Academic Research
Comparative deep learning study classifying proteins into 18 functional categories.
Applied ML Research · Bioinformatics EPFL / Academic
Multi-architecture comparison using amino acid sequences and 3D structural data.
Stack
PyTorchGNNCNNLSTMscikit-learn
Context
Bioinformatics challenge classifying proteins into 18 functional categories using both amino acid sequences and 3D structural graph data.
Highlights
- ●Graph Neural Networks (HGP-SL) for 3D protein structure
- ●Fusion models combining GNN + MLP approaches
- ●Benchmark across GNN, CNN, LSTM, and logistic regression
How Frema Labs applies this for you
Have sequence and structured data to classify? We benchmark graph, sequence, and fusion models to find what genuinely fits your data.
More case studies
Other engagements across luxury manufacturing, life sciences, finance, and applied research.
- RichemontAesthetical Quality Control for Luxury ManufacturingComputer Vision · Luxury ManufacturingIndustrial-grade computer vision system for aesthetical defect detection in luxury watchmaking and jewelry.Read case study
- KeringSupply Chain Replenishment OptimizationSupply-Chain ML · Luxury RetailDynamic warehouse replenishment using statistical modeling and reinforcement learning for a major luxury retailer.Read case study
- Bracco Suisse SALiver Lesion Classification from Contrast-Enhanced UltrasoundMedical Imaging AI · HealthcareDeep learning classification of liver lesions from contrast-enhanced ultrasound images (CEUS) to improve diagnostic confidence.Read case study
- Academic ResearchEmbryo Survival Prediction from Time-Lapse VideoComputer Vision Research · Life SciencesDeep learning pipeline predicting developmental viability from time-lapse video analysis.Read case study
- Academic ResearchReal-Time Stock Market PredictionStreaming Data & ML · FintechDistributed ML pipeline for real-time stock prediction using big data infrastructure.Read case study
- Academic ResearchParkinson's Detection via Gait AnalysisExplainable ML · Digital HealthExplainable AI for early-stage Parkinson's disease detection through gait sensor data.Read case study
Working on a similar problem?
Let's talk about how production-grade ML can move your roadmap forward.