[D] New to DNABERT

• DNABERT

  1 546 3.1 Python

  DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome

If I want to get started, they said it's optional to pre-train (so you can skip to step 3). This is where I got tripped up: "Note that the sequences are in kmer format, so you will need to convert your sequences into that." From what I understand, you need to do this so that all of the sequences are the same length? So kmer=6 means all of the sequences are length 6? Someone suggested that I take the first nucleotide in the promoter and grab 3 nucleotides before and 3 nucleotides after (+/-3 bases). I don't think that's how the kmer thing works though? I tried replicating how I think it works down below (I got confused on the last row of the 'after' df). Please correct me if I'm wrong!

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project