He vist l’article titulat LLMs could rewrite how AIs predict reactions and plan syntheses – but should chemists be wary of them? del Chemistry World, on es comenta una nova IA generativa anomenada Chemma que fa servir dades existents de síntesi orgànica per tal de predir nous compostos, o de predir com sintentitzar-ne. Els autors són de la Shanghai Jiao Tong University, de Shanghai. L’article es pot trobar a la revista Nature Intelligence: https://www.nature.com/articles/s42256-025-01066-y. (article a arxiv.org: https://arxiv.org/abs/2504.18340)
… team fine-tuned Chemma from the open-source Llama-2-7B and trained it on more than 1.28 million ‘question-and-answer pairs’, based on publicly available chemistry datasets. These prompts were designed to teach it three key skills: predicting what a reaction will produce, figuring out how to make a target molecule via retrosynthesis and suggesting the best conditions to run a reaction.
Es tracta, doncs, de generar retrosíntesis:
Chemma bypasses this by learning chemical reasoning directly from data, allowing it to make instant predictions. That means lower costs and faster results, especially when tackling new problems. ‘Condition screening that would take weeks of DFT or robotic testing can be narrowed down [to] minutes,’ says Xu.
A diferència d’altres IA generatives, sembla que en aquest cas es tracta d’ajudar els humans, no pas de substituir-los:
A real strength of this paper is that it envisions the LLM as a tool that enables – but does not replace – a human expert
I em sembla interessant el que diu l’article del Chemistry World, que hauria de ser aplicable a totes les IA:
It is important that we start to teach students how to effectively use tools like these, as well as how to be critical of their outputs