Most proteins have no known function, so there is no pile of solid data for a model to learn most of cell biology from.

Added to korrents 19 Sept 2024 · How quotes work · Something wrong? Tell us

Where this collides

• In tension with

  Understanding the biological machine is about five years away, not ten.

  Lowe points out that most proteins have no known function, so there is no pile of solid data for a model to learn most of cell biology from. Huang expects the machine to be understood in five years. The missing data is not an argument that it cannot be done; it is an argument about what would have to happen first, and nobody has said what.

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Biology keeps turning up whole classes of things nobody knew existed, and that is what defeats attempts to model it. DLDerek Lowe19 Sept 2024similar wording
• AI will not produce a big breakthrough in biological understanding any time soon, because biology has nothing like the clean, complete, high-quality data that made protein-structure prediction work. DLDerek Lowe19 Sept 2024similar wording
• Biology models are smaller than language models only because there is less data, not because biology is simpler. MZMark Zuckerberg10 Jun 2026similar wording
• Biology has already handed us an alien library: hundreds of millions of protein machines we do not understand and can only study one at a time. MNMichael Nielsen7 Apr 2026similar wording
• A narrow, highly accurate model can beat a general one inside its own domain, as AlphaFold did, and materials science and chip design are next. JDJeff Dean30 Jul 2026similar wording

On the map

Open the map on its own page →