Emanuele Rossi

MLxBio @ Vant AI

me.jpg

I am currently working as a Machine Learning Researcher at Vant AI, where I focus on generative models for structural biology and drug discovery. Our team recently introduced Neo-1, an all-atom multimodal and multi-task latent diffusion model that achieves state-of-the-art performance in both structure prediction and de-novo generation of biomolecules.

I earned my PhD from Imperial College London, working on Graph Neural Networks under the supervision of Prof. Michael Bronstein. During my PhD, I also worked as a Machine Learning Researcher at Twitter, focusing on both foundamental research and applied product problems. Prior to that, I was part of Fabula AI, a startup creating deep learning technology for fake news detection, subsequently acquired by Twitter in 2019. My educational background includes an undergraduate degree from Imperial College London and a master’s degree from the University of Cambridge, both in Computer Science.

Outside of machine learning, you’ll find me scuba diving, hiking trails, or simply enjoying quiet moments in nature.

News

Mar 21, 2025 Excited to finally share what we’ve been working on at Vant AI for the past year and a half: Neo-1, a unified model for all-atom structure prediction and generation of all biomolecules 🔬
Jul 19, 2024 The lack of large, high-quality datasets and robust evaluation is holding back ML in Drug Discovery. We are releasing Pinder (Protein-Protein) and Plinder (Protein-Ligand) to help bridge this gap and drive meaningful progress 🧬
Jan 16, 2024 I’m thrilled to announce that I’ve joined Vant AI as a Machine Learning Researcher. Vant combines a compelling ML vision with a proprietary data generation platform, focusing on the novel field of molecular glues. I’ll be developing generative models for structural biology to advance the drug discovery process 🚀
Jul 31, 2023 We are excited to release the Temporal Graph Benchmark, a collection of seven realistic, large-scale and diverse benchmarks for learning on temporal graphs! The accompanying paper has been accepted to NeurIPS 2023 Datasets and Benchmark track 📝
Jun 08, 2023 Our new paper on Graph Neural Networks for Directed Graphs, and how they improve learning on heterophilic graph, is out along with its associated blog post 📝

Selected Publications

  1. bioRxiv
    pinder.png
    PINDER: The Protein Interaction Dataset and Evaluation Resource
    Daniel Kovtun, Mehmet Akdel, Alexander Goncearenco, and 16 more authors
    bioRxiv, 2024
  2. bioRxiv
    plinder.png
    PLINDER: The Protein-Ligand Interactions Dataset and Evaluation Resource
    Janani Durairaj, Yusuf Adeshina, Zhonglin Cao, and 20 more authors
    ICML ML for Life and Material Science Workshop, 2024
  3. NeurIPS
    tgb.png
    Temporal Graph Benchmark for Machine Learning on Temporal Graphs
    Shenyang Huang, Farimah Poursafaei, Jacob Danovitch, and 7 more authors
    Advances in Neural Information Processing Systems, 2023
  4. arXiv
    dir-gnn.png
    Edge Directionality Improves Learning on Heterophilic Graphs
    Emanuele Rossi, Bertrand Charpentier, Francesco Di Giovanni, and 3 more authors
    Learning on Graphs Conference (LoG), 2023
  5. ICML
    tgn.png
    Temporal Graph Networks for Deep Learning on Dynamic Graphs
    Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, and 3 more authors
    ICML Workshop on Graph Representation Learning, 2020
  6. ICML
    sign.png
    SIGN: Scalable Inception Graph Neural Networks
    Emanuele Rossi, Fabrizio Frasca, Ben Chamberlain, and 3 more authors
    ICML Workshop on Graph Representation Learning, 2020