Commit
•
d15f1ce
1
Parent(s):
a7bd966
Update README.md
Browse files
README.md
CHANGED
@@ -21,6 +21,7 @@ for multi-label classification. In particular, the model is fine-tuned on the CA
|
|
21 |
[here](). More precisely, the `train_sequences.fasta` file is the list of protein sequences that were trained on, and the
|
22 |
`train_terms.tsv` file contains the gene ontology protein function labels for each protein sequence. For more details on using
|
23 |
ESM-2 models for multi-label sequence classification, [see here](https://huggingface.co/docs/transformers/model_doc/esm).
|
|
|
24 |
|
25 |
## Fine-Tuning
|
26 |
|
|
|
21 |
[here](). More precisely, the `train_sequences.fasta` file is the list of protein sequences that were trained on, and the
|
22 |
`train_terms.tsv` file contains the gene ontology protein function labels for each protein sequence. For more details on using
|
23 |
ESM-2 models for multi-label sequence classification, [see here](https://huggingface.co/docs/transformers/model_doc/esm).
|
24 |
+
Due to the potentially complicated class weighting necessary for the hierarchical ontology, further fine-tuning will be necessary.
|
25 |
|
26 |
## Fine-Tuning
|
27 |
|