Providing critical data curation and anonymisation support for an industry-leading global pharmaceutical company developing cutting-edge AI-driven digital pathology algorithms for personalised healthcare in the hematology/oncology space.Key Responsibilities:-Collaborate with cross-functional teams to ensure the integrity. accessibility and usability of diverse datasets for algorithm development-Curate pathology image datasets and associated metadata, applying data anonymisation tools to ensure compliance with data governance and privacy policies under GDPR and GCDMP-Communicate and build/maintain relationships with multiple internal and external stakeholders, managing data delivery timelines according to contractual agreements in place-Design and implement automated data pipelines for efficient ETL processes for data curation, QC and visualization-Execute cloud transfers of big, multi-modal data across different servers and maintain data infrastructure-Programmatically ingest, curate, transform andharmonize large datasets from diverse sources including both real-world data (RWD) and clinical trial (RCT) data-Contribute to the maintenance and optimization of data curation and anonymisation scripts, leveraging Git for version control-Understanding of current healthcare data standards and terminology (CDISC), as well as common data models (OMOP) supported for regulatory submissions within the product development space-Ensure that all data is compliant with the data principles frameworks e.g. FAIR, DAMA-DMBOK, Data Ethics & Quality Principles

Research Project: Identifying the chromatin signatures characteristic of proto-oncogenes and tumour-suppressor genes that regulate the cell cycle-Handled and processed large genomic and epigenomic databases, built bioinformatic pipelines and interpreted and presented bioscientific results-Mined ChIP-Seq datasets of histone modifications from the International Human Epigenome Consortium (IHEC) data portal-Applied diverse bioinformatic approaches including alignments, hidden markov models, machine learning techniques and multiple correspondence analysis to extract epigenomic signatures of selected tumour-associated genes by comparing healthy and tumour samples -Participated in active IHEC integrative analysis and attended regular meetings to collaborate internationally with other researchers in the same field-Critically analysed and effectively communicated my progress on a weekly basis to other members of the research team through formal presentations-Demonstrated excellent technical writing skills by producing a 16-page Bioinformatics Journal style dissertation