AneuGuide™ software-assisted vs. manual measurements in sizing for pipeline embolization device: An agreement study.

Sizing of flow diverters (FDs) is a challenging task in the treatment of intracranial aneurysms due to their foreshortening behavior. The purpose of this study is to evaluate the difference between the sizing results from the AneuGuide™ software and from conventional 2D measurement. Ninety-eight consecutive patients undergoing pipeline embolization device (PED) treatment between October 2018 and April 2023 in the First Medical Center of Chinese PLA General Hospital (Beijing, China) were retrospectively analyzed. For all cases, the optimal PED dimensions were both manually determined through 2D measurements on pre-treatment 3D-DSA and computed by AneuGuide™ software. The inter-rater reliability between the two sets of sizing results for each methodology was analyzed using intraclass correlation coefficient (ICC). The degree of agreement between manual sizing and software sizing were analyzed with the Bland-Altman plot and Pearson's test. Differences between two methodologies were analyzed with Wilcoxon signed rank test. Statistical significance was defined as p < 0.05. There was better inter-rater reliability between AneuGuide™ measurements both for diameter (ICC 0.92, 95%CI 0.88-0.95) and length (ICC 0.93, 95%CI 0.89-0.96). Bland-Altman plots showed a good agreement for diameter selection between two methodologies. However, the median length proposed by software group was significantly shorter (16 mm versus 20 mm, p < 0.001). No difference was found for median diameter (4.25 mm versus 4.25 mm). We demonstrated that the AneuGuide™ software provides highly reliable results of PED sizing compared with manual measurement, with a shorter stent length. AneuGuide™ may aid neurointerventionalists in selecting optimal dimensions for FD treatment.

Hybrid Bayesian Optimization-Based Graphical Discovery for Methylation Sites Prediction.

Protein methylation is one of the most important reversible post-translational modifications (PTMs), playing a vital role in the regulation of gene expression. Protein methylation sites serve as biomarkers in cardiovascular and pulmonary diseases, influencing various aspects of normal cell biology and pathogenesis. Nonetheless, the majority of existing computational methods for predicting protein methylation sites (PMSP) have been constructed based on protein sequences, with few methods leveraging the topological information of proteins. To address this issue, we propose an innovative framework for predicting Methylation Sites using Graphs (GraphMethySite) that employs graph convolution network in conjunction with Bayesian Optimization (BO) to automatically discover the graphical structure surrounding a candidate site and improve the predictive accuracy. In order to extract the most optimal subgraphs associated with methylation sites, we extend GraphMethySite by coupling it with a hybrid Bayesian optimization (together named GraphMethySite +) to determine and visualize the topological relevance among amino-acid residues. We evaluated our framework on two extended protein methylation datasets, and empirical results demonstrate that it outperforms existing state-of-the-art methylation prediction methods.

Elaborated pseudoknots that stimulate -1 programmed ribosomal frameshifting or stop codon readthrough in RNA viruses.

Pseudoknots assume various functions including stimulation of -1 programmed ribosomal frameshifting (PRF) or stop codon readthrough (SCR) in RNA viruses. These pseudoknots vary greatly in sizes and structural complexities. Recent biochemical and structural studies confirm the three-stemmed pseudoknots as the -1 PRF stimulators in the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and related coronaviruses. We reexamined previously reported -1 PRF or SCR stimulating pseudoknots, especially those containing a relatively long connecting loop between the two pseudoknot-forming stems, for their ability to form elaborated structures. Many potential elaborated pseudoknots were identified that contain one or more of the following extra structural elements: stem-loop, embedded pseudoknot, kissing hairpins, and additional loop-loop interactions. The elaborated pseudoknots are found in several different virus families that utilize either the -1 PRF or SCR recoding mechanisms. Model-building studies were performed to not only establish the structural feasibility of the elaborated pseudoknots but also reveal potential additional structural features that cannot be readily inferred from the predicted secondary structures. Some of the structures, such as embedded double pseudoknots and compact loop-loop pseudoknots mediated by the previously established common pseudoknot motif-1 (CPK-1), represent the first of its kind in the literatures. By advancing discovery of new functional RNA structures, we significantly expand the repertoire of known elaborated pseudoknots that could potentially play a role in -1 PRF and SCR regulation. These results contribute to a better understanding of RNA structures in general, facilitating the design of engineering RNA molecules with certain desired functions.Communicated by Ramaswamy H. Sarma.

Prokaryotic virus host prediction with graph contrastive augmentaion.

Prokaryotic viruses, also known as bacteriophages, play crucial roles in regulating microbial communities and have the potential for phage therapy applications. Accurate prediction of phage-host interactions is essential for understanding the dynamics of these viruses and their impacts on bacterial populations. Numerous computational methods have been developed to tackle this challenging task. However, most existing prediction models can be constrained due to the substantial number of unknown interactions in comparison to the constrained diversity of available training data. To solve the problem, we introduce a model for prokaryotic virus host prediction with graph contrastive augmentation (PHPGCA). Specifically, we construct a comprehensive heterogeneous graph by integrating virus-virus protein similarity and virus-host DNA sequence similarity information. As the backbone encoder for learning node representations in the virus-prokaryote graph, we employ LGCN, a state-of-the-art graph embedding technique. Additionally, we apply graph contrastive learning to augment the node representations without the need for additional labels. We further conducted two case studies aimed at predicting the host range of multi-species phages, helping to understand the phage ecology and evolution.

scPML: pathway-based multi-view learning for cell type annotation from single-cell RNA-seq data.

Recent developments in single-cell technology have enabled the exploration of cellular heterogeneity at an unprecedented level, providing invaluable insights into various fields, including medicine and disease research. Cell type annotation is an essential step in its omics research. The mainstream approach is to utilize well-annotated single-cell data to supervised learning for cell type annotation of new singlecell data. However, existing methods lack good generalization and robustness in cell annotation tasks, partially due to difficulties in dealing with technical differences between datasets, as well as not considering the heterogeneous associations of genes in regulatory mechanism levels. Here, we propose the scPML model, which utilizes various gene signaling pathway data to partition the genetic features of cells, thus characterizing different interaction maps between cells. Extensive experiments demonstrate that scPML performs better in cell type annotation and detection of unknown cell types from different species, platforms, and tissues.

Efficient and accurate registration with BWPH descriptor for low-quality point clouds.

Point cloud registration based on local descriptors plays a crucial role in 3D computer vision applications. However, existing methods often suffer from limitations such as low accuracy, a large memory footprint, and slow speed, particularly when dealing with 3D point clouds from low-cost sensors. To overcome these challenges, we propose an efficient local descriptor called Binary Weighted Projection-point Height (BWPH) for point cloud registration. The core idea behind the BWPH descriptor is the integration of Gaussian kernel density estimation with weighted height characteristics and binarization components to encode distinctive information for the local surface. Through extensive experiments and rigorous comparisons with state-of-the-art methods, we demonstrate that the BWPH descriptor achieves high matching accuracy, strong compactness, and feasibility across contexts. Moreover, the proposed BWPH-based point cloud registration successfully registers real datasets acquired by low-cost sensors with small errors, enabling accurate initial alignment positions.

A case series on the efficacy and safety of a PD-1 inhibitor combined with antiangiogenic agents in the treatment of recurrent MSI-H endometrial cancer.

