/week_1_welcome

Primary LanguageJupyter Notebook

Week 1: Welcome!

Meeting Notes

All slides presented are in week_1_slides.pdf.

Teams

Neural Network Implementation

  • Raw DNA to Tensors, What are our options?
  • One Hot encoding (2D)
  • What layers make sense to include?
  • Incorporate more data (mapped TFBS, DNAseI, species relatedness, ect)

Quality Control Pipeline

  • Quantify and analyze the input data
  • Are these sequences valid?
  • Which sequences do we remove?
  • Visualize

TFBS mapping

  • Map all TFBS onto sequence
  • Visualize TFBS and conservation
  • Make tools for community

To do for next week

  • Email your team preference
  • Give me your github username
  • In the folder fasta_exercise. Make a program that reads in the pdm2_neurogenic.fa and performs one or all of the tasks mentioned below. You can perform in R or Python. When you have a working script, please up load into the fasta_exercise directory. Please fork repo and make pull request to add.

Program Tasks:

  • Make a sequence alignment
  • turns sequences into a basic python / R data structure
  • measures GC content per sequence