Update README.md

README.md

@@ -20,27 +20,3 @@ Welcome to the official dataset repository for **Deepcell** on Hugging Face Spac
 We are committed to creating a repository of datasets that will not only support our internal AI development but also contribute to the broader scientific community. The datasets hosted here will be used in **NeurIPS 2025** submissions and beyond, helping to benchmark our models and facilitate reproducibility in scientific research.
 
 ---
-
-### Datasets Available
-
-Here, you will find datasets collected and processed using Deepcell's imaging systems. These datasets cover a range of experimental conditions and cell types, and are suitable for training and evaluating models in the field of single-cell analysis.
-
-1. **Single-Cell Embeddings for Benchmarking**  
-   This dataset includes single-cell embeddings of various cell types, generated from images using Deepcell's advanced algorithms. It will be used to benchmark model performance on common tasks such as classification, clustering, and morphotype identification.
-
-2. **Synthetic Cell Imaging Dataset**  
-   Generated using Generative Adversarial Networks (GANs), this dataset simulates cell morphology under different conditions. It will be used for evaluating the robustness and generalizability of our models across synthetic environments.
-
-3. **Immunology Cell Dataset**  
-   This dataset focuses on immune cell populations, including T-cells and B-cells, and their responses to various stimuli. It is useful for studying immune cell behavior, detecting rare cell populations, and understanding immune responses.
-
----
-
-### NeurIPS 2025 Dataset Submission
-
-Deepcell is actively contributing to **NeurIPS 2025** (Conference on Neural Information Processing Systems) with datasets designed to benchmark our AI models for biological data analysis. These datasets will be part of our submission to demonstrate the performance and scalability of our models, including single-cell classification and clustering.
-
-We aim to provide researchers with high-quality, pre-processed data to facilitate reproducibility and foster collaboration across research communities. By hosting these datasets, we hope to advance the understanding of deep learning methods in the context of cellular analysis.
-
----
-