A graded, cited target assessment dossier for any target and indication, built by agents and signed by your therapeutic-area lead
A graded, cited assessment of any target in about five days, with weak evidence challenged before anyone signs.
See one case, screen by screen ↓A target and an indication sound like one question. They are six: does human genetics link the target to the disease and in which direction, is it in the cells that drive the disease, is there functional proof, can the planned modality reach it, what happens when it is taken away, and who else is on it. Each answer lives somewhere different — genome-wide studies and target–disease portals, single-cell atlases and internal omics, screening and chemistry reports, variant databases, competitor pipelines, patent families.
So the work is mostly gathering and writing. A computational biologist, a chemist, a safety scientist and competitive intelligence each assemble their part, in their own format, with their own idea of what “strong” means. The dossier that reaches the portfolio committee is weeks old, graded unevenly, and hard to check: an RNA-only expression signal reads the same as confirmed protein, and a single-laboratory finding reads the same as a replicated one.
Estimated split for one target and indication, in working days, by hand and with the solution.
Nine agents plan, research six questions in parallel, challenge the evidence and assemble the dossier; the therapeutic-area lead signs.
The discovery portfolio committee meets on Oct 22. Dr. Maya Chen, head of Immunology target discovery, has a new request to start and the RKN2 dossier in ulcerative colitis to sign. Here is her morning, screen by screen, in the working solution.
Twelve targets across Immunology, Oncology and Neuroscience on one evidence matrix, graded A to D on genetics, expression, biology, tractability, safety and competition. Four items wait for her: RKN2 in ulcerative colitis ready for sign-off, a challenge to decide on IL1RL4, a new request from Sam Patel, and a change the weekly refresh found on GPR214.
“GPR214 — the weekly refresh found a change. A third competitor entered Phase 1 on Oct 3 — Competition may change.”
Sam Patel’s request names the target, the indication and the modality: small molecule or degrader. Maya types it into the bar and presses Build dossier. The dossier planner splits the template into 6 sections and 38 research questions, and six specialist agents start in parallel, one on each section.
Each lane shows what its agent is working on as it runs — “Off-tissue expression…”, “Modality fit…”, “Congress abstracts…”.
Grades land as each agent finishes: genetics B, expression A, biology B, tractability C, safety B, competition A. The critic raised 6 challenges; the agents resolved 5 and left 1 for the owner. The assembler wrote 128 claims from 54 sources into the dossier — overall B+ — and routed it to Dr. Maya Chen.
The one challenge left: “Tractability rests on a predicted pocket with no ligand.” Proposed: keep C and add a fragment screen as an open question.
The RKN2 dossier came in at overall B+ with the recommendation “Advance to validation with conditions”: 61 sources, 142 claims, built in 4.6 days. Genetics is A — a protective missense variant, p.Arg412Gln, lowers ulcerative colitis risk with an odds ratio of 0.71 (p = 3.1 × 10⁻¹⁹, 59,957 cases), and fine-mapping gives it a posterior of 0.86. Loss of function protects, so inhibition is the right direction.
“Built by 9 agents in 38 minutes of agent time. Every claim links to its source passage.”
Safety is graded C, at 81 % agent confidence. 212 heterozygous loss-of-function carriers show no immune deficiency or serious infection across 1,400 phenotypes. But two siblings with homozygous partial loss of function had chronic mucocutaneous candidiasis from early childhood, and knock-in mice clear oral Candida more slowly. Infection risk needs a monitoring plan.
The critic, on safety: “Candidiasis is a known, monitorable effect of IL-17 pathway medicines … the risk looks dose-dependent.” Proposed: consider raising Safety from C to B, with a fungal-infection monitoring condition.
Maya clicks the citation on the case report. The passage opens with the sentence the claim rests on highlighted — Clinical Immunogenetics Reports, 2023. Every claim in the dossier opens the same way, at the passage it came from.
“Two siblings homozygous for a partial loss-of-function RKN2 variant presented with chronic mucocutaneous candidiasis from early childhood; no other infections were reported.”
