3,855
AI-driven protein research publications in 2025 across four areas, up 71% from 2,259 in 2024

What the chart shows

PubMed publications on AI-driven protein research across four areas rose from 2,259 in 2024 to 3,855 in 2025, up 71%. Protein–drug interactions were the largest area, with 2,097 papers (54.4%), up from 1,127 (49.9%) the year before.

Protein structure prediction came second with 922 papers, but its share fell from 28.7% to 23.9%. Synthetic protein design (434) and function prediction (402) each grew by more than 60%, and every area grew in number.

Key numbers

MeasureValue
All four areas, 20253,855
All four areas, 20242,259
Protein–drug interactions, 20252,097
Protein–drug interactions, 20241,127
Protein structure prediction, 2025922
Synthetic protein design, 2025434

How to read it

  • Publications counted by RAISE Health in PubMed for four research areas. The chart shows 2025; the CSV also holds 2024 (the first four rows).
  • The data file labels function prediction ‘Future prediction’; the AI Index text and chart call it function prediction.
  • Counts measure research activity, not quality or clinical use.
Source: RAISE Health, 2026, via the AI Index Report 2026 (Stanford HAI), figure 6.1.1: Number of AI-driven protein research publications, 2024 vs. 2025. Chart and text by AI Adoption.
Numbers checked against the published data on 20 October 2026.
Download the data (CSV) · Cite this chart