Gihan Jayatilaka

Bio: Gihan Jayatilaka is an academic researcher from University of Peradeniya. The author has contributed to research in topics: Deep learning & Refresh rate. The author has an hindex of 4, co-authored 14 publications receiving 32 citations.

GPU accelerated adaptive banded event alignment for rapid comparative nanopore signal analysis

Abstract: Nanopore sequencing enables portable, real-time sequencing applications, including point-of-care diagnostics and in-the-field genotyping. Achieving these outcomes requires efficient bioinformatic algorithms for the analysis of raw nanopore signal data. However, comparing raw nanopore signals to a biological reference sequence is a computationally complex task. The dynamic programming algorithm called Adaptive Banded Event Alignment (ABEA) is a crucial step in polishing sequencing data and identifying non-standard nucleotides, such as measuring DNA methylation. Here, we parallelise and optimise an implementation of the ABEA algorithm (termed f5c) to efficiently run on heterogeneous CPU-GPU architectures. By optimising memory, computations and load balancing between CPU and GPU, we demonstrate how f5c can perform ∼3-5 × faster than an optimised version of the original CPU-only implementation of ABEA in the Nanopolish software package. We also show that f5c enables DNA methylation detection on-the-fly using an embedded System on Chip (SoC) equipped with GPUs. Our work not only demonstrates that complex genomics analyses can be performed on lightweight computing systems, but also benefits High-Performance Computing (HPC). The associated source code for f5c along with GPU optimised ABEA is available at https://github.com/hasindu2008/f5c .

Use of Artificial Intelligence on spatio-temporal data to generate insights during COVID-19 pandemic: A Review

Abstract: The COVID-19 pandemic, within a short time span, has had a significant impact on every aspect of life in almost every country on the planet. As it evolved from a local epidemic isolated to certain regions of China, to the deadliest pandemic since the influenza outbreak of 1918, scientists all over the world have only amplified their efforts to combat it. In that battle, Artificial Intelligence, or AI, with its wide ranging capabilities and versatility, has played a vital role and thus has had a sizable impact. In this review, we present a comprehensive analysis of the use of AI techniques for spatio-temporal modeling and forecasting and impact modeling on diverse populations as it relates to COVID-19. Furthermore, we catalogue the articles in these areas based on spatio-temporal modeling, intrinsic parameters, extrinsic parameters, dynamic parameters and multivariate inputs (to ascertain the penetration of AI usage in each sub area). The manner in which AI is used and the associated techniques utilized vary for each body of work. Majority of articles use deep learning models, compartment models, stochastic methods and numerous statistical methods. We conclude by listing potential paths of research for which AI based techniques can be used for greater impact in tackling the pandemic.

A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

Abstract: Low light image enhancement is an important challenge for the development of robust computer vision algorithms The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process Cycle consistency loss and a patched discriminator are utilized to further improve the performance The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline

GPU Accelerated Adaptive Banded Event Alignment for Rapid Comparative Nanopore Signal Analysis

Abstract: Nanopore sequencing has the potential to revolutionise genomics by realising portable, real-time sequencing applications, including point-of-care diagnostics and in-the-field genotyping. Achieving these applications requires efficient bioinformatic algorithms for the analysis of raw nanopore signal data. For instance, comparing raw nanopore signals to a biological reference sequence is a computationally complex task despite leveraging a dynamic programming algorithm for Adaptive Banded Event Alignment (ABEA)—a commonly used approach to polish sequencing data and identify non-standard nucleotides, such as measuring DNA methylation. Here, we parallelise and optimise an implementation of the ABEA algorithm (termed f5c) to efficiently run on heterogeneous CPU-GPU architectures. By optimising memory, compute and load balancing between CPU and GPU, we demonstrate how f5c can perform ~3-5× faster than the original implementation of ABEA in the Nanopolish software package. We also show that f5c enables DNA methylation detection on-the-fly using an embedded System on Chip (SoC) equipped with GPUs. Our work not only demonstrates that complex genomics analyses can be performed on lightweight computing systems, but also benefits High-Performance Computing (HPC). The associated source code for f5c along with GPU optimised ABEA is available at https://github.com/hasindu2008/f5c.

