An individual-level weighted artificial neural network method to improve the systematic bias in BrainAGE analysis.

BrainAGE is a commonly used machine learning technique to measure the accelerated/delayed development pattern of human brain structure/function with neuropsychiatric disorders. However, recent studies have shown a systematic bias ("regression toward mean" effect) in the BrainAGE method, which indicates that the prediction error is not uniformly distributed across Chronological Ages: for the older individuals, the Brain Ages would be under-estimated but would be over-estimated for the younger individuals. In the present study, we propose an individual-level weighted artificial neural network method and apply it to simulation datasets (containing 5000 simulated subjects) and a real dataset (containing 135 subjects). Results show that compared with traditional machine learning methods, the individual-level weighted strategy can significantly reduce the "regression toward mean" effect, while the prediction performance can achieve the comparable level with traditional machine learning methods. Further analysis indicates that the sigmoid active function for artificial neural network shows better performance than the relu active function. The present study provides a novel strategy to reduce the "regression toward mean" effect of BrainAGE analysis, which is helpful to improve accuracy in exploring the atypical brain structure/function development pattern of neuropsychiatric disorders.

Different functional connectivity optimal frequency in autism compared with healthy controls and the relationship with social communication deficits: Evidence from gene expression and behavior symptom analyses.

Studies have reported that different brain regions/connections possess distinct frequency properties, which are related to brain function. Previous studies have proposed altered brain activity frequency and frequency-specific functional connectivity (FC) patterns in autism spectrum disorder (ASD), implying the varied dominant frequency of FC in ASD. However, the difference of the dominant frequency of FC between ASD and healthy controls (HCs) remains unclear. In the present study, the dominant frequency of FC was measured by FC optimal frequency, which was defined as the intermediate of the frequency bin at which the FC strength could reach the maximum. A multivariate pattern analysis was conducted to determine whether the FC optimal frequency in ASD differs from that in HCs. Partial least squares regression (PLSR) and enrichment analyses were conducted to determine the relationship between the FC optimal frequency difference of ASD/HCs and cortical gene expression. PLSR analyses were also performed to explore the relationship between FC optimal frequency and the clinical symptoms of ASD. Results showed a significant difference of FC optimal frequency between ASD and HCs. Some genes whose cortical expression patterns are related to the FC optimal frequency difference of ASD/HCs were enriched for social communication problems. Meanwhile, the FC optimal frequency in ASD was significantly related to social communication symptoms. These results may help us understand the neuro-mechanism of the social communication deficits in ASD.

Electromagnetic navigational bronchoscopy-directed dye marking for locating pulmonary nodules.

BACKGROUND: Small peripheral pulmonary nodules, which are usually deep-seated with no visual markers on the pleural surface, are often difficult to locate during surgery. At present, CT-guided percutaneous techniques are used to locate pulmonary nodules, but this method has many limitations. Thus, we aimed to evaluate the accuracy and feasibility of electromagnetic navigational bronchoscopy (ENB) with pleural dye to locate small peripheral pulmonary nodules before video-associated thoracic surgery (VATS). METHODS: The ENB localisation procedure was performed under general anaesthesia in an operating room. Once the locatable guide wire, covered with a sheath, reached the ideal location, it was withdrawn and 0.2-1.0 mL of methylene blue/indocyanine green was injected through the guide sheath. Thereafter, 20-60 mL of air was instilled to disperse the dye to the pleura near the nodules. VATS was then performed immediately. RESULTS: Study subjects included 25 patients with 28 nodules. The mean largest diameter of the pulmonary nodules was 11.8 mm (range, 6.0-24.0 mm), and the mean distance from the nearest pleural surface was 13.4 mm (range, 2.5-34.9 mm). After the ENB-guided localisation procedure was completed, the dye was visualised in 23 nodules (82.1%) using VATS. The average duration of the ENB-guided pleural dye marking procedure was 12.6 min (range, 4-30 min). The resection margins were negative in all malignant nodules. Complications unrelated to the ENB-guided localisation procedure occurred in two patients, including one case of haemorrhage and one case of slow intraoperative heart rate. CONCLUSION: ENB can be used to safely and accurately locate small peripheral pulmonary nodules and guide surgical resection. TRIAL REGISTRATION NUMBER: ChiCTR1900021963.

BDB: biopanning data bank.

The BDB database (http://immunet.cn/bdb) is an update of the MimoDB database, which was previously described in the 2012 Nucleic Acids Research Database issue. The rebranded name BDB is short for Biopanning Data Bank, which aims to be a portal for biopanning results of the combinatorial peptide library. Last updated in July 2015, BDB contains 2904 sets of biopanning data collected from 1322 peer-reviewed papers. It contains 25,786 peptide sequences, 1704 targets, 492 known templates, 447 peptide libraries and 310 crystal structures of target-template or target-peptide complexes. All data stored in BDB were revisited, and information on peptide affinity, measurement method and procedures was added for 2298 peptides from 411 sets of biopanning data from 246 published papers. In addition, a more professional and user-friendly web interface was implemented, a more detailed help system was designed, and a new on-the-fly data visualization tool and a series of tools for data analysis were integrated. With these new data and tools made available, we expect that the BDB database would become a major resource for scholars using phage display, with improved utility for biopanning and related scientific communities.

Current Development of Data Resources and Bioinformatics Tools for Anticoronavirus Peptide.

BACKGROUND: Since December 2019, the emergence of severe acute respiratory syndrome coronavirus 2, which gave rise to coronavirus disease 2019 (COVID-19), has considerably impacted global health. The identification of effective anticoronavirus peptides (ACVPs) and the establishment of robust data storage methods are critical in the fight against COVID-19. Traditional wet-lab peptide discovery approaches are timeconsuming and labor-intensive. With advancements in computer technology and bioinformatics, machine learning has gained prominence in the extraction of functional peptides from extensive datasets. METHODS: In this study, we comprehensively review data resources and predictors related to ACVPs published over the past two decades. In addition, we analyze the influence of various factors on model performance. RESULTS: We have reviewed nine ACVP-containing databases, which integrate detailed information on protein fragments effective against coronaviruses, providing crucial references for the development of antiviral drugs and vaccines. Additionally, we have assessed 15 peptide predictors for antiviral or specifically anticoronavirus activity. These predictors employ computational models to swiftly screen potential antiviral candidates, offering an efficient pathway for drug development. CONCLUSION: Our study provides conclusive results and insights into the performance of different computational methods, and sheds light on the future trajectory of bioinformatics tools for ACVPs. This work offers a representative overview of contributions to the field, with an emphasis on the crucial role of ACVPs in combating COVID-19.

[Non-real-time endobronchial bronchoscopy ultrasound assisted transbronchial lung biopsy in diagnosing peripheral pulmonary lesions].

OBJECTIVE: To evaluate the role of non-real-time endobronchial bronchoscopy ultrasound(EBUS) assisted transbronchial lung biopsy (TBLB) in diagnosing peripheral pulmonary lesions (PPL). METHODS: One hundred and five patients [68 males and 37 females, mean age (59 ± 12) years, ranged from 39 - 81 years] with PPL confirmed by computered tomography (CT) were recruited in this study between June 1st 2011 and March 1st 2012. All cases received bronchoscopy examinations and presented with roughly normal results. Fifty-four cases received EBUS examinations. For peripheral lesions with accessible EBUS images, blind biopsy was performed with biopsy forceps through pathways of the ultrasonic probe after the retreat of the probe. In those cases without accessible EBUS images, blind biopsy was performed based on the localization by image data. The other 51 cases without EBUS testing underwent blind biopsy on the localization by image data. Positive rates of pathological diagnosis of the 2 groups were compared. Analysis was by χ(2)-test. RESULTS: In 54 patients who received EBUS examinations, 76% (41/54) of PPLs were detected performed by EBUS. The positive rate of the EBUS assisted TBLB group was 67% (36/54), compared with 45% (23/51) in the general TBLB group. There was a better diagnostic rate (P < 0.05) in the EBUS assisted TBLB group than the general TBLB group. Thirteen patients without accessible EBUS images obtained negative pathological results. The diagnosis rate of EBUS assisted TBLB on lesions with ≤ 30 mm minimum diameter was 44% (8/18), lower than 78% (28/36) on lesions with > 30 mm minimum diameter (P < 0.05). In terms of diagnosis rate on lesions with ≤ 30 mm minimum diameter, EBUS assisted TBLB was 44% (8/18), higher than 12% (2/17) of TBLB alone (P < 0.05). As for lesions with > 30 mm minimum diameter, diagnosis rate of EBUS assisted TBLB was 52% (28/54) and TBLB alone was 41% (21/51), representing insignificant difference (P > 0.05). In the EBUS assisted TBLB group, we performed 269 blind biopsies, with an average of 4.8 times per case, whereas the general TBLB group required 398 times, with an average of 7.8 times per case. EBUS assisted TBLB decreased the operation times of blind biopsy (P < 0.05) to acquire adequate and appropriate specimen. Complications of biopsy occurred in this study included slight haemoptysis (61/105, 58.1%), chest pain (25/105, 23.8%) and pneumothorax (2/105, 1.9%). Patients with these complications recovered spontaneously without special managements. CONCLUSIONS: Non-real-time EBUS assisted TBLB could improve diagnostic positive rate without increasing operational risk. In most cases, the blind biopsy did not succeed if EBUS failed to detect the lesions. The success rate of non-real-time EBUS assisted TBLB was related to the minimum diameter of PPL. In terms of diagnosis rate on lesions with ≤ 30 mm minimum diameter, EBUS assisted TBLB was higher than TBLB alone. As for lesions with >30mm minimum diameter, there was no significant difference in the diagnosis rate between these 2 groups. EBUS assisted TBLB decreased the times of blind biopsy process (P < 0.05) to obtain adequate and appropriate specimen.

CD47Binder: Identify CD47 Binding Peptides by Combining Next-Generation Phage Display Data and Multiple Peptide Descriptors.

CD47/SIRPα pathway is a new breakthrough in the field of tumor immunity after PD-1/PD-L1. While current monoclonal antibody therapies targeting CD47/SIRPα have demonstrated some anti-tumor effectiveness, there are several inherent limitations associated with these formulations. In the paper, we developed a predictive model that combines next-generation phage display (NGPD) and traditional machine learning methods to distinguish CD47 binding peptides. First, we utilized NGPD biopanning technology to screen CD47 binding peptides. Second, ten traditional machine learning methods based on multiple peptide descriptors and three deep learning methods were used to build computational models for identifying CD47 binding peptides. Finally, we proposed an integrated model based on support vector machine. During the five-fold cross-validation, the integrated predictor demonstrated specificity, accuracy, and sensitivity of 0.755, 0.764, and 0.772, respectively. Furthermore, an online bioinformatics tool called CD47Binder has been developed for the integrated predictor. This tool is readily accessible on http://i.uestc.edu.cn/CD47Binder/cgi-bin/CD47Binder.pl .

[Quantitative analysis of the ultrasonogram and histological findings in normal airway wall].

OBJECTIVE: To find out the correlation between endobronchial ultrasonography (EBUS) images and histologic findings in normal bronchial wall via quantitative analysis of the airway wall thickness and the layer thickness. METHODS: From July 1st to December 31th in 2010, patients underwent lobectomy performed endobronchial ultrasonography (EBUS) before surgery and frost pathological examination after surgery. The layer thickness of EBUS and pathological images were measured. Bland-Altman plots were used to analyze the agreement between EBUS measurements and pathological measurements. RESULTS: Twenty-one patients were enrolled in the study. Five layers of the wall were distinguished at the ultrasonogram. Starting on the luminal side, the first, third and fifth layer (L1, L3, L5) were hyperechoic while the second, fourth layer (L2, L4) were hypoechoic. The wall thickness with good agreement was almost equal between the 2 kinds of images (1.877:1.745). L1 thickness was lager than the mucosa thickness (0.275:0.164). L2 thickness was smaller than the submucosa thickness (0.100:0.202). L1 + L2 thickness was almost equal to the thickness of mucosa and submucosa layer (0.375:0.366). The Bland-Altman plots showed poor agreement between the L1, L2 thickness and the mucosa thickness, the submucosa thickness while good agreement between the L1 + L2 thickness and the thickness of mucosa and submucosa layer. L3 thickness was lager than the inner perichondrium thickness (0.241:0.075), and L4 thickness was smaller than the cartilage layer thickness (0.655:0.811). L3 + L4 thickness was almost equal to thickness of the inner perichondrium and the cartilage layer (0.895:0.887). L5 thickness was almost equal to thickness of the outer perichondrium and the connective tissue outside the cartilage layer (0.533:0.491). The Bland-Altman plots showed poor agreement between the L3, L4 thickness and the inner perichondrium thickness, cartilage layer thickness, while good agreement between L5, L3 + L4, L3 + L4 + L5 thickness and the corresponding indexes. CONCLUSIONS: There is a five-layer structure on the bronchial EBUS image including the first layer at the luminal side corresponding to the mucosa and inner part of the submucosa; the second layer corresponding to the outer part of submucosal tissue; the third layer corresponding to the inner perichondrium and the inner part of the cartilage; the fourth layer corresponding to the outer part of cartilage; the fifth layer corresponding to the outer perichondrium and the connective tissue outside the cartilage layer.