Background: Endometrial cancer (EC) is one of the most common gynecological malignancies in developed countries worldwide. The treatment of recurrent endometrial cancer is a very difficult problem in clinical work. Studies on patients with recurrent EC microsatellite instability-high (MSI-H) are very rare. The objective of this study is to initially evaluate the therapeutic effect of a PD-1 inhibitor combined with antiangiogenic agents in the treatment of recurrent MSI-H endometrial cancer. Methods: Eight patients with recurrent MSI-H endometrial cancer were recruited from Tianjin Medical University Cancer Institute and Hospital from July 2019 to July 2021, and their median age was 55.3 (range, 46-62) years. All patients experienced recurrence after surgical treatment, and the median recurrence and metastasis time was 6.6 (range, 4-10) months. The pathological types were all endometrioid carcinomas. PD-1 inhibitors were selected from camrelizumab or pembrolizumab, and antiangiogenic targeted agents were selected from apatinib or anlotinib. Results: The median follow-up time was 11.0 (range, 5-19) months. In the case series, all 8 cases could be evaluated for curative effect with complete response in 4 cases and partial response in 4 cases. The overall objective response rate was 100%. Conclusions: PD-1 inhibitors combined with antiangiogenic agents may have good therapeutic effects on patients with recurrent MSI-H endometrial cancer and may become an important method for the treatment of recurrent endometrial cancer in the future.

MInet: A Novel Network Model for Point Cloud Processing by Integrating Multi-Modal Information.

Three-dimensional LiDAR systems that capture point cloud data enable the simultaneous acquisition of spatial geometry and multi-wavelength intensity information, thereby paving the way for three-dimensional point cloud recognition and processing. However, due to the irregular distribution, low resolution of point clouds, and limited spatial recognition accuracy in complex environments, inherent errors occur in classifying and segmenting the acquired target information. Conversely, two-dimensional visible light images provide real-color information, enabling the distinction of object contours and fine details, thus yielding clear, high-resolution images when desired. The integration of two-dimensional information with point clouds offers complementary advantages. In this paper, we present the incorporation of two-dimensional information to form a multi-modal representation. From this, we extract local features to establish three-dimensional geometric relationships and two-dimensional color relationships. We introduce a novel network model, termed MInet (Multi-Information net), which effectively captures features relating to both two-dimensional color and three-dimensional pose information. This enhanced network model improves feature saliency, thereby facilitating superior segmentation and recognition tasks. We evaluate our MInet architecture using the ShapeNet and ThreeDMatch datasets for point cloud segmentation, and the Stanford dataset for object recognition. The robust results, coupled with quantitative and qualitative experiments, demonstrate the superior performance of our proposed method in point cloud segmentation and object recognition tasks.

Dural sinus septum: an underlying cause of cerebral venous sinus stenting failure and complications.

OBJECTIVES: The presence of dural sinus septum has long been identified anatomically but is often neglected for its clinical significance. Our findings revealed the association of dural sinus septum with venous sinus stenting failure and complications supported by clinical evidence. METHODS: This retrospective study included 185 consecutive patients treated with cerebral venous sinus stenting from January 2009 to May 2022. We identified the dural sinus septa using digital subtraction angiography (DSA) and classified them into three types based on their location. The septa at the transverse sinus were defined as type I, those at the junction between the transverse sinus and sigmoid sinus were defined as type II and those at the sigmoid sinus were defined as type III. Based on the anatomic features and neuroimaging clues, we investigated the correlation of dural sinus septa with stenting failure and complications. RESULTS: 32 (17.1%) out of 185 patients (121 with idiopathic intracranial hypertension and 64 with venous pulsatile tinnitus) were identified with dural sinus septa by DSA. More than half of the septa were type I (18/32, 56.2%), followed by type II (11/32, 34.4%) and type III (3/32, 9.4%). The dural sinus septa caused three stenting failures and complications, including one case of venous sinus injury with subdural haemorrhage and two cases of incomplete stent expansion. Statistical analysis revealed that the presence of dural sinus septum (p<0.01) was associated with complications of cerebral venous sinus stenting. DISCUSSION: The dural sinus septum is a common structure in the cerebral venous sinus. We found that the presence of dural sinus septa introduces uncertainties to cerebral venous sinus stenting and suggested precautions and ingenious skills in imaging and treatment.

