feat: python client; resolves #44

[jdpearce4]

Summary

Introduce a first-class Python client (TranscriptFormerClient) for inference and artifact/data downloads. The client mirrors the CLI configuration behavior while providing a simple, programmatic API that returns an in-memory AnnData object.

Key Features

• In-memory inference: inference(...) returns an anndata.AnnData without writing to disk.
• Config parity with CLI: Builds a Hydra-compatible config by:
• Loading the same CLI YAML defaults.
• Applying dataclass overrides from kwargs (InferenceConfig, DataConfig).
• Merging with the checkpoint config.json via the same utility used by the CLI.

Convenience downloads:

• download_model(...) for checkpoints and embeddings.
• download_data(...) for CellxGene datasets by species.
• download_dataset(...) for curated sources (e.g., Tabula Sapiens, Bgee).
• Logging control: Optional log_level argument to run quietly or verbosely without affecting global logging.

API Surface

• TranscriptFormerClient.inference(data_file, checkpoint_path, **kwargs) -> anndata.AnnData
• Accepts most InferenceConfig and DataConfig fields as kwargs (e.g., batch_size, output_keys, gene_col_name, use_raw, use_oom_dataloader, n_data_workers, etc.).
• Returns a single AnnData with obsm/uns populated per output_keys.
• TranscriptFormerClient.download_model(model, checkpoint_dir=...) -> None
• TranscriptFormerClient.download_data(species=[...], output_dir=..., ...) -> int
• TranscriptFormerClient.download_dataset(dataset, ...) -> anndata.AnnData | None

[Copilot]

Pull Request Overview

This PR introduces a first-class Python client (TranscriptFormerClient) that enables programmatic inference and downloads for TranscriptFormer models. The client provides in-memory inference operations that return AnnData objects directly, mirroring CLI configuration behavior while offering a simplified API.

Key Changes

• Adds Python client with inference(), download_model(), download_data(), and download_dataset() methods
• Refactors config merging logic into reusable utility for consistency between CLI and client
• Enhances inference configuration with new checkpoint_path and model_type fields

Reviewed Changes

Copilot reviewed 10 out of 13 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
src/transcriptformer/client/client.py	Core client implementation with inference and download methods
src/transcriptformer/config/build_config.py	Shared config merging utility extracted from CLI
src/transcriptformer/data/dataclasses.py	Added checkpoint_path and model_type fields to InferenceConfig
src/transcriptformer/cli/inference.py	Refactored to use shared config merging utility
src/transcriptformer/cli/download_artifacts.py	Performance improvements to progress tracking
src/transcriptformer/init.py	Package-level client exports
README.md	Documentation for Python client usage

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}