Life Sciences Commons^™

A Reliable Diabetic Retinopathy Grading Via Transfer Learning And Ensemble Learning With Quadratic Weighted Kappa Metric, Sai Venkatesh Chilukoti, Liqun Shan, Vijay Srinivas Tida, Anthony S. Maida, Xiali Hei

Computer Science Faculty Publications

The most common eye infection in people with diabetes is diabetic retinopathy (DR). It might cause blurred vision or even total blindness. Therefore, it is essential to promote early detection to prevent or alleviate the impact of DR. However, due to the possibility that symptoms may not be noticeable in the early stages of DR, it is difficult for doctors to identify them. Therefore, numerous predictive models based on machine learning (ML) and deep learning (DL) have been developed to determine all stages of DR. However, existing DR classification models cannot classify every DR stage or use a computationally heavy …

Cellbrf: A Feature Selection Method For Single-Cell Clustering Using Cell Balance And Random Forest, Yunpei Xu, Hong-Dong Li, Cui-Xiang Lin, Ruiqing Zheng, Yaohang Li, Jinhui Xu, Jianxin Wang

Computer Science Faculty Publications

Motivation

Single-cell RNA sequencing (scRNA-seq) offers a powerful tool to dissect the complexity of biological tissues through cell sub-population identification in combination with clustering approaches. Feature selection is a critical step for improving the accuracy and interpretability of single-cell clustering. Existing feature selection methods underutilize the discriminatory potential of genes across distinct cell types. We hypothesize that incorporating such information could further boost the performance of single cell clustering. Results

We develop CellBRF, a feature selection method that considers genes’ relevance to cell types for single-cell clustering. The key idea is to identify genes that are most important for discriminating …

Dfhic: A Dilated Full Convolution Model To Enhance The Resolution Of Hi-C Data, Bin Wang, Kun Liu, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Motivation: Hi-C technology has been the most widely used chromosome conformation capture(3C) experiment that measures the frequency of all paired interactions in the entire genome, which is a powerful tool for studying the 3D structure of the genome. The fineness of the constructed genome structure depends on the resolution of Hi-C data. However, due to the fact that high-resolution Hi-C data require deep sequencing and thus high experimental cost, most available Hi-C data are in low-resolution. Hence, it is essential to enhance the quality of Hi-C data by developing the effective computational methods.

Results: In this work, we propose …

An Approach To Developing Benchmark Datasets For Protein Secondary Structure Segmentation From Cryo-Em Density Maps, Thu Nguyen, Yongcheng Mu, Jiangwen Sun, Jing He

Computer Science Faculty Publications

More and more deep learning approaches have been proposed to segment secondary structures from cryo-electron density maps at medium resolution range (5--10Å). Although the deep learning approaches show great potential, only a few small experimental data sets have been used to test the approaches. There is limited understanding about potential factors, in data, that affect the performance of segmentation. We propose an approach to generate data sets with desired specifications in three potential factors - the protein sequence identity, structural contents, and data quality. The approach was implemented and has generated a test set and various training sets to study …

Intergenic Transcription In In Vivo Developed Bovine Oocytes And Pre-Implantation Embryos, Saurav Ranjitkar, Mohammad Shiri, Jiangwen Sun, Xiuchun Tian

Computer Science Faculty Publications

Background

Intergenic transcription, either failure to terminate at the transcription end site (TES), or transcription initiation at other intergenic regions, is present in cultured cells and enhanced in the presence of stressors such as viral infection. Transcription termination failure has not been characterized in natural biological samples such as pre-implantation embryos which express more than 10,000 genes and undergo drastic changes in DNA methylation.

Results

Using Automatic Readthrough Transcription Detection (ARTDeco) and data of in vivo developed bovine oocytes and embryos, we found abundant intergenic transcripts that we termed as read-outs (transcribed from 5 to 15 kb after TES) and …

Npgreat: Assembly Of The Human Subtelomere Regions With The Use Of Ultralong Nanopore Reads And Linked Reads, Eleni Adam, Desh Ranjan, Harold Riethman

Computer Science Faculty Publications

Background: Human subtelomeric DNA regulates the length and stability of adjacent telomeres that are critical for cellular function, and contains many gene/pseudogene families. Large evolutionarily recent segmental duplications and associated structural variation in human subtelomeres has made complete sequencing and assembly of these regions difficult to impossible for many loci, complicating or precluding a wide range of genetic analyses to investigate their function.

Results: We present a hybrid assembly method, NanoPore Guided REgional Assembly Tool (NPGREAT), which combines Linked-Read data with mapped ultralong nanopore reads spanning subtelomeric segmental duplications to potentially overcome these difficulties. Linked-Read sets of DNA sequences identified …

Completing Single-Cell Dna Methylome Profiles Via Transfer Learning Together With Kl-Divergence, Sanjeeva Dodlapati, Zongliang Jiang, Jiangwen Sun

Computer Science Faculty Publications

The high level of sparsity in methylome profiles obtained using whole-genome bisulfite sequencing in the case of low biological material amount limits its value in the study of systems in which large samples are difficult to assemble, such as mammalian preimplantation embryonic development. The recently developed computational methods for addressing the sparsity by imputing missing have their limits when the required minimum data coverage or profiles of the same tissue in other modalities are not available. In this study, we explored the use of transfer learning together with Kullback-Leibler (KL) divergence to train predictive models for completing methylome profiles with …

Non-Transgenic Crispr-Mediated Knockout Of Entire Ergot Alkaloid Gene Clusters In Slow-Growing Asexual Polyploid Fungi, Simona Florea, Jolanta Jaromczyk, Christopher L. Schardl

Computer Science Faculty Publications

The Epichloë species of fungi include seed-borne symbionts (endophytes) of cool-season grasses that enhance plant fitness, although some also produce alkaloids that are toxic to livestock. Selected or mutated toxin-free endophytes can be introduced into forage cultivars for improved livestock performance. Long-read genome sequencing revealed clusters of ergot alkaloid biosynthesis (EAS) genes in Epichloë coenophiala strain e19 from tall fescue (Lolium arundinaceum) and Epichloë hybrida Lp1 from perennial ryegrass (Lolium perenne). The two homeologous clusters in E. coenophiala—a triploid hybrid species—were 196 kb (EAS1) and 75 kb (EAS2), and …

Analysis Of Subtelomeric Rextal Assemblies Using Quast, Tunazzina Islam, Desh Ranjan, Mohammad Zubair, Eleanor Young, Ming Xiao, Harold Riethman

Computer Science Faculty Publications

Genomic regions of high segmental duplication content and/or structural variation have led to gaps and misassemblies in the human reference sequence, and are refractory to assembly from whole-genome short-read datasets. Human subtelomere regions are highly enriched in both segmental duplication content and structural variations, and as a consequence are both impossible to assemble accurately and highly variable from individual to individual. Recently, we developed a pipeline for improved region-specific assembly called Regional Extension of Assemblies Using Linked-Reads (REXTAL). In this study, we evaluate REXTAL and genome-wide assembly (Supernova) approaches on 10X Genomics linked-reads data sets partitioned and barcoded using the …

Fmri Feature Extraction Model For Adhd Classification Using Convolutional Neural Network, Senuri De Silva, Sanuwani Udara Dayarathna, Gangani Ariyarathne, Dulani Meedeniya, Sampath Jayarathna

Computer Science Faculty Publications

Biomedical intelligence provides a predictive mechanism for the automatic diagnosis of diseases and disorders. With the advancements of computational biology, neuroimaging techniques have been used extensively in clinical data analysis. Attention deficit hyperactivity disorder (ADHD) is a psychiatric disorder, with the symptomology of inattention, impulsivity, and hyperactivity, in which early diagnosis is crucial to prevent unwelcome outcomes. This study addresses ADHD identification using functional magnetic resonance imaging (fMRI) data for the resting state brain by evaluating multiple feature extraction methods. The features of seed-based correlation (SBC), fractional amplitude of low-frequency fluctuation (fALFF), and regional homogeneity (ReHo) are comparatively applied to …