AntiDMPpred: a web service for identifying anti-diabetic peptides.

Diabetes mellitus (DM) is a chronic metabolic disease that has been a major threat to human health globally, causing great economic and social adversities. The oral administration of anti-diabetic peptide drugs has become a novel route for diabetes therapy. Numerous bioactive peptides have demonstrated potential anti-diabetic properties and are promising as alternative treatment measures to prevent and manage diabetes. The computational prediction of anti-diabetic peptides can help promote peptide-based drug discovery in the process of searching newly effective therapeutic peptide agents for diabetes treatment. Here, we resorted to random forest to develop a computational model, named AntiDMPpred, for predicting anti-diabetic peptides. A benchmark dataset with 236 anti-diabetic and 236 non-anti-diabetic peptides was first constructed. Four types of sequence-derived descriptors were used to represent the peptide sequences. We then combined four machine learning methods and six feature scoring methods to select the non-redundant features, which were fed into diverse machine learning classifiers to train the models. Experimental results show that AntiDMPpred reached an accuracy of 77.12% and area under the receiver operating curve (AUCROC) of 0.8193 in the nested five-fold cross-validation, yielding a satisfactory performance and surpassing other classifiers implemented in the study. The web service is freely accessible at http://i.uestc.edu.cn/AntiDMPpred/cgi-bin/AntiDMPpred.pl. We hope AntiDMPpred could improve the discovery of anti-diabetic bioactive peptides.

Development and application of ribonucleic acid therapy strategies against COVID-19.

The Coronavirus disease 2019 (COVID-19) pandemic is caused by the severe acute respiratory syndrome 2 coronavirus (SARS-CoV-2), remaining a global health crisis since its outbreak until now. Advanced biotechnology and research findings have revealed many suitable viral and host targets for a wide range of therapeutic strategies. The emerging ribonucleic acid therapy can modulate gene expression by post-transcriptional gene silencing (PTGS) based on Watson-Crick base pairing. RNA therapies, including antisense oligonucleotides (ASO), ribozymes, RNA interference (RNAi), aptamers, etc., were used to treat SARS-CoV whose genome is similar to SARV-CoV-2, and the past experience also applies for the treatment of COVID-19. Several studies against SARS-CoV-2 based on RNA therapeutic strategy have been reported, and a dozen of relevant preclinical or clinical trials are in process globally. RNA therapy has been a very active and important part of COVID-19 treatment. In this review, we focus on the progress of ribonucleic acid therapeutic strategies development and application, discuss corresponding problems and challenges, and suggest new strategies and solutions.

BBPpredict: A Web Service for Identifying Blood-Brain Barrier Penetrating Peptides.

Blood-brain barrier (BBB) is a major barrier to drug delivery into the brain in the treatment of central nervous system (CNS) diseases. Blood-brain barrier penetrating peptides (BBPs), a class of peptides that can cross BBB through various mechanisms without damaging BBB, are effective drug candidates for CNS diseases. However, identification of BBPs by experimental methods is time-consuming and laborious. To discover more BBPs as drugs for CNS disease, it is urgent to develop computational methods that can quickly and accurately identify BBPs and non-BBPs. In the present study, we created a training dataset that consists of 326 BBPs derived from previous databases and published manuscripts and 326 non-BBPs collected from UniProt, to construct a BBP predictor based on sequence information. We also constructed an independent testing dataset with 99 BBPs and 99 non-BBPs. Multiple machine learning methods were compared based on the training dataset via a nested cross-validation. The final BBP predictor was constructed based on the training dataset and the results showed that random forest (RF) method outperformed other classification algorithms on the training and independent testing dataset. Compared with previous BBP prediction tools, the RF-based predictor, named BBPpredict, performs considerably better than state-of-the-art BBP predictors. BBPpredict is expected to contribute to the discovery of novel BBPs, or at least can be a useful complement to the existing methods in this area. BBPpredict is freely available at http://i.uestc.edu.cn/BBPpredict/cgi-bin/BBPpredict.pl.