Knowledge graph embedding for profiling the interaction between transcription factors and their target genes.

Interactions between transcription factor and target gene form the main part of gene regulation network in human, which are still complicating factors in biological research. Specifically, for nearly half of those interactions recorded in established database, their interaction types are yet to be confirmed. Although several computational methods exist to predict gene interactions and their type, there is still no method available to predict them solely based on topology information. To this end, we proposed here a graph-based prediction model called KGE-TGI and trained in a multi-task learning manner on a knowledge graph that we specially constructed for this problem. The KGE-TGI model relies on topology information rather than being driven by gene expression data. In this paper, we formulate the task of predicting interaction types of transcript factor and target genes as a multi-label classification problem for link types on a heterogeneous graph, coupled with solving another link prediction problem that is inherently related. We constructed a ground truth dataset as benchmark and evaluated the proposed method on it. As a result of the 5-fold cross experiments, the proposed method achieved average AUC values of 0.9654 and 0.9339 in the tasks of link prediction and link type classification, respectively. In addition, the results of a series of comparison experiments also prove that the introduction of knowledge information significantly benefits to the prediction and that our methodology achieve state-of-the-art performance in this problem.

A potential long-range RNA-RNA interaction in the HIV-1 RNA.

It is well-established that viral and cellular mRNAs alike harbour functional long-range intra-molecular RNA-RNA interactions. Despite the biological importance of such interactions, their identification and characterization remain challenging. Here we present a computational method for the identification of certain kinds of long-range intra-molecular RNA-RNA interactions involving the loop nucleotides of a hairpin loop. Using the computational method, we analysed 4272 HIV-1 genomic mRNAs. A potential long-range intra-molecular RNA-RNA interaction within the HIV-1 genomic RNA was identified. The long-range interaction is mediated by a kissing loop structure between two stem-loops of the previously reported SHAPE-based secondary structure of the entire HIV-1 genome. Structural modelling studies were carried out to show that the kissing loop structure not only is sterically feasible, but also contains a conserved RNA structural motif often found in compact RNA pseudoknots. The computational method should be generally applicable to the identification of potential long-range intra-molecular RNA-RNA interactions in any viral or cellular mRNA sequence.Communicated by Ramaswamy H. Sarma.

Predicting TF Proteins by Incorporating Evolution Information Through PSSM.

Transcription factors (TFs) are DNA binding proteins involved in the regulation of gene expression. They exist in all organisms and activate or repress transcription by binding to specific DNA sequences. Traditionally, TFs have been identified by experimental methods that are time-consuming and costly. In recent years, various computational methods have been developed to identify TF to overcome these limitations. However, there is a room for further improvement in the predictive performance of these tools in terms of accuracy. We report here a novel computational tool, TFnet, that provides accurate and comprehensive TF predictions from protein sequences. The accuracy of these predictions is substantially better than the results of the existing TF predictors and methods. Especially, it outperforms comparable methods significantly when sequence similarity to other known sequences in the database drops below 40%. Ablation tests reveal that the high predictive performance stems from innovative ways used in TFnet to derive sequence Position-Specific Scoring Matrix (PSSM) and encode inputs.

Inference of gene regulatory networks based on the Light Gradient Boosting Machine.

Inference of gene regulatory networks (GRNs) is one of the major challenges in molecular biology, understanding of which can reveal the regulatory relationship between transcription factors (TFs) and target genes. Although in the past decades many methods were developed to reconstruct GRNs, the accuracy of traditional methods can be further improved. In this work, we proposed a new method, GRN-LightGBM (Light Gradient Boosting Machine), to reconstruct GRNs. GRN-LightGBM is a non-linear. Ordinary differential equations (ODEs) model established by LightGBM, which is considering regulatory and target genes for a specific gene. Furthermore, GRN-LightGBM utilizes time-series data, steady-state data, and temporal time-delay data together to evaluate the features of regulatory genes important for target genes. GRN-LightGBM is evaluated both in the DREAM4 simulated datasets and Escherichia coli real datasets. The results show that the proposed method outperforms other popular inference algorithms in terms of area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPR).

