Skip to main content
To KTH's start page

Computational Biology and Machine Learning in Biomedicine

We are located at SciLifeLab, Sweden’s main centre for high-throughput biology. Our research focuses on developing advanced machine learning methods for analyzing cutting-edge biological data, including single-cell and spatial information, with different contributions to computational modeling and bioimage analysis. We apply these methods to understand cellular behavior, interactions, and the underlying biological processes.

Computational Biology and Machine Learning in Biomedicine brings together four research groups with a shared foundation in machine learning and probabilistic modeling. Each group explores complementary areas within computational biology and medicine, collectively advancing the field through the development and application of cutting-edge machine learning techniques. Our work focuses on uncovering patterns in complex biological data to enhance our understanding of biological systems and drive improvements in healthcare.

We design advanced inference models, leveraging variational methods and particle-based algorithms to analyze dynamic and structured data. These methods are applied across a wide range of domains, including genomics, transcriptomics, drug discovery, and cancer biology. Our research covers topics such as reconstructing evolutionary relationships in phylogenetics and identifying gene modules and molecular pathways associated with disease. A central focus lies in integrating diverse omics datasets and building scalable, interpretable models that deliver actionable insights for both biological research and clinical practice.
 
In the imaging domain, our research combines machine learning with computer vision to analyze biomedical images, offering new insights into cellular and tissue-level organization. This includes developing deep learning models for high-resolution image analysis, with applications in radiology, digital pathology, high-content screening, and spatial proteomics. We place a strong focus on multimodal imaging datasets, supporting precision medicine by enabling the detection, quantification, and interpretation of phenotypic patterns relevant to disease diagnosis and treatment.
 
Our groups have been awarded several national and international grants, including funding from the Swedish Research Council, WASP, the SciLifeLab and Knut and Alice Wallenberg Data-Driven Life Sciences programs, and the Chan Zuckerberg Initiative.

Researchers

Jens Lagergren
Jens Lagergren professor
Kevin Smith
Kevin Smith associate professor
Gisele Barboni Miranda
Gisele Barboni Miranda assistant professor, researcher
Golnaz Taheri
Golnaz Taheri assistant professor

Courses

  • Statistical Methods in Applied Computer Science ( DD2447 )

  • Foundations of Machine Learning ( DD1420 )

  • Deep Learning Methods for Biomedical Image Analysis ( FDD3020 )

  • Advanced Machine Learning ( DD2434 )

Infrastructure

SciLifeLab BioImage Infarmatics Facility

Visiting Address:

SciLifeLab - Gamma building, 6th floor,
Tomtebodavägen 23, 171 65 Solna

Current Projects

  • Swedish Research Council – Mathematical models, algorithms, and tools for regulatory and comparative genomics
  • SFO project at SciLifeLab – Cancer Progression
  • Project within the Erasmus Mundus PhD program EuroSPIN – Adaptive evolution in primate brain

Previous Projects

  • Swedish Research Council – Algorithms for Eukaryote Comparative Genomics
  • Swedish Research Council - Algorithms for genome assembly
  • Project within the Swedish Foundation for Strategic Research funded Center for Industrial and Applied Mathematics – Disease progression.