Human Blood-Brain Differential Gene-Expression Correlates with Dipeptide Frequency of Gene Products

  • Shandar Ahmad
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4983)


Differential gene expression in different tissues is largely considered to be the specific property of individual genes. In this work a relationship between overall dipeptide composition of proteins encoded by genes on the one hand and the difference in their expression level in two of the most important human organs i. e. blood and brain have been studied. Study is designed by developing a neural network that tries to predict the difference between expression of a gene in blood and brain from a 400-dimensional relative dipeptide composition vector. These vectors are derived from the amino acid sequence obtained by translating the corresponding gene. In a holdout validation scheme, such a model can predict gene expression from dipeptide composition with a significant Pearson’s correlation of 0.49 with a classification capacity between (expression wise) blood favored and brain favored genes reaching 68 to 70% accuracy. Results indicate that despite diverse biological function of each expressed gene within a tissue, some similarities in gene products do exist.


Neural Network Differential Gene Expression Dipeptide Composition Estimate Gene Expression Predict Gene Expression 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beer, M.A., Tavazoie, S.: Predicting gene expression from sequence. Cell 117(2), 185–198 (2004)CrossRefGoogle Scholar
  2. 2.
    Haverty, P.M., Weng, Z., Best, N.L., Auerbach, K.R., Hsiao, L.L., Jensen, R.V., Gullans, S.: HugeIndex: A database with visualization tools for high-density oligonucleotide array data from normal human tissues. Nucleic Acids Res 30(1), 214–217 (2002)CrossRefGoogle Scholar
  3. 3.
    SNNS: Stuttgart Neural Network Simulator User manual, version 4.2,
  4. 4.
    Ahmad, S., Gromiha, M.M., Sarai, A.: Analysis and prediction of DNA-binding proteins and their binding residues based on composition, sequence and structural information. Bioinformatics 20, 477–486 (2004)CrossRefGoogle Scholar
  5. 5.
    Malik, A., Ahmad, S.: Sequence and structural features of carbohydrate binding in proteins and assessment of predictability using a neural network. BMC Struct Biol. 7, 1 (2007)CrossRefGoogle Scholar
  6. 6.
    Sharabiani, M.T., Siermala, M., Lehtinen, T.O., Vihinen, M.: Dynamic covariation between gene expression and proteome characteristics. BMC Bioinformatics 6, 215 (2005)CrossRefGoogle Scholar
  7. 7.
    Raghava, G.P., Han, J.: Correlation and prediction of gene expression level from amino acid and dipeptide composition of its protein. BMC Bioinformatics 6, 59 (2005)CrossRefGoogle Scholar
  8. 8.
    Altschul, S.F., Gish, W., Miller, W., Myers, E.W., Lipman, D.J.: Basic Local Alignment Search Tool. J. Mol. Biol. 215, 403–410 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Shandar Ahmad
    • 1
  1. 1.  OsakaJapan

Personalised recommendations