Recent advancements in Large Language Models (LLMs) harness linguistic associations in vast natural language data for practical applications. However, their ability to understand the physical world using only language data remains a question. After reviewing existing protocols, we explore this question using a novel and tightly controlled reasoning test (ART) and compare human norms against versions of GPT-3. Our findings highlight the categories of common-sense relations models that could learn directly from data and areas of weakness. GPT-3 offers evidence for verbal reasoning on a par with human subjects for several relations including Synonymy, Antonymy, and Default inheritance, Without reinforcement learning from human judgements, it appears GPT-3 performs at the lower end of the reference interval for Has-part and Contained-in. Weaknesses were observed also in affordance characteristics through Necessary-quality, Order-of-size and Order-of-intensity. Combining LLMs with symbolic world grounding is a promising direction to address associative learning.

Cystic fibrosis is a fatal disease caused by mutations in the cystic fibrosis transmembrane conductance regulator (CFTR). Two main categories of drugs are being developed: correctors that improve folding of CFTR and potentiators that recover the function of CFTR. Here, we report two cryo-electron microscopy structures of human CFTR in complex with potentiators: one with the U.S. Food and Drug Administration (FDA)-approved drug ivacaftor at 3.3-angstrom resolution and the other with an investigational drug, GLPG1837, at 3.2-angstrom resolution. These two drugs, although chemically dissimilar, bind to the same site within the transmembrane region. Mutagenesis suggests that in both cases, hydrogen bonds provided by the protein are important for drug recognition. The molecular details of how ivacaftor and GLPG1837 interact with CFTR may facilitate structure-based optimization of therapeutic compounds.

The cystic fibrosis transmembrane conductance regulator (CFTR) is a crucial ion channel whose loss of function leads to cystic fibrosis, whereas its hyperactivation leads to secretory diarrhea. Small molecules that improve CFTR folding (correctors) or function (potentiators) are clinically available. However, the only potentiator, ivacaftor, has suboptimal pharmacokinetics and inhibitors have yet to be clinically developed. Here, we combine molecular docking, electrophysiology, cryo-EM, and medicinal chemistry to identify CFTR modulators. We docked ∼155 million molecules into the potentiator site on CFTR, synthesized 53 test ligands, and used structure-based optimization to identify candidate modulators. This approach uncovered mid-nanomolar potentiators, as well as inhibitors, that bind to the same allosteric site. These molecules represent potential leads for the development of more effective drugs for cystic fibrosis and secretory diarrhea, demonstrating the feasibility of large-scale docking for ion channel drug discovery.