Research library
Drug discovery
View the four-date completion graphs and reconstruction notes.
Promise and evidence
AI could identify useful targets and molecules, improve candidate selection, and reduce the cost of developing effective medicines. The published rentosertib phase 2a trial is a concrete example of an AI-associated drug program reaching randomized human testing. One program cannot establish that AI improves development success across the industry.
Apply the shared measurement protocol. Targets are proposed research measures, not treatment recommendations.
Dated baseline coverage
All linked measurable-outcome files below contain an evidence baseline reviewed November 7, 2026, with source dates, findings, limitations and follow-up measurements. These distinguish measured results from proxies and unknown values; they do not assert that proposed milestones are achieved. See the baseline coverage notes.
Progress estimates
Judgment-based estimates as of November 7, 2026, using the same 0–100% scale and five-part rubric as mathematics. 0% anchors the period before ChatGPT's public release in 2022; 100% requires AI to manage this field's continuing advancement without human participation. Confidence is low. These are evidence-based judgments, not empirical completion measurements, forecasts or percentages of jobs replaced.
| Measurable outcome | Estimated progress | Execution / breadth / agenda / validation / improvement (each out of 20) |
|---|---|---|
| Candidate quality | 25% | 10 / 5 / 5 / 5 / 0 |
| Clinical benefit | 15% | 5 / 5 / 0 / 5 / 0 |
| Development efficiency | 25% | 10 / 5 / 5 / 5 / 0 |
| Portfolio productivity | 10% | 5 / 5 / 0 / 0 / 0 |
| Target validation | 25% | 10 / 5 / 5 / 5 / 0 |
| Translation | 20% | 10 / 5 / 0 / 5 / 0 |
Each linked outcome explains its score, cites its dated evidence baseline and identifies the next measurement. Zero indicates no qualifying post-anchor progress established by the reviewed evidence for that outcome, not proof of no relevant capability. Do not average these overlapping indicators into a field-wide percentage or interpret their differences as a precise ranking of fields. All outcomes reaching 100% would still require a separate field-wide demonstration of sustained autonomous advancement.
Measurable features
| Feature | Measurement and acceptance rule |
|---|---|
| Target validation | Proposed targets with independently reproduced disease-relevant experimental support / all targets selected for validation. |
| Candidate quality | Fraction of candidates meeting prespecified potency, selectivity, exposure, and toxicity requirements in relevant assays. |
| Development efficiency | Elapsed months, total dollars, and human effort from fixed program start to candidate nomination and each trial phase; include failed programs. |
| Translation | Phase-transition success by indication and modality, using complete cohorts, explicit follow-up, and time-to-event methods for ongoing programs. |
| Clinical benefit | Prespecified patient-relevant primary outcomes, effect sizes, uncertainty, adverse events, and withdrawals in controlled trials. |
| Portfolio productivity | Independently demonstrated beneficial treatments per total portfolio dollar and year, accounting for attrition and delayed outcomes. |
Evidence requirements
Document exactly where AI contributed: target choice, molecular design, experiments, or trial operations. Compare matched programs and control for indication, modality, starting maturity, and selection bias. Use registered trial protocols, full outcome reporting, and independent analysis. Docking scores, animal responses, and biomarker changes must not be presented as established patient benefit.
Proposed milestones
Reproduce one AI-originated candidate's prespecified biological activity and selectivity in an independent laboratory, with a complete candidate-selection record.
Across at least ten comparable development programs, estimate time and cost differences against matched controls, report every failure, and treat the result as a pilot rather than proof of industry-wide superiority.
Demonstrate a clinically meaningful benefit in a prospectively powered controlled trial with acceptable adverse outcomes; replicate or confirm in an appropriate additional study.
Establish better portfolio-level productivity over multiple completed cohorts. Count approvals separately from demonstrated comparative benefit. Medical progress is consequential impact; it is not by itself evidence of recursive AI improvement.