About Me

I am a Principal Scientist, AI/ML at Johnson & Johnson (Janssen R&D) in High Wycombe, UK working on building novel Machine Learning tools for drug discovery. My work aims to advance personalized medicine by utilizing machine learning, computational systems biology methods, and large-scale health data to better understand and treat complex diseases. I build scalable ML solutions across omics, molecular structure, gene regulation, and clinical data to advance therapeutic design and delivery. I also lead and manage a team of research scientists in my current role.

Prior to this, I was an AI Research Scientist at Exscientia (now Recursion) in Oxford, UK where I led a team in the area of Molecular Property Prediction. I was a PhD candidate at TU Dresden/Max-Planck Institute of Molecular Cell Biology and Genetics, advised by Dr. Florian Jug. In my PhD, I developed methods and software using deep learning and graphical models for image denoising, object segmentation, and tracking in biomedical images. I obtained my MSc degree in Electrical Engineering from the University of Minnesota, Twin Cities with a specialization in distributed control systems and its application to smart grids. I completed my B.Tech degree in Electrical Engineering from the National Institute of Technology, Durgapur, India.

Research Areas
Deep Probabilistic Generative Models, Language Models, Geometric Deep Learning, Computer Vision
Picture of Mangal Prakash

News

Publications

  • HELM: Hierarchical Encoding for mRNA Language Modeling
    M. Prakash, M.Y. Jahromi, T. Mansi, A. Moskalev, and R. Liao
    International Conference on Learning Representations (ICLR) 2025
  • Beyond Sequence: Impact of Geometric Context for RNA Property Prediction
    J. Xu, A. Moskalev, T. Mansi, R. Liao, and M. Prakash
    International Conference on Learning Representations (ICLR) 2025
  • InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference
    T. Cui, S.J. Xu, A. Moskalev, S. Li, T. Mansi, R. Liao, and M. Prakash
    AI4NA@ International Conference on Learning Representations (ICLR) 2025 (Oral)
  • HARMONY: A Multi-Representation Framework for RNA Property Prediction
    J. Xu, A. Moskalev, T. Mansi, R. Liao, and M. Prakash
    AI4NA@ International Conference on Learning Representations (ICLR) 2025
  • SE(3)-Hyena Operator for Scalable Equivariant Learning
    A. Moskalev, M. Prakash, R. Liao, and T. Mansi
    GRaM@ International Conference on Machine Learning (ICML) 2024 (Outstanding paper award)
  • Bridging biomolecular modalities for knowledge transfer in bio-language models
    M. Prakash, A. Moskalev, P. DiMaggio, S. Combs, T. Mansi, J. Scheer, and R. Liao
    FM4Science@ Neural Information Processing Systems (NeurIPS) 2024
  • Addressing label noise for electronic health records: insights from computer vision for tabular data
    J. Yang, H. Triendl, A. Soltan, D. Clifton, and M. Prakash
    BMC Medical Informatics and Decision Making 2024
  • Zyxin contributes to coupling between cell junctions and contractile actomyosin networks during apical constriction
    M. Slabodnick, S. Tintori, M. Prakash, C. Higgins, A. Chen, T. Cupp, T. Wong, E. Bowie, F. Jug, B. Goldstein
    PLOS Genetics, 2023
  • Interpretable Unsupervised Diversity Denoising and Artefact Removal
    M. Prakash, M. Delbracio, P. Milanfar, and F. Jug
    International Conference on Learning Representations (ICLR) 2022 (Spotlight)
  • Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
    M. Prakash, A. Krull, and F. Jug
    International Conference on Learning Representations (ICLR) 2021
  • Extracellular Mechanical Forces Drive Endocardial Cell Volume Decrease During Cardiac Valve Morphogenesis
    H. Vignes, C. Vagena-Pantoula, M. Prakash, C. Norden, F. Jug, and J. Vermot
    Developmental Cell, 2021
  • A Primal-Dual Solver for Large-Scale Tracking-by-Assignment
    S. Haller, M. Prakash, L. Hutschenreiter, T. Pietzsch, C. Rother, F. Jug, P. Swoboda, and B. Savchynskyy
    Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2020
  • DenoiSeg: Joint Denoising and Segmentation
    M. Prakash, T-O. Buchholz, D. Schmidt, A. Krull, and F. Jug
    Bio Image Computing@ ECCV 2020 (Oral)
  • Fully Unsupervised Probabilistic Noise2Void
    M. Prakash, M. Lalit, P. Tomancak, A. Krull, and F. Jug
    IEEE International Symposium on Biomedical Imaging (ISBI) 2020 (Oral)
  • Leveraging Self-Supervised Denoising for Image Segmentation
    M. Prakash, T-O. Buchholz, M. Lalit, P. Tomancak, F. Jug, and A. Krull
    IEEE International Symposium on Biomedical Imaging (ISBI) 2020
  • Probabilistic Noise2Void: Unsupervised Content-Aware Denoising
    A. Krull, T. Vicar, M. Prakash, M. Lalit, and F. Jug
    Frontiers in Computer Science, 2020
  • Regionalized tissue fluidization is required for epithelial gap closure during insect gastrulation
    A. Jain, V. Ulman, A. Mukherjee, M. Prakash, M.B. Cuenca, L.G. Pimpale, S. Münster, R. Haase, K.A. Panfilio, F. Jug, S.W. Grill, P. Tomancak, and A. Pavlopoulos
    Nature Communications, 2020
  • Collagen structure maintains mesenchymal stem cell fate and nuclear shape in embryonic sutures
    D.A. Afonso, A. Ryan, A.L. Chomiak, M. Prakash, F. Jug, C. Modes, and J. Tabler
    Under review at Cell Reports

Intern Supervision

  • Mehdi Yazdani-Jahromi
    University of Central Florida
    Hierarchical encoding for mRNA language modeling
    May 2024 - Nov 2024
  • Junjie Xu
    Pennsylvania State University
    Impact of geometric context for mRNA property prediction
    May 2024 - Nov 2024
  • Jenny Yang
    University of Oxford
    Addressing label noise for electronic health records
    Oct 2023 - Mar 2024

Scholarships and Awards

  • INSPIRE Award at J&J
    Awarded in recognition of exceptional leadership and scientific contribution
    2024-2025
  • College of Science and Engineering Fellowship
    University of Minnesota for graduate studies
    2014-2015
  • Graduate Research and Teaching Assistantship
    University of Minnesota for graduate studies
    2015-2016
  • Summer Research Fellowship
    Awarded by Indian Academy of Sciences but could not undergo internship
    2013
  • Merit certificate
    Awarded by CBSE to top 0.1% students nationwide for matriculation exams
    2007