A Text-guided Protein Design Framework
Abstract
Current AI-assisted protein design mainly utilizes protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in the text format describing proteins' high-level properties. Yet, whether the incorporation of such text data can help protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multi-modal framework that leverages textual descriptions for protein design. ProteinDT consists of three subsequent steps: ProteinCLAP that aligns the representation of two modalities, a facilitator that generates the protein representation from the text modality, and a decoder that generates the protein sequences from the representation. To train ProteinDT, we construct a large dataset, SwissProtCLAP, with 441K text and protein pairs. We empirically verify the effectiveness of ProteinDT from three aspects: (1) consistently superior performance on four out of six protein property prediction benchmarks; (2) over 90% accuracy for text-guided protein generation; and (3) promising results for zero-shot text-guided protein editing.
Additional Information
This project was partly done during Shengchao Liu's internship at Nvidia, and was supported in part by the Natural Sciences and Engineering Research Council (NSERC) Discovery Grant, the Canada CIFAR AI Chair Program, collaboration grants between Microsoft Research and Mila, Samsung Electronics Co., Ltd., Amazon Faculty Research Award, Tencent AI Lab Rhino-Bird Gift Fund, two NRC Collaborative R&D Projects (AI4D-CORE-06, AI4D-CORE-08), IVADO Fundamental Research Project grant PRF-2019-3583139727, and NSF award CHE 2226451.Attached Files
Submitted - 2302.04611.pdf
Files
Name | Size | Download all |
---|---|---|
md5:e79aedc2c4d6a6ef32c80e866d929da8
|
3.3 MB | Preview Download |
Additional details
- Eprint ID
- 120087
- Resolver ID
- CaltechAUTHORS:20230316-153746362
- Natural Sciences and Engineering Research Council of Canada (NSERC)
- Canadian Institute for Advanced Research (CIFAR)
- Microsoft Research
- Mila
- Samsung Electronics
- Amazon
- Tencent AI Lab
- AI4D-CORE-06
- National Research Council of Canada
- AI4D-CORE-08
- National Research Council of Canada
- PRF-2019-3583139727
- IVADO
- CHE-2226451
- NSF
- Created
-
2023-03-16Created from EPrint's datestamp field
- Updated
-
2023-03-16Created from EPrint's last_modified field