Deepfrag-K: A Fragment-Based Deep Learning Approach For Protein Fold Recognition, Wessam Elhefnawy, Min Li, Jianxin Wang, Yaohang Li

Computer Science Faculty Publications

Background: One of the most essential problems in structural bioinformatics is protein fold recognition. In this paper, we design a novel deep learning architecture, so-called DeepFrag-k, which identifies fold discriminative features at fragment level to improve the accuracy of protein fold recognition. DeepFrag-k is composed of two stages: the first stage employs a multi-modal Deep Belief Network (DBN) to predict the potential structural fragments given a sequence, represented as a fragment vector, and then the second stage uses a deep convolutional neural network (CNN) to classify the fragment vector into the corresponding fold.

Results: Our results show that DeepFrag-k yields …

Timing Of Maximal Weight Reduction Following Bariatric Surgery: A Study In Chinese Patients, Ting Xu, Chen Wang, Hongwei Zhang, Xiaodong Han, Weijie Liu, Junfeng Han, Haoyong Yu, Jin Chen, Pin Zhang, Jianzhong Di

Computer Science Faculty Publications

Introduction: Bariatric surgery is a well-received treatment for obesity with maximal weight loss at 12–36 months postoperatively. We investigated the effect of early bariatric surgery on weight reduction of Chinese patients in accordance with their preoperation characteristics.

Materials and Methods: Altogether, 409 patients with obesity from a prospective cohort in a single bariatric center were enrolled retrospectively and evaluated for up to 4 years. Measurements obtained included surgery type, duration of diabetic condition, besides the usual body mass index data tuple. Weight reduction was expressed as percent total weight loss (%TWL) and percent excess weight loss (%EWL).

Results: RYGB or …

Outlier Profiles Of Atomic Structures Derived From X-Ray Crystallography And From Cryo-Electron Microscopy, Lin Chen, Jing He, Angelo Facchiano

Computer Science Faculty Publications

Background: As more protein atomic structures are determined from cryo-electron microscopy (cryo-EM) density maps, validation of such structures is an important task. Methods: We applied a histogram-based outlier score (HBOS) to six sets of cryo-EM atomic structures and five sets of X-ray atomic structures, including one derived from X-ray data with better than 1.5 Å resolution. Cryo-EM data sets contain structures released by December 2016 and those released between 2017 and 2019, derived from resolution ranges 0–4 Å and 4–6 Å respectively. Results: The distribution of HBOS values in five sets of X-ray structures show that HBOS is sensitive distinguishing …

A Genome-Wide Association Study Of Cocaine Use Disorder Accounting For Phenotypic Heterogeneity And Gene–Environment Interaction, Jiangwen Sun, Henry R. Kranzler, Joel Gelernter, Jinbo Bi

Computer Science Faculty Publications

Background: Phenotypic heterogeneity and complicated gene-environment interplay in etiology are among the primary factors that hinder the identification of genetic variants associated with cocaine use disorder. Methods: To detect novel genetic variants associated with cocaine use disorder, we derived disease traits with reduced phenotypic heterogeneity using cluster analysis of a study sample (n = 9965). We then used these traits in genome-wide association tests, performed separately for 2070 African Americans and 1570 European Americans, using a new mixed model that accounted for the moderating effects of 5 childhood environmental factors. We used an independent sample (918 African Americans, 1382 European …

Overlap Matrix Completion For Predicting Drug-Associated Indications, Menhyun Yang, Huimin Luo, Yaohang Li, Fang-Xiang Wu, Jianxin Wang

Computer Science Faculty Publications

Identification of potential drug-associated indications is critical for either approved or novel drugs in drug repositioning. Current computational methods based on drug similarity and disease similarity have been developed to predict drug-disease associations. When more reliable drug- or disease-related information becomes available and is integrated, the prediction precision can be continuously improved. However, it is a challenging problem to effectively incorporate multiple types of prior information, representing different characteristics of drugs and diseases, to identify promising drug-disease associations. In this study, we propose an overlap matrix completion (OMC) for bilayer networks (OMC2) and tri-layer networks (OMC3) to predict potential drug-associated …

Discerning Novel Splice Junctions Derived From Rna-Seq Alignment: A Deep Learning Approach, Yi Zhang, Xinan Liu, James N. Macleod, Jinze Liu

Computer Science Faculty Publications

Background: Exon splicing is a regulated cellular process in the transcription of protein-coding genes. Technological advancements and cost reductions in RNA sequencing have made quantitative and qualitative assessments of the transcriptome both possible and widely available. RNA-seq provides unprecedented resolution to identify gene structures and resolve the diversity of splicing variants. However, currently available ab initio aligners are vulnerable to spurious alignments due to random sequence matches and sample-reference genome discordance. As a consequence, a significant set of false positive exon junction predictions would be introduced, which will further confuse downstream analyses of splice variant discovery and abundance estimation.

Results: …

Seqothello: Querying Rna-Seq Experiments At Scale, Ye Yu, Jinpeng Liu, Xinan Liu, Yi Zhang, Eamonn Magner, Erik Lehnert, Chen Qian, Jinze Liu

Computer Science Faculty Publications

We present SeqOthello, an ultra-fast and memory-efficient indexing structure to support arbitrary sequence query against large collections of RNA-seq experiments. It takes SeqOthello only 5 min and 19.1 GB memory to conduct a global survey of 11,658 fusion events against 10,113 TCGA Pan-Cancer RNA-seq datasets. The query recovers 92.7% of tier-1 fusions curated by TCGA Fusion Gene Database and reveals 270 novel occurrences, all of which are present as tumor-specific. By providing a reference-free, alignment-free, and parameter-free sequence search system, SeqOthello will enable large-scale integrative studies using sequence-level data, an undertaking not previously practicable for many individual labs.

Imapsplice: Alleviating Reference Bias Through Personalized Rna-Seq Alignment, Xinan Liu, James N. Macleod, Jinze Liu

Computer Science Faculty Publications

Genomic variants in both coding and non-coding sequences can have functionally important and sometimes deleterious effects on exon splicing of gene transcripts. For transcriptome profiling using RNA-seq, the accurate alignment of reads across exon junctions is a critical step. Existing algorithms that utilize a standard reference genome as a template sometimes have difficulty in mapping reads that carry genomic variants. These problems can lead to allelic ratio biases and the failure to detect splice variants created by splice site polymorphisms. To improve RNA-seq read alignment, we have developed a novel approach called iMapSplice that enables personalized mRNA transcriptome profiling. The …

Tracing Actin Filament Bundles In Three-Dimensional Electron Tomography Density Maps Of Hair Cell Stereocilia, Salim Sazzed, Junha Song, Julio Kovacs, Willi Wriggers, Manfred Auer, Jing He

Computer Science Faculty Publications

Cryo-electron tomography (cryo-ET) is a powerful method of visualizing the three-dimensional organization of supramolecular complexes, such as the cytoskeleton, in their native cell and tissue contexts. Due to its minimal electron dose and reconstruction artifacts arising from the missing wedge during data collection, cryo-ET typically results in noisy density maps that display anisotropic XY versus Z resolution. Molecular crowding further exacerbates the challenge of automatically detecting supramolecular complexes, such as the actin bundle in hair cell stereocilia. Stereocilia are pivotal to the mechanoelectrical transduction process in inner ear sensory epithelial hair cells. Given the complexity and dense arrangement of actin …

Prediction Of Lncrna-Disease Associations Based On Inductive Matrix Completion, Chengqian Lu, Mengyun Yang, Feng Luo, Fang-Xiang Wu, Min Li, Yi Pan, Yaohang Li, Jianxin Wang

Computer Science Faculty Publications

Motivation: Accumulating evidences indicate that long non-coding RNAs (lncRNAs) play pivotal roles in various biological processes. Mutations and dysregulations of lncRNAs are implicated in miscellaneous human diseases. Predicting lncRNA–disease associations is beneficial to disease diagnosis as well as treatment. Although many computational methods have been developed, precisely identifying lncRNA–disease associations, especially for novel lncRNAs, remains challenging.

Results: In this study, we propose a method (named SIMCLDA) for predicting potential lncRNA– disease associations based on inductive matrix completion. We compute Gaussian interaction profile kernel of lncRNAs from known lncRNA–disease interactions and functional similarity of diseases based on disease–gene and gene–gene onotology …

Auditing Snomed Ct Hierarchical Relations Based On Lexical Features Of Concepts In Non-Lattice Subgraphs, Licong Cui, Olivier Bodenreider, Jay Shi, Guo-Qiang Zhang

Computer Science Faculty Publications

Objective—We introduce a structural-lexical approach for auditing SNOMED CT using a combination of non-lattice subgraphs of the underlying hierarchical relations and enriched lexical attributes of fully specified concept names. Our goal is to develop a scalable and effective approach that automatically identifies missing hierarchical IS-A relations.

Methods—Our approach involves 3 stages. In stage 1, all non-lattice subgraphs of SNOMED CT’s IS-A hierarchical relations are extracted. In stage 2, lexical attributes of fully-specified concept names in such non-lattice subgraphs are extracted. For each concept in a non-lattice subgraph, we enrich its set of attributes with attributes from its ancestor …

Quantification Of Twist From The Central Lines Of Β-Strands, Tunazzina Islam, Michael Poteat, Jing He

Computer Science Faculty Publications

Since the discovery of right-handed twist of a β-strand, many studies have been conducted to understand the twist. Given the atomic structure of a protein, twist angles have been defined using atomic positions of the backbone. However, limited study is available to characterize twist when the atomic positions are not available, but the central lines of β-strands are. Recent studies in cryoelectron microscopy show that it is possible to predict the central lines of β-strands from a medium-resolution density map. Accurate measurement of twist angles is important in identification of β-strands from such density maps. We propose an effective method …

Ordinal Convolutional Neural Networks For Predicting Rdoc Positive Valence Psychiatric Symptom Severity Scores, Anthony Rios, Ramakanth Kavuluru

Computer Science Faculty Publications

Background—The CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing (NLP) provided a set of 1000 neuropsychiatric notes to participants as part of a competition to predict psychiatric symptom severity scores. This paper summarizes our methods, results, and experiences based on our participation in the second track of the shared task.

Objective—Classical methods of text classification usually fall into one of three problem types: binary, multi-class, and multi-label classification. In this effort, we study ordinal regression problems with text data where misclassifications are penalized differently based on how far apart the ground truth and model predictions are …

Predicting Mental Conditions Based On "History Of Present Illness" In Psychiatric Notes With Deep Neural Networks, Tung Tran, Ramakanth Kavuluru

Computer Science Faculty Publications

Background—Applications of natural language processing to mental health notes are not common given the sensitive nature of the associated narratives. The CEGS N-GRID 2016 Shared Task in Clinical Natural Language Processing (NLP) changed this scenario by providing the first set of neuropsychiatric notes to participants. This study summarizes our efforts and results in proposing a novel data use case for this dataset as part of the third track in this shared task.

Objective—We explore the feasibility and effectiveness of predicting a set of common mental conditions a patient has based on the short textual description of patient’s history …

Forest Understory Trees Can Be Segmented Accurately Within Sufficiently Dense Airborne Laser Scanning Point Clouds, Hamid Hamraz, Marco A. Contreras, Jun Zhang

Computer Science Faculty Publications

Airborne laser scanning (LiDAR) point clouds over large forested areas can be processed to segment individual trees and subsequently extract tree-level information. Existing segmentation procedures typically detect more than 90% of overstory trees, yet they barely detect 60% of understory trees because of the occlusion effect of higher canopy layers. Although understory trees provide limited financial value, they are an essential component of ecosystem functioning by offering habitat for numerous wildlife species and influencing stand development. Here we model the occlusion effect in terms of point density. We estimate the fractions of points representing different canopy layers (one overstory and …

Modeling Beta-Traces For Beta-Barrels From Cryo-Em Density Maps, Dong Si, Jing He

Computer Science Faculty Publications

Cryo-electron microscopy (cryo-EM) has produced density maps of various resolutions. Although ά-helices can be detected from density maps at 5-8 angstrom resolutions, β-strands are challenging to detect at such density maps due to close-spacing of β-strands. The variety of shapes of β-sheets adds the complexity of β-strands detection from density maps. We propose a new approach to model traces of β-strands for β-barrel density regions that are extracted from cryo-EM density maps. In the test containing eight β-barrels extracted from experimental cryo-EM density maps at 5.5 angstrom-8.25 angstrom resolution, StrandRoller detected about 74.26% of the amino acids in the β-strands …

Comparing An Atomic Model Or Structure To A Corresponding Cryo-Electron Microscopy Image At The Central Axis Of A Helix, Stephanie Zeil, Julio Kovacs, Willy Wriggers, Jing He

Computer Science Faculty Publications

Three-dimensional density maps of biological specimens from cryo-electron microscopy (cryo-EM) can be interpreted in the form of atomic models that are modeled into the density, or they can be compared to known atomic structures. When the central axis of a helix is detectable in a cryo-EM density map, it is possible to quantify the agreement between this central axis and a central axis calculated from the atomic model or structure. We propose a novel arc-length association method to compare the two axes reliably. This method was applied to 79 helices in simulated density maps and six case studies using cryo-EM …

An Effective Computational Method Incorporating Multiple Secondary Structure Predictions In Topology Determination For Cryo-Em Images, Abhishek Biswas, Desh Ranjan, Mohammad Zubair, Stephanie Zeil, Kamal Al Nasr, Jing He

Computer Science Faculty Publications

A key idea in de novo modeling of a medium-resolution density image obtained from cryo-electron microscopy is to compute the optimal mapping between the secondary structure traces observed in the density image and those predicted on the protein sequence. When secondary structures are not determined precisely, either from the image or from the amino acid sequence of the protein, the computational problem becomes more complex. We present an efficient method that addresses the secondary structure placement problem in presence of multiple secondary structure predictions and computes the optimal mapping. We tested the method using 12 simulated images from alpha-proteins and …

Graph Mining For Next Generation Sequencing: Leveraging The Assembly Graph For Biological Insights, Julia Warnke-Sommer, Hesham Ali

Computer Science Faculty Publications

Background: The assembly of Next Generation Sequencing (NGS) reads remains a challenging task. This is especially true for the assembly of metagenomics data that originate from environmental samples potentially containing hundreds to thousands of unique species. The principle objective of current assembly tools is to assemble NGS reads into contiguous stretches of sequence called contigs while maximizing for both accuracy and contig length. The end goal of this process is to produce longer contigs with the major focus being on assembly only. Sequence read assembly is an aggregative process, during which read overlap relationship information is lost as reads are …

Flexc: Protein Flexibility Prediction Using Context-Based Statistics, Predicted Structural Features, And Sequence Information, Ashraf Yaseen, Mais Nijim, Brandon Williams, Lei Qian, Min Li, Jianxin Wang, Yaohang Li

Computer Science Faculty Publications

The fluctuation of atoms around their average positions in protein structures provides important information regarding protein dynamics. This flexibility of protein structures is associated with various biological processes. Predicting flexibility of residues from protein sequences is significant for analyzing the dynamic properties of proteins which will be helpful in predicting their functions.