High-accuracy protein model quality assessment using attention graph neural networks.

Great improvement has been brought to protein tertiary structure prediction through deep learning. It is important but very challenging to accurately rank and score decoy structures predicted by different models. CASP14 results show that existing quality assessment (QA) approaches lag behind the development of protein structure prediction methods, where almost all existing QA models degrade in accuracy when the target is a decoy of high quality. How to give an accurate assessment to high-accuracy decoys is particularly useful with the available of accurate structure prediction methods. Here we propose a fast and effective single-model QA method, QATEN, which can evaluate decoys only by their topological characteristics and atomic types. Our model uses graph neural networks and attention mechanisms to evaluate global and amino acid level scores, and uses specific loss functions to constrain the network to focus more on high-precision decoys and protein domains. On the CASP14 evaluation decoys, QATEN performs better than other QA models under all correlation coefficients when targeting average LDDT. QATEN shows promising performance when considering only high-accuracy decoys. Compared to the embedded evaluation modules of predicted ${C}_{\alpha^{-}} RMSD$ (pRMSD) in RosettaFold and predicted LDDT (pLDDT) in AlphaFold2, QATEN is complementary and capable of achieving better evaluation on some decoy structures generated by AlphaFold2 and RosettaFold. These results suggest that the new QATEN approach can be used as a reliable independent assessment algorithm for high-accuracy protein structure decoys.

Leveraging scaffold information to predict protein-ligand binding affinity with an empirical graph neural network.

Protein-ligand binding affinity prediction is an important task in structural bioinformatics for drug discovery and design. Although various scoring functions (SFs) have been proposed, it remains challenging to accurately evaluate the binding affinity of a protein-ligand complex with the known bound structure because of the potential preference of scoring system. In recent years, deep learning (DL) techniques have been applied to SFs without sophisticated feature engineering. Nevertheless, existing methods cannot model the differential contribution of atoms in various regions of proteins, and the relationship between atom properties and intermolecular distance is also not fully explored. We propose a novel empirical graph neural network for accurate protein-ligand binding affinity prediction (EGNA). Graphs of protein, ligand and their interactions are constructed based on different regions of each bound complex. Proteins and ligands are effectively represented by graph convolutional layers, enabling the EGNA to capture interaction patterns precisely by simulating empirical SFs. The contributions of different factors on binding affinity can thus be transparently investigated. EGNA is compared with the state-of-the-art machine learning-based SFs on two widely used benchmark data sets. The results demonstrate the superiority of EGNA and its good generalization capability.

CoCoPRED: coiled-coil protein structural feature prediction from amino acid sequence using deep neural networks.

MOTIVATION: Coiled-coil is composed of two or more helices that are wound around each other. It widely exists in proteins and has been discovered to play a variety of critical roles in biology processes. Generally, there are three types of structural features in coiled-coil: coiled-coil domain (CCD), oligomeric state and register. However, most of the existing computational tools only focus on one of them. RESULTS: Here, we describe a new deep learning model, CoCoPRED, which is based on convolutional layers, bidirectional long short-term memory, and attention mechanism. It has three networks, i.e. CCD network, oligomeric state network, and register network, corresponding to the three types of structural features in coiled-coil. This means CoCoPRED has the ability of fulfilling comprehensive prediction for coiled-coil proteins. Through the 5-fold cross-validation experiment, we demonstrate that CoCoPRED can achieve better performance than the state-of-the-art models on both CCD prediction and oligomeric state prediction. Further analysis suggests the CCD prediction may be a performance indicator of the oligomeric state prediction in CoCoPRED. The attention heads in CoCoPRED indicate that registers a, b and e are more crucial for the oligomeric state prediction. AVAILABILITY AND IMPLEMENTATION: CoCoPRED is available at http://www.csbio.sjtu.edu.cn/bioinf/CoCoPRED. The datasets used in this research can also be downloaded from the website. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Fast protein structure comparison through effective representation learning with contrastive graph neural networks.

Protein structure alignment algorithms are often time-consuming, resulting in challenges for large-scale protein structure similarity-based retrieval. There is an urgent need for more efficient structure comparison approaches as the number of protein structures increases rapidly. In this paper, we propose an effective graph-based protein structure representation learning method, GraSR, for fast and accurate structure comparison. In GraSR, a graph is constructed based on the intra-residue distance derived from the tertiary structure. Then, deep graph neural networks (GNNs) with a short-cut connection learn graph representations of the tertiary structures under a contrastive learning framework. To further improve GraSR, a novel dynamic training data partition strategy and length-scaling cosine distance are introduced. We objectively evaluate our method GraSR on SCOPe v2.07 and a new released independent test set from PDB database with a designed comprehensive performance metric. Compared with other state-of-the-art methods, GraSR achieves about 7%-10% improvement on two benchmark datasets. GraSR is also much faster than alignment-based methods. We dig into the model and observe that the superiority of GraSR is mainly brought by the learned discriminative residue-level and global descriptors. The web-server and source code of GraSR are freely available at www.csbio.sjtu.edu.cn/bioinf/GraSR/ for academic use.

GraphBind: protein structural context embedded rules learned by hierarchical graph neural networks for recognizing nucleic-acid-binding residues.

Knowledge of the interactions between proteins and nucleic acids is the basis of understanding various biological activities and designing new drugs. How to accurately identify the nucleic-acid-binding residues remains a challenging task. In this paper, we propose an accurate predictor, GraphBind, for identifying nucleic-acid-binding residues on proteins based on an end-to-end graph neural network. Considering that binding sites often behave in highly conservative patterns on local tertiary structures, we first construct graphs based on the structural contexts of target residues and their spatial neighborhood. Then, hierarchical graph neural networks (HGNNs) are used to embed the latent local patterns of structural and bio-physicochemical characteristics for binding residue recognition. We comprehensively evaluate GraphBind on DNA/RNA benchmark datasets. The results demonstrate the superior performance of GraphBind than state-of-the-art methods. Moreover, GraphBind is extended to other ligand-binding residue prediction to verify its generalization capability. Web server of GraphBind is freely available at http://www.csbio.sjtu.edu.cn/bioinf/GraphBind/.

Protein-ligand binding residue prediction enhancement through hybrid deep heterogeneous learning of sequence and structure data.

MOTIVATION: Knowledge of protein-ligand binding residues is important for understanding the functions of proteins and their interaction mechanisms. From experimentally solved protein structures, how to accurately identify its potential binding sites of a specific ligand on the protein is still a challenging problem. Compared with structure-alignment-based methods, machine learning algorithms provide an alternative flexible solution which is less dependent on annotated homogeneous protein structures. Several factors are important for an efficient protein-ligand prediction model, e.g. discriminative feature representation and effective learning architecture to deal with both the large-scale and severely imbalanced data. RESULTS: In this study, we propose a novel deep-learning-based method called DELIA for protein-ligand binding residue prediction. In DELIA, a hybrid deep neural network is designed to integrate 1D sequence-based features with 2D structure-based amino acid distance matrices. To overcome the problem of severe data imbalance between the binding and nonbinding residues, strategies of oversampling in mini-batch, random undersampling and stacking ensemble are designed to enhance the model. Experimental results on five benchmark datasets demonstrate the effectiveness of proposed DELIA pipeline. AVAILABILITY AND IMPLEMENTATION: The web server of DELIA is available at www.csbio.sjtu.edu.cn/bioinf/delia/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Salt-template preparation of Mo5N6 nanosheets with peroxidase- and catalase-like activities and application for colorimetric determination of 4-aminophenol.

