Alán Aspuru‐Guzik

This study shows that fine-tuning protein models on text annotations improves their predictive power for function prediction tasks, outperforming BLAST in some cases.

DORA AI Scientist automates scientific research tasks and report generation using multi-agent AI systems and LLMs, reducing manuscript preparation time and enabling more focus on discovery.

This paper introduces a computational pipeline for identifying SARS-CoV-2 nsp14 inhibitors using virtual screening, identifying seven candidates including NSC620333 and SS148, with experimental validation of binding affinity and structural insights.

AdaptiveFlow enables large-scale virtual screening of 69 billion molecules to discover validated FSP1 inhibitors, improving efficiency and scalability in drug discovery.

The paper compares the thermodynamic properties of biological and non-biological compounds in redox chemical space, finding metabolites have lower Gibbs energies and specific functional group enrichments.