Distill

The chemistry is in the paper.
Getting it out is the work.

Distill does that work.

Reactions, chemicals and procedures — with their conditions, quantities and outcomes — read from the text, the schemes and the tables, then resolved, reconciled and balance-checked. Structured chemical data you can check.

A product of CDI Pte Ltd · Singapore

Distill's procedure view: two manufacturing routes drawn as ordered step graphs — Manufacture of Diaminopyrimidine and Manufacture of CME — each node carrying its operation and real quantity, such as Charge KOt-Bu 277 kg, Cool minus 12 to minus 8 degrees C and Age 3 h, with stoichiometry badges beneath the charge steps and a line carrying NMP from one route into the other.

The problem

The data is in the document. Getting it out takes a chemist’s time.

The reactions, the chemicals and the procedure are all there — with the quantities, conditions, equipment, yields and purities — spread across the text, the schemes and the tables of a paper, a patent or a report. Getting all of it into one structured form means going through every document, in full, every time.

That is time spent away from the chemistry. And what comes out varies with who did it, the numbers are seldom checked against each other, and once a value is in a spreadsheet nobody can say which sentence it came from.

in a paragraph

… The cold mixture was aged for 3 h when solid guanidine·HCl (834.1 kg, 8731.2 mol, 8.0 equiv) was charged to the reactor 1 followed by a NMP-flush (123 kg). The reactor was heated to 115 °C and aged for 6 h. …

chemicalactionconditionequipment

in a scheme

Scheme 13 of the paper, 'Optimized Process for Converting CME 2 to Product 1', drawing the route from CME 2 and ethyl formate with potassium tert-butoxide to the potassium enolate 7, then with 8 equivalents of guanidine hydrochloride at 115 °C for 6 h to the diaminopyrimidine product.

in a table

Table 6 of the paper, 'Tabulated Scale-Up Data for the Synthesis of Diaminopyrimidine 1': six batches listing the amount of CME 2 used in kilograms, the amount of product 1 made with its percentage yield, and the purity of 1 by LCAP.

Distill reads all three automatically. Upload the document; the data comes back in minutes, in the same format every time, with the quantities cross-checked and every value linked to its sentence. The time goes back to the chemistry.

The deliverable

What you get back

Four things, from every paper, in the same format.

01

One entry per compound

The paper calls the same compound 2, CME 2, and the free base. Distill gives it one entry with structure, formula, CAS and InChIKey, so it is counted once and found once.

Where no structure could be confirmed, the row is marked.

Distill's chemical registry: a table of species, each row showing the drawn structure, the compound name and id, role badges, how many reactions use it, its SMILES, formula, molecular weight, CAS number, InChIKey and a resolution status. Most rows read RESOLVED; enolate 7 reads MODEL with its CAS marked not found.
Enolate 7 has no CAS number. The row says not found.

02

Balanced, including the by-products

Each reaction with its reactants, reagents, solvent and products, balanced atom by atom. The by-products the paper leaves out are included, which is what you need for a mass balance and a waste estimate.

Inferred species are marked inferred.

A reaction card in Distill, tagged Balanced: potassium enolate 7 plus guanidine hydrochloride in NMP, giving diaminopyrimidine 1 at 89% isolated and over 97% pure, with water and potassium chloride as by-products. Every species is drawn and labelled with its role, chemical id and SMILES, and the balanced reaction SMILES is printed underneath.
This cyclisation also produces a mole of water and a mole of KCl. Neither appears in the paper.

03

The procedure, step by step

Each step classified — charge, heat, age, filter — with its charges and conditions in order. Click a step to see the sentence it was read from, then open that sentence in the paper. Where the paper gives no source for a value, none is claimed.

Distill's procedure view: two manufacturing routes drawn as ordered step graphs, each node carrying its operation and quantity. One step, Charge G-HCl, is selected, and a panel beside it shows that step's record — the verbatim sentence it came from with an 'open in document' link, two review notes, and its inputs: guanidine hydrochloride as reagent at 834.1 kg, 8731.2 mol, 8.0 equivalents, and NMP as solvent at 123 kg.
The step — its source sentence, its inputs with roles and equivalents.
The same procedure regrouped by equipment: a 'reactor' row carrying 21 steps from Charge KOt-Bu (277 kg) through the washes, an 'agitated filter dryer' row carrying the single Filter step, and a 'No equipment stated' row carrying the 13 steps of the second procedure for which the paper names no vessel.
The same steps, by vessel — 21 in the reactor, 1 in the agitated filter dryer. Where the paper names no vessel, the step is not assigned one.

04

What it isn’t sure about, it shows you

A consistency check runs on every extraction at no cost, with no model involved. The audit is a separate, costed step: one click, and a model reads the finished extraction and lists what looks wrong. Nothing is changed unless you accept it.

In this paper it found a published mass that does not match the moles beside it. The row is marked below.

Distill's review panel: issues grouped by cause into seven kinds. The group 'Value disagrees with the paper' is open, showing eleven issues. Three rows are marked Fixed in green; the row reading 'Cited mass and moles are physically inconsistent: needs 170.0kg have 110.0kg' is marked Open.
Findings are grouped by cause. This one is the paper’s own error, so it is left open rather than corrected. Click the row ↗

05

Export

Everything above downloads as one JSON file: every reaction, chemical, step and condition, with each value’s source sentence. Load it into a route planner, a process model or an LCA tool.

Distill's Export button, with its panel open: 'Export extraction as JSON — includes Reactions 5, Steps 35, Chemicals 16, plus conditions and equipment', above a Download JSON button.
Distill's split view: the procedure spine on the left; on the right the same run as a JSON tree — Chemicals 16, Reactions 5, Procedures 2, Actions 35, Materials 30 — every entry expandable, with the Export button in the toolbar above.
The same run, as your systems will read it. Every step on the left is a record on the right.

Every paper comes back in the same format. Run fifty and you can query them together.

If you’re interested in booking a demo or would like to learn more about pricing, please contact us at info@cdi-sg.com