Intestinal absorption from structure
Draw a molecule and get the fraction of an oral dose a human is predicted to absorb. The answer arrives as a band, because a band is what the data supports. Separate models report Caco-2 permeability for small molecules, and cyclic peptide permeability on two assays that are never pooled.
The four models
Each answers its own question, on its own compounds. Absorption error is in percentage points and the three permeability errors are in log10 Papp units, which are different measurements and do not compare between them.
| Model | Compounds | Descriptors | rms | R |
|---|---|---|---|---|
| Absorption, % absorbed | 780 | 25 | 20.47 | 0.76 |
| Caco-2 small molecules, log10 Papp | 3,771 | 55 | 0.35 | 0.84 |
| Caco-2 peptides, log10 Papp | 1,281 | 50 | 0.49 | 0.84 |
| Artificial-membrane peptides, log10 Papp | 7,298 | 25 | 0.82 | 0.67 |
Every figure is measured over 250 extractions of that model's fixed consensus set. Absorption error is in percentage points. The three permeability errors are in log10 Papp units. The two units are different measurements and the numbers do not compare between them.
Twenty absorption units is a wide band, and the page says so
A prediction of 70 means the compound is probably somewhere between 50 and 90. This site is useful for separating well absorbed compounds from poorly absorbed ones and for ranking a series against itself. It is not useful for telling 85 apart from 90, and any reading that suggests otherwise is wrong. Every prediction is drawn as a bar with a shaded interval for that reason, and no prediction is ever shown without it.
The ceiling is in the data, not in the model
Published absorption values for the same drug disagree with each other. Of the 780 compounds modeled, 262 carry more than one published value. Sixty one of those disagree by more than 20 points and 31 by more than 40. Methotrexate appears in the literature at 20, 59, 65, 70 and 100. A model cannot be more precise than the measurements it is fitted to, so a 20 unit error is close to the resolution the field currently has rather than a shortfall against it.
What the algorithm chose, twenty eight years apart
A genetic algorithm searched a pool of 1,301 modern descriptors over 780 compounds, 250 times, each time on a different stratified extraction. Mean partial charge was chosen in every one of them, a carboxylic acid fragment and hydrogen bond donor count in more than half, and donor surface fraction in 34.40 percent. The 1998 model, searching a pool that no longer exists with software that no longer runs, chose hydrogen bonding and geometric descriptors. Two unrelated descriptor pools, twenty eight years apart, landed on the same physics: how much charge a molecule carries and how much polar surface it presents.
Applicability is a feature, not a disclaimer
The model fails on molecules unlike its training set, and it fails quietly. A compound can break no descriptor range and still sit in a thin region these descriptors do not resolve. Every prediction therefore carries its distance to the five nearest training compounds, and one drawn from outside the covered region is marked as an extrapolation in the interface rather than buried in a footnote. The mark is an answer. It is never hidden and never filled in.
Two peptide assays, never pooled
Two assays, two models, never pooled. Both are served here and each answers for itself. The membrane model is passive diffusion through lipid, with no cells present. The Caco-2 model is transport across a living monolayer of a human intestinal cell line, where transporters and efflux are active. On the 229 peptides a single study measured in both, the assays correlate 0.62, with the membrane value about half a log unit below the Caco-2 value. A relationship that loose between two assays on the same peptides is the reason this site keeps two models rather than one.
The two released files share 588 peptides, and comparing those two files row by row is the wrong comparison: most of those pairs come from different studies, and across studies the two assays carry no usable relationship. The figures above come from the single-study records instead.
A value of exactly -10.00 is a below-detection placeholder, not a measurement. It stands for a peptide whose permeability was under the limit of the assay, and it appears for 21 peptides in the Caco-2 file and 269 in the membrane file. Treat it as a floor, and censor or filter it before fitting anything to these files.
No combined number is offered, no conversion between them is valid, and a query is never answered by whichever model happens to be available. Falling back would return a confident number measuring something you did not ask about.
A structure is scored by both models in one request, and each result is labeled with the assay it belongs to. Two answers that differ are two measurements that differ, not a disagreement to resolve.
What it is for
Triaging a series before any of it is made, and knowing when the model has nothing useful to say. The full method covers the 1998 model, what reproduced, what did not, and what the larger data changed.