Open to opportunities

Fatemeh Omidi

@fatemehomidi

Message

Bioinformatician specializing in genomics and AI-driven analysis.

Spain

Message

What I'm looking for

I seek a role that fosters innovation in genomic medicine, emphasizing collaboration and growth.

I am a dedicated Bioinformatician with a strong focus on genomics and AI-driven analysis. My expertise lies in developing and implementing machine learning workflows for Next-Generation Sequencing (NGS) analysis, optimizing genomic data pipelines using Python and MongoDB, and integrating predictive models to enhance diagnostic yield and efficiency. Currently, I am a Marie Skłodowska-Curie Fellow under the PIPgen Project, where I lead AI-based initiatives to improve diagnostic outcomes for rare diseases.

Throughout my academic journey, I have successfully spearheaded projects that have identified causative variants in clinical cases, developed scalable data management systems, and designed end-to-end workflows for clinical genomic pipelines. My collaborative approach with clinicians ensures that computational tools align with patient needs, fostering a patient-centric approach to precision medicine. I am passionate about leveraging my skills to contribute to advancements in genomic medicine and improve patient outcomes.

Experience

Work history, roles, and key accomplishments

Current

Research Collaborator, EvoPronet Team

Current

Institut de Biologia Evolutiva (IBE) - CSIC UPF

May 2024 - Present (1 year)

Contributed to the EvoPronet project, leveraging DNA and protein network interactions to design bio-inspired computational frameworks with AI-based approaches. Applied transformer-based architectures to analyze large-scale protein interaction networks, improving predictive accuracy and interpretability. Collaborated with an interdisciplinary team to integrate computational AI methods with biologic

AI Transformer Architecture Computational Biology Bioinformatics

Researcher, R&D Department

Quantitative Genomic Medicine Laboratories (qGenomics)

Feb 2022 - Feb 2025 (3 years)

Spearheaded AI-based initiatives to improve diagnostic yield for rare diseases, successfully identifying causative variants in 86 out of 95 clinical cases. Developed a scalable data management system using MongoDB and Python to store and annotate over 8 million genomic variants, optimizing the system for efficient reanalysis. Designed and implemented end-to-end workflows for clinical genomic pipel

AI Machine Learning Python MongoDB Data Pipelines Diagnostic Yield Improvement Data Management Workflows

Research Internship

Barcelona Supercomputing Center (BSC)

May 2024 - Jul 2024 (2 months)

Integrated additional layers to enhance the precision and adaptability of existing Machine Learning workflows. Worked under the supervision of Dr. Marta Mele to improve computational models.

Machine Learning Computational Models

Laboratory Expert Intern

Javad Al Aeme Genetics Clinic

Sep 2019 - Sep 2020 (1 year)

Managed and analyzed Whole Exome Sequencing (WES) data for clinical diagnostics, ensuring data quality and integrity. Collaborated closely with clinical teams to integrate genetic data with phenotypic and familial histories, enhancing diagnostic accuracy for patients.

Phenotypic Integration Familial History Analysis

Education

Degrees, certifications, and relevant coursework

Universitat Pompeu Fabra

Ph.D., Biomedicine

Pursuing a Ph.D. in Biomedicine with a focus on improving diagnostic yield and time-to-diagnosis for rare diseases. Developing AI-based algorithms for this purpose. Thesis title: Improving diagnostic yield and time-to-diagnosis of rare diseases by developing AI-based algorithms.

Kerman University of Medical Sciences

M.Sc., Medical Genetics

Grade: 18.4/20 (4/4)

Completed a Master of Science in Medical Genetics. Investigated genetic variants through network interactions to design bio-inspired computational frameworks, with a focus on AI-based approaches in patients with congenital cataract. Thesis title: Investigation of genetic variants through network interactions to design bio-inspired computational frameworks with a focus on AI-based approaches in pat