nferruz commited on
Commit
3277fbc
·
1 Parent(s): 4214bff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -7
README.md CHANGED
@@ -23,20 +23,22 @@ inference:
23
  # **REXzyme: A Translation Machine for the Generation of New-to-Nature Enzymes**
24
  **Work in Progress**
25
 
26
- REXzyme (Reaction to Enzyme) (manuscript in preparation) is a translation machine for the generation of enzymes that catalize user-defined reactions.
 
27
 
28
  ![Inference of REXzyme](./REXzyme.png)
29
 
30
  It is possible to provide fine-grained input at the substrate level.
31
  Akin to how translation machines have learned to translate between complex language pairs with great success,
32
- often diverging in their representation at the character level, (Japanese - English), we posit that an advanced architecture will
33
- be able to translate between the chemical and sequence spaces. REXzyme was trained on a set of 2480 reactions and ~32M enzyme pairs and it produces
34
- sequences that putatitely perform their intended reactions.
35
 
36
- To run it, you will need to provide a reaction in the SMILE format (Simplified molecular-input line-entry system), which you can do online here: https://cactus.nci.nih.gov/chemical/structure.
 
37
 
38
- After converting each of the reaction components you should combine them in the following scheme : ```ReactantA.ReactantB>AgentA>ProductA.ProductB```<br/>
39
- Additionally prepend the task suffix ```r2s``` and append the eos token ```</s>```
40
  e.g. for the carbonic anhydrase ```r2sO.COO>>HCOOO.[H+]</s>```
41
 
42
  or via this simple python script:
 
23
  # **REXzyme: A Translation Machine for the Generation of New-to-Nature Enzymes**
24
  **Work in Progress**
25
 
26
+ REXzyme (Reaction to Enzyme) (manuscript in preparation) is a translation machine, similar to Google Translator,
27
+ for the generation of enzymes that catalize user-defined reactions.
28
 
29
  ![Inference of REXzyme](./REXzyme.png)
30
 
31
  It is possible to provide fine-grained input at the substrate level.
32
  Akin to how translation machines have learned to translate between complex language pairs with great success,
33
+ often diverging in their representation at the character level (Japanese - English), we posit that an advanced architecture will
34
+ be able to translate between the chemical and sequence spaces. REXzyme was trained on a set of 2480 reactions
35
+ and ~32M enzyme pairs and it produces sequences that are predicted to perform their intended reactions.
36
 
37
+ To run it, you will need to provide a reaction in the SMILE format
38
+ (Simplified molecular-input line-entry system), which you can do online here: https://cactus.nci.nih.gov/chemical/structure.
39
 
40
+ After converting each of the reaction components you should combine them in the following scheme: ```ReactantA.ReactantB>AgentA>ProductA.ProductB```<br/>
41
+ Additionally prepending the task suffix ```r2s``` and append the eos token ```</s>```
42
  e.g. for the carbonic anhydrase ```r2sO.COO>>HCOOO.[H+]</s>```
43
 
44
  or via this simple python script: