![](https://images.squarespace-cdn.com/content/v1/63e000c6b31c4e4f5a061653/1677116586141-GHN7S7BSVYMC8UJ2ECN8/unsplash-image-xuTJZ7uD7PI.jpg)
[1] Amer Marwan El-Samman and Stijn De Baerdemacker. “Amide - amine + alcohol = carboxylic acid." Chemical reactions as linear algebraic analogies in graph neural networks.” In: Chemical Science (2025, Under Review) (10.26434/chemrxiv-2024-fmck4)
[2] Amer Marwan El-Samman, Incé Amina Husain, Mai Huynh, Stefano De Castro, Brooke Morton, and Stijn De Baerdemacker.“Global geometry of chemical graph neural network representations in terms of chemical moieties”. Digital Discovery 3 (2024), p. 544-557
[3] Amer Marwan El-Samman, Stefano De Castro, Brooke Morton, and Stijn De Baerdemacker. “Transfer Learning Graph Representations of Molecules for pKa, 13C-NMR, and Solubility”. Canadian Journal of Chemistry 102 (2024), p. 275-288
[4] Amer Marwan El-Samman, Egor Ospadov, and Viktor Staroverov. First Ionization Energy as the Asymptotic Limit of the Average Local Electron Energy. Journal of Chemical Theory and Computation 16 (2020), p. 6886-6893
[5] Amer Marwan El-Samman, and Viktor Staroverov. Asymptotic behavior of the average local ionization energy in finite basis sets. The Journal of Chemical Physics 153, 134109 (2020)
[6] Amer Marwan El-Samman and Stijn De Baerdemacker. “A Global Explanation of Graph Neural Network Models of Chemistry: Applications in Molecular Modelling.” In: Preparation (2025)
Amer El-Samman: Exploring the Future Through AI and Innovation
I am first and foremost a family man, a cat-lover, and a lifelong explorer of intelligence—both natural and artificial. Growing up in the vibrant city of Tripoli, Lebanon, I was surrounded by computers, internet cafés, and endless possibilities. I spent hours tinkering with machines, breaking them down to understand how they worked, and imagining new ways to solve problems. That curiosity never left me. Today, I channel it into AI, intelligent systems, and the future of technology.
My journey has taken me across multiple domains, from materials science to computational chemistry, but the common thread has always been data, models, and decision-making. I am passionate about how intelligence emerges, how it can be modeled, and how it can be leveraged to drive innovation. Whether predicting molecular properties with AI or designing systems that make sense of complex data, I focus on building trustworthy, scalable, and interpretable AI solutions that push the boundaries of what’s possible.
At the core of my work is a fundamental question: How do we design AI that understands the world the way we do—or even better? I explore this through probabilistic modeling, inference-driven AI, and human-AI collaboration. The goal isn’t just automation, but augmentation—AI that enhances human decision-making, accelerates innovation, and creates real-world impact.
Beyond my technical work, I am deeply invested in bridging the gap between AI and society. As the founder of SciClub, I lead discussions that make complex ideas accessible and relevant. I believe the future of AI isn’t just about algorithms—it’s about how we integrate intelligence into our world responsibly, ethically, and effectively.
When I’m not working on AI-driven solutions, you’ll find me playing the guitar, hiking, or curled up with my cats—always thinking about the next big question in intelligence and technology.