What is DLKcat?
DLKcat predicts enzyme turnover numbers (kcat values) from protein sequences and substrate structures. The turnover number represents how many substrate molecules an enzyme can convert to product per second under saturating conditions—a fundamental kinetic parameter for understanding enzyme efficiency.
Developed at Chalmers University of Technology and published in Nature Catalysis (2022), DLKcat combines a convolutional neural network (CNN) for processing protein sequences with a graph neural network (GNN) for analyzing substrate molecular structures. This dual-network architecture allows the model to learn patterns in enzyme-substrate interactions that correlate with catalytic rates.
The model was trained on over 16,000 experimentally measured kcat values from the BRENDA and SABIO-RK enzyme databases, covering both wild-type and engineered enzymes across diverse species.
How does DLKcat work?
DLKcat processes enzyme-substrate pairs through two parallel neural networks:
- Protein encoding: The enzyme sequence is split into overlapping 3-gram amino acid fragments. A CNN with three layers extracts features that capture sequence patterns associated with catalytic activity.
- Substrate encoding: The substrate's SMILES representation is converted to a molecular graph where atoms are nodes and bonds are edges. A GNN with three time steps propagates information through the graph, learning structural features relevant to enzymatic processing.
The outputs from both networks are concatenated and passed through fully connected layers to predict log10(kcat). Training used radius-2 substrate subgraphs and 20-dimensional vector embeddings.
How to use DLKcat online
ProteinIQ runs DLKcat on cloud GPUs, delivering turnover number predictions in seconds without local installation.
Inputs
| Input | Description |
|---|---|
Enzyme sequence(s) | FASTA format protein sequences. Multiple enzymes supported for batch analysis. |
Substrate(s) | SMILES strings or compound names (one per line). The tool will pair each enzyme with each substrate. |
Settings
| Setting | Description |
|---|---|
Temperature | Prediction temperature in °C (0–100, default 37). Note: The model was not trained with temperature dependence, so this is primarily for record-keeping. |
pH | Prediction pH (4.0–10.0, default 7.0). Like temperature, included for documentation rather than influencing predictions. |
Results
The output table contains predicted kcat values for each enzyme-substrate pair:
| Column | Description |
|---|---|
Enzyme Sequence | The input protein sequence |
Substrate | The input substrate (SMILES or name) |
Predicted kcat (1/s) | Turnover number in reactions per second |
Confidence | Model confidence score |
Temperature (°C) | The temperature setting used |
pH | The pH setting used |
Interpreting predictions
DLKcat predicts log10(kcat), then converts to linear scale. Predictions span a wide range:
| kcat (1/s) | Interpretation |
|---|---|
| > 1000 | Fast enzyme, typical of metabolic enzymes |
| 100–1000 | Moderate catalytic rate |
| 10–100 | Slow enzyme |
| < 10 | Very slow, may indicate poor substrate match |
The model achieves Pearson's r ≈ 0.71 and RMSE < 1 (log10 scale) on held-out test data. Performance is best for enzymes similar to the training set—predictions become less reliable as sequence similarity to training enzymes decreases.
Limitations
DLKcat has important constraints to consider:
Sequence similarity dependence: The model performs well when test enzymes share >70% sequence identity with training examples. For dissimilar enzymes, predictions may not outperform simple kcat averages.
No environmental factors: Despite the temperature and pH settings, the original model was not trained with environmental condition data. The tool includes these settings for record-keeping, but they do not affect predictions.
Mutant enzymes: While trained on some mutant data, predictions for novel mutations—especially those affecting catalytic residues—should be validated experimentally.
Substrate coverage: Predictions are most reliable for substrates similar to those in the BRENDA/SABIO-RK training data.
Applications
Enzyme turnover predictions support several research applications:
- Metabolic modeling: Parameterizing enzyme-constrained genome-scale models (ecGEMs) with predicted kcat values
- Enzyme engineering: Screening mutant libraries computationally before experimental characterization
- Pathway design: Identifying rate-limiting enzymes in synthetic biology pathways
- Comparative enzymology: Analyzing kcat distributions across species or enzyme families
Related tools
- ESM-2: Generate protein sequence embeddings for enzyme analysis
- Molecular Descriptors: Calculate substrate physicochemical properties
- NetSolP-1.0: Predict enzyme solubility for expression optimization