On expression, RNA places RKN2 in Th17 cells, ILC3 and γδ T cells and 2.4-fold higher in inflamed mucosa — but there is no protein data yet. The critic will not let that pass as an A. Maya can accept, keep as is, or ask the agent to look again.
“Expression rests on RNA only. A grade of A needs protein in the diseased tissue.” Proposed: keep B and add an open question — confirm RKN2 protein in UC biopsies by immunostaining.
She accepts. Expression stays B, and the open question goes to Sam Patel, due Nov 14. It joins the others, each with an owner and a date: cellular selectivity against RKN1 in human cardiomyocytes for Priya Raman, a freedom-to-operate opinion on the allosteric pocket for Omar Haddad, serum IL-22 as a pharmacodynamic biomarker for Sam Patel.
“Accepted · open question added for Sam Patel.”
Four choices: advance to validation, advance with conditions, hold for more evidence, or stop. The conditions are filled from the open questions. The safety challenge is still open, so it is recorded with her signature, and because safety is graded C, Lena Ortiz co-signs after her. Maya signs with her password; the meaning is recorded with it.
“Signing as Dr. Maya Chen · Meaning: scientific approval of this dossier · Oct 7, 2026.”
Lena Ortiz co-signs the safety grade C, and RKN2 goes into the Oct 22 committee pack. The review record shows every step since Sam Patel’s request on Sep 30 — the planner’s 41 questions, each agent’s grade, the critic’s 7 challenges, the refreshed competitor extract — people and agents, newest first.
The same dossier, seen by the five people who build, check and decide on it — what their week looked like, and what it looks like now.
Nine agents plan, research six questions in parallel, challenge the evidence and assemble the dossier; the therapeutic-area lead signs.
Splits a target request into the template sections and 35–45 research questions, assigns each to a specialist agent and sets the evidence bar for every grade.
Finds genome-wide and rare-variant evidence, fine-mapping and colocalisation, with effect size, p-value and cohort size, and states the direction of effect for every claim.
Places the target in tissues and cell types — disease against healthy, RNA against protein — from internal single-cell and bulk omics and the public tissue atlas, and lists where it must not be hit.
Gathers mechanism, knockdown and knockout screens and animal-model evidence, places the target in its pathway, and says whether a medicine on the same pathway has worked in the clinic.
Judges whether the planned modality can work — pockets, structures, ligands and hit series for small molecules; surface location and internalisation for antibodies and conjugates; knockdown and delivery for oligonucleotides.
Asks what happens when the target is taken away — in loss-of-function carriers, knockout animals, essential tissues and medicines on the same pathway — and reports any human phenotype first.
Maps competitor programmes by target and modality with phase and last update, checks trial registries and congress abstracts, and summarises the patent landscape with chemical similarity to your series.
Challenges every section like a sceptical committee member — single-source claims, animal-only evidence, RNA without protein, stale data, wrong direction of effect — and proposes grade changes and open questions.
Writes the templated dossier, the scorecard, the open-question list and the references, and routes the dossier to the right reviewer.
Accepts challenges and signs. The agents propose; a named person decides.
Anyone on the team can ask in plain words — or tell it what to change. Answers come from the dossiers, their cited sources and the critic’s challenges.
Why is RKN2 graded C on safety?
Because of infection risk. Two siblings with a partial loss-of-function variant had chronic mucocutaneous candidiasis from early childhood, and knock-in mice clear oral Candida more slowly. Against that, 212 heterozygous carriers show no immune deficiency across 1,400 phenotypes. The critic suggests B with a monitoring condition. That call is yours, and Lena Ortiz co-signs any C.
Which targets have a safety red flag?
Three targets have safety graded C or D: RKN2, KCNT4 and TMEM421. TMEM421 was stopped for normal-lung expression. RKN2 needs your decision: the fungal-infection signal. I have filtered the target list to these.
