Biology subjects

Samarajiwa, S. A.

Publications and source records attributed to Samarajiwa, S. A..

5 recordsLinked to original sources

bioRxiv2020

Identifying regulatory and spatial genomic architectural elements using cell type independent machine and deep learning models

Chromosome conformation capture methods such as Hi-C enables mapping of genome-wide chromatin interactions and is a promising technology to understand the role of spatial chromatin organisation in gene regulation. However, the generation and analysis of these data sets at high resolutions remain technically challenging and costly. We developed a machine and deep learning approach to predict functionally important, highly interacting chromatin regions (HICR) and topologically associated domain (TAD) boundaries independent of Hi-C data in both normal physiological states and pathological conditions such as cancer. This approach utilises gradient boosted trees and convolutional neural networks trained on both Hi-C and histone modification epigenomic data from three different cell types. Given only epigenomic modification data these models are able to predict chromatin interactions and TAD boundaries with high accuracy. We demonstrate that our models are transferable across cell types, indicating that combinatorial histone mark signatures may be universal predictors for highly interacting chromatin regions and spatial chromatin architecture elements.

genomics↗

bioRxiv2020

SpiderSeqR: an R package for crawling the web of high-throughput multi-omic data repositories for data-sets and annotation

AO_SCPLOWBSTRACTC_SCPLOWMore than three decades ago, the microarray revolution brought about high-throughput data generation capability to biology and medicine. Subsequently, the emergence of massively parallel sequencing technologies led to many big-data initiatives such as the human genome project and the encyclopedia of DNA elements (ENCODE) project. These, in combination with cheaper, faster massively parallel DNA sequencing capabilities, have democratised multi-omic (genomic, transcriptomic, translatomic and epigenomic) data generation leading to a data deluge in bio-medicine. While some of these data-sets are trapped in inaccessible silos, the vast majority of these data-sets are stored in public data resources and controlled access data repositories, enabling their wider use (or misuse). Currently, most peer reviewed publications require the deposition of the data-set associated with a study under consideration in one of these public data repositories. However, clunky and difficult to use interfaces, subpar or incomplete annotation prevent discovering, searching and filtering of these multi-omic data and hinder their re-purposing in other use cases. In addition, the proliferation of multitude of different data repositories, with partially redundant storage of similar data are yet another obstacle to their continued usefulness. Similarly, interfaces where annotation is spread across multiple web pages, use of accession identifiers with ambiguous and multiple interpretations and lack of good curation make these data-sets difficult to use. We have produced SpiderSeqR, an R package, whose main features include the integration between NCBI GEO and SRA databases, enabling an integrated unified search of SRA and GEO data-sets and associated annotations, conversion between database accessions, as well as convenient filtering of results and saving past queries for future use. All of the above features aim to promote data reuse to facilitate making new discoveries and maximising the potential of existing data-sets. Availabilityhttps://github.com/ss-lab-cancerunit/SpiderSeqR

bioinformatics↗

bioRxiv2020

Machine Classification of Methylomes in Cancer

Cancer remains a leading cause of morbidity and mortality worldwide. Its evolutionary nature and resultant complex interactions with the tumour micro-environment and the host immune system engender heterogeneity, make developing interventions difficult. Usually detected at the advanced stages of disease, metastatic cancer accounts for 90% of cancer-associated deaths. Therefore early detection of cancer, combined with current therapies, would have a significant impact on survival and treatment of this insidious disease. Epigenetic changes such as DNA methylation are some of the early events in carcinogenesis. Here, we report on a machine learning model that can classify 13 types of cancer as well as non-cancer tissue samples using only DNA methylome data, with an accuracy of 98.2%. We utilise the features identified by this model to develop a robust deep neural network that can generalise to independent data sets. We also demonstrate that the methylation associated genomic loci detected by the classifier are associated with genes involved in cancer, providing insights into the epigenomic regulation of carcinogenesis.

bioinformatics↗

bioRxiv2020

Pangaea: A modular and extensible collection of tools for mining context dependent gene relationships from the biomedical literature

MotivationPangaea is a scalable and extensible command line interface (CLI) software that integrates gene-relationship detection features to extract context-dependent structured gene-gene and gene-term relationships from the biomedical literature. It provides computational methods to identify biological relationships between a collection of genes and can be used to search and extract different types of contextual relationships amongst genes. ResultsWe implemented a CLI-based software for downloading PubMed articles and extracting gene relationships from abstracts using natural language processing methods. In terms of scalability, the software was designed to support the retrieval and processing of millions of articles whilst minimising memory requirements and optimising for parallel processing on multiple CPU cores. To allow extensibility, the tool permits the use of contextual custom-made models for the text processing parts, and the output is serialised as JSON objects to allow flexible post-processing workflows. AvailabilityThe software is available online at: https://github.com/ss-lab-cancerunit/pangaea

bioinformatics↗

bioRxiv2019

Transcription-driven cohesin repositioning rewires chromatin loops in cellular senescence

Senescence is a phenotypic state of stable proliferative arrest, typically occurring in lineage-committed cells and triggered by various stimuli. It is generally accompanied by activation of a secretory program (senescence-associated secretory phenotype, SASP), which modulates both local (tissue microenvironment) and systemic (ageing) homeostasis1,2. Enhancer-promoter interactions play a key role in gene regulation3-5, facilitated by chromatin loops, mostly formed via CCCTC binding factor (CTCF) and cohesin tethering6-8. The three-dimensional chromatin structure of senescent cells has been characterised9-11 mostly in terms of macro-domain structures, but its relevance in gene expression remains elusive. Here, we use Hi-C and capture Hi-C12,13 to show that oncogenic HRAS-induced senescence (RIS) in human diploid fibroblasts (HDFs) is accompanied by extensive enhancer-promoter rewiring, which is closely connected with dynamic cohesin binding to the genome. We find de novo cohesin peaks at the 3 end of a subset of active genes, reminiscent of the transcription-driven cohesin islands recently discovered in mouse embryonic fibroblasts deficient in both CTCF and the cohesin release factor Wings apart-like (Wapl)14. RIS de novo cohesin peaks are also transcription-dependent and enriched for SASP genes, as exemplified by IL1B, where de novo cohesin binding is involved in new loop formation. Cytokine induction is associated with similar cohesin islands appearance and enhancer-promoter rewiring during the terminal differentiation of monocytes to macrophages15, but not upon acute TNF treatment of HDFs16. These results suggest that RIS represents a fate-determined process in which gene expression is regulated beyond the cell type specific 3D chromatin framework, in part through cohesin redistribution.

molecular biology↗