AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

PoET: A generative model of protein families as sequences-of-sequences

Timothy Fei Truong Jr, Tristan Bepler

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Biological sequence transformers · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use PoET for conditional variant scoring instead of TranceptEVE LProtein variant fitness prediction · ProteinGym substitutionsAverage Spearman correlation: Δρ̄=0.013Improved
Ensemble PoET with TranceptEVE LProtein variant fitness prediction · ProteinGym substitutionsAverage Spearman correlation: Δρ̄=0.021Improved
Use PoET or PoET plus TranceptEVE L instead of TranceptEVE LProtein variant fitness prediction · ProteinGym indelsAverage Spearman correlation: Δρ̄∈[0.044,0.055]Improved
Replace TranceptEVE M with PoET or PoET plus TranceptEVE LProtein variant fitness prediction · ProteinGym indelsAverage Spearman correlation: Δρ̄∈[-0.006,0.005]No clear effect
Increase training context length from 4K to 8K (ablation)PoET variant fitness prediction · ProteinGym validationVariant effect prediction performanceImproved
Increase training context length from 8K to 16K (ablation)PoET variant fitness prediction · ProteinGym validationVariant effect prediction performanceMixed
Use inverse-count sequence-set sampling instead of uniform sampling (ablation)PoET · ProteinGym validationVariant fitness prediction performanceImproved
Increase model size from 57M to 201M parameters (ablation)PoET · ProteinGym validationVariant fitness prediction performanceImproved
Increase model size from 201M to 604M parameters (ablation)PoET · ProteinGym validationVariant fitness prediction performanceNo clear effect
Use tiered Transformer decoder layers instead of regular RoPE Transformer layers (ablation)PoET · Protein sequence generation at long context lengthsPerplexityImproved
Use shortest-to-longest rather than random sequence ordering (ablation)PoET · Heldout UniRef50 next-sequence predictionPerplexity: 7.44075 -> 7.44828No clear effect
Use longest-to-shortest rather than random sequence ordering (ablation)PoET · Heldout UniRef50 joint likelihoodMean joint log likelihood: -8099.74973 -> -8091.89462No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy