BioPhi: A platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning

Prihoda, David; Maamary, Jad; Waight, Andrew B.; Juan, Veronica; Fayadat‐Dilman, Laurence; Svozil, Daniel; Bitton, Danny A.

doi:10.1080/19420862.2021.2020203

Cited by 87 publications

(125 citation statements)

References 63 publications

Supporting

Mentioning

103

Contrasting

Order By: Relevance

“…AntiBERTa is based on the RoBERTa architecture, 39 as it allows a more direct comparison to established BERT-based protein language models, such as ProtBERT and Sapiens. 29 , 36 …”

Section: Resultsmentioning

confidence: 99%

“…AntiBERTa is pre-trained using a self-supervised MLM task, like other transformer-based protein LMs. 26 , 29 , 36 Briefly, 15% amino acids within the input BCR sequence are randomly perturbed, and the model determines the correct amino acid in place of these masked positions. This task encourages the model to develop a contextual understanding of the BCR sequence.…”

Section: Resultsmentioning

confidence: 99%

“…To date, two LMs have been developed for BCRs and antibodies: DeepAb 13 and Sapiens. 36 DeepAb is a bidirectional long short-term memory (LSTM) network that is pre-trained on 100k paired BCR sequences from the Observed Antibody Space. 37 , 38 As sequence embeddings from DeepAb naturally separate into distinct structural clusters, they can help to produce structural predictions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deciphering the language of antibodies using self-supervised learning

Leem¹,

Mitchell²,

Farmery³

et al. 2022

Patterns

View full text Add to dashboard Cite

“…AntiBERTa is based on the RoBERTa architecture, 39 as it allows a more direct comparison to established BERT-based protein language models, such as ProtBERT and Sapiens. 29 , 36 …”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deciphering the language of antibodies using self-supervised learning

Leem¹,

Mitchell²,

Farmery³

et al. 2022

Patterns

View full text Add to dashboard Cite

“…Examples of categorical predictions include predicting the source of an antibody (e.g. murine or human) from its amino acid sequence [ 24 ] or the incidence of amino acids at specific positions in protein sequence [ 25 ]. On the other hand, continuous predictions aim to capture values such as aggregation propensity [ 26 ] or orientation angles of residues in a structure [ 27 ].…”

Section: Encoding Antibody Antigen Sequence and Structure For Machine...mentioning

confidence: 99%

“…Another computer method that intends to accelerate the process of humanization is BioPhi [ 24 ], an antibody design interface with automated methods that capture the diversity of natural human antibody repertoires. By combining adaptive immune repertoire sequencing and antibody engineering, BioPhi integrates two data-driven methods—novel humanization (Sapiens) and humanness evaluation methods (OASis).…”

Section: Developability—deimmunization Using Large-scale Ngs Data And...mentioning

confidence: 99%

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Wilman¹,

Wróbel²,

Bielska³

et al. 2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Antibodies are versatile molecular binders with an established and growing role as therapeutics. Computational approaches to developing and designing these molecules are being increasingly used to complement traditional lab-based processes. Nowadays, in silico methods fill multiple elements of the discovery stage, such as characterizing antibody–antigen interactions and identifying developability liabilities. Recently, computational methods tackling such problems have begun to follow machine learning paradigms, in many cases deep learning specifically. This paradigm shift offers improvements in established areas such as structure or binding prediction and opens up new possibilities such as language-based modeling of antibody repertoires or machine-learning-based generation of novel sequences. In this review, we critically examine the recent developments in (deep) machine learning approaches to therapeutic antibody design with implications for fully computational antibody design.

show abstract

Single-Cell B-Cell Sequencing to Generate Natively Paired scFab Yeast Surface Display Libraries

Pascual¹,

Belecciu²,

Schmidt³

et al. 2023

Methods in Molecular Biology

View full text Add to dashboard Cite

The immune cell pro ling capabilities of single-cell RNA sequencing (scRNA-seq) are powerful tools that can be applied to the design of theranostic monoclonal antibodies (mAbs). Using scRNA-seq to determine natively-paired B-cell receptor (BCR) sequences of immunized mice as a starting point for design, this method outlines a simpli ed work ow to express single-chain antibody fragments (scFabs) on the surface of yeast for high-throughput characterization and further re nement with directed evolution experiments. While not extensively detailed in this chapter, this method easily accommodates the implementation of a growing body of in silico tools that improve a nity and stability among a range of other developability criteria (e.g., solubility, immunogenicity).

show abstract

BioPhi: A platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning

Cited by 87 publications

References 63 publications

Deciphering the language of antibodies using self-supervised learning

Deciphering the language of antibodies using self-supervised learning

Machine-designed biotherapeutics: opportunities, feasibility and advantages of deep learning in computational antibody discovery

Single-Cell B-Cell Sequencing to Generate Natively Paired scFab Yeast Surface Display Libraries

Contact Info

Product

Resources

About