@article {Kovaltsuk316026, author = {Aleksandr Kovaltsuk and Jinwoo Leem and Sebastian Kelm and James Snowden and Charlotte M. Deane and Konrad Krawczyk}, title = {Observed Antibody Space: a resource for data mining next generation sequencing antibody repertoires}, elocation-id = {316026}, year = {2018}, doi = {10.1101/316026}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Antibodies are immune system proteins that recognize noxious molecules for elimination. Their sequence diversity and binding versatility have made antibodies the primary class of biopharmaceuticals. Recently it has become possible to query their immense natural diversity using next-generation sequencing of immunoglobulin gene repertoires (Ig-seq). However, Ig-seq outputs are currently fragmented across repositories and tend to be presented as raw nucleotide reads, which means nontrivial effort is required to reuse the data for analysis. To address this issue, we have collected Ig-seq outputs from 53 studies, covering more than half a billion antibody sequences across diverse immune states, organisms and individuals. We have sorted, cleaned, annotated, translated and numbered these sequences and make the data available via our Observed Antibody Space (OAS) resource at antibodymap.org. The data within OAS will be regularly updated with newly released Ig-seq datasets. We believe OAS will facilitate data mining of immune repertoires for improved understanding of the immune system and development of better biotherapeutics.}, URL = {https://www.biorxiv.org/content/early/2018/05/10/316026}, eprint = {https://www.biorxiv.org/content/early/2018/05/10/316026.full.pdf}, journal = {bioRxiv} }