How danielgarzonotero/pepmnet works
PepMNet is a peptide-property prediction project with two user-facing tasks: antimicrobial-peptide classification (AMP) and chromatographic retention-time prediction (RT). Users supply sequence CSVs for independent prediction, or use the training entry points to retrain models; both workflows encode sequences as hierarchical graph data and run task-specific graph models. The README also documents pretrained weights, multiple RT models, and AMP/RT evaluation. Edges follow excerpted imports/calls or README statements; unsampled implementation details and result-writing links are omitted where not evidenced.
Main entry points: data.py Graph Dataset · amp_main.py AMP Training · amp_tester.py AMP Testing · rt_tester.py RT Testing
Components 16
User Workflows
- AMP Training
amp_main.py - AMP Testing
amp_tester.py - RT Training
rt_main.py - RT Testing
rt_tester.py
Graph Encoding
- Graph Dataset
src/data.py - Sequence Features
src/aminoacids_features.py - Graph Utilities
src/utils.py - Compute Device
src/device.py
Prediction Models
- AMP Graph Model
src/amp_model.py - RT Graph Model
src/rt_model.py - AMP Processing
src/amp_process.py - RT Processing
src/rt_process.py - Pretrained Weights
weights
Evaluation and Analysis
- AMP Metrics
src/amp_evaluation_metrics.py - AMP Feature Analysis
results/figures/distributions/distribution.py
Other components
- Researcher
Connections 26
- Researcher → AMP Training: trains AMP
README.md - Researcher → AMP Testing: tests sequences
README.md - Researcher → RT Training: trains RT
README.md - Researcher → RT Testing: tests sequences
README.md - AMP Training → Graph Dataset: loads graphs
amp_main.py - AMP Training → AMP Graph Model: trains model
amp_main.py - AMP Training → AMP Processing: calls processing
amp_main.py - AMP Training → AMP Metrics: evaluates predictions
amp_main.py - AMP Training → Compute Device: selects device
amp_main.py - AMP Testing → Graph Dataset: loads graphs
amp_tester.py - AMP Testing → AMP Graph Model: creates model
amp_tester.py - AMP Testing → AMP Processing: predicts with
amp_tester.py - AMP Testing → Compute Device: selects device
amp_tester.py - RT Training → Graph Dataset: loads graphs
rt_main.py - RT Training → RT Graph Model: trains model
rt_main.py - RT Training → RT Processing: trains and tests
rt_main.py - RT Training → Compute Device: selects device
rt_main.py - RT Testing → Graph Dataset: loads graphs
rt_tester.py - RT Testing → RT Graph Model: creates model
rt_tester.py - RT Testing → RT Processing: predicts with
rt_tester.py - RT Testing → Compute Device: selects device
rt_tester.py - Graph Dataset → Graph Utilities: gets graph features
src/data.py - Graph Dataset → Sequence Features: gets amino features
src/data.py - Graph Dataset → Compute Device: gets device
src/data.py - AMP Testing → Pretrained Weights: loads weights
README.md - RT Testing → Pretrained Weights: loads weights
README.md