Publications

@article{Mangul:IeeeTransNanobioscience:2017,
title = {HapIso : An Accurate Method for the Haplotype-Specific Isoforms Reconstruction from Long Single-Molecule Reads.},
author = { Serghei Mangul and Harry Taegyun Yang and Farhad Hormozdiari and Alex Dainis and Elizabeth Tseng and Euan A. Ashley and Alex Zelikovsky and Eleazar Eskin},
url = {http://dx.doi.org/10.1109/TNB.2017.2675981},
issn = {1558-2639},
year = {2017},
date = {2017-01-01},
journal = {IEEE Trans Nanobioscience},
volume = {16},
number = {2},
pages = {108-115},
address = {United States},
abstract = {Sequencing of RNA provides the possibility to study an individual's transcriptome landscape and determine allelic expression ratios. Single-molecule protocols generate multi-kilobase reads longer than most transcripts allowing sequencing of complete haplotype isoforms. This allows partitioning the reads into two parental haplotypes. While the read length of the single-molecule protocols is long, the relatively high error rate limits the ability to accurately detect the genetic variants and assemble them into the haplotype-specific isoforms. In this paper, we present HapIso (Haplotype-specific Isoform Reconstruction), a method able to tolerate the relatively high error-rate of the single-molecule platform and partition the isoform reads into the parental alleles. Phasing the reads according to the allele of origin allows our method to efficiently distinguish between the read errors and the true biological mutations. HapIso uses a k-means clustering algorithm aiming to group the reads into two meaningful clusters maximizing the similarity of the reads within cluster and minimizing the similarity of the reads from different clusters. Each cluster corresponds to a parental haplotype. We used family pedigree information to evaluate our approach. Experimental validation suggests that HapIso is able to tolerate the relatively high error-rate and accurately partition the reads into the parental alleles of the isoform transcripts. We also applied HapIso to novel clinical single-molecule RNA-Seq data to estimate ASE of genes of interest. Our method was able to correct reads and determine Glu1883Lys point mutation of clinical signifcance validated by GeneDx HCM Panel. Furthermore, our method is the first method able to reconstruct the haplotype-specific isoforms from long single-molecule reads},
keywords = {Allele Specific Expression, Haplotype Phasing, Haplotyping from Sequences, RNAseq, Sequence Assembly},
pubstate = {published},
tppubtype = {article}
}

@article{Hormozdiari:JBioinformComputBiol:2014,
title = {Memory efficient assembly of human genome.},
author = {Farhad Hormozdiari and Eleazar Eskin},
url = {http://dx.doi.org/10.1142/S0219720015500080},
issn = {1757-6334},
year = {2014},
date = {2014-01-01},
journal = {J Bioinform Comput Biol},
pages = {1550008},
abstract = {The ability to detect the genetic variations between two individuals is an essential component for genetic studies. In these studies, obtaining the genome sequence of both individuals is the first step toward variation detection problem. The emergence of high-throughput sequencing (HTS) technology has made DNA sequencing practical, and is widely used by diagnosticians to increase their knowledge about the casual factor in genetic related diseases. As HTS advances, more data are generated every day than the amount that scientists can process. Genome assembly is one of the existing methods to tackle the variation detection problem. The de Bruijn graph formulation of the assembly problem is widely used in the field. Furthermore, it is the only method which can assemble any genome in linear time. However, it requires an enormous amount of memory in order to assemble any mammalian size genome. The high demands of sequencing more individuals and the urge to assemble them are the driving forces for a memory efficient assembler. In this work, we propose a novel method which builds the de Bruijn graph while consuming lower memory. Moreover, our proposed method can reduce the memory usage by 37% compared to the existing methods. In addition, we used a real data set (chromosome 17 of A/J strain) to illustrate the performance of our method},
keywords = {Sequence Assembly},
pubstate = {published},
tppubtype = {article}
}

@article{Parrish:BmcGenomics:2013,
title = {Genome reassembly with high-throughput sequencing data},
author = { Nathaniel Parrish and Benjamin Sudakov and Eleazar Eskin},
url = {http://dx.doi.org/10.1186/1471-2164-14-S1-S8},
issn = {1471-2164},
year = {2013},
date = {2013-01-01},
journal = {BMC Genomics},
volume = {14},
number = {Suppl 1},
pages = {S8},
publisher = {BioMed Central Ltd},
address = {England},
abstract = {MOTIVATION: Recent studies in genomics have highlighted the significance of structural variation in determining individual variation. Current methods for identifying structural variation, however, are predominantly focused on either assembling whole genomes from scratch, or identifying the relatively small changes between a genome and a reference sequence. While significant progress has been made in recent years on both de novo assembly and resequencing (read mapping) methods, few attempts have been made to bridge the gap between them. RESULTS: In this paper, we present a computational method for incorporating a reference sequence into an assembly algorithm. We propose a novel graph construction that builds upon the well-known de Bruijn graph to incorporate the reference, and describe a simple algorithm, based on iterative message passing, which uses this information to significantly improve assembly results. We validate our method by applying it to a series of 5 Mb simulation genomes derived from both mammalian and bacterial references. The results of applying our method to this simulation data are presented along with a discussion of the benefits and drawbacks of this technique},
keywords = {Sequence Assembly},
pubstate = {published},
tppubtype = {article}
}

@article{Parrish:BmcBioinformatics:2011,
title = {Assembly of non-unique insertion content using next-generation sequencing.},
author = { Nathaniel Parrish and Farhad Hormozdiari and Eleazar Eskin},
url = {http://dx.doi.org/10.1186/1471-2105-12-S6-S3},
issn = {1471-2105},
year = {2011},
date = {2011-01-01},
journal = {BMC Bioinformatics},
volume = {12 Suppl 6},
pages = {S3},
address = {England},
organization = {Department of Computer Science, University of California Los Angeles, CA, USA.},
abstract = {Recent studies in genomics have highlighted the significance of sequence insertions in determining individual variation. Efforts to discover the content of these sequence insertions have been limited to short insertions and long unique insertions. Much of the inserted sequence in the typical human genome, however, is a mixture of repeated and unique sequence. Current methods are designed to assemble only unique sequence insertions, using reads that do not map to the reference. These methods are not able to assemble repeated sequence insertions, as the reads will map to the reference in a different locus.In this paper, we present a computational method for discovering the content of sequence insertions that are unique, repeated, or a combination of the two. Our method analyzes the read mappings and depth of coverage of paired-end reads to identify reads that originated from inserted sequence. We demonstrate the process of assembling these reads to characterize the insertion content. Our method is based on the idea of segment extension, which progressively extends segments of known content using paired-end reads. We apply our method in simulation to discover the content of inserted sequences in a modified mouse chromosome and show that our method produces reliable results at 40x coverage.},
keywords = {Sequence Assembly, Structural Variation},
pubstate = {published},
tppubtype = {article}
}