Title:	AI for Molecular Engineering
DNr:	Berzelius-2026-62
Project Type:	LiU Berzelius
Principal Investigator:	Rocio Mercado <rocio.mercado@chalmers.se>
Affiliation:	Chalmers tekniska högskola
Duration:	2026-03-05 – 2026-10-01
Classification:	10210
Homepage:	https://ailab.bio/
Keywords:

Abstract

The AI Laboratory for Molecular Engineering (AIME) at Chalmers develops machine learning methods at the intersection of artificial intelligence, chemistry, and the life sciences to engineer molecular systems for therapeutic and sustainable materials applications. Our team, led by Dr. Rocío Mercado Oropeza, focuses on developing and applying deep generative models, graph neural networks, and other AI methods to accelerate molecular design for drug discovery and materials science. We request 10,000 GPU-hours per month on Berzelius (divided between Ampere and Hopper clusters) to support the computationally intensive work of our KAW-funded team members. Our research encompasses several major projects funded by the Knut and Alice Wallenberg Foundation, including: (1) AI method development for targeted protein degradation (PROTACs and molecular glues), (2) time-resolved Cell Painting image analysis and generative modeling for drug discovery through the WASP/DDLS TIMED NEST, (3) AI-driven solid polymer electrolyte design through the WASP/WISE SPEED NEST, and (4) multi-component oxide design for sustainable materials (through a WASP/WISE pilot project). Our computational workflows require significant GPU resources for training large-scale deep learning models, including graph neural network- and transformer-based models for molecular property prediction, diffusion and language models for molecular generation, vision transformers for microscopy image analysis, and reinforcement learning agents for molecular optimization. The Berzelius infrastructureis ideally suited for our GPU training requirements, which are more and more going in the direction of multi-GPU training. We currently utilize NAISS Medium Compute allocations on Alvis and Dardel but consistently exceed our monthly allocations, necessitating additional resources on Berzelius to support our expanding team and ambitious research agenda. Our team, as of February 2026, consists of a core of 9 PhDs and 4 postdocs, of whom 9 are KAW-funded; note this count does not include co-supervised PhD students (10) and MSc students (8), some of whom are also KAW-funded and who are also involved in projects relevant to this proposal. All projects below involve KAW-affiliated researchers and are designed to advance Swedish competitiveness in AI-driven molecular engineering, with applications in precision medicine, sustainable battery technology, and environmentally friendly materials.