Protein engineering
Protein design now covers open atom-level tools and drug candidates in trials. RFdiffusion3 widens what researchers can design. Generate lists its engineered antibody GB-0895 in Phase 3 asthma studies. Good computational performance does not show that a drug works, and GB-0895 is still investigational.
Research snapshot · updated Nov 12, 2026
Core thesis
Protein engineering now includes designing new proteins from scratch as well as predicting the shape of existing ones. The 2024 Nobel Prize in Chemistry recognised both: half went to David Baker for computational protein design, and half jointly to Demis Hassabis and John Jumper for protein structure prediction. Uses include new enzymes for manufacturing, protein medicines, biosensors and materials. The same tools could in principle be used to design harmful proteins. A designed protein still has to prove in clinical trials that it works as a medicine.
State of the art (2026)
Protein engineering in 2026 is defined by three converging fronts. Generation: David Baker’s Institute for Protein Design released RFdiffusion3 in December 2025 – an all-atom diffusion model that designs binders to DNA, ligands and enzyme active sites, alongside EvolutionaryScale’s ESM3 and DeepMind’s AlphaFold 3 for structure and interactions. Clinic: Generate Biomedicines began global Phase 3 trials of GB-0895, an AI-engineered long-acting anti-TSLP antibody for severe asthma, in late 2025 – among the first generative-AI molecules to reach Phase 3. Industry: Isomorphic Labs runs multi-billion-dollar pharma deals, while Codexis, Arzeda and Novonesis push designed enzymes into manufacturing. The open question is whether fully de novo proteins, not just optimised antibodies, deliver clinical efficacy.
Explore the deeper analysis in CanaryIQ
Explore what is covered below. These previews show the structure; log in to read the full analysis.
Signal stack
Evidence stacked leading → lagging
8 signals
Signal stack
Evidence stacked leading → lagging
Technology-native KPIs
Metrics that predict trajectory, tracked over time
3 tracked
Technology-native KPIs
Metrics that predict trajectory, tracked over time
Landscape map
Who builds what, and who depends on whom
70 players · 5 layers
Landscape map
Who builds what, and who depends on whom
Catalyst calendar
Dated events that will move the position
3 ahead
Catalyst calendar
Dated events that will move the position
Watchlists
Companies, people and papers, each with a condition for removing it
19 · 3
Watchlists
Companies, people and papers, each with a condition for removing it
Decision frameworks
What our view means for your job
Locked
Decision frameworks
What our view means for your job
Thesis changelog
When our view changed, and why
8 updates
Thesis changelog
When our view changed, and why
Change our mind
3 disconfirming conditions
You've read the verdict. The file is much deeper.
The full signal stack, technology-native KPIs tracked over time, the landscape of who depends on whom, the dated catalyst calendar, decision frameworks for every desk, live watchlists and a record of every time our view on Protein engineering has changed. All of it is in CanaryIQ.