A database of anti-coronavirus peptides.

Since 2019, the novel coronavirus (SARS-COV-2) disease (COVID-19) has caused a worldwide epidemic. Anti-coronavirus peptides (ACovPs), a type of antimicrobial peptides (AMPs), have demonstrated excellent inhibitory effects on coronaviruses. However, state-of-the-art AMP databases contain only a small number of ACovPs. Additionally, the fields of these databases are not uniform, and the units or evaluation standards of the same field are inconsistent. Most of these databases have not included the target domains of ACovPs and description of in vitro and in vivo assays to measure the inhibitory effects of ACovPs. Here, we present a database focused on ACovPs (ACovPepDB), which contains comprehensive and precise ACovPs information of 518 entries with 214 unique ACovPs manually collected from public databases and published peer-reviewed articles. We believe that ACovPepDB is of great significance for facilitating the development of new peptides and improving treatment for coronavirus infection. The database will become a portal for ACovPs and guide and help researchers perform further studies. The ACovPepDB is available at http://i.uestc.edu.cn/ACovPepDB/ .

PDL1Binder: Identifying programmed cell death ligand 1 binding peptides by incorporating next-generation phage display data and different peptide descriptors.

Monoclonal antibody drugs targeting the PD-1/PD-L1 pathway have showed efficacy in the treatment of cancer patients, however, they have many intrinsic limitations and inevitable drawbacks. Peptide inhibitors as alternatives might compensate for the drawbacks of current PD-1/PD-L1 interaction blockers. Identifying PD-L1 binding peptides by random peptide library screening is a time-consuming and labor-intensive process. Machine learning-based computational models enable rapid discovery of peptide candidates targeting the PD-1/PD-L1 pathway. In this study, we first employed next-generation phage display (NGPD) biopanning to isolate PD-L1 binding peptides. Different peptide descriptors and feature selection methods as well as diverse machine learning methods were then incorporated to implement predictive models of PD-L1 binding. Finally, we proposed PDL1Binder, an ensemble computational model for efficiently obtaining PD-L1 binding peptides. Our results suggest that predictive models of PD-L1 binding can be learned from deep sequencing data and provide a new path to discover PD-L1 binding peptides. A web server was implemented for PDL1Binder, which is freely available at http://i.uestc.edu.cn/pdl1binder/cgi-bin/PDL1Binder.pl.

AGODB: a comprehensive domain annotation database of argonaute proteins.

Argonaute (Ago) proteins are widely expressed in almost all organisms. Eukaryotic Ago (eAgo) proteins bind small RNA guides forming RNA-induced silencing complex that silence gene expression, and prokaryotic Ago (pAgo) proteins defend against invading nucleic acids via binding small RNAs or DNAs. pAgo proteins have shown great potential as a candidate 'scissors' for gene editing. Protein domains are fundamental units of protein structure, function and evolution; however, the domains of Ago proteins are not well annotated/curated currently. Therefore, full functional domain annotation of Ago proteins is urgently needed for researchers to understand the function and mechanism of Ago proteins. Herein, we constructed the first comprehensive domain annotation database of Ago proteins (AGODB). The database curates detailed information of 1902 Ago proteins, including 1095 eAgos and 807 pAgos. Especially for long pAgo proteins, all six domains are annotated and curated. Gene Ontology (GO) enrichment analysis revealed that Ago genes in different species were enriched in the following GO terms: biological processes (BPs), molecular function and cellular compartment. GO enrichment analysis results were integrated into AGODB, which provided insights into the BP that Ago genes may participate in. AGODB also allows users to search the database with a variety of options and download the search results. We believe that the AGODB will be a useful resource for understanding the function and domain components of Ago proteins. This database is expected to cater to the needs of scientific community dedicated to the research of Ago proteins. DATABASE URL: http://i.uestc.edu.cn/agodb/.

