Computational counterselection identifies nonspecific therapeutic biologic candidates

Saksena, Sachit D.; Liu, Ge; Banholzer, Christine; Horny, Geraldine; Ewert, Stefan; Gifford, David K.

doi:10.1016/j.crmeth.2022.100254

Cited by 13 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As recently reported 24 , 51 , 52 , similar approaches could be applied to fully characterize sequence features of polyreactive conventional antibody clones. These methods can be expanded by analyzing large antigen-naïve libraries and adding in the three light-chain CDRs and germline gene choice as additional factors for polyreactivity prediction and optimization.…”

Section: Discussionmentioning

confidence: 82%

An in silico method to assess antibody fragment polyreactivity

et al. 2022

View full text Add to dashboard Cite

Antibodies are essential biological research tools and important therapeutic agents, but some exhibit non-specific binding to off-target proteins and other biomolecules. Such polyreactive antibodies compromise screening pipelines, lead to incorrect and irreproducible experimental results, and are generally intractable for clinical development. Here, we design a set of experiments using a diverse naïve synthetic camelid antibody fragment (nanobody) library to enable machine learning models to accurately assess polyreactivity from protein sequence (AUC > 0.8). Moreover, our models provide quantitative scoring metrics that predict the effect of amino acid substitutions on polyreactivity. We experimentally test our models’ performance on three independent nanobody scaffolds, where over 90% of predicted substitutions successfully reduced polyreactivity. Importantly, the models allow us to diminish the polyreactivity of an angiotensin II type I receptor antagonist nanobody, without compromising its functional properties. We provide a companion web-server that offers a straightforward means of predicting polyreactivity and polyreactivity-reducing mutations for any given nanobody sequence.

show abstract

Section: Discussionmentioning

confidence: 82%

An in silico method to assess antibody fragment polyreactivity

et al. 2022

View full text Add to dashboard Cite

show abstract

“…These methods link the phenotype and genotype of proteins displayed and allow for rapid selection of large libraries of proteins including antibodies and antibody fragments. For phage display, the platform used in Saksena et al. (2022) , the most common type of antibody fragments displayed are single-chain variable fragments (scFvs) and antigen-binding fragments (Fabs).…”

Section: Main Textmentioning

confidence: 99%

“… Saksena et al. (2022) now report an application of deep sequencing and machine learning for antibody discovery, which identifies and removes nonspecific antibodies by computational counterselection ( Figure 1 ).…”

Section: Main Textmentioning

confidence: 99%

“…First, by performing two rounds of selections on their target antigens, trastuzumab and omalizumab, and then one round of counterselection on the opposing off-target antibody, Saksena et al. (2022) generated three sets of labeled deep sequencing data for model training: trastuzumab-specific, omalizumab-specific, and cross-reactive antibody sequences that were enriched in the counterselections.…”

Section: Main Textmentioning

confidence: 99%

“…One of the major utilities of computational counterselection described in Saksena et al. (2022) is that it incorporates data from antibody binding to unrelated targets to improve off-target sequence identification.…”

Section: Main Textmentioning

confidence: 99%

See 2 more Smart Citations