CRanker for Peptide/Protein Identification

Develop new models to improve accuracy of peptide and protein identification using deep learning

Computational methods:

We first apply the deep learning model on feature extraction from peptide and protein data, and then use weighted SVM classifier to identify correct target.

Students:

• Chandra sekhar polavarapu (MS student)

Software Used:

• Python
• Tensorflow
• LibSVM

Grants:

None

Publications

1. Ling Jian, Zhonghang Xia, Xinnan Niu, Xijun Liang, Primal Samir, Andrew Link, l2 multiple kernel fuzzy SVM-based data fusion for improving peptide identification, IEEE/ACM Transactions on Computational Biology and Bioinformatics 2016; 13(4).
2. Xijun Liang, Zhonghang Xia, Ling Jian, Xinnan Niu, Andrew Link, An adaptive classification model for peptide identification, BMC Genomics, 2015,16(Suppl 11): S1.
3. Ling Jian, Xinnan Niu, Zhonghang Xia, Parimal Samir, Chiranthani Sumanasekera, Zheng Mu, Jennifer L. Jennings, Kristen L. Hoek, Tara Allos, Leigh M. Howard, Kathryn M. Edwards, P. Anthony Weil, Andrew J. Link*, A novel algorithm for validating peptide identification from a shotgun proteomics search engine, Journal of Proteome Research, 2013, 12(3), pp. 1108-1119

Feature Selection on big data

Explore important features hidden in variety of big datasets.

Computational methods: We investigate statistical approaches, deep learning models, and classification models for feature extraction.

Students:

• Rajesh Kumar Goud Bodampati (MS student)

Software Used:

• Python
• Hadoop

Grants:

None

Publications

None