L2,1-Extreme Learning Machine: An Efficient Robust Classifier for Tumor Classification.

Abstract:

:With the development of cancer research, various gene expression datasets containing cancer information show an explosive growth trend. In addition, due to the continuous maturity of single-cell RNA sequencing (scRNA-seq) technology, the protein information and pedigree information of a single cell are also continuously mined. It is a technical problem of how to classify these high-dimensional data correctly. In recent years, Extreme Learning Machine (ELM) has been widely used in the field of supervised learning and unsupervised learning. However, the traditional ELM does not consider the robustness of the method. To improve the robustness of ELM, in this paper, a novel ELM method based on L2,1-norm named L2,1-Extreme Learning Machine (L2,1 -ELM) has been proposed. The method introduces L2,1-norm on loss function to improve the robustness, and minimizes the influence of noise and outliers. Firstly, we evaluate the new method on five UCI datasets. The experiment results prove that our method can achieve competitive results. Next, the novel method is applied to the problem of classification of cancer samples and single-cell RNA sequencing datasets. The experimental results on The Cancer Genome Atlas (TCGA) datasets and scRNA-seq datasets prove that ELM and its variants has great potential in the classification of cancer samples.

journal_name

Comput Biol Chem

authors

Ren LR,Gao YL,Liu JX,Zhu R,Kong XZ

doi

10.1016/j.compbiolchem.2020.107368

subject

Has Abstract

pub_date

2020-12-01 00:00:00

pages

107368

eissn

1476-9271

issn

1476-928X

pii

S1476-9271(19)31035-7

journal_volume

89

pub_type

杂志文章
  • Anti-haemostatic compounds from the vampire snail Cumia reticulata: Molecular cloning and in-silico structure-function analysis.

    abstract::Blood-feeding animals are known for their ability to produce bioactive compounds to impair haemostasis and suppress pain perception in the host. These compounds are extremely appealing for pharmacological development since they are generally very effective and specific for their molecular target. A preliminary RNA-Seq...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2018.05.014

    authors: Modica MV,Reinoso Sánchez J,Pasquadibisceglie A,Oliverio M,Mariottini P,Cervelli M

    更新日期:2018-08-01 00:00:00

  • Predicting human intestinal absorption of diverse chemicals using ensemble learning based QSAR modeling approaches.

    abstract::Human intestinal absorption (HIA) of the drugs administered through the oral route constitutes an important criterion for the candidate molecules. The computational approach for predicting the HIA of molecules may potentiate the screening of new drugs. In this study, ensemble learning (EL) based qualitative and quanti...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2016.01.005

    authors: Basant N,Gupta S,Singh KP

    更新日期:2016-04-01 00:00:00

  • In silico structural and functional analysis of Mesorhizobium ACC deaminase.

    abstract::Nodulation is one of the very important processes of legume plants as it is the initiating event of fixing nitrogen. Although ethylene has essential role in normal plant metabolism but it has also negative impact on plants particularly in nodule formation in legume plants. It is also produced due to a variety of bioti...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2017.02.005

    authors: Pramanik K,Soren T,Mitra S,Maiti TK

    更新日期:2017-06-01 00:00:00

  • Multilocus consensus genetic maps (MCGM): formulation, algorithms, and results.

    abstract::In process of creating genetic maps different labs/research groups obtain overlapping parts of the map. Merging these parts into one integrative map is based on looking for maximum shared marker orders among the maps. Really, not all shared markers of such maps have consensus order that obstructs building of the integ...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2005.09.007

    authors: Mester DI,Ronin YI,Korostishevsky MA,Pikus VL,Glazman AE,Korol AB

    更新日期:2006-02-01 00:00:00

  • MATEPRED-A-SVM-Based Prediction Method for Multidrug And Toxin Extrusion (MATE) Proteins.

    abstract::The growth and spread of drug resistance in bacteria have been well established in both mankind and beasts and thus is a serious public health concern. Due to the increasing problem of drug resistance, control of infectious diseases like diarrhea, pneumonia etc. is becoming more difficult. Hence, it is crucial to unde...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2015.07.011

    authors: Tamanna,Ramana J

    更新日期:2015-10-01 00:00:00

  • In silico study of porphyrin-anthraquinone hybrids as CDK2 inhibitor.