Compare RKN2, CDH31 and KCNT4 for the Oct 22 committee
RKN2 (B+) is strongest on genetics and biology — a protective variant with odds ratio 0.71; watch safety (C). CDH31 (B) is strongest on expression and tractability for an ADC — 74% of tumours stain; two competitors are ahead. KCNT4 (B) has genetics A from four families; safety C for cardiac conduction. I have opened them side by side.
Add a biomarkers section to the dossier template
Done. The dossier template now has a seventh section, Biomarkers & translation — patient selection, pharmacodynamic markers and translational models. The Pathway biology agent writes it and the critic checks it like any other section. New dossiers get it from today; signed dossiers are unchanged.
13 screens from the working solution, on its sample data. Pick one to see it large.
How a grade is earned, how hard the critic pushes and who signs are settings, not a project.
| Setting | Default | Choose from |
|---|---|---|
| Grade A needs | Two independent human sources | Two independent human sources · One human source and one functional study · Any three sources |
| Critic strictness | Standard | Standard · Strict (also challenges every single-source claim) |
| Resolve every critic challenge before sign-off | Off — open challenges are recorded as conditions | On · Off |
| Safety C or D needs a co-signature | Lena Ortiz, safety scientist | Any named person on the team |
| Dossier template | Six required sections | Add Biomarkers & translation · Clinical precedent |
| Who signs, per therapeutic area | Immunology: Dr. Maya Chen | Any named person, per area |
| Re-check signed dossiers for new evidence | Weekly | Weekly · Every two weeks · Monthly |
| Tell the owner when a grade may change | On | A notification and a Needs-you item |
Every figure is labelled: a target the solution is built to, an estimate, a typical published result, or a proven one.
“demo” = seen in the working solution, on its sample portfolio · “target” = the design goal, measured in the live solution · “estimated” = our estimate · “typical” = published figures (vendor case study on target prioritisation — about 4 weeks by hand). Background: GOT-IT target-assessment recommendations. Targets, companies and people named on this page are characters in the working solution, which is for research use and is not a GxP record.
A structured case for or against pursuing a drug target in an indication. Target Dossier Builder answers six questions — genetics, expression, pathway biology, tractability, safety and competition & IP — grades each from A (strong) to D (gap or red flag), and ends with a recommendation and the open questions for the portfolio committee.
Against your rubric. The dossier planner sets the evidence bar for every grade before the research starts, and the default bar for an A is two independent human sources. The critic then checks that each claim’s source supports it and that the evidence type matches the grade — RNA without protein, animal-only or single-laboratory findings are challenged.
Yes. Every claim carries a citation, and one click opens the source passage with the sentence highlighted — the paper, table or figure, internal report or database extract. Uncited claims never reach the dossier.
No. The agents research, grade and propose; the critic only proposes changes. The therapeutic-area lead decides each challenge and signs the dossier, and a safety grade of C or D needs the safety scientist’s co-signature. A grade changed by a person needs a written reason.
Yes. Tractability is graded against the planned modality only: pockets, ligands and hit series for small molecules; surface location and internalisation for antibodies and conjugates; knockdown and delivery for oligonucleotides. The working solution carries examples of each.
A scheduled refresh re-checks signed dossiers for new genetics, competitor and safety evidence — weekly by default. When a grade may change, the owner gets a notification and decides whether to re-grade or keep it.
The ones you switch on: a licensed literature index, public genetics and target–disease portals, your internal omics, screening and chemistry reports, a competitor pipeline database and a patent landscape service. Preprints are off by default and labelled “not peer reviewed” when on. Licensed content stays inside the dossier.
The Agentic Solution Engine builds and deploys it from your requirements — your dossier template, grading rubric, source list and signatories — and it goes live once every quality gate has passed. We will walk you through it on targets from your own portfolio first.
Ask the literature in plain words and get a sourced answer in seconds.
1-min filmPipeline WatchEvery rival trial, readout and approval lands in a sourced brief for each programme, every Monday.
1-min filmPreclinical ReportsRaw study data becomes a draft report in hours, with every number traced to its source.
1-min filmWe’ll run Target Dossier Builder on targets from your own portfolio.