Introducing π-HelixNovo for practical large-scale de novo peptide sequencing.

De novo peptide sequencing is a promising approach for novel peptide discovery, highlighting the performance improvements for the state-of-the-art models. The quality of mass spectra often varies due to unexpected missing of certain ions, presenting a significant challenge in de novo peptide sequencing. Here, we use a novel concept of complementary spectra to enhance ion information of the experimental spectrum and demonstrate it through conceptual and practical analyses. Afterward, we design suitable encoders to encode the experimental spectrum and the corresponding complementary spectrum and propose a de novo sequencing model $\pi$-HelixNovo based on the Transformer architecture. We first demonstrated that $\pi$-HelixNovo outperforms other state-of-the-art models using a series of comparative experiments. Then, we utilized $\pi$-HelixNovo to de novo gut metaproteome peptides for the first time. The results show $\pi$-HelixNovo increases the identification coverage and accuracy of gut metaproteome and enhances the taxonomic resolution of gut metaproteome. We finally trained a powerful $\pi$-HelixNovo utilizing a larger training dataset, and as expected, $\pi$-HelixNovo achieves unprecedented performance, even for peptide-spectrum matches with never-before-seen peptide sequences. We also use the powerful $\pi$-HelixNovo to identify antibody peptides and multi-enzyme cleavage peptides, and $\pi$-HelixNovo is highly robust in these applications. Our results demonstrate the effectivity of the complementary spectrum and take a significant step forward in de novo peptide sequencing.

Effects of spongioplasty on neourethral function following hypospadias repair: an experimental study in rabbits.

PURPOSE: Spongioplasty (mobilization and midline approximation of the two branches of the bifid dysplastic distal corpus spongiosum) can form a covering layer for the neourethra to prevent urethrocutaneous fistula in hypospadias repair surgery. However, it remains unclear whether spongioplasty affects neourethral function. The objective of this study was to compare neourethral function after hypospadias repair with and without spongioplasty. MATERIALS AND METHODS: Fourteen congenital hypospadiac New Zealand male rabbits were randomly allocated into two groups, seven animals underwent Duplay hypospadias repair and spongioplasty (experimental group), while seven underwent Duplay surgery alone (control group). Functional differences between groups were assessed by comparing neourethral compliance and flow rate. Two months after surgery, in vivo neourethral compliance was assessed by measuring intraluminal pressure with a digital pressure meter of an isolated neourethral segment, following progressive distension with 1, 2, and 3mL of air. Penises were harvested for uroflowmetry test using a simple device. RESULTS: Postoperatively, fistula developed in one and zero rabbits in the control and experimental groups, respectively. Mean pressures tended to be higher in the experimental group than in the control group (82.14 vs. 69.57, 188.43 vs. 143.26, and 244.71 vs. 186.29mmHg for 1, 2, and 3mL of air, respectively), but the difference was not statistically significant. Mean flow rates also did not significantly differ between the experimental and control groups (2.93mL/s vs. 3.31mL/s). CONCLUSION: In this congenital rabbit model, no obvious functional differences were found between reconstructed urethras after hypospadias repair with and without spongioplasty.

Ten years' experience for hypospadias repair: combined buccal mucosa graft and local flap for urethral reconstruction.

OBJECTIVES: To share our experience in hypospadias repair and discuss the clinical implications of our method, which consists of a combined buccal mucosa graft and local flap for urethroplasty. PATIENTS AND METHODS: 1,394 cases (median age 11.3 years, age range 5 months to 53 years) of hypospadias which were repaired using our method between July 2000 and December 2010 in our department were included in this study. The patients who had a short penis or did not have chordee were excluded from the data. 588 cases (42.2%) had previously undergone surgery in other hospitals but failed; 806 (57.8%) cases had undergone the first treatment in our department. RESULTS: Of the 806 cases which had undergone the first treatment in our department, we successfully reconstructed the urethra for 747 patients (92.3%), and 59 patients had complications (7.7%); of the 588 cases which had previously undergone surgery but failed, we successfully reconstructed the urethra for 522 patients (88.8%), and 66 patients had complications (11.2%). The most common complication was urethra fistula (70; 5%); other complications include necrosis of the skin flap and infection resulting in wound disruption (19; 1.4%), urethral diverticula (11; 0.8%) and urethral stricture (25; 1.8%). CONCLUSIONS: Our method appears to be a safe, simple and satisfactory surgical procedure and can provide relatively enough tissue to reconstruct the urethra with a higher success rate.

