Design-partner evaluations open for chemistry-heavy patent review teamsApply

Chemistry-heavy patent PDFs, turned into reviewable scientific evidence.

Jubust extracts exemplified compounds, assay results, and example-level disclosures from patent filings — each finding anchored to its exact source page. Every answer is inspectable.

From hard patent artifacts to clean high quality machine-readable data

The bottleneck is not finding patent documents. It is reconstructing compounds, assay results, formulation details, and cross-page context quickly enough for real scientific decisions.

WO2021041671 · Ex 1Trace verified

KRas G12D KD

97.7nM
Compound structure

PDF p.2

Structure proof

PDF p.13

Table 1 · Row 1

Compound and assay records

Extract exemplified compounds, reported assay values, and example-level details into structured records tied to the original filing.

p.2

Structure diagram

p.13

Table 1 · KD

p.47

Assay conditions

Example 1 · 97.7 nM · KRas G12D

3 sources linked

Page-level provenance

Preserve provenance across structures, tables, footnotes, and formulation details instead of splitting the evidence into isolated extraction fragments.

Quality signals

1 flagged field

Compound

Target

Value

Signal

Ex 1KRas G12D97.7 nMVerified
Ex 2KRas G12D142 nMVerified
Ex 7KRas G12C—Check
Ex 12KRas G12D58 nMStable

High-quality scientific output

Improve result quality through active learning on the fields scientists challenge, correct, and rely on most.

Current scientific review

Questions that shape real patent review.

Across competitor sets, patent families, and compound series, scientific teams need clear answers on what was made, tested, and shown. Jubust returns source-linked records they can inspect directly.
Today

What did they actually make and test — not just claim?

Which compounds were actually exemplified, which assays were run, what results were reported, and where is that shown in the source? Jubust returns source-linked compound, assay, and example records as structured, machine-readable data with provenance that a scientist can review directly.

Current scope: extracting reviewable evidence from the patent text itself.

Source passage · p.13

Example 1. To a 50 mL flask was added intermediate 3 (2.3 g, 8.5 mmol) in anhydrous DMF (20 mL) under N₂. The mixture was stirred at 60 °C for 18 h. After workup and silica gel purification, KD = 97.7 nM as determined by TR-FRET binding assay for KRas G12D. Fractions were pooled and concentrated under reduced pressure to afford the title compound as a white solid (1.1 g, 47% yield).

Extracted record

Verified

KRas G12D · KD

97.7nM
PDF p.2 · StructurePDF p.13 · Table 1 · KD
Today

What evidence across relevant patents should change our decision on this target?

Across the patents relevant to this target, mechanism, or lead series, which findings should affect a competitive or experimental decision? Jubust assembles a review pack with cited records across the selected filings, not just a summary paragraph.

Supported by cross-patent evidence linking.

KRas G12DAll assignees2021–2024Binding affinity
WO2021041671Ex 1KD 97.7 nMp.13
WO2022051443Ex 7KD 142 nMp.19
WO2023189012Ex 4IC₅₀ 68 nMp.8

3 compounds shown · 12 total for this target

Soon

Who is patenting compounds close to our lead series?

Which patents disclose chemistry structurally close to the series your team is working on — and what exactly did they show? This becomes available once extracted structures and scaffold linking are consistently good at scale.

Query series

Query compound scaffold

KRas G12D scaffold

Close disclosures

WO2023041892

p.5

High

WO2022098763

p.12

Medium

Requires structural extraction at scale — available as evidence coverage grows.

Source-linked workspace

Detailed provenance. Fast validation.

The workspace links compound structures, binding values, and assay context directly to the patent pages they came from. Open any citation badge to inspect the source.
app.jubust.com/workspace/WO2021041671
WO2021041671·12 compoundsTrace verified
+7 more

Binding affinity · KRas G12D KD

97.7nM

IC₅₀ 114 nM · selectivity confirmed

Structure

Compound structure Example 1

Record fields

Compound

Example 1

Target

KRas G12D

Assay type

TR-FRET

Patent

WO2021041671

Filing date

Feb 2021

Source pages

p.2 + p.13

PDF p.2

Structure · anchor region

PDF p.13

Table 1 · Row 1 · KD

Design-partner evaluation

Evaluate Jubust on a patent set your team already reviews.

Each evaluation is scoped around a target, competitor set, patent family, or lead series your team already reviews. The goal: see whether the output holds up in real scientific review.

Evaluation flow

01

Define the scope

Choose the target, competitor set, patent family, or lead series to review.
02

We process the filings

Jubust extracts source-linked compound, assay, and example records from the filings in scope.
03

Your team reviews the output

Scientists inspect the records, open the cited pages, and note what is usable, missing, or incorrect.
04

Decide whether to expand

If the output improves review speed and supports decisions on the set in scope, we expand. If not, we stop.

Best fit

Teams with a defined patent-review workflow

  • Medicinal chemistry teams reviewing target-specific or competitor patent sets
  • Translational research teams comparing evidence across related patent families
  • Oncology and adjacent programs where assay details and example context drive decisions

Not included

Work outside the evaluation

  • Broad document discovery or generic patent search
  • Claim interpretation, legal opinion, or freedom-to-operate analysis
  • Promises of exhaustive coverage or automated legal conclusions

Next evidence layer

More evidence unlocks harder questions.

These use cases become credible once evidence is structured and linked at scale. They sit directly above reviewed evidence packs.
Soon

What compound families are heating up around this target?

Which scaffold or compound families are seeing rising patent activity around this target or modality? Each trend row backed by the source patents underneath — not naked counts.

Scaffold familyRecent filings
KRas G12C covalent
8
SOS1 interface
6
KRas G12D non-covalent
5
KRAS-PPI disruptors
3

3 new filings in the past 90 days · Each row links to source patents

Soon

Which programs are starting to show cell, in vivo, or translational evidence — not just potency tables?

Which patent programs are moving beyond binding or potency claims into stronger biological or translational evidence? Evidence-type tracking, not quality assessment.

ProgramBindingCellularPK / in vivo
WO2021041671
WO2023189012
WO2022051443

Evidence type tracking only — does not imply scientific quality or program success.

Longer-term direction

A patent-native chemistry intelligence layer.

These questions become worth asking once enough reviewable evidence is structured and linked. We are not there yet, but this is the direction that justifies the current work.
Later

Where are the underexplored regions worth reviewing next?

Which parts of this chemical neighborhood appear thinly covered by current patent literature — and which nearby patents are worth deeper investigation? Framed as exploration and hypothesis generation, not definitive white-space discovery.

Chemical space · KRas G12D

Covalent warhead variants7 patents · Low coverage
Non-covalent groove binders18 patents · Medium coverage
Switch II pocket29 patents · Well covered

Coverage reflects structured evidence only. Not a definitive prior-art landscape.

Later

What evidence links this scaffold, target, assay, and assignee across the field?

Navigate connected scientific evidence — how is this chemistry connected across patents, targets, assays, and companies? Every edge resolves back to source evidence. Not abstract network art.

SOS1/KRas G12D interface · non-covalent

Assays

  • TR-FRET
  • Biochemical displacement
  • Cellular viability

Assignees

  • Amgen
  • Mirati
  • Rev. Medicines

Patent families

  • WO2021041671
  • WO2023189012
  • WO2022051443
  • WO2020186101
  • WO2021252339
  • WO2022147188
  • WO2023034499

Each entity resolves to patent source evidence — not inferred relationships.

Common questions

What we do, how design-partner evaluations work, and where we stop.
Jubust extracts compounds and their measured assay results directly from patents, and links every datapoint to its exact source in the document so it can be verified instantly.
Search and summarisation tools stop at finding or condensing documents. Jubust is built to produce reviewable evidence packs: structured compound records, assay data, and provenance citations that a scientist can inspect and use in real decision-making — not trust blindly.
No. Jubust does not replace claim interpretation, legal status analysis, or legal opinion. The evidence packs we produce support downstream IP and FTO workflows — but the legal analysis stays with counsel.
Medicinal chemists, translational researchers, and scientific CI teams reviewing chemistry-heavy patent literature — primarily in oncology and related programs. IP and patent-intelligence teams can work from the same evidence packs, but the workflow is optimised for scientific review first.
We scope design-partner engagements around a specific patent slice your team cares about — a target, competitor, or program area. The goal is to measure whether the evidence quality and review speed hold up for real scientific decisions, not to run a generic demo.

Design partner program

Evaluate Jubust on the patents your team actually reviews.

Bring the compounds, assay evidence, and competitive questions that matter to your team. We scope design-partner engagements around reviewable output, not generic demos.