Fast-Breaking Paper in Biology & Biochemistry Reveals a New Method to Predict Lysine Succinylation Sites

The article “pSuc-Lys: predict lysine succinylation sites in proteins with PseAAC and ensemble random forest approach” (J. Theor. Biol.  394: 223-230 April 7 2016), was recently named a Fast-Breaking Paper for Biology & Biochemistry in Essential Science Indicators. At present, this paper has 32 citations in the Web of Science.

 Below, lead author Dr. Jianhua Jia talks about this paper and its implications for its field.


Why do you think your paper is highly cited?

We expected this, because protein lysine succinylation is a special type of post-translational modifications (PTMs). It plays very important roles in regulating varieties of biological processes, but it is also involved with some major diseases. Therefore, knowledge of lysine succinylation sites in proteins is very important for both basic research and drug development.


Does it describe a new discovery, methodology, or synthesis of knowledge?

Yes, it does. In this paper, we developed a powerful predictor called “pSuc-Lys”, by which any one can easily obtain information on lysine succinylation sites for uncharacterized protein sequences. Meanwhile, some important methods have been developed accordingly. They are:

  1. Incorporating the sequence-coupled information into the Chou’s general pseudo amino acid composition or PseAAC (Chou, KC, Journal of Theoretical Biology 273: 236-247, 2011);
  2. Balancing out skewed training datasets by random sampling, and
  3. Constructing an ensemble predictor by fusing a series of individual random forest classifiers.

Actually, these powerful methods can also be used in many areas of computational biology and biomedicine, stimulating a series of powerful new predictors for proteome analysis and genome analysis.


Would you summarize the significance of your paper in layman’s terms?

It can significantly speed up the process of drug development against the diseases associated with protein lysine succinylation.


How did you become involved in this research, and how would you describe the particular challenges, setbacks, and successes that you’ve encountered along the way?

I was involved in this research while on sabbatical leave in the USA and was fortunately guided by Professor Dr. Kuo-Chen Chou of the Gordon Life Science Institute. Professor Chou is one of the world’s best computational biologists, who has been selected by Clarivate Analytics as a Highly Cited Researcher in 2014, 2015, and 2016, and was listed in the “World’s Most Influential Scientific Minds”. Many difficult problems were solved after illuminating discussions with Professor Chou.


Where do you see your research leading in the future?

Nowadays, many scientists are making considerable efforts to develop various prediction methods for proteome and genome analysis. This is a correct trend/direction because, facing the explosive growth of biological sequence generated in the post-genomic age, we are challenged to develop various predictors for quickly and effectively analyzing such a huge amount of DNA/RNA and protein/peptide sequences. However, to make the prediction methods really useful, we should comply with the Chou’s five-step rule (Chou KC, 2011, ibid.) as we did in our Fast-Breaking paper; i.e.:

  1. Construct or select a valid benchmark dataset to train and test the predictor;
  2. Formulate the biological sequence samples with an effective mathematical expression that can truly reflect their intrinsic correlation with the target to be predicted;
  3. Introduce or develop a powerful algorithm (or engine) to operate the prediction;
  4. Properly perform cross-validation tests to objectively evaluate the anticipated accuracy of the predictor; and
  5. Establish a user-friendly web-server for the predictor that is accessible to the public.


Do you foresee any social or political implications for your research?

I foresee impacts in the following three aspects:

  1. User-friendly and publicly accessible web-servers such as “pSuc-Lys” presented in this paper) represent the future direction for developing practically more useful methods, as pointed out in a review article (Chou KC and Shen HB, Natural Science 1: 63-92, 2009)
  2. Driven by these very useful web-servers, the methodology in studying medicinal chemistry will undergo an unprecedented revolution (Chou KC, Medicinal Chemistry 11: 218-234, 2015
  3. Exchanging ideas or collaboration between scientists in China and other countries such as the USA and the UK will significantly speed up the pace of scientific development and benefit mankind.


Jianhua Jia, Ph.D.
Associate Professor and Vice Dean
School of Information Engineering
Jingdezhen Ceramic Institute
Jingdezhen Shi, Jiangxi Sheng, China