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

AbstractMolecular 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.

Download Full-text

Machine Learning Approach for Confirmation of COVID-19 Cases: Positive, Negative, Death and Release (Preprint)

10.2196/preprints.19526 ◽

2020 ◽

Cited By ~ 1

Author(s):

Samir Bandyopadhyay Sr ◽

SHAWNI DUTTA ◽

SHAWNI DUTTA

Keyword(s):

Machine Learning ◽

Short Term Memory ◽

Health Workers ◽

Original Data ◽

High Rate ◽

Learning Approach ◽

Good Decision ◽

Number Of Patients ◽

Machine Learning Approach ◽

Death Cases

BACKGROUND In recent days, Covid-19 coronavirus has been an immense impact on social, economic fields in the world. The objective of this study determines if it is feasible to use machine learning method to evaluate how much prediction results are close to original data related to Confirmed-Negative-Released-Death cases of Covid-19. For this purpose, a verification method is proposed in this paper that uses the concept of Deep-learning Neural Network. In this framework, Long short-term memory (LSTM) and Gated Recurrent Unit (GRU) are also assimilated finally for training the dataset and the prediction results are tally with the results predicted by clinical doctors. The prediction results are validated against the original data based on some predefined metric. The experimental results showcase that the proposed approach is useful in generating suitable results based on the critical disease outbreak. It also helps doctors to recheck further verification of virus by the proposed method. The outbreak of Coronavirus has the nature of exponential growth and so it is difficult to control with limited clinical persons for handling a huge number of patients with in a reasonable time. So it is necessary to build an automated model, based on machine learning approach, for corrective measure after the decision of clinical doctors. It could be a promising supplementary confirmation method for frontline clinical doctors. The proposed method has a high prediction rate and works fast for probable accurate identification of the disease. The performance analysis shows that a high rate of accuracy is obtained by the proposed method. OBJECTIVE Validation of COVID-19 disease METHODS Machine Learning RESULTS 90% CONCLUSIONS The combined LSTM-GRU based RNN model provides a comparatively better results in terms of prediction of confirmed, released, negative, death cases on the data. This paper presented a novel method that could recheck occurred cases of COVID-19 automatically. The data driven RNN based model is capable of providing automated tool for confirming, estimating the current position of this pandemic, assessing the severity, and assisting government and health workers to act for good decision making policy. It could be a promising supplementary rechecking method for frontline clinical doctors. It is now essential for improving the accuracy of detection process. CLINICALTRIAL 2020-04-03 3:22:36 PM

Download Full-text

Detection of Cystic Fibrosis Serological Biomarkers Using a T7 Phage Display Library

Scientific Reports ◽

10.1038/s41598-017-18041-2 ◽

2017 ◽

Vol 7 (1) ◽

Cited By ~ 3

Author(s):

Harvinder Talwar ◽

Samer Najeeb Hanoudi ◽

Andreea Geamanu ◽

Dana Kissner ◽

Sorin Draghici ◽

...

Keyword(s):

Cystic Fibrosis ◽

Phage Display ◽

Phage Display Library ◽

T7 Phage Display ◽

Serological Biomarkers ◽

T7 Phage

Download Full-text

Production, characterization and in-vitro applications of single-domain antibody against thyroglobulin selected from novel T7 phage display library

Journal of Immunological Methods ◽

10.1016/j.jim.2021.112990 ◽

2021 ◽

Vol 492 ◽

pp. 112990

Author(s):

Jothivel Kumarasamy ◽

Samar Kumar Ghorui ◽

Chandrakala Gholve ◽

Bharti Jain ◽

Yogesh Dhekale ◽

...

Keyword(s):

Phage Display ◽

Phage Display Library ◽

Single Domain ◽

Single Domain Antibody ◽

Domain Antibody ◽

T7 Phage Display ◽

T7 Phage

Download Full-text

Stable heterodimers from remodeling the domain interface of a homodimer using a phage display library

Journal of Molecular Biology ◽

10.1006/jmbi.1997.1116 ◽

1997 ◽

Vol 270 (1) ◽

pp. 26-35 ◽

Cited By ~ 145

Author(s):

Shane Atwell ◽

John B.B Ridgway ◽

James A Wells ◽

Paul Carter

Keyword(s):

Phage Display ◽

Phage Display Library

Download Full-text

Isolation of a highly specific ligand for the alpha 5 beta 1 integrin from a phage display library

The Journal of Cell Biology ◽

10.1083/jcb.124.3.373 ◽

1994 ◽

Vol 124 (3) ◽

pp. 373-380 ◽

Cited By ~ 225

Author(s):

E Koivunen ◽

B Wang ◽

E Ruoslahti

Keyword(s):

Phage Display ◽

Cyclic Peptide ◽

Cell Attachment ◽

Phage Display Library ◽

Cell Binding ◽

Rgd Peptides ◽

Beta 1 Integrin ◽

Alpha V Beta 3 ◽

Integrin Ligand ◽

Specific Ligand

Our previous studies showed that the alpha 5 beta 1 integrin selects cysteine pair-containing RGD peptides from a phage display library based on a random hexapeptide. We have therefore searched for more selective peptides for this integrin using a larger phage display library, where heptapeptides are flanked by cysteine residues, thus making the inserts potentially cyclic. Most of the phage sequences that bound to alpha 5 beta 1 (69 of 125) contained the RGD motif. Some of the heptapeptides contained an NGR motif. As the NGR sequence occurs in the cell-binding region of the fibronectin molecule, this sequence could contribute to the specific recognition of fibronectin by alpha 5 beta 1. Selection for high affinity peptides for alpha 5 beta 1 surprisingly yielded a sequence RRETAWA that does not bear obvious resemblance to known integrin ligand sequences. The synthetic cyclic peptide GACRRETAWACGA (*CRRETAWAC*) was a potent inhibitor of alpha 5 beta 1-mediated cell attachment to fibronectin. This peptide is nearly specific for the alpha 5 beta 1 integrin, because much higher concentrations were needed to inhibit the alpha v beta 1 integrin, and there was no effect on alpha v beta 3- and alpha v beta 5-mediated cell attachment to vitronectin. The peptide also did not bind to the alpha IIb beta 3 integrin. *CRRETAWAC* appears to interact with the same or an overlapping binding site in alpha 5 beta 1 as RGD, because cell attachment to *CRRETAWAC* coated on plastic was divalent cation dependent and could be blocked by an RGD-containing peptide. These results reveal a novel binding specificity in the alpha 5 beta 1 integrin.

Download Full-text