicing levels along various directions. The appearances of aneurysms in the projection images are enhanced in morphology and 3D neighborhood features, and thus are easy to be detected and segmented by the widely-used faster RCNN and V-Net. To evaluate our method, we collect CTA images from 145 patients (including 148 IAs) for training and testing. The proposed method achieves 96.0 % sensitivity for all aneurysms, and 80.0% sensitivity for aneurysms smaller than 4mm, better than the state-of-the-art methods. Also, the segmentation performance is improved on the detected IAs.

Existing single image super-resolution (SISR) methods usually focus on Low-Resolution (LR) images which are artificially generated from High-Resolution (HR) images by a down-sampling process, but are not robust for unmatched training set and testing set. This paper proposes a GAN Flexible Lmser (GFLmser) network that bidirectionally learns the High-to-Low (H2L) process that degrades HR images to LR images and the Low-to-High (L2H) process that recovers the LR images back to HR images. The two directions share the same architecture, added with the gated skip connections from the H2L-net to the L2H-net in order to enhance information transferring for super-resolution. In comparison with several related state-of-the-art methods, experiments demonstrate that not only GFLmser is the most robust method on images of unmatched training set and testing set, but also its performance on real-world face LR images is best in PSNR and reasonably good in FID.

BACKGROUND: With the widespread use of multiple amplicon-sequencing (MAS) in genetic variation detection, an efficient tool is required to remove primer sequences from short reads to ensure the reliability of downstream analysis. Although some tools are currently available, their efficiency and accuracy require improvement in trimming large scale of primers in high throughput target genome sequencing. This issue is becoming more urgent considering the potential clinical implementation of MAS for processing patient samples. We here developed pTrimmer that could handle thousands of primers simultaneously with greatly improved accuracy and performance. RESULT: pTrimmer combines the two algorithms of k-mers and Needleman-Wunsch algorithm, which ensures its accuracy even with the presence of sequencing errors. pTrimmer has an improvement of 28.59% sensitivity and 11.87% accuracy compared to the similar tools. The simulation showed pTrimmer has an ultra-high sensitivity rate of 99.96% and accuracy of 97.38% compared to cutPrimers (70.85% sensitivity rate and 58.73% accuracy). And the performance of pTrimmer is notably higher. It is about 370 times faster than cutPrimers and even 17,000 times faster than cutadapt per threads. Trimming 2158 pairs of primers from 11 million reads (Illumina PE 150 bp) takes only 37 s and no more than 100 MB of memory consumption. CONCLUSIONS: pTrimmer is designed to trim primer sequence from multiplex amplicon sequencing and target sequencing. It is highly sensitive and specific compared to other three similar tools, which could help users to get more reliable mutational information for downstream analysis.