| Download | - View final version: Disentangled wasserstein autoencoder for T-cell receptor engineering (PDF, 7.1 MiB)
|
|---|
| Link | https://neurips.cc/virtual/2023/poster/72313 |
|---|
| Author | Search for: Li, Tianxiao; Search for: Guo, Hongyu1ORCID identifier: https://orcid.org/0000-0002-7663-2421; Search for: Grazioli, Filippo; Search for: Gerstein, Mark; Search for: Min, Martin Renqiang |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 37th Conference on Neural Information Processing Systems (NeurIPS) 2023, December 10-16, 2023, New Orleans, Louisianna, USA |
|---|
| Subject | cell engineering; cell membranes; domain knowledge; learning systems; T-cells; active site; auto encoders; binding surface; data driven; functional sites; protein engineering; T cells receptors; proteins |
|---|
| Abstract | In protein biophysics, the separation between the functionally important residues (forming the active site or binding surface) and those that create the overall structure (the fold) is a well-established and fundamental concept. Identifying and modifying those functional sites is critical for protein engineering but computationally non-trivial, and requires significant domain knowledge. To automate this process from a data-driven perspective, we propose a disentangled Wasserstein autoencoder with an auxiliary classifier, which isolates the function-related patterns from the rest with theoretical guarantees. This enables one-pass protein sequence editing and improves the understanding of the resulting sequences and editing actions involved. To demonstrate its effectiveness, we apply it to T-cell receptors (TCRs), a well-studied structure-function case. We show that our method can be used to alter the function of TCRs without changing the structural backbone, outperforming several competing methods in generation quality and efficiency, and requiring only 10% of the running time needed by baseline models. To our knowledge, this is the first approach that utilizes disentangled representations for TCR engineering. |
|---|
| Publication date | 2023-12-10 |
|---|
| Publisher | Neural Information Processing Systems Foundation |
|---|
| In | |
|---|
| Series | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | cf5d1096-2edb-40b5-abe1-4da6a86eb52d |
|---|
| Record created | 2024-07-18 |
|---|
| Record modified | 2024-11-19 |
|---|
