The RESP AI model accelerates the identification of tight-binding antibodies

Parkinson, Jonathan; Hard, Ryan L.; Wang, Wei

doi:10.1038/s41467-023-36028-8

Cited by 19 publications

(11 citation statements)

References 66 publications

(72 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a study involving protein engineering, Parkinson et al use uncertainty to select and narrow down the most certain predictions for experimental evaluation to save cost and time. 30 While we cannot experimentally validate predictions in this study, we describe a practical application of uncertainty awareness using the Bernett test set. For selecting experimental candidates, precision is a key metric considering the number of false positives must be minimized.…”

Section: Effect Of Uncertainty Awarenessmentioning

confidence: 94%

TUnA: An uncertainty aware transformer model for sequence-based protein-protein interaction prediction

Ko,

Parkinson,

Liu

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Protein-protein interactions (PPIs) are important for many biological processes, but predicting them from sequence data remains challenging. Existing deep learning models often cannot generalize to proteins not present in the training set, and do not provide uncertainty estimates for their predictions. To address these limitations, we present TUnA, a Transformer-based uncertainty aware model for PPI prediction. TUnA uses ESM-2 embeddings with Transformer encoders and incorporates a Spectral-normalized Neural Gaussian Process. TUnA achieves state-of-the-art performance and, importantly, evaluates uncertainty for unseen sequences. We demonstrate that TUnA’s uncertainty estimates can effectively identify the most reliable predictions, significantly reducing false positives. This capability is crucial in bridging the gap between computational predictions and experimental validation.

show abstract

Section: Effect Of Uncertainty Awarenessmentioning

confidence: 94%

TUnA: An uncertainty aware transformer model for sequence-based protein-protein interaction prediction

Ko,

Parkinson,

Liu

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The number of reports of such AI/ML approaches in combination with NGS and biopanning is rapidly increasing 70,71 , demonstrating their general potential to transform the Biologics drug discovery process. In conclusion, these studies demonstrate how AI/ML models can be built based on sequence enrichments that are observed in antibody libraries through different rounds of biopanning.…”

Section: Whereas Mason Et Al Applied In Silico Developability Scoring...mentioning

confidence: 99%

SUMO –In SilicoSequence Assessment Using Multiple Optimization Parameters

Evers

Malhotra

Bolick

et al. 2022

Preprint

View full text Add to dashboard Cite

To select the most promising screening hits from antibody and VHH display campaigns for subsequent in-depth profiling and optimization, it is highly desirable to assess and select sequences on properties beyond only their binding signals from the sorting process. In addition, developability risk criteria, sequence diversity and the anticipated complexity for sequence optimization are relevant attributes for hit selection and optimization. Here, we describe an approach for the in silico developability assessment of antibody and VHH sequences. This method not only allows for ranking and filtering multiple sequences with regard to their predicted developability properties and diversity, but also visualizes relevant sequence and structural features of potentially problematic regions and thereby provides rationales and starting points for multi-parameter sequence optimization.

show abstract

“…For example, Marks et al note that Hu-mAb is best used for humanizing sequences of murine origin only since it was primarily trained on human and mouse sequences 5 . Classifiers are not generative models and do not directly generate synthetic libraries, which is desirable for some machine learning assisted approaches to antibody discovery 14 . Finally, they provide a single score for the entire sequence and hence limited interpretability / granularity to the end user.…”

Section: Introductionmentioning

confidence: 99%

For antibody sequence generative modeling, mixture models may be all you need

Parkinson,

Wang

2024

Preprint

Self Cite

View full text Add to dashboard Cite

Antibody therapeutic candidates must exhibit not only tight binding to their target but also good developability properties, especially low risk of immunogenicity. In this work, we fit a simple generative model, SAM, to sixty million human heavy and seventy million human light chains. We show that the probability of a sequence calculated by the model distinguishes human sequences from other species with the same or better accuracy on a variety of benchmark datasets containing >400 million sequences than any other model in the literature, outperforming large language models (LLMs) by large margins. SAM can humanize sequences, generate new sequences, and score sequences for humanness. It is both fast and fully interpretable. Our results highlight the importance of using simple models as baselines for protein engineering tasks. We additionally introduce a new tool for numbering antibody sequences which is orders of magnitude faster than existing tools in the literature. Both these tools are available at https://github.com/Wang-lab-UCSD/AntPack .

show abstract

The RESP AI model accelerates the identification of tight-binding antibodies

Cited by 19 publications

References 66 publications

TUnA: An uncertainty aware transformer model for sequence-based protein-protein interaction prediction

TUnA: An uncertainty aware transformer model for sequence-based protein-protein interaction prediction

SUMO –In SilicoSequence Assessment Using Multiple Optimization Parameters

For antibody sequence generative modeling, mixture models may be all you need

Contact Info

Product

Resources

About