| 研究実績の概要 |
In the second year, our research focused on detail of "adopting feature fusion and feature compression method for identifying IDRs and motifs in IDPs"; the main works were as follows: (1) Applied effective feature-encoding scheme to combine more predictive features into fewer dimensions for prediction, it includes: (a) Remove the redundant features and strengthen the predictive features to enhance the accuracy of prediction. Using the scaling skills to enhance the predictive features and weaken the noise features; (b) Adopt the image processing technology to preprocess the conserved features included in PSSM; (c) Modify PSSM to combine the detailed local conservation patterns of residues with the distribution of scores in PSSM for prediction. (2) Adopted the feature fusion method, rather than connecting all features in series to design the algorithms, it includes: (a) Firstly, all the physicochemical features were clustered; (b) Secondly, factors were calculated to represent each clustering; (c) Finally, all features (including the revised PSSM and factors calculated from physicochemical features) were fused and compressed by matrix operations to reduce the feature dimensions. (3) For MoRFs in IDPs, detailed analysis was carried out according to their different lengths, and the related algorithms was designed respectively for them. (4) Implemented the related web tools for publication.
|
