AI for biotech, particularly with drug discovery applications, has been used for more than a decade, with ambiguous success. But in the era of foundation models we may have experienced a step change in what's possible.

I used to work on AI-for-drug-discovery years ago, at Recursion, where we sought to identify phenotypes of genetic diseases visible in microscopic images of cells, and screen for drugs that made the cells visually “look healthy” in the hopes that those drugs would also turn out to be effective against the symptoms of the disease.

Circa 2016, we were just beginning to transition from the old-fashioned sort of machine learning based heavily on feature engineering, to the new “deep learning” paradigm with much larger neural nets. “Old-school” machine learning was often accused of being nothing more than logistic regression in fancy VC-funded branding, and there was often some truth to that. When our [...]

---

Outline:

(03:54) Structure Prediction Models

(05:09) AlphaFold2

(05:48) What Can You Do With It?

(07:13) ESM3

(08:07) What Can You Do With It?

(09:28) Evo

(09:55) What Can You Do With It?

(10:41) Protein and Peptide Binding Models

(10:46) RFDiffusion

(11:23) What Can You Do With It?

(11:52) RESP AI

(12:38) What Can You Do With It?

(13:30) Molecular Binding Models

(14:21) AlphaFold3

(14:53) What Can You Do With It?

(15:18) BioSimDock

(15:49) What Can You Do With It?

(16:17) MoLFormerXL

(16:49) What Can You Do With It?

(17:27) BELKA

(17:51) What Can You Do With It?

(18:29) Cell Models

(18:32) CZI's Virtual Cells

(18:52) What Can You Do With It?

(19:26) Phenom-Beta

(19:49) What Can You Do With It?

(21:44) VISTA-2D

(22:29) What Can You Do With It?

(22:45) Target Discovery Models

(23:24) PandaOmics

(24:31) What Can You Do With It?

(25:10) Conclusions

The original text contained 1 image which was described by AI.

---

First published:

Source:

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.