How mbkemec/signal_peptide_prediction_model works
This repository is a research pipeline for predicting protein signal peptides, with two prediction approaches: a feature-based SVM and a von Heijne-style PSWM. The documented workflow collects and curates protein sequences, analyzes the resulting datasets, trains and evaluates predictors, and interprets benchmark errors. The graph preserves those stages and the major visualization and optimization branches. Some subsystems are represented from README descriptions because their implementation was not sampled; those relationships cite the README rather than implying source inspection.
Main entry points: merge_data.py Combined dataset · filter_reps.py Representative filtering · final_model_test_benchmark.py Benchmark evaluation · model_creation.py PSWM training and CV
Components 20
Data curation
- Positive retrieval
data_collection/data_collection_positive.py - Negative retrieval
data_collection/data_collection_negative.py - Representative filtering
data_collection/filter_reps.py - Sequence FASTA files
data_collection/fasta_sep.py - Shuffle and split
data_collection/shuffle_NR.py - Fold datasets
data_collection/split_cross_validation.py - Dataset assembly
data_collection/merge_data.py - Combined dataset
data_collection/merge_data.py
Dataset analysis
- Analysis dataset shuffle
data_visualization/file_shuffle.py - Biological visualizations
data_visualization
SVM prediction
- Sequence features
SVM_optimization/feature_extraction.py - Feature matrices
SVM_optimization/feature_extraction.py - SVM selection
SVM_optimization/svm_and_feature_selection.py - Final SVM model
SVM_optimization/final_model_creation.py
PSWM prediction
- PSWM training and CV
von_heine_method/model_creation.py
Evaluation and interpretation
- Benchmark evaluation
SVM_optimization/final_model_test_benchmark.py - Benchmark error motifs
von_heine_method/false_negative_motifs.py - Motif logos
data_visualization/motif_logo.py
Other components
- Researcher
- UniProt
Connections 28
- Researcher → Positive retrieval: initiates collection
README.md - Researcher → Negative retrieval: initiates collection
README.md - Positive retrieval → UniProt: queries
data_collection/data_collection_positive.py - Negative retrieval → UniProt: queries
data_collection/data_collection_negative.py - Positive retrieval → Representative filtering: curated by
README.md - Negative retrieval → Representative filtering: curated by
README.md - Representative filtering → Sequence FASTA files: separates sequences
README.md - Representative filtering → Shuffle and split: feeds
README.md - Shuffle and split → Fold datasets: splits training data
README.md - Fold datasets → Dataset assembly: assembled by
README.md - Dataset assembly → Combined dataset: writes
data_collection/merge_data.py - Researcher → Analysis dataset shuffle: starts analysis
README.md - Analysis dataset shuffle → Combined dataset: shuffles dataset
README.md - Combined dataset → Biological visualizations: analyzed for
README.md - Combined dataset → Sequence features: provides labels
SVM_optimization/feature_extraction.py - Sequence FASTA files → Sequence features: provides sequences
SVM_optimization/feature_extraction.py - Sequence features → Feature matrices: writes features
SVM_optimization/feature_extraction.py - Feature matrices → SVM selection: loads matrices
SVM_optimization/svm_and_feature_selection.py - SVM selection → Final SVM model: guides optimization
- Combined dataset → PSWM training and CV: provides folds and labels
von_heine_method/model_creation.py - Sequence FASTA files → PSWM training and CV: provides sequences
von_heine_method/model_creation.py - Researcher → Final SVM model: trains predictor
README.md - Researcher → PSWM training and CV: trains and evaluates
README.md - Final SVM model → Benchmark evaluation: evaluated on benchmark
README.md - PSWM training and CV → Benchmark evaluation: scores benchmark
von_heine_method/model_creation.py - Benchmark evaluation → Benchmark error motifs: provides false negatives
von_heine_method/false_negative_motifs.py - Benchmark evaluation → Motif logos: supports motif analysis
README.md - Biological visualizations → Motif logos: extracts cleavage motifs
README.md