Server
The POSSUM server is now in service with a new configuration of 16 cores and 64GB RAM. We apologize for any inconvenience due to the hardware upgrading during last few days. To improve the throughput, the uniref90 and uniref100 database used in blast process on POSSUM server are not provided currently. If you want to use uniref90/100 for specific purpose, please generate the corresponding PSSM files locally and use the standalone toolkit of POSSUM to calculate the feature descriptors.
POSSUM is designed in order to offer users a comprehensive and flexible generator for various kinds of PSSM-based descriptors. This web server is currently the first integrated toolkit for generating such types of descriptors.
If you find our work useful for your research work, please cite:
- Wang J, Yang B et al. POSSUM: a bioinformatics toolkit for generating numerical sequence feature descriptors based on PSSM profiles. Bioinformatics 2017;33(17):2756-2758. DOI: 10.1093/bioinformatics/btx302.
-
If you use AAC-PSSM/DPC-PSSM/AADP-PSSM, please cite:
- Liu, T., Zheng, X. and Wang, J. (2010) Prediction of protein structural class for low-similarity sequences using support vector machine and PSI-BLAST profile, Biochimie, 92, 1330-1334.
-
If you use D-FPSSM/S-FPSSM, please cite:
- Zahiri, J., et al. (2013) PPIevo: protein-protein interaction prediction from PSSM based evolutionary information, Genomics, 102, 237-242.
-
If you use smoothed-PSSM, please cite:
- Cheng, C.W., et al. (2008) Predicting RNA-binding sites of proteins using support vector machines and evolutionary information, BMC Bioinformatics, 9 Suppl 12, S6.
-
If you use AB-PSSM/RPM-PSSM, please cite:
- Jeong, J.C., Lin, X. and Chen, X.W. (2011) On position-specific scoring matrix for protein function prediction, IEEE/ACM transactions on computational biology and bioinformatics / IEEE, ACM, 8, 308-315.
-
If you use PSSM-composition, please cite:
- Zou, L., Nan, C. and Hu, F. (2013) Accurate prediction of bacterial type IV secreted effectors using amino acid composition and PSSM profiles, Bioinformatics, 29, 3135-3142.
-
If you use k-separated-bigrams-PSSM, please cite:
- Saini, H., et al.(2016) Protein Fold Recognition Using Genetic Algorithm Optimized Voting Scheme and Profile Bigram.
-
If you use tri-gram-PSSM, please cite:
- Paliwal, K.K., et al. (2014) A tri-gram based feature extraction technique using linear probabilities of position specific scoring matrix for protein fold recognition, IEEE transactions on nanobioscience, 13, 44-50.
-
If you use EDP/EEDP/MEDP, please cite:
- Zhang, L., Zhao, X. and Kong, L. (2014) Predict protein structural class for low-similarity sequences by evolutionary difference information into the general form of Chou's pseudo amino acid composition, Journal of Theoretical Biology, 355, 105-110.
-
If you use TPC/AATP, please cite:
- Zhang, S., Ye, F. and Yuan, X. (2012) Using principal component analysis and support vector machine to predict protein structural class for low-similarity sequences via PSSM, Journal of Biomolecular Structure & Dynamics, 29, 634-642.
-
If you use RPSSM, please cite:
- Ding, S., et al. (2014) A protein structural classes prediction method based on predicted secondary structure and PSI-BLAST profile, Biochimie, 97, 60-65.
-
If you use Pse-PSSM, please cite:
- Chou, K.C. and Shen, H.B. (2007) MemType-2L: a web server for predicting membrane proteins and their types by incorporating evolution information through Pse-PSSM, Biochemical and Biophysical Research Communications, 360, 339-345.
-
If you use DP-PSSM, please cite:
- Juan, E.Y., et al. (2009) Predicting Protein Subcellular Localizations for Gram-Negative Bacteria using DP-PSSM and Support Vector Machines. Complex, Intelligent and Software Intensive Systems, 2009. CISIS'09. International Conference on. IEEE, pp. 836-841.
-
If you use PSSM-AC/PSSM-CC, please cite:
- Dong, Q., Zhou, S. and Guan, J. (2009) A new taxonomy-based protein fold recognition approach based on autocross-covariance transformation, Bioinformatics, 25, 2655-2662.