Configure inputs to begin
Set options on the left, then click “Submit job”.

Identify toxic, reactive, and pharmacokinetically problematic molecular fragments using structural alert patterns

Screen for lead-like compounds using stricter molecular descriptor criteria than Lipinski or Veber rules for early-stage drug discovery

Screen compounds for Pan-Assay Interference patterns that cause false positives in biological assays

Veber's Rule predicts oral bioavailability by evaluating molecular weight, LogP, hydrogen bond donors/acceptors, and rotatable bonds

Predict ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties from SMILES strings using machine learning models trained on Therapeutics Data Commons datasets.

Predict 22 ADMET properties from SMILES strings with the native Admetica Chemprop models from Datagrok.

Predict toxicity and synthetic accessibility of small molecules using machine learning. eToxPred combines toxicity risk assessment with synthetic accessibility scoring to help prioritize drug candidates.

Quantitative estimate for protein-protein interaction inhibitor potential. Evaluates drug-likeness for compounds targeting PPIs.

Screen compounds for structural toxicity alerts using PAINS, Brenk, and NIH filters. For focused screening, see PAINS Filter, Brenk Filter, or Veber's Rule.

AF2BIND predicts ligand-binding residues from a protein structure using AlphaFold2 pair representations and a 20-residue bait sequence.
Lipinski's rule of five (Ro5), also known as Pfizer's rule of five, is a guideline for evaluating the druglikeness of chemical compounds. The rule estimates whether a compound with pharmacological or biological activity has physicochemical properties consistent with being an orally active drug in humans.
Christopher A. Lipinski formulated the rule in 1997 based on analysis of orally administered drugs, which tend to be relatively small and moderately lipophilic. The name derives from the cutoff values for four parameters, three of which are multiples of five.
Poor absorption or permeation is more likely when more than one criterion is violated:
| Property | Threshold | Rationale |
|---|---|---|
| Molecular weight | Da | Larger molecules diffuse more slowly across membranes |
| Partition coefficient (LogP) | High lipophilicity reduces aqueous solubility | |
| Hydrogen bond donors | Counted as N–H and O–H bonds | |
| Hydrogen bond acceptors | Counted as nitrogen and oxygen atoms |
A compound violating one criterion may still be orally active. Two or more violations indicate probable absorption problems via passive diffusion.
The easiest way to get Lipinski's values for any set of molecules is to use ProteinIQ's online Lipinski's rule of five calculator. You can input just smiles (up to tens of thousands of molecules) or tab-delimited list with names of molecules and smiles formula.
The calculator accepts SMILES notation in two formats:
Plain SMILES, one compound per line:
CCO
CC(=O)Oc1ccccc1C(=O)OTab-delimited, with a compound name followed by SMILES, separated by a \t):
ethanol CCO
aspirin CC(=O)Oc1ccccc1C(=O)OTab-delimited input preserves compound names in results. Plain SMILES input assigns generic identifiers (Compound_1, Compound_2, etc.).
You can also retrieve compound from PubChem by name or CID using the batch fetcher.
The following is a sample result from our Lipinski's rule calculator of 10 SMILES.
| Name | SMILES | Weight (Da) | LogP | HBD | HBA | Violations | Passes RO5 |
|---|---|---|---|---|---|---|---|
| 2-Hydroxy-3-oxobutyl phosphate | CC(=O)C(COP(=O)(O)O)O | 184.08 | -0.95 | 3 | 4 | 0 | true |
| Acetaminophen | CC(=O)NC1=CC=C(C=C1)O | 151.16 | 1.35 | 2 | 2 | 0 | true |
| Aspirin | CC(=O)OC1=CC=CC=C1C(=O)O | 180.16 | 1.31 | 1 | 3 | 0 | true |
| Atorvastatin | CC(C)C1=C(C(=C(N1CCC(CC(CC(=O)O)O)O)C2=CC=C(C=C2)F)C3=CC=CC=C3)C(=O)NC4=CC=CC=C4 | 558.65 | 6.31 | 4 | 5 | 2 | false |
| Caffeine | CN1C=NC2=C1C(=O)N(C(=O)N2C)C | 194.19 | -1.03 | 0 | 6 | 0 | true |
| Ciprofloxacin | C1CC1N2C=C(C(=O)C3=CC(=C(C=C32)N4CCNCC4)F)C(=O)O | 331.35 | 1.58 | 2 | 5 | 0 | true |
| Fluoxetine | CNCCC(C1=CC=CC=C1)OC2=CC=C(C=C2)C(F)(F)F | 309.33 | 4.44 | 1 | 2 | 0 | true |
| Metformin | CN(C)C(=N)N=C(N)N | 129.17 | -1.24 | 3 | 1 | 0 |
The outputs are relatively self-explanatory:
The rule serves as a preliminary filter rather than a definitive predictor. Compounds passing all criteria may fail in development for other reasons (toxicity, metabolic instability, lack of efficacy), while some rule-violating compounds achieve clinical success.
The rule applies specifically to oral drugs absorbed via passive transcellular diffusion. Several categories of clinically successful compounds violate Ro5:
The rule does not apply to non-oral routes (intravenous, subcutaneous, inhaled) where gastrointestinal absorption is not required.
| true |
| Sitagliptin | C1CN2C(=NN=C2C(F)(F)F)CN1C(=O)CC(CC3=CC(=C(C=C3F)F)F)N | 407.32 | 2.02 | 1 | 5 | 0 | true |
| Sunitinib | CCN(CC)CCNC(=O)C1=C(NC(=C1C)C=C2C3=C(C=CC(=C3)F)NC2=O)C | 398.48 | 3.33 | 3 | 3 | 0 | true |