Building dataset · No result yet · Biology · Medicine · Chemistry

Did the public availability of useful AlphaFold structures increase the rate at which previously structureless protein targets received experimentally measured potent ligands?

Compare protein targets that gained AlphaFold models with targets that already had experimental structures.

No result yet

5 / 8 checks passed
Targets
849
More exposed
218
Comparison
609
Post-launch events
2

What is compared

More AI exposure

Eligible protein targets with no qualifying experimental structure before 22 July 2021 and a usable AlphaFold prediction after launch.

Comparison group

Eligible protein targets that already had a qualifying experimental structure before 22 July 2021 and had not yet crossed the relevant ligand-potency threshold.

Primary outcome

First ligand below 100 nM

The first dated experimental BindingDB measurement for the target with an accepted affinity value below 100 nanomolar, among targets still at risk on the treatment date.

Strict cohort snapshot

BindingDB rows
93,712
Exact Ki/Kd
23,778
At-risk exposed
110
At-risk comparison
232

3 checks remain

Full study design
Treatment date
22 July 2021
Exposure
A target is treated when it lacked an experimental structure before the AlphaFold Database launch but received a mappable predicted structure that passes the study's predeclared usability rule.
Unit
protein target-month
Estimand
The change after 22 July 2021 in the target-month hazard of first crossing an experimental binding-affinity threshold below 100 nanomolar for targets that lacked an experimental structure before AlphaFold, relative to comparable targets that already had structural information.
Adjustment
Match or weight targets using pre-2021 target class, organism, sequence and family features, prior publications, prior BindingDB activity, disease relevance, experimental-structure history, and pre-treatment affinity-frontier movement.
Assumption
Conditional on observed pre-treatment characteristics and trends, targets without prior structures would have followed the same post-2021 potent-ligand trajectory as structurally characterized targets in the absence of AlphaFold.
Outcomes
OutcomeDefinition
First ligand below 100 nMPrimary The first dated experimental BindingDB measurement for the target with an accepted affinity value below 100 nanomolar, among targets still at risk on the treatment date.
First ligand below 1 µM The first dated accepted experimental affinity measurement below 1 micromolar for a target that had not crossed that threshold before treatment.
First ligand below 10 nM The first dated accepted experimental affinity measurement below 10 nanomolar for a target that had not crossed that threshold before treatment.
Affinity-frontier improvement The frequency and log magnitude of new best experimental affinity measurements for each target after treatment.
All data checks
CheckStatusEvidence
Target-Identity-Map Passed 98.6% unique row mapping; 849 core targets.
Publication-Date-Coverage Passed 100.0% of exact Ki/Kd rows have a parsable publication date.
Assay-Comparability Passed 23778 dated exact Ki/Kd rows across 849 targets.
Pre-Treatment-Structure-Map Passed 100.0% of 32252 mapped PDB IDs have release dates.
Alphafold-Usability-Rule Pending A predeclared rule distinguishes merely available AlphaFold predictions from predictions usable for the intended structural analysis.
Cohort-Size-And-Overlap Pending Treated and comparison groups have adequate sample size, covariate overlap, and threshold-specific risk sets.
Pre-Trend-Credibility Pending Event-study leads and pre-period outcome trends do not show a large treatment-group divergence before AlphaFold.
Public-Rebuild-Path Passed Release 202609, SHA-256 1203194f366623ae9b4caee34f2477d412ebddbda267593df9d1d92d0c66fb74; no AlphaFold API errors.
Analysis plan

Analysis

  1. Build a target-month panel with threshold-specific risk sets and explicit treatment exposure.
  2. Plot event-study coefficients before and after July 2021 so pre-treatment differences are visible.
  3. Estimate a survival or discrete-time hazard model with target covariates, calendar-time effects, and treatment-by-post interactions.
  4. Report absolute cumulative-incidence differences as well as relative hazard estimates.
  5. Use the 100 nM outcome as primary and treat 1 µM, 10 nM, and frontier magnitude as predefined secondary analyses.
  6. Run alternative treatment dates, matching rules, target definitions, and structure-usability thresholds.
  7. Publish the cohort, mapping decisions, exclusions, code, and analysis specification before presenting an effect estimate.

Falsification

  • Use pre-2021 placebo intervention dates and test whether an apparent effect appears before AlphaFold was available.
  • Test for differential pre-treatment trends in threshold crossings and affinity-frontier improvements.
  • Repeat the analysis on target groups for which the predicted structure fails the predeclared usability rule.
  • Check whether results disappear when targets are matched more tightly on pre-treatment publications and medicinal-chemistry activity.
  • Test outcomes less directly connected to structural information as negative-control outcomes where the data permit it.
Sources and limits
Feasibility report Target cohort Documentation
  • The strict audit cohort is article-curated and does not represent all BindingDB records, patents, or medicinal-chemistry activity.
  • The design remains biased if treated and comparison targets have different unobserved post-2021 opportunities after matching.
  • Binding affinity is a research milestone, not a clinical outcome, and threshold crossing does not imply a safe or effective drug.
  • The current strict cohort contains 2 post-treatment 100 nM first-crossing events; outcome power must be evaluated before estimation.
  • Pre-treatment event counts and calendar coverage need explicit modelling rather than a simple before-and-after comparison.
  • The study should not be described as causal until the remaining gates pass and the identifying assumptions survive the stated falsification tests.