Screen compounds for structural toxicity alerts using PAINS filters, BRENK filters, and NIH filters for safer drug discovery. Learn more
Input
What is structural alert screening?
Structural alert screening checks compounds for problematic molecular fragments before expensive biological testing. Rather than predicting specific toxicity endpoints, structural alert filters match known toxic, reactive, or interference-prone substructures curated from decades of medicinal chemistry. This makes them useful throughout drug discovery, from filtering compound libraries and triaging virtual screening hits to tracking safety profiles during lead optimization.
Keep in mind that structural alerts are context-independent: a flagged substructure may be benign in certain scaffolds, and many approved drugs trigger alerts (aspirin flags Brenk patterns for its acetyl group). They also cannot cover every toxic structure or explain the specific toxicity mechanism. Alerts work best as one layer in a broader safety assessment alongside druglikeness filters like Lipinski's Rule of Five, Veber's Rule, and the Lead-Likeness Filter, not as a standalone pass/fail gate.
How structural alert screening works
ProteinIQ runs three RDKit structural alert catalogs independently:
- PAINS filters flag assay interference compounds
- Brenk filters flag toxic, reactive, and pharmacokinetically problematic fragments
- NIH filters flag problematic functional groups from NIH/MLPCN screening campaigns
Each enabled catalog runs its native SMARTS patterns against the input molecule. The summary reports matched catalog-entry names and counts without converting them into a toxicity score or safety classification. These counts represent distinct matching catalog entries, not the number of times a substructure occurs within the molecule. A match is an alert for review, not evidence that a compound is toxic.
For every alert, ProteinIQ preserves RDKit's native matched filter name and query-to-molecule atom mapping in the Alert matches table. The Catalog references table records each matched catalog entry's filter-set name, reference, and scope once, avoiding repeated metadata across compounds.
How to screen structural alerts online
ProteinIQ screens compounds for structural alerts using PAINS, Brenk, and NIH filters online with no local installation required.
Enter SMILES strings in the text area, one per line. Each SMILES string may contain up to 10,000 characters. Compound names can be included using tab-separated format (aspirin\tCC(=O)Oc1ccccc1C(=O)O). File upload is supported for .txt, .smi, .smiles, .csv, and .tsv formats, and compounds can also be fetched from PubChem by name or CID.
Settings
All three filter sets run by default. To focus on a specific category, toggle off the ones not needed.
| Setting | Description |
|---|---|
PAINS filter | Screen for pan-assay interference compounds (PAINS A, B, C). Default: on. |
Brenk filter | Screen for toxic, reactive, and pharmacokinetically problematic fragments. Default: on. |
NIH filter | Screen for compounds with problematic functional groups (NIH/MLPCN). Default: on. |
If all three are toggled off, no catalogs are run and every alert count is zero.
Results
The Results table contains one summary row per compound:
| Column | Description |
|---|---|
Name | Compound name (if provided) or SMILES |
SMILES | Input SMILES string |
Total alerts | Sum of alerts across all enabled filters |
PAINS alerts | Number of matching PAINS catalog entries |
Brenk alerts | Number of matching Brenk catalog entries |
NIH alerts | Number of matching NIH catalog entries |
PAINS patterns | Names of matched PAINS patterns |
Brenk patterns | Names of matched Brenk patterns |
NIH patterns | Names of matched NIH patterns |
The Alert matches table contains one row per native RDKit filter match:
| Column | Description |
|---|---|
Catalog | ProteinIQ catalog grouping: PAINS, Brenk, or NIH |
Catalog entry | RDKit catalog-entry description |
Matched filter | Native RDKit filter name |
Atom mapping | [zero-based query atom index, zero-based molecule atom index] pairs returned by RDKit |
The Catalog references table contains one row per matched catalog entry and reports its catalog grouping, entry description, native filter-set metadata, source reference, and scope.
Related tools
ADMET-AI
Predict ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties from SMILES strings using machine learning models trained on Therapeutics Data Commons datasets.
Admetica
Predict 22 ADMET properties from SMILES strings with the native Admetica Chemprop models from Datagrok.
Brenk filter
Identify toxic, reactive, and pharmacokinetically problematic molecular fragments using structural alert patterns
eToxPred
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.
Lead-likeness filter
Screen for lead-like compounds using stricter molecular descriptor criteria than Lipinski or Veber rules for early-stage drug discovery
PAINS filter
Screen compounds for Pan-Assay Interference patterns that cause false positives in biological assays
QEPPI
Quantitative estimate for protein-protein interaction inhibitor potential. Evaluates drug-likeness for compounds targeting PPIs.
Veber's rule
Screen molecular flexibility and polarity using Veber's rotatable-bond and topological polar surface area criteria.
Lipinski's rule of 5
Lipinski's Rule of Five predicts whether compounds will be orally bioavailable by evaluating molecular weight, LogP, hydrogen bond donors, and acceptors.
AF2BIND
AF2BIND predicts ligand-binding residues from a protein structure using AlphaFold2 pair representations and a 20-residue bait sequence.