Performance Improvement of NIR Spectral Pattern Recognition from Three Compensation Models' Voting and Multi-Modal Fusion.

Inspired by aquaphotomics, the optical path length of measurement was regarded as a perturbation factor. Near-infrared (NIR) spectroscopy with multi-measurement modals was applied to the discriminant analysis of three categories of drinking water. Moving window-k nearest neighbor (MW-kNN) and Norris derivative filter were used for modeling and optimization. Drawing on the idea of game theory, the strategy for two-category priority compensation and three-model voting with multi-modal fusion was proposed. Moving window correlation coefficient (MWCC), inter-category and intra-category MWCC spectra, and k-shortest distances plotting with MW-kNN were proposed to evaluate weak differences between two spectral populations. For three measurement modals (1 mm, 4 mm, and 10 mm), the optimal MW-kNN models, and two-category priority compensation models were determined. The joint models for three compensation models' voting were established. Comprehensive discrimination effects of joint models were better than their sub-models; multi-modal fusion was better than single-modal fusion. The best joint model was the dual-modal fusion of compensation models of one- and two-category priority (1 mm), one- and three-category priority (10 mm), and two- and three-category priority (1 mm), validation's total recognition accuracy rate reached 95.5%. It fused long-wave models (1 mm, containing 1450 nm) and short-wave models (10 mm, containing 974 nm). The results showed that compensation models' voting and multi-modal fusion can effectively improve the performance of NIR spectral pattern recognition.

GraphTGI: an attention-based graph embedding model for predicting TF-target gene interactions.

MOTIVATION: Interaction between transcription factor (TF) and its target genes establishes the knowledge foundation for biological researches in transcriptional regulation, the number of which is, however, still limited by biological techniques. Existing computational methods relevant to the prediction of TF-target interactions are mostly proposed for predicting binding sites, rather than directly predicting the interactions. To this end, we propose here a graph attention-based autoencoder model to predict TF-target gene interactions using the information of the known TF-target gene interaction network combined with two sequential and chemical gene characters, considering that the unobserved interactions between transcription factors and target genes can be predicted by learning the pattern of the known ones. To the best of our knowledge, the proposed model is the first attempt to solve this problem by learning patterns from the known TF-target gene interaction network. RESULTS: In this paper, we formulate the prediction task of TF-target gene interactions as a link prediction problem on a complex knowledge graph and propose a deep learning model called GraphTGI, which is composed of a graph attention-based encoder and a bilinear decoder. We evaluated the prediction performance of the proposed method on a real dataset, and the experimental results show that the proposed model yields outstanding performance with an average AUC value of 0.8864 +/- 0.0057 in the 5-fold cross-validation. It is anticipated that the GraphTGI model can effectively and efficiently predict TF-target gene interactions on a large scale. AVAILABILITY: Python code and the datasets used in our studies are made available at https://github.com/YanghanWu/GraphTGI.

DeepA-RBPBS: A hybrid convolution and recurrent neural network combined with attention mechanism for predicting RBP binding site.

It's important to infer the binding site of RNA-binding proteins (RBP) for understanding the interaction between RBP and its RNA targets and decipher the mechanisms of transcriptional regulation. However, experimental detection of RBP binding sites is still time-intensive and expensive. Algorithms based on machine learning can speed up detection of RBP binding sites. In this article, we propose a new deep learning method, DeepA-RBPBS, which can use RNA sequences and structural features to predict RBP binding site. DeepA-RBPBS uses CNN and BiGRU to extract sequences and structural features without long-term dependence issues. It also utilizes an attention mechanism to enhance the contribution of key features. The comparison shows that the performance of DeepA-RBPBS is better than that of the state-of-the-art predictors. In the testing on 31 datasets of CLIP-seq experiments over 19 proteins, MCC (AUC) is 8% (5%) higher than those of the latest method based on deep learning, iDeepS. We also apply DeepA-RBPBS to the target RNA data of RBPs related to diabetes (LIN28, RBFOX2, FTO, IGF2BP2, CELF1 and HuR). The results show that DeepA-RBPBS correctly predicted 41,693 samples, where iDeepS predicted 31,381 samples.Communicated by Ramaswamy H. Sarma.

DeepCLD: An Efficient Sequence-Based Predictor of Intrinsically Disordered Proteins.

Intrinsic disorder is common in proteins, plays important roles in protein functionality, and is commonly associated with various human diseases. To have an accurate tool for the annotation of intrinsic disorder in proteins, this paper proposes a novel algorithm, DeepCLD, for sequence-based prediction of intrinsically disordered proteins. This algorithm uses amino acid position specific scoring matrix (PSSM) to capture the intrinsic variability characteristic of sequence patterns, ResNet to preserve feature space structure, and bidirectional CudnnLSTM as recurrent layer to further improve the efficiency. Futhermore, DeepCLD also utilized the attention mechanism to solve the problem of gradient disappearing in deep network. Comparative analyses show that DeepCLD has faster training speed and higher prediction accuracy than comparable methods.

AngioSuite-Assisted Volume Calculation and Coil Use Prediction in the Endovascular Treatment of Tiny Volume Intracranial Aneurysms.

METHODS: Thirty-three consecutive patients with 34 TVIAs were prospectively recruited and treated with endovascular techniques. The volume of TVIAs and the required length of coils were calculated by the AngioSuite software before embolization. The treatment efficacy of TVIAs was assessed using the Raymond scale (Rs) and the modified Rankin scale (mRs). RESULTS: Of the 34 aneurysms with an average volume of 7.16 mm3, 13 aneurysms were treated with sole coil embolization, 19 by stent-assisted embolization, and 2 by balloon-assisted embolization. The average coil length was 5.32 cm, and the average packing density was 41.21%. The immediate DSA showed that total occlusion (Rs = 1) was achieved in 15 aneurysms, subtotal (Rs = 2) in 9, and partial (Rs = 3) in 11. Total occlusion was achieved in 30 aneurysms and subtotal in the other 4 aneurysms at 6-month follow-up. Baseline volume and diameter of aneurysms were significantly correlated with the coil length (r = 0.801, P < 0.001; r = 0.711, P < 0.001). CONCLUSIONS: Coil embolization of TVIAs was easy to achieve high packing density. According to the data from AngioSuite, relative few coils can increase the safety in procedure and stenting may reduce risk of aneurysmal recurrence.

Effects of the Vertebral Artery Ostium/Subclavian Artery Angle on In-Stent Restenosis after Vertebral Artery Ostium Stenting.

METHODS: Between January 2016 and October 2018, sixty-four consecutive patients who underwent a total of 66 stenting procedures were screened for symptomatic and asymptomatic atherosclerotic VAOS. Of these patients, 57 had complete follow-up data. The baseline patient demographics and morphological features of the VAO were recorded. Potential factors influencing ISR, including conventional cerebrovascular disease risk factors, were assessed, together with outcome events including recurrent transient ischemic attack (TIA), stroke, and vascular-related mortality. RESULTS: The average follow-up period was 13.2 ± 4.6 months. Technical success was achieved in all interventions. The degree of stenosis was reduced from 77.2 ± 6.1% to 13.7 ± 8.9% after the procedure. ISR was detected in eight treated vessels (14.0%) and occlusion in two (5.3%) arteries. Of the 57 patients, one had an ischemic stroke and 5 had TIAs. The angle of the VAO at the subclavian artery was associated with the risk of restenosis (preoperative, P = 0.04; postoperative, P = 0.02). CONCLUSIONS: Stenting is a feasible and effective treatment for VAOS. The angle of the VAO at the subclavian artery may contribute to the development of ISR.