Dr Jing Li's Group

  Department of Bioinformatics and Biostatistics

  Shanghai Jiao Tong University


*Description: DeepNetBim is a deep learning model for predicting HLA-epitope interaction based on net work analysis by harnessing Binding and immunogenicity information. In DeepNetBim model, both binding intensity of HLA-peptide pairs and potential immunogenicity of epitopes which are capable of eliciting CD8+ T cell responses were considered. In addition, to improve model accuracy, network centrality metrics were extracted through network construction which proved to possess sufficient prediction power in comparison. Extensive tests on independent and benchmark datasets demonstrate that DeepNetBim can significantly outperform other well-known binding prediction tools.
* URL: https://github.com/Li-Lab-SJTU/DeepNetBim
* Reference: X.Yang, L.Zhao, F.Wei, J.Li*. DeepNetBim: deep learning model for predicting HLA-epitope interactions based on network analysis by harnessing binding and immunogenicity information. BMC Bioinformatics. 2021 May 5;22(1):231. PMID: 33952199


*Description: SAVControl is a software tool for site-level quality control of variant peptide identifications. It first filters variant peptide identifications by transfer FDR control, and then evaluates the reliability of the variant sites by unrestrictive mass shift relocalization and introducing alternative in- terpretations, e.g. modifications. Finally, all identified variant sites are classified into three levels: Level I (reliable), Level II (ambiguous) and Level III (unreliable).
* URL: http://fugroup.amss. ac.cn/software/SAVControl/SAVControl.html.
* Reference: X.Yi,B.Wang, Z.An, F.Gong, J.Li*, Y.Fu*. Quality control of single amino acid variations detected by tandem mass spectrometry. Journal of Proteomics 187,144-151, 2018. PMID: 30012419


*Description: NIPS is the 3D net- work-integrated risk predictor of somatic SAPs tool, which integrates 3D interface interactions, network topology and information on sequence evolution to determine which mutations identified in cancer genomes are likely to be deleterious.
* URL: http://lilab.life.sjtu.edu.cn:8080/nips/
* Reference: B.Wang, J.Li, X.Cheng, Q.Zhou, J.Yang, M.Zhang, H.Chen, J.Li*. NIPS, a 3D network-integrated predictor of deleterious protein SAPs, and its application in cancer prognosis. Scientific Reports 8:6021, 2018. PMID: 29662108


*Description: The R package SeqMADE was designed for the RNA-seq differential expression analysis pipeline. SeqMADE implements within a well-established generalized linear model framework integrating gene expression into the network module, instead of computing the gene scores and gene set score to achieve biological insights, respectively. Besides, the package also provides the ability to combine and borrow strength across genes that are both up- and down-regulated in one module.
* URL: https://cran.r-project.org/ web/packages/SeqMADE/
* Reference: M.Lei, J.Xu, LC.Huang, L.Wang, J.Li*. Network module-based model in the differential expression analysis for RNA-seq. Bioinformatics. 33(17):2699-2705, 2017


* Description: CanProVar is designed to store and display single amino acid alterations including both germline and somatic variations in the human proteome, especially those related to the genesis or development of human cancer based on the published literatures. Cancer-related variations and conrresponding annotations can be queried through the web-interface using Protein IDs in the Ensembl, IPI, RefSeq, and Uniport/Swiss-Prot databases or gene names and Entrez gene IDs. Fasta files with variation information are also available for download.
* Version:2.0
* URL: http://lilab.life.sjtu.edu.cn:8080/canprovar2 (China) and http://canprovar2.zhang-lab.org/ (USA).
* Reference:
M.Zhang, B.Wang, J.Xu, X.Wang, L.Xie, B.Zhang*, Y.Li*, J.Li*.CanProVar 2.0: An Updated Database of Human Cancer Proteome Variation.Journal of Proteome Research,16(2):421-432, 2017.
Jing Li, Dexter T Duncan, Bing Zhang. CanProVar: a human cancer proteome variation database. Hum Mutat, 31(3):219-228, 2010.


*Description: proAP, Protein Allergenicity Prediction, is a web-based application which provides one-stop search for all known allergens and allergen prediction. So far, sequence-based, motif-based and SVM-based allergen prediction approaches were integrated in proAP. User may perform allergen prediction for unknown ones using individual or combined bioinformatic methods. It allows the search of allergens by species as well as by category. Flexible parameter setting and batch prediction were also implemented.
* URL: http://gmobl.sjtu.edu.cn/proAP/
* Reference: Jing Wang, Yabin Yu, Yunan Zhao, Dabing. Zhang and Jing. Li*. Evaluation and Integration of Existing Methods for Computational Prediction of Allergens. BMC Bioinformatics. 14(Suppl 4):S1, 2013


©2012-2013 Jing Li