gbyuvd commited on
Commit
7aedee9
1 Parent(s): 227c1b1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -422,6 +422,14 @@ top 10 (returned in 3.9s with visualization):
422
 
423
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/667da868d653c0b02d6a2399/PcitabdJHrGrgucsoj13i.png)
424
 
 
 
 
 
 
 
 
 
425
  ## Testing Generated Embeddings' Clusters
426
  The plot below shows how the model's embeddings (at this stage) cluster different classes of compounds, compared to using MACCS fingerprints.
427
 
 
422
 
423
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/667da868d653c0b02d6a2399/PcitabdJHrGrgucsoj13i.png)
424
 
425
+ or you can take multiple inputs then average their embeddings to find those most similar. For example, using 5 samples of MRSA-antibiotics: Vancomycin, Linezolid, Tigecycline, and Ceftobiprole
426
+
427
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/667da868d653c0b02d6a2399/ignKU4vvwpkuG6lj6r9O4.png)
428
+
429
+ then query similars based on the average embeddings:
430
+
431
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/667da868d653c0b02d6a2399/cuGQ8EAfAn-28poChTg0Q.png)
432
+
433
  ## Testing Generated Embeddings' Clusters
434
  The plot below shows how the model's embeddings (at this stage) cluster different classes of compounds, compared to using MACCS fingerprints.
435