CASPredict: a web service for identifying Cas proteins.

Clustered regularly interspaced short palindromic repeats (CRISPR) and their associated (Cas) proteins constitute the CRISPR-Cas systems, which play a key role in prokaryote adaptive immune system against invasive foreign elements. In recent years, the CRISPR-Cas systems have also been designed to facilitate target gene editing in eukaryotic genomes. As one of the important components of the CRISPR-Cas system, Cas protein plays an irreplaceable role. The effector module composed of Cas proteins is used to distinguish the type of CRISPR-Cas systems. Effective prediction and identification of Cas proteins can help biologists further infer the type of CRISPR-Cas systems. Moreover, the class 2 CRISPR-Cas systems are gradually applied in the field of genome editing. The discovery of Cas protein will help provide more candidates for genome editing. In this paper, we described a web service named CASPredict (http://i.uestc.edu.cn/caspredict/cgi-bin/CASPredict.pl) for identifying Cas proteins. CASPredict first predicts Cas proteins based on support vector machine (SVM) by using the optimal dipeptide composition and then annotates the function of Cas proteins based on the hmmscan search algorithm. The ten-fold cross-validation results showed that the 84.84% of Cas proteins were correctly classified. CASPredict will be a useful tool for the identification of Cas proteins, or at least can play a complementary role to the existing methods in this area.

Atypical Functional Covariance Connectivity Between Gray and White Matter in Children With Autism Spectrum Disorder.

Autism spectrum disorder (ASD) is a type of neurodevelopmental disorder with atypical gray matter (GM) and white matter (WM) functional developmental course. However, the functional co-developmental pattern between GM and WM in ASD is unclear. Here, we utilized a functional covariance connectivity method to explore the concordance pattern between GM and WM function in individuals with ASD. A multi-center resting-state fMRI dataset composed of 105 male children with ASD and 102 well-matched healthy controls (HCs) from six sites of the ABIDE dataset was utilized. GM and WM ALFF maps were calculated for each subject. Voxel by voxel functional covariance connectivity of the ALFF values across subjects was calculated between GM and WM for children with ASD and HCs. A Z-test combining FDR multi-comparison correction was then employed to determine whether the functional covariance is significantly different between the two groups. A "bundling" strategy was utilized to ensure that the GM/WM clusters showing atypical functional covariance were larger than 5 voxels. Finally, canonical correlation analysis was conducted to explore whether the atypical GM/WM functional covariance is related to ASD symptoms. Results showed atypical functional covariance connections between specific GM and WM regions, whereas the ALFF values of these regions indicated no significant difference between the two groups. Canonical correlation analysis revealed a significant relationship between the atypical functional covariance and stereotyped behaviors of ASD. The results indicated an altered functional co-developmental pattern between WM and GM in ASD. LAY SUMMARY: White matter (WM) and gray matter (GM) are two major human brain organs supporting brain function. WM and GM functions show a specific co-developmental pattern in typical developed individuals. This study showed that this GM/WM co-developmental pattern was altered in children with ASD, while this altered GM/WM co-developmental pattern was related to stereotyped behaviors. These findings may help understand the GM/WM functional development of ASD.

Parcellation of the thalamus by using a dual-segment method based on resting-state functional connectivity: An application on autism spectrum disorder.

BACKGROUND: Evidence suggests thalamus is a key "information relay" center and all cortical areas receive inputs from the thalamus and each of the main nuclei of thalamus connects a single one or a few cortical areas. The traditional "winner-takes-all" thalamus parcellation method was then proposed based on this assumption. However, this method is based on the structural segments of the cortex which is not suitable for the functional parcellation of the thalamus. METHOD: Here we proposed a dual-segment method for thalamus functional parcellation based on the resting-state fMRI data. The traditional "winner-takes-all" and the proposed dual-segment methods were both applied to the dataset of 76 healthy controls (HCs) and 34 subjects with autism spectrum disorder. RESULTS: The results showed that the thalamus was subdivided into two sub-regions by using the dual-segment method: one is located in the dorsomedial part of thalamus which connects the high-level cognitive cortical regions; the other is located in the ventrolateral part of thalamus which connects the low-level sensory cortical areas. The functional connectivity strength between thalamus sub-regions and the corresponding cortical regions based on the dual-segment method was higher than that of results from the traditional "winner-takes-all" method. The thalamo-cortical functional connectivity based on our proposed method also showed higher classification ability to distinguish subjects with autism spectrum disorder from HCs. CONCLUSION: Our study will provide a new method for functional thalamus parcellation which might help understand the sub-regions functions of thalamus in neuroscience studies.

TUPDB: Target-Unrelated Peptide Data Bank.

The isolation of target-unrelated peptides (TUPs) through biopanning remains as a major problem of phage display selection experiments. These TUPs do not have any actual affinity toward targets of interest, which tend to be mistakenly identified as target-binding peptides. Therefore, an information portal for storing TUP data is urgently needed. Here, we present a TUP data bank (TUPDB), which is a comprehensive, manually curated database of approximately 73 experimentally verified TUPs and 1963 potential TUPs collected from TUPScan, the BDB database, and public research articles. The TUPScan tool has been integrated in TUPDB to facilitate TUP analysis. We believe that TUPDB can help identify and remove TUPs in future reports in the biopanning community. The database is of great importance to improving the quality of phage display-based epitope mapping and promoting the development of vaccines, diagnostics, and therapeutics. The TUPDB database is available at http://i.uestc.edu.cn/tupdb .

NeuroCS: A Tool to Predict Cleavage Sites of Neuropeptide Precursors.

BACKGROUND: Neuropeptides are a class of bioactive peptides produced from neuropeptide precursors through a series of extremely complex processes, mediating neuronal regulations in many aspects. Accurate identification of cleavage sites of neuropeptide precursors is of great significance for the development of neuroscience and brain science. OBJECTIVE: With the explosive growth of neuropeptide precursor data, it is pretty much needed to develop bioinformatics methods for predicting neuropeptide precursors' cleavage sites quickly and efficiently. METHODS: We started with processing the neuropeptide precursor data from SwissProt and NueoPedia into two sets of data, training dataset and testing dataset. Subsequently, six feature extraction schemes were applied to generate different feature sets and then feature selection methods were used to find the optimal feature subset of each. Thereafter the support vector machine was utilized to build models for different feature types. Finally, the performance of models were evaluated with the independent testing dataset. RESULTS: Six models are built through support vector machine. Among them the enhanced amino acid composition-based model reaches the highest accuracy of 91.60% in the 5-fold cross validation. When evaluated with independent testing dataset, it also showed an excellent performance with a high accuracy of 90.37% and Area under Receiver Operating Characteristic curve up to 0.9576. CONCLUSION: The performance of the developed model was decent. Moreover, for users' convenience, an online web server called NeuroCS is built, which is freely available at http://i.uestc.edu.cn/NeuroCS/dist/index.html#/. NeuroCS can be used to predict neuropeptide precursors' cleavage sites effectively.

AGONOTES: A Robot Annotator for Argonaute Proteins.

The argonaute protein (Ago) exists in almost all organisms. In eukaryotes, it functions as a regulatory system for gene expression. In prokaryotes, it is a type of defense system against foreign invasive genomes. The Ago system has been engineered for gene silencing and genome editing and plays an important role in biological studies. With an increasing number of genomes and proteomes of various microbes becoming available, computational tools for identifying and annotating argonaute proteins are urgently needed. We introduce AGONOTES (Argonaute Notes). It is a web service especially designed for identifying and annotating Ago. AGONOTES uses the BLASTP similarity search algorithm to categorize all submitted proteins into three groups: prokaryotic argonaute protein (pAgo), eukaryotic argonaute protein (eAgo), and non-argonaute protein (non-Ago). Argonaute proteins can then be aligned to the corresponding standard set of Ago sequences using the multiple sequence alignment program MUSCLE. All functional domains of Ago can further be curated from the alignment results and visualized easily through Bio::Graphic modules in the BioPerl bundle. Compared with existing tools such as CD-Search and available databases such as UniProt and AGONOTES showed a much better performance on domain annotations, which is fundamental in studying the new Ago. AGONOTES can be freely accessed at http://i.uestc.edu.cn/agonotes/. AGONOTES is a friendly tool for annotating Ago domains from a proteome or a series of protein sequences.