A multi-fold string kernel for sequence classification

Author(s):  
Aniruddha Maiti ◽  
Santanu Ghorai ◽  
Anirban Mukherjee
PLoS ONE ◽  
2011 ◽  
Vol 6 (11) ◽  
pp. e25353 ◽  
Author(s):  
Peng Jia ◽  
Liming Xuan ◽  
Lei Liu ◽  
Chaochun Wei

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Jiuwen Cao ◽  
Lianglin Xiong

Precisely classifying a protein sequence from a large biological protein sequences database plays an important role for developing competitive pharmacological products. Comparing the unseen sequence with all the identified protein sequences and returning the category index with the highest similarity scored protein, conventional methods are usually time-consuming. Therefore, it is urgent and necessary to build an efficient protein sequence classification system. In this paper, we study the performance of protein sequence classification using SLFNs. The recent efficient extreme learning machine (ELM) and its invariants are utilized as the training algorithms. The optimal pruned ELM is first employed for protein sequence classification in this paper. To further enhance the performance, the ensemble based SLFNs structure is constructed where multiple SLFNs with the same number of hidden nodes and the same activation function are used as ensembles. For each ensemble, the same training algorithm is adopted. The final category index is derived using the majority voting method. Two approaches, namely, the basic ELM and the OP-ELM, are adopted for the ensemble based SLFNs. The performance is analyzed and compared with several existing methods using datasets obtained from the Protein Information Resource center. The experimental results show the priority of the proposed algorithms.


2012 ◽  
Vol 37 (2) ◽  
pp. 251-278 ◽  
Author(s):  
Chieh-Yuan Tsai ◽  
Chih-Jung Chen ◽  
Chun-Ju Chien

Development ◽  
1999 ◽  
Vol 126 (23) ◽  
pp. 5495-5504 ◽  
Author(s):  
D.M. Supp ◽  
M. Brueckner ◽  
M.R. Kuehn ◽  
D.P. Witte ◽  
L.A. Lowe ◽  
...  

Vertebrates develop distinct asymmetries along the left-right axis, which are consistently aligned with the anteroposterior and dorsoventral axes. The mechanisms that direct this handed development of left-right asymmetries have been elusive, but recent studies of mutations that affect left-right development have shed light on the molecules involved. One molecule implicated in left-right specification is left-right dynein (LRD), a microtubule-based motor protein. In the LRD protein of the inversus viscerum (iv) mouse, there is a single amino acid difference at a conserved position, and the lrd gene is one of many genes deleted in the legless (lgl) mutation. Both iv and lgl mice display randomized left-right development. Here we extend the analysis of the lrd gene at the levels of sequence, expression and function. The complete coding sequence of the lrd gene confirms its classification as an axonemal, or ciliary, dynein. Expression of lrd in the node at embryonic day 7.5 is shown to be symmetric. At embryonic day 8.0, however, a striking asymmetric expression pattern is observed in all three germ layers of the developing headfold, suggesting roles in both the establishment and maintenance of left-right asymmetries. At later times, expression of lrd is also observed in the developing floorplate, gut and limbs. These results suggest function for LRD protein in both ciliated and non-ciliated cells, despite its sequence classification as axonemal. In addition, a targeted mutation of lrd was generated that deletes the part of the protein required for ATP binding, and hence motor function. The resulting left-right phenotype, randomization of laterality, is identical to that of iv and lgl mutants. Gross defects in ciliary structure were not observed in lrd/lrd mutants. Strikingly, however, the monocilia on mutant embryonic node cells were immotile. These results prove the identity of the iv and lrd genes. Further, they argue that LRD motor function, and resulting nodal monocilia movement, are required for normal left-right development.


Sign in / Sign up

Export Citation Format

Share Document