Mo5N6 nanosheets were synthesized by a nickel-induced growth method and were found to possess peroxidase-like activity in acidic condition and catalase-like activity in weak basic condition. In acidic condition, Mo5N6 nanosheets can catalyze the oxidation of 3,3',5,5'-tetramethylbenzidine (TMB) by H2O2 to form a blue color product (TMBOX). At the co-existence of 4-aminophenol (4-AP), 4-AP can react with H2O2 and TMBOX, resulting in the decrease of TMBOX and the fading of blue color. Therefore, a facile, sensitive colorimetric method for the quantitative detection of 4-AP was developed. The linear range for 4-AP was 1.0 to 80.0 µmol⋅L‒1 (R2 = 0.999), and the detection limit was 0.56 µmol⋅L‒1 based on 3σ/k. Resorcinol, aniline, humic acid, and common ions and anions in surface water did not interfere the determination of 4-AP. This colorimetric method was applied to measure the 4-AP in real water sample from Wulong River in Fujian Province of China. The relative standard deviation for the determination of 4-AP was ranged from 0.03 to 1.88%, and the recoveries from spiked samples were ranged between 99.2 and 107.6%. The determination results were consistent with those obtained by HPLC.

miR-22-3p Suppresses Endothelial Progenitor Cell Proliferation and Migration via Inhibiting Onecut 1 (OC1)/Vascular Endothelial Growth Factor A (VEGFA) Signaling Pathway and Its Clinical Significance in Venous Thrombosis.

BACKGROUND Proliferation and migration play crucial roles in various physiological processes, especially in injured endothelial repair. Endothelial progenitor cells (EPCs), as the precursors of endothelial cell, are involved in the regeneration of the endothelial lining of blood vessels. Furthermore, EPCs were found to be a potential choice for venous thrombosis (VT) treatment. MATERIAL AND METHODS EPCs were isolated from human peripheral blood of healthy adults and VT patients. Differently expressed micro(mi)RNAs were examined by quantitative real-time polymerase chain reaction, after which proliferative capacity and migration effect were tested by Cell-Counting Kit 8, scratch wound assay, and transwell assays. Bioinformatic analysis was applied to investigate the potential target messenger ribonucleic acid and a dual-luciferase reporting system was utilized to confirm the binding of miR-22-3p to its target gene. Western blot was carried out to detect candidate protein expression level. Finally, miR-22-3p expression was monitored in VT patients during follow-up to assess its correlation with prognosis of VT. RESULTS Our data revealed that miR-22-3p was upregulated in EPCs derived from deep VT (DVT) individuals and suppression of miR-22-3p contributed to proliferation and migration of EPCs. In addition, miR-22-3p/onecut 1 (OC1)/vascular endothelial growth factor A (VEGFA) signaling pathway was involved in regulating EPC migration and proliferation. In addition, lower expression of miR-22-3p in DVT patients indicated decreased risk of VT recurrence. CONCLUSIONS Our results suggest that miR-22-3p regulates OC1/VEGFA signaling and is involved in regulating EPC proliferation and migration. The expression level of miR-22-3p could be monitored to predict DVT patients' prognosis.

Oxidation of propyl paraben by ferrate(VI): Kinetics, products, and toxicity assessment.

Propyl paraben (propyl 4-hydroxybenzoate, PPB), one of the typically used paraben species in various pharmaceutical and personal care products, has been found in different aquatic environment, which could affect the water quality and human health. In this paper, the degradation of PPB by aqueous ferrate (Fe(VI)) was investigated in different water matrix and reaction kinetics as a function of pH was determined. Intermediate products of the degradation process were isolated and characterized by the high performance liquid chromatography/mass spectrometry/mass spectrometry techniques. Acute and chronic toxicities during water treatment of PPB using Fe(VI) were calculated using the ECOSAR program at three trophic levels. The obtained apparent second-order rate constant (kapp) for PPB reaction with Fe(VI) ranged from 99.6 ± 0.4 M-1 s-1 to 15.0 ± 0.1 M-1 s-1 with the half-life (t1/2) ranging from 154 s to 1026 s at pH 6.5-10.0 for an Fe(VI) concentration of 600 µM. The proposed pathway for the oxidation of PPB by Fe(VI) involves one electron transfer of phenoxyl radical and breaking of the ether bond. In general, the oxidation of PPB by ferrate resulted in a significant decrease in toxicity at three trophic levels.

Protein tyrosine phosphatases receptor type D is a potential tumour suppressor gene inactivated by deoxyribonucleic acid methylation in paediatric acute myeloid leukaemia.

AIM: Protein tyrosine phosphatases receptor type D (PTPRD) is a tumour suppressor gene, and its epigenetic silencing is frequently found in glioblastoma. As aberrant deoxyribonucleic acid (DNA) methylation patterning has been shown to play a role in leukaemogenesis, we studied the promoter methylation, expression profiles and molecular functions of PTPRD in paediatric patients with acute myeloid leukaemia (AML). METHODS: Bone marrow specimens were obtained from 32 Chinese patients with a mean age of 7.2 years (range 1.1-16.5). PTPRD and methylation status were evaluated by real-time polymerase chain reaction (PCR) and methylation-specific PCR. Western blot and flow cytometry techniques were also used. RESULTS: PTPRD expression was decreased by promoter region methylation in six AML cells and methylated in 21 (65.6%) of the 32 samples. In addition, PTPRD expression could be induced by the DNA demethylating agent 5-aza-2'-deoxycytidine. Furthermore, functional studies showed that overexpression of PTPRD in AML cells inhibited cell proliferation and clonogenicity as well as inducing apoptosis. However, PTPRD knockdown increased cell proliferation. These effects were associated with downregulation of cyclin D1, c-myc and upregulation of Bax. CONCLUSION: The results of this study demonstrated that PTPRD was a potential tumour suppressor gene inactivated by DNA methylation in paediatric AML.

Clinical Outcome of Middle Thoracic Esophageal Cancer with Intrathoracic or Cervical Anastomosis.

BACKGROUNDS: What is the optimal way for the middle esophageal cancer? It is still controversial. In this study, the clinical outcome of middle thoracic esophageal cancer with either intrathoracic or cervical anastomosis was analyzed in our department. PATIENTS AND METHODS: A total of 205 patients who suffered from middle thoracic esophageal cancer were divided into two groups. In group A, 91 patients received intrathoracic anastomosis above aortic arch after esophageal resection via single left thoracotomy, and in group B, 114 patients received cervical anastomosis after esophageal resection via right thoracotomy and median laparotomy. Data of these patients were collected, and morbidity and mortality were analyzed retrospectively. Survival rate was estimated using the Kaplan-Meier method and comparisons between groups were performed with log-rank test. Univariate and multivariate analyses were performed using Cox model to look for independent predictors of survival. RESULTS: Postoperative complications occurred more frequently in group B, such as hemorrhage (p = 0.011), wound infection (p = 0.032), and temporary paresis of the recurrent laryngeal nerve (p = 0.001). Morbidity of anastomotic leak was higher in group B (8.8 vs. 2.2%; p = 0.048), but the associated mortality was not increased. The extent of radical esophagectomy and lymphadenectomy was much greater in group B; therefore, longer esophagus was resected that reduced the cancer residual rate, and more positive lymph nodes were detected that enhanced the accuracy of clinical staging. Fortunately, more patients received adjuvant therapy after operation in group B, and the 5-year survival rate was improved. CONCLUSION: Anastomotic leak rate was higher in cervical anastomosis but with lower mortality. The 5-year survival rate was improved in cervical anastomosis group. The present data support the assumption that cervical anastomosis is a safer and more beneficial procedure for patients with middle thoracic esophageal cancer.

Comparison of thoracolaparoscopic esophagectomy with cervical anastomosis with McKeown esophagectomy for middle esophageal cancer.

