graph LR
Data_Management_Preparation["Data Management & Preparation"]
Model_Core_Architectures["Model Core & Architectures"]
Training_Evaluation_Pipeline["Training & Evaluation Pipeline"]
Utilities["Utilities"]
Data_Management_Preparation -- "provides prepared data batches to" --> Training_Evaluation_Pipeline
Training_Evaluation_Pipeline -- "interacts with" --> Model_Core_Architectures
Training_Evaluation_Pipeline -- "leverages functions from" --> Utilities
click Data_Management_Preparation href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/chemicalx/Data_Management_Preparation.md" "Details"
click Model_Core_Architectures href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/chemicalx/Model_Core_Architectures.md" "Details"
click Training_Evaluation_Pipeline href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/chemicalx/Training_Evaluation_Pipeline.md" "Details"
Abstract Components Overview and Relationships for ChemicalX library.
Data Management & Preparation [Expand]
This component is responsible for the entire lifecycle of data, from loading raw chemical and biological datasets (drug features, context features, interaction triples) from various sources (remote/local) to structuring and transforming them into optimized batches (DrugPairBatch) suitable for efficient model consumption during training and inference. It manages feature sets and ensures data integrity and flow, including utility functions for data handling.
Related Classes/Methods:
chemicalx.data.datasetloader(1:1)chemicalx.data.contextfeatureset(1:1)chemicalx.data.drugfeatureset(1:1)chemicalx.data.labeledtriples(1:1)chemicalx.data.batchgenerator(1:1)chemicalx.data.drugpairbatch(1:1)chemicalx.data.utils(1:1)
Model Core & Architectures [Expand]
This component defines the foundational abstract interface (chemicalx.models.base.Model) for all deep learning models within the library. It also includes the concrete implementations of various high-level model architectures (e.g., CASTER, DeepDDI, MHCADDI, GCNBMP, SSIDDI) tailored for specific tasks like drug-drug interaction or synergy prediction, encapsulating their overall neural network designs.
Related Classes/Methods:
chemicalx.models.base(1:1)chemicalx.models.caster(1:1)chemicalx.models.deepddi(1:1)chemicalx.models.deepdds(1:1)chemicalx.models.deepdrug(1:1)chemicalx.models.deepsynergy(1:1)chemicalx.models.epgcnds(1:1)chemicalx.models.gcnbmp(1:1)chemicalx.models.matchmaker(1:1)chemicalx.models.mhcaddi(1:1)chemicalx.models.mrgnn(1:1)chemicalx.models.ssiddi(1:1)
Training & Evaluation Pipeline [Expand]
This component orchestrates the end-to-end workflow for training, validating, and evaluating deep learning models. It manages the training loop, handles device placement (CPU/GPU), and processes the results generated by the models, providing a structured and reproducible way to run experiments.
Related Classes/Methods:
This component offers a collection of general-purpose helper functions and mathematical operations that support various parts of the library. This includes tensor manipulation functions (e.g., segment operations for sparse tensors) and system-level utilities like device resolution.
Related Classes/Methods: