Next-generation sequencing-guided identification and reconstruction of antibody CDR combinations from phage selection outputs

Barreto, Kris; Maruthachalam, Bharathikumar Vellalore; Hill, Wayne; Hogan, Daniel J.; Sutherland, Ashley R.; Kusalik, Anthony; Fonge, Humphrey; DeCoteau, John F.; Geyer, C. Ronald

doi:10.1093/nar/gkz131

Cited by 44 publications

(33 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, in terms of data acquisition, precise paring of heavy and light chains is important for predicting antigen binding 19 . There are various experimental and analytical approaches that can be used to retain this precision, such as frequency based ranking 20 , utilization of a long read sequencer 21 , single cell analysis by droplets 22 , and CDR recombination 23 . Second, antibody structure and the role of residues in variable regions have been clarified based on some common numbering schemes from the analytical point of view 24 .…”

Section: Discussionmentioning

confidence: 99%

Antibody design using LSTM based deep generative model from phage display library for affinity maturation

Saka¹,

Kakuzaki²,

Metsugi³

et al. 2021

Sci Rep

104

View full text Add to dashboard Cite

Molecular evolution is an important step in the development of therapeutic antibodies. However, the current method of affinity maturation is overly costly and labor-intensive because of the repetitive mutation experiments needed to adequately explore sequence space. Here, we employed a long short term memory network (LSTM)—a widely used deep generative model—based sequence generation and prioritization procedure to efficiently discover antibody sequences with higher affinity. We applied our method to the affinity maturation of antibodies against kynurenine, which is a metabolite related to the niacin synthesis pathway. Kynurenine binding sequences were enriched through phage display panning using a kynurenine-binding oriented human synthetic Fab library. We defined binding antibodies using a sequence repertoire from the NGS data to train the LSTM model. We confirmed that likelihood of generated sequences from a trained LSTM correlated well with binding affinity. The affinity of generated sequences are over 1800-fold higher than that of the parental clone. Moreover, compared to frequency based screening using the same dataset, our machine learning approach generated sequences with greater affinity.

show abstract

Section: Discussionmentioning

confidence: 99%

Antibody design using LSTM based deep generative model from phage display library for affinity maturation

Saka¹,

Kakuzaki²,

Metsugi³

et al. 2021

Sci Rep

104

View full text Add to dashboard Cite

show abstract

“…Currently, over 80 antibodies derived from phage display libraries have entered clinical studies with 10 of these granted marketing authorization [44]. Since Ravn U et al demonstrated the potential for NGS analysis in the phage-displayed antibody repertoire in 2010, numerous groups have leveraged similar strategies for discovering antibodies reactive to specific antigens [16,[45][46][47][48][49][50][51][52][53]. The next hurdle to overcome after the identification of in silico antibody sequences in NGS data was the low-throughput nature of chemically synthesizing all antibody sequences and individually testing their reactivity.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning-Guided Prediction of Antigen-Reactive In Silico Clonotypes Based on Changes in Clonal Abundance through Bio-Panning

Yoo

Lee

Jung³

et al. 2020

Biomolecules

View full text Add to dashboard Cite

c-Met is a promising target in cancer therapy for its intrinsic oncogenic properties. However, there are currently no c-Met-specific inhibitors available in the clinic. Antibodies blocking the interaction with its only known ligand, hepatocyte growth factor, and/or inducing receptor internalization have been clinically tested. To explore other therapeutic antibody mechanisms like Fc-mediated effector function, bispecific T cell engagement, and chimeric antigen T cell receptors, a diverse panel of antibodies is essential. We prepared a chicken immune scFv library, performed four rounds of bio-panning, obtained 641 clones using a high-throughput clonal retrieval system (TrueRepertoireTM, TR), and found 149 antigen-reactive scFv clones. We also prepared phagemid DNA before the start of bio-panning (round 0) and, after each round of bio-panning (round 1–4), performed next-generation sequencing of these five sets of phagemid DNA, and identified 860,207 HCDR3 clonotypes and 443,292 LCDR3 clonotypes along with their clonal abundance data. We then established a TR data set consisting of antigen reactivity for scFv clones found in TR analysis and the clonal abundance of their HCDR3 and LCDR3 clonotypes in five sets of phagemid DNA. Using the TR data set, a random forest machine learning algorithm was trained to predict the binding properties of in silico HCDR3 and LCDR3 clonotypes. Subsequently, we synthesized 40 HCDR3 and 40 LCDR3 clonotypes predicted to be antigen reactive (AR) and constructed a phage-displayed scFv library called the AR library. In parallel, we also prepared an antigen non-reactive (NR) library using 10 HCDR3 and 10 LCDR3 clonotypes predicted to be NR. After a single round of bio-panning, we screened 96 randomly-selected phage clones from the AR library and found out 14 AR scFv clones consisting of 5 HCDR3 and 11 LCDR3 AR clonotypes. We also screened 96 randomly-selected phage clones from the NR library, but did not identify any AR clones. In summary, machine learning algorithms can provide a method for identifying AR antibodies, which allows for the characterization of diverse antibody libraries inaccessible by traditional methods.

show abstract

“…NGS has previously been used for discovery of antibodies from phage display libraries (Ravn et al, 2010; Zhang et al, 2011; Ravn et al, 2013; Lopez et al, 2017; Yang et al, 2017; Stutz et al, 2018; Barreto et al, 2019). These studies have shown that compared with traditional screening, NGS enables discovery of more clones (Ravn et al, 2010; Ravn et al, 2013; Yang et al, 2017; Stutz et al, 2018), clones with higher affinity (Barreto et al, 2019), or clones binding functionally more interesting epitopes (Lopez et al, 2017; Stutz et al, 2018; Barreto et al, 2019). In many of these studies, the most enriched antibody sequences, against one or several proteins, although sometimes in a complex context (Zhang et al, 2011), have been recovered and used for downstream analysis.…”

Section: Discussionmentioning

confidence: 99%

Deep Mining of Complex Antibody Phage Pools Generated by Cell Panning Enables Discovery of Rare Antibodies Binding New Targets and Epitopes

et al. 2019

View full text Add to dashboard Cite

Phage display technology is a common approach for discovery of therapeutic antibodies. Drug candidates are typically isolated in two steps: First, a pool of antibodies is enriched through consecutive rounds of selection on a target antigen, and then individual clones are characterized in a screening procedure. When whole cells are used as targets, as in phenotypic discovery, the output phage pool typically contains thousands of antibodies, binding, in theory, hundreds of different cell surface receptors. Clonal expansion throughout the phage display enrichment process is affected by multiple factors resulting in extremely complex output phage pools where a few antibodies are highly abundant and the majority is very rare. This is a huge challenge in the screening where only a fraction of the antibodies can be tested using a conventional binding analysis, identifying mainly the most abundant clones typically binding only one or a few targets. As the expected number of antibodies and specificities in the pool is much higher, complementing methods, to reach deeper into the pool, are required, called deep mining methods. In this study, four deep mining methods were evaluated: 1) isolation of rare sub-pools of specific antibodies through selection on recombinant proteins predicted to be expressed on the target cells, 2) isolation of a sub-pool enriched for antibodies of unknown specificities through depletion of the primary phage pool on recombinant proteins corresponding to receptors known to generate many binders, 3) isolation of a sub-pool enriched for antibodies through selection on cells blocked with antibodies dominating the primary phage pool, and 4) next-generation sequencing-based analysis of isolated antibody pools followed by antibody gene synthesis and production of rare but enriched clones. We demonstrate that antibodies binding new targets and epitopes, not discovered through screening alone, can be discovered using described deep mining methods. Overall, we demonstrate the complexity of phage pools generated through selection on cells and show that a combination of conventional screening and deep mining methods are needed to fully utilize such pools. Deep mining will be important in future phenotypic antibody drug discovery efforts to increase the diversity of identified antibodies and targets.

show abstract

Next-generation sequencing-guided identification and reconstruction of antibody CDR combinations from phage selection outputs

Cited by 44 publications

References 47 publications

Antibody design using LSTM based deep generative model from phage display library for affinity maturation

Antibody design using LSTM based deep generative model from phage display library for affinity maturation

Machine Learning-Guided Prediction of Antigen-Reactive In Silico Clonotypes Based on Changes in Clonal Abundance through Bio-Panning

Deep Mining of Complex Antibody Phage Pools Generated by Cell Panning Enables Discovery of Rare Antibodies Binding New Targets and Epitopes

Contact Info

Product

Resources

About