BACKGROUND: In China, the middle esophageal squamous cell cancer is the most common tumor type, and Mckeown esophagectomy (ME) is preferably adopted by thoracic surgeon. But, the surgical trauma of ME is great. Thoracolaparoscopic esophagectomy (TE) was developed to decrease the operative stress; however, the safety and efficacy were not defined. In this study, clinical outcomes were compared between patients who received ME and TE. METHODS: The data of 113 patients who suffered from middle-thoracic esophageal cancer during the same period were collected. Sixty-two patients received ME (ME group), and 51 patients received TE (TE group). Patients' demographics and short-term clinicopathologic outcomes were comparable between the two groups. Survival rate was estimated using the Kaplan-Meier method, and comparisons between groups were performed with log-rank test. RESULTS: Patients in TE group had lower body mass index (BMI). Preoperative tumor stage in TE group was much earlier. Both overall and thoracic operation time were longer in TE group. The blood loss during operation and postoperative day (POD) 1 was less in TE group, which contributed to the less blood transfusion. In TE group, postoperative incidence of pulmonary complications and atrial fibrillation (p = 0.035 and p = 0.033) was lower; the inflammatory response and incision pain were significantly alleviated; the ICU and in-hospital stay was shorter as well because of less surgical trauma. No statistically significant difference was found between two groups in terms of overall survival or disease-free survival. CONCLUSIONS: The efficacy and safety of TE were supported by the selected patients in this cohort study. Although it is lack of randomness in this research, some advantages of TE were gratifying such as lower postoperative complications and similar survival with ME. A multicenter prospective randomized study is now required.

Mo5N6 nanosheets for fluorescent quenching and target recognition: Highly selectively sensing of sodium hexametaphosphate.

Typical fluorescent biosensors use fluorescently labeled ssDNA for target recognition and nanomaterials for signal transduction. Herein, we propose a reverse sensing strategy that Mo5N6 nanosheets are used for target recognition while fluorescein (FAM)-labeled ssDNA only serves for signal generation. We discover that Mo5N6 nanosheets show high fluorescence quenching ability (>95%) and selective recognition for sodium hexametaphosphate (SHMP). After FAM-labeled ssDNA is adsorbed on Mo5N6 nanosheets, the fluorescence is quenched due to the photoinduced electron transfer (PET) effect between FAM and Mo5N6 nanosheets. SHMP can specifically displace the adsorbed FAM-labeled ssDNA from Mo5N6 nanosheets, resulting in more than 80% fluorescence recovery on addition of 5 µmol L-1 SHMP. This biosensor can sensitively detect SHMP down to 150 nmol L-1 and selectively recognize SHMP over glucose, lactose, common amino acids, Zn2+, Mg2+, Ca2+ and other phosphates (such as Na2HPO4, sodium pyrophosphate, sodium tripolyphosphate). This biosensor also shows great potential for the detection of SHMP in bacon sample. This work not only provides a facile sensitive and selective biosensor for SHMP but also exploits the application of transition metal nitrides in the field of sensing and biosensing.

Identification of 5 hub genes for diagnosis of coronary artery disease.

Background: Coronary artery disease (CAD) is a main cause leading to increasing mortality of cardiovascular disease (CVD) worldwide. We aimed to discover marker genes and develop a diagnostic model for CAD. Methods: CAD-related target genes were searched from DisGeNET. Count expression data and clinical information were screened from the GSE202626 dataset. edgeR package identified differentially expressed genes (DEGs). Using online STRING tool and Cytoscape, protein-protein reactions (PPI) were predicted. WebGestaltR package was employed to functional enrichment analysis. We used Metascape to conduct module-based network analysis. VarElect algorithm provided genes-phenotype correlation analysis. Immune infiltration was assessed by ESTIMATE package and ssGSEA analysis. mRNAsi was determined by one class logistic regression (OCLR). A diagnostic model was constructed by SVM algorithm. Results: 162 target genes were screened by intersection 1,714 DEGs and 1,708 CAD related target genes. 137 target genes of the 162 target genes were obtained using PPI analysis, in which those targets were enriched in inflammatory cytokine pathways, such as chemokine signaling pathway, and IL-17 signaling pathway. From the above 137 target genes, four functional modules (MCODE1-4) were extracted. From the 162 potential targets, CAD phenotype were directly and indirectly associated with 161 genes and 22 genes, respectively. Finally, 5 hub genes (CCL2, PTGS2, NLRP3, VEGFA, LTA) were screened by intersections with the top 20, directly and indirectly, and genes in MCODE1. PTGS2, NLRP3 and VEGFA were positively, while LTA was negatively correlated with immune cells scores. PTGS2, NLRP3 and VEGFA were negatively, while LTA was positively correlated with mRNAsi. A diagnostic model was successfully established, evidenced by 92.59% sensitivity and AUC was 0.9230 in the GSE202625 dataset and 94.11% sensitivity and AUC was 0.9706 in GSE120774 dataset. Conclusion: In this work, we identified 5 hub genes, which may be associated with CAD development.

