monsoon-nlp commited on
Commit
415907d
1 Parent(s): 0376554

link to examples

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -71,6 +71,18 @@ Results on 1,000 protein pairs from the validation dataset, during training:
71
 
72
  Scatter plots comparing the full and 128-dim embeddings to the original embeddings, using pairs from the test set: https://colab.research.google.com/drive/1hm4IIMXaLt_7QYRNvkiXl5BqmsHdC1Ue?usp=sharing
73
 
 
 
 
 
 
 
 
 
 
 
 
 
74
  ## Future
75
 
76
  This page will be updated when I have examples using it on protein classification tasks.
 
71
 
72
  Scatter plots comparing the full and 128-dim embeddings to the original embeddings, using pairs from the test set: https://colab.research.google.com/drive/1hm4IIMXaLt_7QYRNvkiXl5BqmsHdC1Ue?usp=sharing
73
 
74
+ ## Finetuning / Tasks
75
+
76
+ One of the more popular evaluations is [Tasks Assessing Protein Embeddings (TAPE)](https://github.com/songlab-cal/tape)
77
+
78
+ Example using SciKit-Learn to train on Fluorescene, a regression task: https://colab.research.google.com/drive/1cH9jOBSC56mqJHU_6ztQPp6qWJguNjAn?usp=sharing
79
+
80
+ TBD: example using SciKit-Learn on a classification task
81
+
82
+ TBD: example using Sentence-Transformers to [finetune embeddings](https://huggingface.co/blog/train-sentence-transformers) for a TAPE regression or classification task
83
+
84
+ TBD: examples using plant proteins from [greenbeing-binary](https://huggingface.co/datasets/monsoon-nlp/greenbeing-binary) to train a binary classifier
85
+
86
  ## Future
87
 
88
  This page will be updated when I have examples using it on protein classification tasks.