ML Research Scientist · Paris
Michail Chatzianastasis
ML Research Scientist on the Natera Therapeutics AI team. Previously PhD at École Polytechnique.
I build genomic large language models for clinical applications and design deep learning methods for neoantigen prediction in cancer immunotherapy. My research lives at the intersection of machine learning, graph representation learning, and foundation models for biology.
About
I am a Machine Learning Research Scientist at Natera in the Therapeutics AI team, where I focus on developing genomic large language models for clinical applications and designing deep learning methods for neoantigen prediction in cancer immunotherapy.
I obtained my PhD at the Data Science and Mining Team of the Computer Science Laboratory at École Polytechnique, under the supervision of Prof. Michalis Vazirgiannis. In 2024, I completed a research internship at InstaDeep working on graph neural networks and single-cell foundation models. In 2022, I interned at the Flatiron Institute of the Simons Foundation in New York, applying graph neural networks to cancer-gene prediction with Dr. Zijun Frank Zhang.
Earlier, I graduated from the School of Electrical and Computer Engineering at the National Technical University of Athens. As an undergraduate I worked at the Laboratory of Algebraic and Geometric Algorithms at the National and Kapodistrian University of Athens with Prof. Ioannis Emiris, and completed Google Summer of Code 2019.
Research interests
Graph representation learning
Expressive GNN architectures, attention, ordering, hyperbolic embeddings, and structural inductive biases.
Foundation models for biology
Genomic LLMs, protein language models, and multimodal alignment of sequence, structure, and text.
AI for precision oncology
Deep learning for neoantigen prediction, cancer-gene discovery, and clinical decision support.
Automated machine learning
Neural architecture search, graph-based search spaces, and operation embeddings.
News
Selected publications
All publications →Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment
Xiao Fei, Michail Chatzianastasis, Sarah Almeida Carneiro, Hadi Abdine, Lawrence P. Petalidis, Michalis Vazirgiannis
Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers
Hadi Abdine, Michail Chatzianastasis, Costas Bouyioukos, Michalis Vazirgiannis
Explainable Multilayer Graph Neural Network for Cancer Gene Prediction
Michail Chatzianastasis, Michalis Vazirgiannis, Zijun Zang
Neural Architecture Search with Multimodal Fusion Methods for Diagnosing Dementia
Michail Chatzianastasis, Loukas Ilias, Dimitris Askounis, Michalis Vazirgiannis
Recent talks
All talks →Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers