Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
---
|
|
|
1 |
+
# Model Card for [HIV_BERT]
|
2 |
+
|
3 |
+
## Table of Contents
|
4 |
+
- [Table of Contents](#table-of-contents)
|
5 |
+
- [Summary](#model-summary)
|
6 |
+
- [Model Description](#model-description)
|
7 |
+
- [Intended Uses & Limitations](#intended-uses-&-limitations)
|
8 |
+
- [How to Use](#how-to-use)
|
9 |
+
- [Training Data](#training-data)
|
10 |
+
- [Training Procedure](#training-procedure)
|
11 |
+
- [Preprocessing](#preprocessing)
|
12 |
+
- [Training](#training)
|
13 |
+
- [Evaluation Results](#evaluation-results)
|
14 |
+
- [BibTeX Entry and Citation Info](#bibtex-entry-and-citation-info)
|
15 |
+
|
16 |
+
## Summary
|
17 |
+
|
18 |
+
[The HIV-BERT model was trained as a refinement of the ProtBert-BFD model (https://huggingface.co/Rostlab/prot_bert_bfd) for HIV centric tasks. It was refined with whole viral genomes from the Los Alamos HIV Sequence Database (https://www.hiv.lanl.gov/content/sequence/HIV/mainpage.html). This pretraining is important for HIV related tasks as the original BFD database contains few viral proteins making it sub-optimal when used as the basis for transfer learning tasks. This model and other related HIV prediction tasks have been published (link).]
|
19 |
+
|
20 |
+
## Model Description
|
21 |
+
|
22 |
+
[Like the original ProtBert-BFD model, this model encodes each amino acid as an individual token. This model was trained using Masked Language Modeling: a process in which a random set of tokens are masked with the model trained on their prediction. This model was trained using the damlab/hiv_flt dataset with 256 amino acid chunks and a 15% mask rate.]
|
23 |
+
|
24 |
+
## Intended Uses & Limitations
|
25 |
+
|
26 |
+
[As a masked language model this tool can be used to predict expected mutations using a masking approach. This could be used to identify highly mutated sequences, sequencing artifacts, or other contexts. As a BERT model, this tool can also be used as the base for transfer learning. This pretrained model could be used as the base when developing HIV-specific classification tasks.]
|
27 |
+
|
28 |
+
## How to use
|
29 |
+
|
30 |
+
[Code snippet of AutoModelForMaskedLM prediction of V3 amino acids.]
|
31 |
+
|
32 |
+
## Training Data
|
33 |
+
|
34 |
+
[The dataset damlab/HIV_FLT was used to refine the original rostlab/Prot-bert-bfd. This dataset contains 1790 full HIV genomes from across the globe. When translated, these genomes contain approximately 3.9 million amino-acid tokens.]
|
35 |
+
|
36 |
+
## Training Procedure
|
37 |
+
|
38 |
+
### Preprocessing
|
39 |
+
|
40 |
+
[As with the rostlab/Prot-bert-bfd model, the rare amino acids U, Z, O, and B were converted to X and spaces were added between each amino acid. All strings were concatenated and chunked into 256 token chunks for training. A random 20% of chunks were held for validation.]
|
41 |
+
|
42 |
+
### Training
|
43 |
+
|
44 |
+
[Training was performed with the HuggingFace training module using the MaskedLM data loader with a 15% masking rate. The learning rate was set at E-5, 50K warm-up steps, and a cosine_with_restarts learning rate schedule and continued until 3 consecutive epochs did not improve the loss on the held-out dataset.]
|
45 |
+
|
46 |
+
## Evaluation Results
|
47 |
+
|
48 |
+
[Table of Prot-Bert and HIV-Bert loss on HIV sequence datasets]
|
49 |
+
|
50 |
+
## BibTeX Entry and Citation Info
|
51 |
+
|
52 |
+
[More Information Needed]
|
53 |
+
|
54 |
---
|
55 |
license: mit
|
56 |
+
---
|