A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images

Abstract: Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study

Abstract: Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.

Getting to Know Low-light Images with The Exclusively Dark Dataset

Abstract: Low-light is an inescapable element of our daily surroundings that greatly affects the efficiency of our vision. Research works on low-light has seen a steady growth, particularly in the field of image enhancement, but there is still a lack of a go-to database as benchmark. Besides, research fields that may assist us in low-light environments, such as object detection, has glossed over this aspect even though breakthroughs-after-breakthroughs had been achieved in recent years, most noticeably from the lack of low-light data (less than 2% of the total images) in successful public benchmark dataset such as PASCAL VOC, ImageNet, and Microsoft COCO. Thus, we propose the Exclusively Dark dataset to elevate this data drought, consisting exclusively of ten different types of low-light images (i.e. low, ambient, object, single, weak, strong, screen, window, shadow and twilight) captured in visible light only with image and object level annotations. Moreover, we share insightful findings in regards to the effects of low-light on the object detection task by analyzing visualizations of both hand-crafted and learned features. Most importantly, we found that the effects of low-light reaches far deeper into the features than can be solved by simple "illumination invariance'". It is our hope that this analysis and the Exclusively Dark dataset can encourage the growth in low-light domain researches on different fields. The Exclusively Dark dataset with its annotation is available at this https URL

DNA methylation-calling tools for Oxford Nanopore sequencing: a survey and human epigenome-wide evaluation.

Abstract: Nanopore long-read sequencing technology greatly expands the capacity of long-range, single-molecule DNA-modification detection. A growing number of analytical tools have been developed to detect DNA methylation from nanopore sequencing reads. Here, we assess the performance of different methylation-calling tools to provide a systematic evaluation to guide researchers performing human epigenome-wide studies. We compare seven analytic tools for detecting DNA methylation from nanopore long-read sequencing data generated from human natural DNA at a whole-genome scale. We evaluate the per-read and per-site performance of CpG methylation prediction across different genomic contexts, CpG site coverage, and computational resources consumed by each tool. The seven tools exhibit different performances across the evaluation criteria. We show that the methylation prediction at regions with discordant DNA methylation patterns, intergenic regions, low CG density regions, and repetitive regions show room for improvement across all tools. Furthermore, we demonstrate that 5hmC levels at least partly contribute to the discrepancy between bisulfite and nanopore sequencing. Lastly, we provide an online DNA methylation database ( https://nanome.jax.org ) to display the DNA methylation levels detected by nanopore sequencing and bisulfite sequencing data across different genomic contexts. Our study is the first systematic benchmark of computational methods for detection of mammalian whole-genome DNA modifications in nanopore sequencing. We provide a broad foundation for cross-platform standardization and an evaluation of analytical tools designed for genome-scale modified base detection using nanopore sequencing.

Comprehensive genetic diagnosis of tandem repeat expansion disorders with programmable targeted nanopore sequencing

Abstract: More than 50 neurological and neuromuscular diseases are caused by short tandem repeat (STR) expansions, with 37 different genes implicated to date. We describe the use of programmable targeted long-read sequencing with Oxford Nanopore’s ReadUntil function for parallel genotyping of all known neuropathogenic STRs in a single assay. Our approach enables accurate, haplotype-resolved assembly and DNA methylation profiling of STR sites, from a list of predetermined candidates. This correctly diagnoses all individuals in a small cohort ( n = 37) including patients with various neurogenetic diseases ( n = 25). Targeted long-read sequencing solves large and complex STR expansions that confound established molecular tests and short-read sequencing and identifies noncanonical STR motif conformations and internal sequence interruptions. We observe a diversity of STR alleles of known and unknown pathogenicity, suggesting that long-read sequencing will redefine the genetic landscape of repeat disorders. Last, we show how the inclusion of pharmacogenomic genes as secondary ReadUntil targets can further inform patient care.