Services

Free where a machine can answer. Quoted where a person is needed.

The platform and the first look cost nothing. Analysis that requires a trained human reading — interpretation, design, a written argument you can act on — is scoped and quoted for the question you actually have.

No cost

Free, and not a trial.

No account, no card, no expiry. These are free because a machine does them end to end, and because the fastest way to show the method is worth paying for is to let you use it.

The platform

Open to everyone

academics · scientists · industry · investors

  • About 17,721 molecules, searchable
  • Indications, safety signals and analogues
  • Six ways to search, no sign-up
  • Same data the paid work is built on
What it does

Technical snapshot

One page, no charge

one compound, or one trial

  • Structure resolved and profiled
  • CYP and pharmacogenomic signal read against your protocol
  • Physician-reviewed before it reaches you
  • No obligation to continue
Request one

Technical sanity-check

20 minutes, no charge

for investors, on one pipeline asset

  • Is the mechanism plausible as described
  • What would have to be true for it to work
  • Which questions are worth paying to answer
  • No deck, no follow-up sequence
Book a slot

Where human work starts

Analysis that needs a person.

Each of these has been run in anger on real programmes, not assembled from a brochure. Scope is agreed in writing before anything begins, and every deliverable is read end to end by a physician before it is sent.

Pharmacogenomic panel evaluation

Which genotypes actually move exposure for your compound, and what that means for a protocol or a label.

  • Metabolic pathway and transporter assignment
  • Allele-frequency modelling across the populations you recruit from
  • Pharmacokinetic liability mapping
  • Biomarker-guided inclusion and stratification recommendations

Technical due diligence

A written technical read on an asset, for an investment committee that needs more than the founder's deck.

  • Molecular pathway and target review
  • Safety signal mining against reported adverse events
  • Mechanism feasibility, stated as what would have to be true
  • Delivered as a referenced memo, typically 15 to 20 pages

Target engagement and structure

Structure-based work on a named target, with the parameters stated so the run can be checked or repeated.

  • Receptor preparation from a named PDB structure
  • AutoDock Vina docking with justified box placement
  • GNINA convolutional rescoring and decoy controls
  • Molecular dynamics and MM/GBSA for relative ranking

Safety liability modelling

Purpose-built models for the off-target risk that would stop a programme, with the uncertainty reported rather than hidden.

  • Regression models trained on curated ChEMBL bioactivity
  • Cross-validated, with error bars and an applicability-domain check
  • ADMET panels: cardiac, blood–brain barrier, efflux, mutagenicity, hepatotoxicity
  • A clear statement when the model is extrapolating

Analogue and bioisostere design

Enumerate the chemically sensible neighbourhood of a lead, then narrow it to a list a chemist can actually make.

  • Combinatorial enumeration around a retained pharmacophore
  • Property filters: basicity, molecular weight, edit distance from parent
  • Multi-objective selection across predicted liability, CNS exposure and similarity
  • Synthetic accessibility and structural-alert screening

Pharmacovigilance signal analysis

What has actually been reported for a compound or its class, read against the labelled indication.

  • Literature-led safety review: PubMed and label evidence first, spontaneous reports as a signal
  • Class-effect comparison against analogues
  • Withdrawn-drug precedent analysis
  • Reporting bias stated; counts are never presented as incidence

Pricing is per engagement. Scope, depth and turnaround differ too much between a single-target docking question and a full due diligence memo for a list price to mean anything. Describe the compound and the decision it has to inform, and you will get a personalised offer — write to sales@pharmacoscribe.com.

What is actually in a report

A report is a written argument, not a data dump. Every section states what was found, how it was found, and what it does not establish.

SectionContains
Question and scopeThe decision the report is meant to inform, restated in our words so you can correct us before we start.
Compound identityCanonical SMILES, ChEMBL identifier, modality, highest clinical phase reached, development status.
Analysis sectionsPathway and target review, pharmacogenomic liability, pharmacovigilance signal mining, and structural or machine-learning work where it is warranted.
InterpretationWhat the combined evidence implies for your protocol, label or investment decision, and where the signals disagree with each other.
LimitationsExplicit statement of what the method cannot show. This section is never omitted.
ReferencesPubMed identifiers, PDB accession codes and database versions, all resolvable.

How an engagement runs

  1. You send the compound, or the trial. A structure, a name, a ChEMBL identifier or a ClinicalTrials.gov NCT number. Most engagements start with the free snapshot.
  2. We reply with scope, a personalised offer and turnaround within two working days — or tell you the question is outside what the method can honestly address.
  3. You confirm in writing. Scope is fixed at this point, and so is the quote.
  4. Analysis and review. Every report is read end to end by a physician before delivery. This is not a pipeline that ships unread.
  5. Delivery, then one revision round on paid work.

Confidential compounds. Work on unpublished structures runs under NDA on request at any level, including the free snapshot. Structures supplied under NDA are never added to the public platform database.

What we do not do

Being clear about this saves both sides time.

  • No wet-lab work. Everything here is computational and literature-based. Where a measurement is the honest next step, the report says so and says which one.
  • No regulatory submissions. A report can inform a submission; it is not one, and it is not a substitute for regulatory affairs review.
  • No clinical advice. Nothing produced here is medical advice or a basis for treating a patient.
  • No guaranteed conclusions. If the evidence does not support the result you were hoping for, the report will say so. A negative result delivered early is the cheapest thing we sell.

Tell us the compound and the question.

Scope and turnaround come back within two working days, with a personalised offer where the work needs a person. If the question is outside what the method can honestly answer, we will say so rather than sell you a report.