K-SVCR. A Multi-class Support Vector Machine
نویسندگان
چکیده
In nanopore sensing experiments, the properties of molecules are probed by the variation of ionic currents flowing through the nanopore. In this context, the electronic properties and the single-layer thickness of graphene constitute a major advantage for molecule characterization. Here we analyze the translocation pathway of the thioredoxin protein across a graphene nanopore, and the related ionic currents, by integrating two nonequilibrium molecular dynamics methods with a bioinformatic structural analysis. To obtain a qualitative picture of the translocation process and to identify salient features we performed unsupervised structural clustering on translocation conformations. This allowed us to identify some specific and robust translocation intermediates, characterized by significantly different ionic current flows. We found that the ion current strictly anticorrelates with the amount of pore occupancy by thioredoxin residues, providing a putative explanation of the multilevel current scenario observed in recently published translocation experiments.
منابع مشابه
A Regularized Nonsmooth Newton Method for Multi-class Support Vector Machines
Multi-class classification is an important and on-going research subject in machine learning. Recently, the ν-K-SVCR method was proposed by the authors for multi-class classification. Since many optimization problems have to be solved in multi-class classification, it is extremely important to develop an algorithm that can solve those optimization problems efficiently. In this paper, the optimi...
متن کاملA Multi-class Algorithm Model Based on p-class Support Vector Ordinal Regression Machine∗
Multi-class classification is an important and on-going research subject in machine learning. In this paper, we propose an algorithm model for k-class multi-class classification problem based on p-class (2≤ p≤ k) support vector ordinal regression machine (SVORM). A series of algorithms can be generated by selecting the different parameters p, L and the code matrix. When p = 2, they reduce to th...
متن کاملRegularized nonsmooth Newton method for multi-class support vector machines
Multi-class classification is an important and on-going research subject in machine learning. Recently, the ν-K-SVCR method was proposed by the authors for multi-class classification. Since many optimization problems have to be solved in multi-class classification, it is extremely important to develop an algorithm that can solve those optimization problems efficiently. In this paper, the optimi...
متن کاملA new multi-class support vector algorithm
Multi-class classification is an important and on-going research subject in machine learning. In this article, we propose a new support vector algorithm, called ν-K-SVCR, for multi-class classification based on ν-SVM. ν-K-SVCR has parameters that enable us to control the numbers of support vectors and margin errors effectively, which is helpful in improving the accuracy of each classifier. We g...
متن کاملFault diagnosis in a distillation column using a support vector machine based classifier
Fault diagnosis has always been an essential aspect of control system design. This is necessary due to the growing demand for increased performance and safety of industrial systems is discussed. Support vector machine classifier is a new technique based on statistical learning theory and is designed to reduce structural bias. Support vector machine classification in many applications in v...
متن کاملProbabilistic outputs for a new multi-class Support Vector Machine
Support Vector Machines are learning paradigm originally developed on the basis of a binary classification problem with signed outputs ±1. The aim of this work is to give a probabilistic interpretation to the numerical output values into a multi-classification learning problem framework. For this purpose, a recent SV Machine, called `-SVCR, addressed to avoid the lose of information occurred in...
متن کامل