Advanced searches left 3/3

Space - BioProject

Summarized by Plex Scholar
Last Updated: 21 June 2022

* If you want to update the article please login/register

Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space

Therapeutic antibody manufacturing requires the design and engineering of molecules with high affinity and other drug-like biophysical properties. Here we've investigated the use of machine learning to greatly simplify the detection of antibodies with co-optimal affinity and specificity for a clinical-stage antibody with both high amounts of on-target and off-target binding. We mutated locations in the antibody complementarity-determining regions that were supposed to mediate non-specific binding, sorted the antibody libraries for elevated and low affinity, non-specific binding, and deep sequenced the enriched libraries. Interestingly, we discovered that machine learning algorithms developed using binary datasets and supervised dimensionality reduction enabled the prediction of continuous metrics that were strongly related to antibody affinity and non-specific binding. Notably, models built with deep learning capabilities enabled extrapolation to predict novel antibody mutations that co-optimized affinity and specificity beyond what was otherwise expected for the initial antibody library.

Source link: https://www.ncbi.nlm.nih.gov/bioproject/850089


Space-time Mapping Identifies Concerted Multicellular Patterns and Gene Programs in Healing Wounds and their Conservation in Cancers.

Tissue repair responses in metazoans are highly coordinated by many cell types, both in space and time. Here, we gathered transcriptional states of single cells in response to space and time after skin wound closure, revealing choreographed gene expression profiles. Finally, we tested the hypothesis that tumors are like u2018wounds that never heal,'u2019 Finds that wound healing movements in the tumor space were conserved, with some tumors preferentially used in one tumor over another. Overall scheme: A single cell RNA-Seq analysis of isolated immune and non-immune cells from unwounded mouse skin, as well as wounds d1,3,7,14 post wounds from 4 pooled wounds.

Source link: https://www.ncbi.nlm.nih.gov/bioproject/842246

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions