Shayan Mostafaei

Shayan Mostafaei

Bioinformatician
Visiting address: ,
Postal address: C8 Medicinsk epidemiologi och biostatistik, C8 MEB II Hägg, 171 77 Stockholm

About me

  • I'm a bioinformatician and my research interests are application of
    advanced statistical methods, Bayesian inference, causal inference,
    longitudinal, time-to-event and machine learning algorithms in
    computational biology, health, and medicine. I'm also interested in the
    statistical genetics and analyzing OMICs data as well as longitudinal data from national registry and surveys.
    Education:
    * PhD in Biostatistics and Bioinformatics, Tehran University of Medical Sciences, Tehran, Iran, 2018.
    Postdocs
    * Postdoc in Machine Learning/AI, School of Electrical Engineering and Computer Science, Department of Intelligent Systems, Division of Information Science and Engineering, Royal Institute of Technology (KTH), Stockholm, Sweden, 2022.
    ** Postdoc in Dementia and Machine Learning, Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences, and Society, Karolinska Institutet, Stockholm, Sweden, 2023.

Research

  • Advanced Clustering, Regression and Classification Algorithms
    Statistical Learning for OMICs data
    Bioinformatics and Statistical Genetics
    Longitudinal Statistical Models for high-dimensional data
    Survival and Risk Modelling
    Bayesian and Network Meta-analysis for GWAS
    Biological Aging

Selected publications

Articles

All other publications

Grants

  • Aging and Diabetes: Unraveling the Interplay through Multi-Cohort Investigations
    KID - partial funding of doctoral education at Karolinska institutet 2024
    14 June 2024 - 14 June 2028
  • Predicting the risk of dementia based on multi-omics profiles and biological aging using generative machine-learning in two Swedish population-based cohorts and the UK Biobank
    Loo and Hans Osterman Foundation
    1 January 2024 - 31 December 2024
  • Explainable Machine Learning based Medication Repurposing for Dementia
    Industrial and Societal Partnership Program (ISPP)
    1 January 2024 - 31 December 2025
    The general purpose of the project is designing explainable machine learning (XML) algorithms for data analysis and hereby guide decisions in medication selection. The term "explainable" in XML refers to the ability of these algorithms to provide transparent and interpretable explanations to doctors for their predictions or decisions. XML based medication repurposing for dementia (XMLD) refers to the development and application of XML algorithms to identify potential drugs among existing drugs or medications that can be repurposed for the treatment or management of dementia. The goal is to develop XML algorithms to discover new uses for approved drugs or therapies that were originally developed for different medical conditions in patients with dementia. Therefore, for a patient and/or a class of patients, identification of potential drugs among many existing drugs is a variable selection problem, where XML can help. Variable selection uses sparsity. Sparsity is ubiquitous in nature, and in this case, sparsity arises because a set of few drugs from many available drugs is more appropriate and efficient for a patient and/or a class of patients. We will use sparsity-inducing XML algorithms to select the important drugs. We will explore classical sparsity-inducing algorithms, as used in sparse representations (like LASSO) and new generation of deep learning-based algorithms. The XML algorithms are used to analyze and identify patterns, relationships, and potential associations between drug characteristics, disease severity, and patient outcomes. There are many advantages of medication repurposing for dementia using XML, such as cost and time saving, safety profile, broad range of medication candidates, and improved treatment efficiency. Overall, it addresses a pressing healthcare problem with potentially widespread impact. While our focus is dementia in this project, the accumulated technological knowledge can be used for medication repurposing of many other health problems and diseases in clinics. The proposed XMLD project will establish a strong cooperation between medical doctors and ML researchers in the clinical environment.
  • Causal inference using Dynamic Bayesian Networks to find medications related to slow cognitive decline in dementia: Studies from the Swedish Dementia Registry
    Loo and Hans Osterman Foundation 2022
    1 July 2022 - 1 July 2023

News from KI

Events from KI