add overview description and metric

README.md

@@ -1,5 +1,20 @@
+# Overview
+The AIDO.Tissue model is develpoed on spatial single-cell transcriptomic data. To incorporate spatial cell information, K nearest neighbor cells (K=8 in our case) are retrieved for each center cell. The center cell and neighbor cell expression vectors are concatenated as model input. Two-dimension positional rotary embedding are introduced to encode both the gene and cell information. The first dim is gene index and second dim is cell index. The overall training scheme is similar to scFoundation with an asymmetric encoder-decoder architecture. 
+
+# Results
+
+We evelauted the model on two spatial data task, including predicting niche label and cell density. The metrics are as below:
+
+| Task    | F1-score |
+| -------- | ------- |
+| niche label type prediction  | 0.67    |
+
+| Task    | Mean absolute error | R square |
+| -------- | ------- | ------- |
+| cell density prediction  | 4.44  | 0.55|
+
 # Finetuning AIDO.Tissue for spatial single cell downstream tasks
-In this file, we introduce how to finetune and evaluate our pre-trained AIDO.Tissue foundation models for downstream tasks. These tasks can be classified into the following categories:
+We introduce how to finetune and evaluate our pre-trained AIDO.Tissue foundation models for downstream tasks. These tasks can be classified into the following categories:
 
   * **Sequence-level classification tasks**: niche label type prediction
   * **Sequence-level regression tasks**: cell density prediction