scCompressSA: dual-channel self-attention based deep autoencoder model for single-cell clustering by compressing gene-gene interactions.

BACKGROUND: Single-cell clustering has played an important role in exploring the molecular mechanisms about cell differentiation and human diseases. Due to highly-stochastic transcriptomics data, accurate detection of cell types is still challenged, especially for RNA-sequencing data from human beings. In this case, deep neural networks have been increasingly employed to mine cell type specific patterns and have outperformed statistic approaches in cell clustering. RESULTS: Using cross-correlation to capture gene-gene interactions, this study proposes the scCompressSA method to integrate topological patterns from scRNA-seq data, with support of self-attention (SA) based coefficient compression (CC) block. This SA-based CC block is able to extract and employ static gene-gene interactions from scRNA-seq data. This proposed scCompressSA method has enhanced clustering accuracy in multiple benchmark scRNA-seq datasets by integrating topological and temporal features. CONCLUSION: Static gene-gene interactions have been extracted as temporal features to boost clustering performance in single-cell clustering For the scCompressSA method, dual-channel SA based CC block is able to integrate topological features and has exhibited extraordinary detection accuracy compared with previous clustering approaches that only employ temporal patterns.

Individualized 3D printed navigation template-assisted atlantoaxial pedicle screws vs. free-hand screws for the treatment of upper cervical fractures.

Objective: This study aims to compare the efficacy and safety of freehand atlantoaxial pedicle screws against custom 3D printed navigation template screws in the treatment of upper cervical fractures. Methods: In our institution from 2010 to 2020, a retrospective cohort analysis of 23 patients with upper cervical fractures was done. These patients were separated into two groups: group A (N = 12), which received customized 3D printed navigation template-assisted screws with virtual reality techniques, and group B (N = 11), which received freehand screws assisted by intraoperative fluoroscopy. Every patient was monitored for more than 1 year. The two groups were contrasted in terms of screw implant accuracy, cervical spine Japanese Orthopaedic Association (JOA) score, American Spinal Injury Association (ASIA) score, visual analogue scale (VAS) score, surgical time, fluoroscopy times, and intraoperative blood loss. Results: A total of 88 atlantoaxial pedicle screws in all, 46 in group A and 42 in group B, were implanted. In group A, the screw insertion accuracy rate was 95.7%, compared to 80.0% in group B (P < 0.05). When compared to group B, group A had shorter surgery times, less blood loss, fewer fluoroscopies, a higher short-term JOA score, and overt pain reduction (P < 0.05). However, there was no discernible difference between the two groups' VAS scores, long-term JOA scores, or ASIA scores (sensory and motor), at the most recent follow-up. Conclusion: Individualized 3D printed guide leads to significant improvement in the screw safety, efficacy, and accuracy, which may be a promising strategy for the treatment of upper cervical fractures.