Biography

I am a PhD student in the Department of Computer Science at Aalto University, advised by Prof. Harri Lähdesmäki. My research focuses on developing machine learning methods for applications in biology and chemistry. I have worked on deep generative models for drug-like molecules (diffusion models), protein language models, and discriminative methods for T cell receptors, signal peptides, and peptide-MHC classification of chemically-modified amino acids.

Education

• PhD in Machine Learning, 2021-present
  Aalto University
  • Research exchange at Broad Institute of MIT and Harvard (Feb-July, 2024)
  • Collaboration with HiLIFE, University of Helsinki (2021-2023)
• MSc in Machine Learning, 2018-2021
  Aalto University
  • Thesis: TCR Sequence Representations Using Deep, Contextualized Language Models.
• BSc in Computer System Engineering, 2014-2018
  Politehnica University of Buchares

• Alexandru Dumitrescu, Dani Korpela, Markus Heinonen, Yogesh Verma, Valerii Iakovlev, Vikas Garg, Harri Lähdesmäki, E(3)-equivariant models cannot learn chirality: Field-based molecular generation. ICLR 2025.
• Alexandru Dumitrescu, Emmi Jokinen, Anja Paatero, Juho Kellosalo, Ville O Paavilainen, Harri Lähdesmäki, TSignal: a transformer model for signal peptide prediction. ISMB 2023 conference (published in Bioinformatics).
• Alexandru Dumitrescu, Emmi Jokinen, Dani Korpela, Harri Lähdesmäki, Structure-guided T cell receptor and epitope interaction prediction. ICML CompBio Workshop 2023.
• Emmi Jokinen, Alexandru Dumitrescu, Jani Huuhtanen, Vladimir Gligorijević, Satu Mustjoki, Richard Bonneau, Markus Heinonen, Harri Lähdesmäki, TCRconv: predicting recognition between T cell receptors and epitopes using contextualized motifs. Bioinformatics 2023.
• Dani Korpela, Emmi Jokinen, Alexandru Dumitrescu, Jani Huuhtanen, Satu Mustjoki, Harri Lähdesmäki, EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings. Bioinformatics 2023.