Anti-apoptotic and anti-fibrotic efficacy of exercise training in hypertensive hearts: A systematic review.

Background: This review aims to summarize the antiapoptotic, pro-survival, and antifibrotic effects of exercise training in hypertensive hearts. Methods: Keyword searches were conducted in PubMed, Web of Science, and Scopus in May 2021. Research published in English on the effects of exercise training on the apoptosis, survival, and fibrosis pathways in hypertension was included. The CAMARADES checklist was used to determine the quality of the studies. Two reviewers independently implemented predesigned protocols for the search and selection of studies, the assessment of study quality, and the evaluation of the strength of evidence. Results: Eleven studies were included after selection. The duration of the exercise training ranged from 5 to 27 weeks. Nine studies showed that exercise training improved cardiac survival rates by increasing IGF-1, IGF-1 receptor, p-PI3K, Bcl-2, HSP 72, and p-Akt. Furthermore, 10 studies showed that exercise training reduced apoptotic pathways by downregulating Bid, t-Bid, Bad, Bak, Bax, TNF, and FADD. Finally, two studies reported the modification and subsequent improvement of physiological characteristics of fibrosis and decreased MAPK p38 and PTEN levels by exercise training in the left ventricle of the heart. Conclusions: The findings of the review showed that exercise training could improve cardiac survival rates and attenuate cardiac apoptotic and fibrotic pathways in hypertension, suggesting that exercise training could act as a therapeutic approach to prevent hypertension-induced cardiac apoptosis and fibrosis. Systematic Review Registration: https://www.crd.york.ac.uk, identifier: CRD42021254118.

Lobar or sublobar resection for early-stage second primary lung cancer ≤ 3 cm in size: a SEER population-based study.

PURPOSE: Surgical strategy for second primary lung cancer (SPLC) may be more conservative due to influence of first primary lung cancer (FPLC). The optimal surgical method for SPLC warrants discussion. We aimed to explore a more suitable surgical approach for early-stage (T1-T2N0, ≤ 3 cm) SPLC and provide insights for clinical practice. METHODS: A retrospective study was conducted using data from the Surveillance, Epidemiology and End Results database between 2004 and 2018, and data of patients with early-stage SPLC who underwent secondary surgery were collected. Propensity score matching (PSM) reduced potential bias between lobar and sublobar resection groups. The effect of lobar and sublobar resection on overall survival (OS) was assessed in all patients and subgroups. RESULTS: A total of 714 patients who met the study entry criteria were enrolled, including 476 patients in the sublobar resection group (66.67%) and 238 patients in the lobar resection group (33.33%). There was no difference in OS between the lobar and sublobar resection groups before and after PSM (P = 0.289) and (P = 0.608), respectively. Subgroup analyses showed that lobar resection achieved a significantly better OS than sublobar resection only in patients with an SPLC tumor size of 2-3 cm (P < 0.05). CONCLUSION: The OS of sublobar resection was not significantly different from that of lobar resection for early-stage SPLC. For SPLC with a 2-3 cm tumor size, lobar resection is more advantageous than sublobar resection.

