Sebastian Paez

Sebastian Paez

Seattle, Washington, United States
122 followers 112 connections

About

Highly motivated Biologist with background in cancer biology and extensive experience in…

Activity

Join now to see all activity

Experience

  • Talus Bio Graphic

    Talus Bio

    Seattle, Washington, United States

  • -

    Remote

  • -

  • -

    West Lafayette, Indiana, United States

  • -

    West Lafayette, Indiana, United States

Education

  • Purdue University Graphic
  • -

    Activities and Societies: Participated in the Hormone research lab (GIH) as an undergraduate research assistant on a project that entailed studying the differences in metalloprotease secretion during epithelial-to-mesenchymal transition of trophoblasts and choriocarcinoma cell lines.

Projects

  • Pytorch Lightning

    Improved the project documentation by fixing a tutorial on fine-tuning computer vision models using the framework (Issue #5174). In addition to recurrent contributions in the form of community support via Slack and discussions in the github repository.

    See project
  • ElFragmentador

    Implements and provides a neural network that leverages the transformer architecture to predict tandem mass spectra. It Currently outperforms state of the art predictions (prosit) and provides an usable API to use a model with pre-trained weights in the inference of the fragmentation pattern.

    See project
  • scTree

    The goal of scTree is to create a tool to accelerate the transition from single cell rna-sequencing to validation and new sub-population discovery. Features suggesting pseudo-gating strategies to purify found populations via flow-cytometry, antibody querying and cross validations between datasets.

    See project
  • Keepmeposted

    Simple utility to continuously monitor the performance of a mass spectrometry system, where quality reports and diagnostic figures of the instrument are sent to a shared chat server upon completion of runs. (Meant for internal use)

    See project
  • Peptides

    R package to calculate several physicochemical properties and indices for amino-acid sequences as well as to read and plot XVG output files from the ’GROMACS’ molecular dynamics package. My contributions added support for the generation of SMILES strings from peptide sequences and improvements on the reading and plotting of data from molecular dynamics software.

    See project
  • Human Proteome Atlas - Single cell classification

    -

    Implemented a model combining a fine-tuned MASK-RCNN to segment cells and a self-supervised classifier backbone to identify and classify the subcellular localization of proteins from confocal microscopy images. Final position in the private testing dataset was 100/757 using exclusively public GPUs for training

    See project

More activity by Sebastian

View Sebastian’s full profile

  • See who you know in common
  • Get introduced
  • Contact Sebastian directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Sebastian Paez in United States

Add new skills with these courses