Back to events
Models
Score 76.3Heat 14.3
Claude was trained on protein sequences at scale
ResearchTrainingMultimodalEvaluationReasoningClaudeAnthropicGoogleOpenAI
Summary
Recent evaluations show that the latest Claude models can accurately predict amino acid sequences for little-studied proteins, outperforming other frontier large language models. This capability indicates that protein sequences formed a sizeable component of their training data at scale.
Why it matters
Demonstrates that frontier general-purpose LLMs can spontaneously acquire specialized domain knowledge like protein structures from massive sequence training data at a level comparable to dedicated language models.
Editorial score
2 reviews8
Significance
8
Novelty
7.5
Credibility
7.5
Reach
6
Actionability