/
© 2026 RiffOn. All rights reserved.

Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

  1. Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders
  2. 297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1
297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders · Oct 20, 2026

AI protein design needs far more high-quality interaction data; AlphaSeq measures millions of protein affinities in batch to close the gap.

AI protein design needs far more data than expected

David Younger says his company's model training showed that solving truly hard protein design problems will require much more data than the field expects. He also warns public binding and affinity data are often not interoperable, lack proper controls, and lack annotations, making them hard to reuse.

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1 thumbnail

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders·a month ago

PDB's 10,000 antibody structures cannot train generalizable design

Younger says the Protein Data Bank today holds about 10,000 antibody-antigen structures and adds roughly 1,000 yearly. Their internal scaling work suggests good generalizable de novo design models may need hundreds of thousands to millions of structures, so waiting on PDB growth is far too slow.

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1 thumbnail

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders·a month ago

PDB structures lack affinity and local mutation data

Younger notes the PDB shows how proteins physically interact but not how strongly, and it has almost no examples of antibodies one or two mutations apart with measured affinities. Zero-shot optimization instead needs local affinity landscapes built from many single-point mutation variants across many targets.

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1 thumbnail

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders·a month ago

Engineered yeast measure a million protein affinities per flask

AlphaSeq re-engineers yeast mating so surface-displayed protein interactions drive cell fusion. Younger says bulk selection and next-generation sequencing read out pairwise affinities, letting one flask measure a million interactions instead of one well measuring a single interaction, avoiding traditional one-at-a-time protein purification and characterization.

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1 thumbnail

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders·a month ago

De novo design hits single-digit success on easy targets

Younger says de novo designs currently achieve reasonable single-digit percent success rates only against the easiest targets and epitopes. The field's ambition is to engineer challenging epitopes and additional properties, where success rates remain very low; he argues more and better data are still needed.

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1 thumbnail

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders·a month ago

Protein model makers need shared benchmarks to compare designs

Younger says model makers evaluate on unique bespoke targets, so pharma buyers cannot tell which model is best. He is working with companies on a benchmark that standardizes target difficulty and characterizes tens of thousands of designs, hoping to get true apples-to-apples comparisons with tighter error bars.

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1 thumbnail

297: 10,000 Structures Are Not Enough: The Data Gap Limiting De Novo Antibody Design with David Younger - Part 1

Smart Biotech Scientist | The CMC and Bioprocessing Podcast for Process Development and Manufacturing Leaders·a month ago