    abstract::Cyclin-Dependent Kinases (CDKs) are known to play crucial roles in controlling cell cycle progression of eukaryotic cell and inhibition of their activity has long been considered as potential strategy in anti-cancer drug research. In the present work, a series of porphyrin-anthraquinone hybrids bearing meso-substituen...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2016.12.005

    authors: Arba M,Ihsan S,Ramadhan OA,Tjahjono DH

    更新日期:2017-04-01 00:00:00

  • Phosphorylation mapping of laminin α1-chain: Kinases in association with active sites.

    abstract::Laminin-111 is a trimeric glycoprotein of the extracellular matrix (ECM) that holds a significant role in cell adhesion, migration and differentiation. Laminin-111 is the most studied laminin isoform, composed of three chains; α1, β1 and γ1. Phosphorylation is the most common eukaryotic post - translational modificati...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2019.04.012

    authors: Galliou PA,Verrou KM,Koliakos G

    更新日期:2019-06-01 00:00:00

  • Analysis of compensatory substitution and gene evolution on the MAGEA/CSAG-palindrome of the primate X chromosomes.

    abstract::The human X chromosome contains a large number of inverted repeat DNA palindromes. Although arbitrary substitutions destroyed the inverted repeat structure of MAGEA/CSAG-palindrome during the evolutionary process of the primates, most of the substitutions are compensatory. Using maximum parsimony, it is demonstrated t...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2012.11.002

    authors: Qi Y,Lu H,Ai D

    更新日期:2013-02-01 00:00:00

  • ProSTRIP: A method to find similar structural repeats in three-dimensional protein structures.

    abstract::The occurrence of similar structural repeats in a protein structure has evolved through gene duplication. These repeats act as a structural building block and form more than one compact structural and functional unit called a repeat domain. The protein families comprising similar structural repeats are mainly involved...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2010.03.006

    authors: Sabarinathan R,Basu R,Sekar K

    更新日期:2010-04-01 00:00:00

  • Computer evaluation of VirE2 protein complexes for ssDNA transfer ability.

    abstract::The single-stranded transfer DNA from the Ti plasmid of the soil bacteria Agrobacterium nonspecifically integrates into the plant chromosome and is inherited at subsequent cell divisions. How it is transferred across host membranes is unknown, but it is believed that VirE2 proteins form a membrane-spanning pore or cha...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2017.01.016

    authors: Volokhina I,Gusev Y,Mazilov S,Moiseeva Y,Chumakov M

    更新日期:2017-06-01 00:00:00

  • The anesthetic action of some polyhalogenated ethers-Monte Carlo method based QSAR study.

    abstract::Up to this date, there has been an ongoing debate about the mode of action of general anesthetics, which have postulated many biological sites as targets for their action. However, postoperative nausea and vomiting are common problems in which inhalational agents may have a role in their development. When a mode of ac...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2018.04.009

    authors: Golubović M,Lazarević M,Zlatanović D,Krtinić D,Stoičkov V,Mladenović B,Milić DJ,Sokolović D,Veselinović AM

    更新日期:2018-08-01 00:00:00

  • QSAR study of pyrazolo[4,3-e][1,2,4]triazine sulfonamides against tumor-associated human carbonic anhydrase isoforms IX and XII.

    abstract::The QSAR models for a set of pyrazolo[4,3-e][1,2,4]triazines incorporating benzenesulfonamide moiety combined directly with the heterocyclic ring or by NH linkage were generated. The inhibitory potency of compounds against human carbonic anhydrase isoforms IX and XII and antiproliferative activity against human MCF-7 ...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2017.09.006

    authors: Matysiak J,Skrzypek A,Tarasiuk P,Mojzych M

    更新日期:2017-12-01 00:00:00

  • QSAR classification-based virtual screening followed by molecular docking studies for identification of potential inhibitors of 5-lipoxygenase.

    abstract::Developments of novel inhibitors to prevent the function of 5-lipoxygenase (5-LOX) proteins that are responsible for a variety of inflammatory and allergic disease are a major challenge in the scientific community. In this study, robust QSAR classification models for predicting 5-LOX activity were developed using mach...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2018.10.002

    authors: Shameera Ahamed TK,Rajan VK,Sabira K,Muraleedharan K

    更新日期:2018-12-01 00:00:00

  • PK-means: A new algorithm for gene clustering.

    abstract::Microarray technology has been widely applied in study of measuring gene expression levels for thousands of genes simultaneously. Gene cluster analysis is found useful for discovering the function of gene because co-expressed genes are likely to share the same biological function. K-means is one of well-known clusteri...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2008.03.020

    authors: Du Z,Wang Y,Ji Z

    更新日期:2008-08-01 00:00:00

  • Patterns of cation binding to the aromatic amino acid R groups in Trp, Tyr, and Phe.

    abstract::Previous joint experimental and theoretical work demonstrates that typically soluble peptides will be rendered insoluble in the presence of saturated sodium ions in aqueous solution due to disruption of cation-π interactions between Trp and Lys. The present work utilizes quantum chemical methods including density func...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2017.12.009

    authors: Scherer SL,Stewart AL,Fortenberry RC

    更新日期:2018-02-01 00:00:00

  • Understanding the role of the topology in protein folding by computational inverse folding experiments.

    abstract::Recent studies suggest that protein folding should be revisited as the emergent property of a complex system and that the nature allows only a very limited number of folds that seem to be strongly influenced by geometrical properties. In this work we explore the principles underlying this new view and show how helical...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2008.03.015

    authors: Mucherino A,Costantini S,di Serafino D,D'Apuzzo M,Facchiano A,Colonna G

    更新日期:2008-08-01 00:00:00

  • CAMWI: Detecting protein complexes using weighted clustering coefficient and weighted density.

    abstract::Detection of protein complexes is very important to understand the principles of cellular organization and function. Recently, large protein-protein interactions (PPIs) networks have become available using high-throughput experimental techniques. These networks make it possible to develop computational methods for pro...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2015.07.012

    authors: Lakizadeh A,Jalili S,Marashi SA

    更新日期:2015-10-01 00:00:00

  • A pore creation in a triangular network model membrane.

    abstract::Membrane electroporation seems to be a useful method for delivery of biological active compounds into the cell. Although it is known that this phenomenon is sensitive to the electric field intensity, duration of the electric pulse and its shape, it is not fully understood. In some theoretical descriptions it is postul...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2008.02.001

    authors: Kubica K

    更新日期:2008-06-01 00:00:00

  • Guided macro-mutation in a graded energy based genetic algorithm for protein structure prediction.

    abstract::Protein structure prediction is considered as one of the most challenging and computationally intractable combinatorial problem. Thus, the efficient modeling of convoluted search space, the clever use of energy functions, and more importantly, the use of effective sampling algorithms become crucial to address this pro...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2016.01.008

    authors: Rashid MA,Iqbal S,Khatib F,Hoque MT,Sattar A

    更新日期:2016-04-01 00:00:00

  • A class imbalance-aware Relief algorithm for the classification of tumors using microarray gene expression data.

    abstract::DNA microarray data has been widely used in cancer research due to the significant advantage helped to successfully distinguish between tumor classes. However, typical gene expression data usually presents a high-dimensional imbalanced characteristic, which poses severe challenge for traditional machine learning metho...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2019.03.017

    authors: He Y,Zhou J,Lin Y,Zhu T

    更新日期:2019-06-01 00:00:00

  • On interaction of arginine, cysteine and guanine with a nano-TiO2 cluster.

    abstract::Nanoscopic properties of TiO2 augmented with its physicochemical properties and biocompatibility make it a material interest in the biomedical field. Efficient methods to design of such materials require a thorough understanding of associated nano-bio interfaces. In the present study, density functional theory calcula...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2020.107236

    authors: Sai Phani Kumar V,Verma M,Deshpande PA

    更新日期:2020-06-01 00:00:00

  • Tri-peptide reference structures for the calculation of relative solvent accessible surface area in protein amino acid residues.

    abstract::Relative amino acid residue solvent accessibility values allow the quantitative comparison of atomic solvent-accessible surface areas in different residue types and physical environments in proteins and in protein structural alignments. Geometry-optimised tri-peptide structures in extended solvent-exposed reference co...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2014.11.007

    authors: Topham CM,Smith JC

    更新日期:2015-02-01 00:00:00

  • ScGSLC: An unsupervised graph similarity learning framework for single-cell RNA-seq data clustering.

    abstract::Accurate clustering of cells from single-cell RNA sequencing (scRNA-seq) data is an essential step for biological analysis such as putative cell type identification. However, scRNA-seq data has high dimension and high sparsity, which makes traditional clustering methods less effective to reflect the similarity between...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2020.107415

    authors: Li J,Jiang W,Han H,Liu J,Liu B,Wang Y

    更新日期:2020-11-18 00:00:00

  • Drug-target network and polypharmacology studies of a Traditional Chinese Medicine for type II diabetes mellitus.

    abstract::Many Traditional Chinese Medicines (TCMs) are effective to relieve complicated diseases such as type II diabetes mellitus (T2DM). In this work, molecular docking and network analysis were employed to elucidate the action mechanism of a medical composition which had clinical efficacy for T2DM. We found that multiple ac...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2011.07.003

    authors: Gu J,Zhang H,Chen L,Xu S,Yuan G,Xu X

    更新日期:2011-10-12 00:00:00

  • In silico pharmacophore modeling and simulation studies for searching potent antileishmanials targeted against Leishmania donovani nicotinamidase.

    abstract::Nicotinamidase is a key enzyme for the salvage pathway catalyzing the first step for the conversion of nicotinamide (NAm) to nicotinic acid (NA) required for the synthesis of Nicotinamide Adenine Dinucleotide (NAD+) in the subsequent steps. Leishmania protozoan parasites are NAD+ auxotrophs and need precursors (nicoti...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2019.107150

    authors: Chauhan N,Poddar R

    更新日期:2019-12-01 00:00:00

  • Ambush hypothesis revisited: Evidences for phylogenetic trends.

    abstract::Recoding events occur in competition with standard readout of the transcript, and are site-specific. Recoding is the reprogramming of mRNA translation by localized alterations in the standard translational rules. Frame-shifting is one class of recoding and defined as protein translations that start not at the first, b...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2009.04.002

    authors: Singh TR,Pardasani KR

    更新日期:2009-06-01 00:00:00

  • Optimal hybrid sequencing and assembly: Feasibility conditions for accurate genome reconstruction and cost minimization strategy.

    abstract::Recent advances in high-throughput genome sequencing technologies have enabled the systematic study of various genomes by making whole genome sequencing affordable. Modern sequencers generate a huge number of small sequence fragments called reads, where the read length and the per-base sequencing cost depend on the te...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2017.03.016

    authors: Chen CC,Ghaffari N,Qian X,Yoon BJ

    更新日期:2017-08-01 00:00:00

  • Genome-wide identification and expression analysis of SWI1 genes in Boechera species.

    abstract::As a mode of reproduction in plants, apomixis leads to the generation of clones via seeds. Apomictic plants form viable diploid female gametes without meiosis (apomeiosis) and produce embryos without fertilization (parthenogenesis). Apomeiosis, as a major component of apomixis, has recently been reported in some Arabi...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2016.04.004

    authors: Sezer F,Yüzbaşioğlu G,Özbilen A,Taşkin KM

    更新日期:2016-06-01 00:00:00

  • 1,3-Oxazole derivatives of cytisine as potential inhibitors of glutathione reductase of Candida spp.: QSAR modeling, docking analysis and experimental study of new anti-Candida agents.

    abstract::Natural products as well as their derivatives play a significant role in the discovery of new biologically active compounds in the different areas of our life especially in the field of medicine. The synthesis of compounds produced from natural products including cytisine is one approach for the wider use of natural s...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章

    doi:10.1016/j.compbiolchem.2020.107407

    authors: Metelytsia LO,Trush MM,Kovalishyn VV,Hodyna DM,Kachaeva MV,Brovarets VS,Pilyo SG,Sukhoveev VV,Tsyhankov SA,Blagodatnyi VM,Semenyuta IV

    更新日期:2020-11-05 00:00:00

  • New insights on gene regulation in archaea.

    abstract::Archaea represent an important and vast domain of life. This cellular domain includes a large diversity of organisms characterized as prokaryotes with basal transcriptional machinery similar to eukarya. In this work we explore the most recent findings concerning the transcriptional regulatory organization in archaeal ...

    journal_title:Computational biology and chemistry

    pub_type: 杂志文章,评审

    doi:10.1016/j.compbiolchem.2011.10.006

    authors: Tenorio-Salgado S,Huerta-Saquero A,Perez-Rueda E

    更新日期:2011-12-14 00:00:00