Classification of C2H2 Zinc Finger Domains Using Support Vector Machines
نویسندگان
چکیده
Zinc finger proteins include nuclear receptors for steroid hormones and are mainly DNA-binding transcription factors. Thus those are supposed to be target proteins for drug discovery. C2H2 zinc finger gene family is one of the most popular and complex superfamilies. C2H2 zinc finger domains are composed of approximately 25 to 30 amino acid residues including the paired cysteines and histidines that form coordinate bonds with zinc ion. Although C2H2 domains are well-studied, it is difficult to detect the domains with high accuracy by means of homology search or hidden Markov models(HMMs) owing to a wide variety of the sequences. In this research, we have extended the Support Vector Machine(SVM) based method using the Fisher kernel [1] in order to achieve better accuracy than an HMM. The Fisher kernel extracts a fixed length vector of features known as a Fisher score vector (FSV) from a variable length sequence with an HMM. The method in [1] classifies G-protein coupled receptors (GPCRs) into GPCR subfamilies.
منابع مشابه
Variations of the C2H2 zinc finger motif in the yeast genome and classification of yeast zinc finger proteins.
The PROSITE pattern Zinc_Finger_C2H2 was extended to permit the detection of all C2H2 zinc fingers and their parent proteins in the recently completed sequence of the yeast genome. Additionally, a new computer program was written that extracts other zinc binding motifs (non C2H2 'fingers'), overlapping with the classical zinc finger pattern, from the found set of yeast C2H2 fingers. The complet...
متن کاملC2H2 Zinc Finger Proteins: The Largest but Poorly Explored Family of Higher Eukaryotic Transcription Factors
The emergence of whole-genome assays has initiated numerous genome-wide studies of transcription factor localizations at genomic regulatory elements (enhancers, promoters, silencers, and insulators), as well as facilitated the uncovering of some of the key principles of chromosomal organization. However, the proteins involved in the formation and maintenance of the chromosomal architecture and ...
متن کاملSynthetic protein–protein interaction domains created by shuffling Cys2His2 zinc-fingers
Cys2His2 zinc-fingers (C2H2 ZFs) mediate a wide variety of protein-DNA and protein-protein interactions. DNA-binding C2H2 ZFs can be shuffled to yield artificial proteins with different DNA binding specificities. Here we demonstrate that shuffling of C2H2 ZFs from transcription factor dimerization zinc-finger (DZF) domains can also yield two-finger DZFs with novel protein-protein interaction sp...
متن کاملFace Recognition using Eigenfaces , PCA and Supprot Vector Machines
This paper is based on a combination of the principal component analysis (PCA), eigenface and support vector machines. Using N-fold method and with respect to the value of N, any person’s face images are divided into two sections. As a result, vectors of training features and test features are obtain ed. Classification precision and accuracy was examined with three different types of kernel and...
متن کاملSelective dimerization of a C2H2 zinc finger subfamily.
The C2H2 zinc finger is the most prevalent protein motif in the mammalian proteome. Two C2H2 fingers in Ikaros are dedicated to homotypic interactions between family members. We show here that these fingers comprise a bona fide dimerization domain. Dimerization is highly selective, however, as homologous domains from the TRPS-1 and Drosophila Hunchback proteins support homodimerization, but not...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002