Un gruppo di ricercatori della Collaborations Pharmaceuticals – società privata che si occupa di ricerca sulle malattie rare, ha invertito l’utilizzo di un’Intelligenza Artificiale, solitamente dedicata a individuare sostanze tossiche nei farmaci. All’IA è stato chiesto invece di individuare nuove molecole tossiche: ha prodotto 40.000 risultati in sole 6 ore, alcune di queste potenzialmente letali, o convertibili in armi biochimiche.

Nemmeno i ricercatori si aspettavano un risultato simile e, raggiunti da The Verge per un’intervista più approfondita, hanno spiegato che non hanno fatto nulla che altri, con sufficienti competenze, potrebbero fare. “Se hai qualcuno che sa come programmare in Python e ha qualche capacità di apprendimento automatico, allora, probabilmente in due giorni di lavoro, potrebbe costruire qualcosa simile a questo modello generativo guidato da set di dati su molecole tossiche.”

Ne parla anche il Financial Times, mentre sempre su The Verge potete trovare l’intervista a Fabio Urbina, lead author del paper sul tema pubblicato su Nature Machine Intelligence. Urbina scende più nel dettaglio sull’origine dello studio e gli obiettivi dello stesso.

Can you walk me through how you did that — moved the model to go toward toxicity?

I’ll be a little vague with some details because we were told basically to withhold some of the specifics. Broadly, the way it works for this experiment is that we have a lot of datasets historically of molecules that have been tested to see whether they’re toxic or not.

In particular, the one that we focus on here is VX. It is an inhibitor of what’s known as acetylcholinesterase. Whenever you do anything muscle-related, your neurons use acetylcholinesterase as a signal to basically say “go move your muscles.” The way VX is lethal is it actually stops your diaphragm, your lung muscles, from being able to move so your lungs become paralyzed.

Obviously, this is something you want to avoid. So historically, experiments have been done with different types of molecules to see whether they inhibit acetylcholinesterase. And so, we built up these large datasets of these molecular structures and how toxic they are.

We can use these datasets in order to create a machine learning model, which basically learns what parts of the molecular structure are important for toxicity and which are not. Then we can give this machine learning model new molecules, potentially new drugs that maybe have never been tested before. And it will tell us this is predicted to be toxic, or this is predicted not to be toxic. This is a way for us to virtually screen very, very fast a lot of molecules and sort of kick out ones that are predicted to be toxic. In our study here, what we did is we inverted that, obviously, and we use this model to try to predict toxicity.