Loading
What changed between revision 1 and revision 3, compared over the article's markdown source with its frontmatter — so a change to status, evidence or reversibility shows up as the edit it is.
Older · revision 1
Import· initial corpus import, not an edit
Initial import of content/ai-protein-design.md — the filesystem corpus, unchanged. Not an edit.
17.1 kB
Revision 1
Revision 3
lines 8–14 → 8–147 unchanged lines not shown
categories: ["genetics", "foundations"]categories: ["genetics", "foundations"]tags: ["machine learning", "protein design", "structural biology", "alphafold", "biosecurity", "drug discovery"]tags: ["machine learning", "protein design", "structural biology", "alphafold", "biosecurity", "drug discovery"]summary: "Machine-learning systems that predict what shape a protein sequence folds into and that generate new proteins with no natural counterpart."summary: "Machine-learning systems that predict what shape a protein sequence folds into and that generate new proteins with no natural counterpart."updated: "2026-07-27"updated: "2026-10-27"humanEvidence: "A computationally designed nanoparticle scaffold is a component of a COVID-19 vaccine approved for use in people in South Korea, and a designed cytokine mimic reached early-phase human trials; no de novo designed protein is approved as a therapeutic."humanEvidence: "A computationally designed nanoparticle scaffold is a component of a COVID-19 vaccine approved for use in people in South Korea, and a designed cytokine mimic reached early-phase human trials; no de novo designed protein is approved as a therapeutic."access: "Most prediction and design code is open source and the AlphaFold structure database is public, so the models are free to run; the gene synthesis and wet-lab testing that turn a design into a molecule are not."access: "Most prediction and design code is open source and the AlphaFold structure database is public, so the models are free to run; the gene synthesis and wet-lab testing that turn a design into a molecule are not."reversibility: "context"reversibility: "context"lines 33–39 → 33–3918 unchanged lines not shown
**AI protein design** covers two distinct uses of machine learning on proteins: predicting the**AI protein design** covers two distinct uses of machine learning on proteins: predicting thethree-dimensional structure a given amino acid sequence folds into, and generating new sequencesthree-dimensional structure a given amino acid sequence folds into, and generating new sequencesthat fold into a shape chosen in advance. The first was largely solved for single chains betweenthat fold into a shape chosen in advance. The first was largely solved for single chains between2018 and 2021, mostly by DeepMind's AlphaFold. The second is being solved unevenly, by generative2018 and 2021, mostly by DeepMind's [AlphaFold](https://aiwiki.ai/wiki/alphafold). The second is being solved unevenly, by generativemodels from David Baker's laboratory and others, and it is the half that produces molecules whichmodels from David Baker's laboratory and others, and it is the half that produces molecules whichhave never existed. AlphaFold predicts; it does not design.have never existed. AlphaFold predicts; it does not design. lines 72–84 → 72–8532 unchanged lines not shown
AlphaFold2 takes a sequence, retrieves a multiple sequence alignment of its evolutionary relatives,AlphaFold2 takes a sequence, retrieves a multiple sequence alignment of its evolutionary relatives,and reasons jointly over that alignment and over a matrix of residue pairs before predicting atomicand reasons jointly over that alignment and over a matrix of residue pairs before predicting atomiccoordinates directly. The alignment does much of the work: residues that mutate in a correlated waycoordinates directly. The alignment does much of the work: residues that mutate in a correlated wayacross species tend to touch in three dimensions. AlphaFold3, published in 2024, replaced the finalacross species tend to touch in three dimensions. AlphaFold3, published in 2024 by DeepMind and itsdrug-discovery sister company [[isomorphic-labs|Isomorphic Labs]], replaced the finalgeometric module with a diffusion-based generator and extended the model to complexes of proteinsgeometric module with a diffusion-based generator and extended the model to complexes of proteinswith DNA, RNA, small molecules and ions.[^abramson2024] Protein language models trained on sequencewith DNA, RNA, small molecules and ions.[^abramson2024] Protein language models trained on sequencealone drop the alignment, trading some accuracy for speed and for coverage of sequences with noalone drop the alignment, trading some accuracy for speed and for coverage of sequences with noknown relatives.known relatives. Design runs in two stages. A generative model such as RFdiffusion, adapted from a structureDesign runs in two stages. A generative model such as [RFdiffusion](https://aiwiki.ai/wiki/rfdiffusion), adapted from a structurepredictor by training it to denoise corrupted backbones, produces a protein shape to order: a binderpredictor by training it to denoise corrupted backbones, produces a protein shape to order: a binderagainst a specified epitope, a symmetric assembly, or a scaffold holding catalytic residues inagainst a specified epitope, a symmetric assembly, or a scaffold holding catalytic residues inposition.[^watson2023] A second model, ProteinMPNN, then reads thatposition.[^watson2023] A second model, ProteinMPNN, then reads thatlines 119–125 → 120–12734 unchanged lines not shown
for essentially every sequence in the major reference databases, and models are used routinely tofor essentially every sequence in the major reference databases, and models are used routinely togenerate hypotheses about uncharacterised proteins and to help solve experimental structures. Thatgenerate hypotheses about uncharacterised proteins and to help solve experimental structures. Thatthe code and the database are free is unusual for a result of this weight, and helps explain why itthe code and the database are free is unusual for a result of this weight, and helps explain why itdiffused in months rather than years.diffused in months rather than years. AlphaFold3's code, by contrast, followed publication by sixmonths and only for non-commercial use, while its co-developer uses the model commercially. Design has produced working molecules in narrower domains. Miniprotein binders against viral surfaceDesign has produced working molecules in narrower domains. Miniprotein binders against viral surfaceproteins were designed and shown to bind and neutralise in laboratory assays within months of aproteins were designed and shown to bind and neutralise in laboratory assays within months of alines 197–203 → 199–20671 unchanged lines not shown
Two questions decide how much the technology matters. The first is whether prediction can be pushedTwo questions decide how much the technology matters. The first is whether prediction can be pushedfrom static structures to the quantities that determine whether a molecule works: binding affinity,from static structures to the quantities that determine whether a molecule works: binding affinity,conformational ensembles, and the effect of a mutation. The second is whether design can deliverconformational ensembles, and the effect of a mutation. Isomorphic Labs claimed such gains forbinding affinity in 2026, in a company technical report rather than a peer-reviewed paper. The second is whether design can deliverfunction rather than form, since a de novo enzyme matching a natural one would be a stronger resultfunction rather than form, since a de novo enzyme matching a natural one would be a stronger resultthan any binder.than any binder. removed, struck through added, underlinedLine numbers count the serialised markdown of each revision, frontmatter included.
232 lines are the same in both revisions, and 197 of them are not shown. Neither revision here is necessarily the current article — read AI protein design for the text this wiki stands behind today.