A review of machine learning-based methods for predicting drug-target interactions.

The prediction of drug-target interactions (DTI) is a crucial preliminary stage in drug discovery and development, given the substantial risk of failure and the prolonged validation period associated with in vitro and in vivo experiments. In the contemporary landscape, various machine learning-based methods have emerged as indispensable tools for DTI prediction. This paper begins by placing emphasis on the data representation employed by these methods, delineating five representations for drugs and four for proteins. The methods are then categorized into traditional machine learning-based approaches and deep learning-based ones, with a discussion of representative approaches in each category and the introduction of a novel taxonomy for deep neural network models in DTI prediction. Additionally, we present a synthesis of commonly used datasets and evaluation metrics to facilitate practical implementation. In conclusion, we address current challenges and outline potential future directions in this research field.

Surgical treatment and prevention of recurrence of urethral calculi associated with hairballs after urethroplasty.

OBJECTIVES: To evaluate technical aspects and outcome of preventing urethrocutaneous fistula and calculi recurrence in surgical treatment of urethral calculi associated with hairballs after urethroplasty. PATIENTS AND METHODS: Sixteen patients who had urethral calculi associated with hairballs after urethroplasty underwent urethrolithotomy and trimming and epilation of the neourethra. While operating, we made a staggered incision of the skin and urethra, carefully sutured the urethral incision, and covered it by well-vascularized tissue. A tube-in-tube stent method was performed on the latter 12 patients for better drainage of the exudates that accumulated in the urethra. RESULTS: All calculi were successfully removed. Surgical site infection occurred in the last one of the former 4 patients and resulted in an urethrocutaneous fistula. There were no other complications. All patients were followed up for 2-7 years; no urethral stenosis or recurrence of calculi was observed, and remarkable reduction of urethral hair was obtained. CONCLUSIONS: Urethrolithotomy and trimming and epilation of the neourethra seem to be appropriate treatments for urethral calculi associated with hairballs after urethroplasty. Full attention should be paid to fistula prevention.

DeepRTAlign: toward accurate retention time alignment for large cohort mass spectrometry data analysis.

Retention time (RT) alignment is a crucial step in liquid chromatography-mass spectrometry (LC-MS)-based proteomic and metabolomic experiments, especially for large cohort studies. The most popular alignment tools are based on warping function method and direct matching method. However, existing tools can hardly handle monotonic and non-monotonic RT shifts simultaneously. Here, we develop a deep learning-based RT alignment tool, DeepRTAlign, for large cohort LC-MS data analysis. DeepRTAlign has been demonstrated to have improved performances by benchmarking it against current state-of-the-art approaches on multiple real-world and simulated proteomic and metabolomic datasets. The results also show that DeepRTAlign can improve identification sensitivity without compromising quantitative accuracy. Furthermore, using the MS features aligned by DeepRTAlign, we trained and validated a robust classifier to predict the early recurrence of hepatocellular carcinoma. DeepRTAlign provides an advanced solution to RT alignment in large cohort LC-MS studies, which is currently a major bottleneck in proteomics and metabolomics research.

Learning Semantic Segmentation of Large-Scale Point Clouds With Random Sampling.

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass up to 200× faster than existing approaches. Moreover, extensive experiments on five large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, NPM3D and S3DIS, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.

Learning With Stochastic Guidance for Robot Navigation.

Due to the sparse rewards and high degree of environmental variation, reinforcement learning approaches, such as deep deterministic policy gradient (DDPG), are plagued by issues of high variance when applied in complex real-world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an agent to choose between high- and low-variance policies. The stochastic switch can be jointly trained with the original DDPG in the same framework. In this article, we demonstrate the power of the framework in a navigation task, where the robot can dynamically choose to learn through exploration or to use the output of a heuristic controller as guidance. Instead of starting from completely random actions, the navigation capability of a robot can be quickly bootstrapped by several simple independent controllers. The experimental results show that with the aid of stochastic guidance, we are able to effectively and efficiently train DDPG navigation policies and achieve significantly better performance than state-of-the-art baseline models.

Effects of spongioplasty on neourethral function following hypospadias repair: an experimental study in rabbits

ABSTRACT Purpose: Spongioplasty (mobilization and midline approximation of the two branches of the bifid dysplastic distal corpus spongiosum) can form a covering layer for the neourethra to prevent urethrocutaneous fistula in hypospadias repair surgery. However, it remains unclear whether spongioplasty affects neourethral function. The objective of this study was to compare neourethral function after hypospadias repair with and without spongioplasty. Materials and Methods: Fourteen congenital hypospadiac New Zealand male rabbits were randomly allocated into two groups, seven animals underwent Duplay hypospadias repair and spongioplasty (experimental group), while seven underwent Duplay surgery alone (control group). Functional differences between groups were assessed by comparing neourethral compliance and flow rate. Two months after surgery, in vivo neourethral compliance was assessed by measuring intraluminal pressure with a digital pressure meter of an isolated neourethral segment, following progressive distension with 1, 2, and 3mL of air. Penises were harvested for uroflowmetry test using a simple device. Results: Postoperatively, fistula developed in one and zero rabbits in the control and experimental groups, respectively. Mean pressures tended to be higher in the experimental group than in the control group (82.14 vs. 69.57, 188.43 vs. 143.26, and 244.71 vs. 186.29mmHg for 1, 2, and 3mL of air, respectively), but the difference was not statistically significant. Mean flow rates also did not significantly differ between the experimental and control groups (2.93mL/s vs. 3.31mL/s). Conclusion: In this congenital rabbit model, no obvious functional differences were found between reconstructed urethras after hypospadias repair with and without spongioplasty.

Three-layer reconstruction of large urethrocutaneous fistulas using scrotal-septal flaps.

INTRODUCTON: The repair of large urethrocutaneous fistulas (UCFs) commonly involves reconstruction of the urethra, waterproof layer and skin coverage, which deploy different tissues from different flaps. To simplify the multiple procedures, we explored to use one flap (a scrotal-septal flap) to reconstruct three layers in UCF repairing in one stage. METHODS: Between January 2011 and July 2012, 29 patients with large UCFs (ranging from 1.0 to 2.0 cm) were treated using scrotal-septal flaps for three-layer reconstruction. Every patient has an unbroken scrotum. The hair follicles in the donor site were destroyed using a radiosurgical knife 2 months before the operation. The flap was divided into three zones, which were flipped, folded, and extended respectively to form the urethra, waterproof layer and skin coverage. RESULTS: The patients were followed up between 6 to 12 months. No fistula recurrence was observed. All flaps survived, except in one case, in which the distal skin flap was lost but stenosis or fistula did not develop. Two patients underwent second operations to refine the aesthetic results. CONCLUSIONS: The scrotal-septal flap can be transferred in an overturning-folding-advancement fashion and can simultaneously involve the reconstruction of the urethra, waterproof barrier and skin coverage. This is a simple and reliable alternative for large UCFs (≤2 cm) repairing at the penoscrotal junction; however, it cannot be used in patients with a damaged scrotal septum.

Spontaneous ventral urethral fistula in a young man whose mother had a retained IUD in uterus during the gestation.

Urethral fistula is rare and is usually a complication of penile and urethral surgery. A few congenital cases have been reported. To our knowledge, there are only 2 reports about spontaneous ventral urethral fistula in the English literature. We present what we believe is the first case of a patient with spontaneous ventral urethral fistula whose mother had a retained IUD in uterus during the gestation.