[Preliminary Recommendations on the Timing of Lung Surgery after 
Novel Coronavirus Infection in Patients with Pulmonary Nodules and Lung Cancer].

In recent years, the corona virus disease 2019 (COVID-19) pandemic has had a huge impact on the global medical, political and economic fields. Since the beginning of the COVID-19 epidemic, our understanding of the impact of COVID-19 has grown exponentially. Recently, the COVID-19 epidemic has changed rapidly in China, and there has been controversy over how to carry out surgical operations for patients with lung neoplastic lesions. Some studies have shown that lung cancer patients undergoing surgery are more likely to experience respiratory failure and perioperative death after contracting COVID-19 than the general population, however, delays in cancer treatment are also associated with increased mortality among these patients. In particular, the novel coronavirus Omikron variant has a higher transmissibility and may escape the immunity obtained through the previous novel coronavirus infection and vaccination. In order to minimize the risk of novel coronavirus infection in surgical patients, it is necessary to develop new treatment guidelines, expert consensus and preventive measures. However, the current rapid change of the epidemic situation has led to insufficient time and evidence to develop guidelines and consensus. Therefore, thoracic surgeons need to evaluate specific patient populations at higher risk of severe complications before surgery and weigh the benefit of surgical treatment against the risk of novel coronavirus infection. We try to give some recommendations on lung surgery during the current domestic epidemic situation based on the guidelines and consensus of oncology and thoracic surgery organizations in different regions on lung surgery.
.

BindWeb: A web server for ligand binding residue and pocket prediction from protein structures.

Knowledge of protein-ligand interactions is beneficial for biological process analysis and drug design. Given the complexity of the interactions and the inadequacy of experimental data, accurate ligand binding residue and pocket prediction remains challenging. In this study, we introduce an easy-to-use web server BindWeb for ligand-specific and ligand-general binding residue and pocket prediction from protein structures. BindWeb integrates a graph neural network GraphBind with a hybrid convolutional neural network and bidirectional long short-term memory network DELIA to identify binding residues. Furthermore, BindWeb clusters the predicted binding residues to binding pockets with mean shift clustering. The experimental results and case study demonstrate that BindWeb benefits from the complementarity of two base methods. BindWeb is freely available for academic use at http://www.csbio.sjtu.edu.cn/bioinf/BindWeb/.

Molecular Features of a Primary Transmural Tracheal Schwannoma: Clinical Experience and Review of the Literature.

Primary tracheal schwannoma is a rare disease with no specific symptoms. At the molecular level, neurofibromatosis type 2 (NF2) gene mutation of Schwann cells is the major tumorigenic element. Herein, we present the case of a 54-year-old man with refractory shortness of breath and dry cough, which was resistant to bronchodilator treatment. Computed tomography revealed a transmural mass in the dorsolateral trachea. The tumor was surgically resected, and the diagnosis of schwannoma was confirmed by pathological examination. Furthermore, for this case, we performed whole-exome sequencing and identified several novel mutated schwannoma genes. The specific roles of these mutations need further confirmation.

Ab-Initio Membrane Protein Amphipathic Helix Structure Prediction Using Deep Neural Networks.

Amphipathic helix (AH)features the segregation of polar and nonpolar residues and plays important roles in many membrane-associated biological processes through interacting with both the lipid and the soluble phases. Although the AH structure has been discovered for a long time, few ab initio machine learning-based prediction models have been reported, due to the limited amount of training data. In this study, we report a new deep learning-based prediction model, which is composed of a residual neural network and the uneven-thresholds decision algorithm. It is constructed on 121 membrane proteins, in total 51640 residue samples, which are curated from an up-to-date membrane protein structure database. Through a rigid 10-fold nested cross-validation experiment, we demonstrate that our model can achieve promising predictions and exceed current state-of-the-art approaches in this field. This presents a new avenue for accurately predicting AHs. Analysis on the contribution of the input residues and some cases further reveals the high interpretability and the generalization of our model.