Join Aqemia: Machine Learning - Research Internship Opportunity

About Aqemia

Aqemia is a pioneering pharmatech company revolutionizing the drug discovery landscape with one of the world's fastest-growing pipelines. Our mission is to swiftly design innovative drug candidates for numerous critical diseases. What sets us apart is our unique blend of quantum and statistical mechanics algorithms, harnessed by generative artificial intelligence to design novel drug candidates. Our cutting-edge technological platform delivers unparalleled speed and accuracy, allowing us to scale drug discovery projects akin to tech ventures. Our efforts are supported by eminent partners from leading pharmaceutical firms, the FrenchTech ecosystem, and prestigious investment funds.

About the Team

As a Machine Learning Research Intern, you’ll be part of an elite team of engineers and researchers developing algorithms to enhance and expedite our internal drug discovery pipeline. Specifically, you will be integrated into the series-expansion team, comprising 3 ML engineers, and will collaborate closely with Victor Saillant.

Your Role

Your focus will be on delving deep into molecular generation, involving literature review, implementation, and training/evaluation of models on both public and proprietary data. The internship duration is flexible, ranging between 4 to 6 months, with potential start dates as early as 2024.

Subject of the Internship

The internship aims to tackle the challenge of molecule generation conditioned on a protein, possibly within a constrained chemical space and with additional physico-chemical properties. The approach involves the use of diffusion models on graphs (see references [1][2]). You may also explore alternative methods, such as auto-regressive models, in a later phase (see references [3][4]).

Skills Required

• Masters or PhD student in Computer Science, Applied Mathematics, Bioinformatics, or a related field.
• Strong interest in machine learning, with a penchant for staying updated on current advancements.
• Solid understanding of mathematics and statistics to critically assess research papers.
• Experience with Python programming and hands-on expertise with deep learning frameworks like PyTorch/Jax/TensorFlow.
• Curiosity and enthusiasm for learning new topics from diverse experts, with a belief in the pivotal role of machine learning in drug discovery.

Nice to Have

• Experience in representation learning and generative modeling.
• Interest in working with complex structured data such as graphs, point clouds, and text.
• Knowledge in biology, chemistry, or chemoinformatics is a significant advantage.

References

• Huang, L., Xu, T., Yu, Y. et al. “A dual diffusion model enables 3D molecule generation and lead optimization based on target pockets”. Nat Commun 15, 2657 (2024).
• Schneuing, Arne, Yuanqi Du, Charles Harris, et al. "Structure-based drug design with equivariant diffusion models." arXiv preprint arXiv:2210.13695 (2022).
• Zhung, W., Kim, H. & Kim, W.Y. 3D molecular generative framework for interaction-guided drug design. Nat Commun 15, 2688 (2024).
• Alexander S. Powers, et al. Geometric Deep Learning for Structure-Based Ligand Design. ACS Central Science 2023 9 (12), 2257-2267.

Additional Information:

Company Name: Aqemia

Job Title: Machine Learning - Research Internship