Back

Hierarchical Clustering on RNA Dependent RNA Polymerase using Machine Learning.

Kumar, G. P.

2021-08-23 bioinformatics
10.1101/2021.08.23.457366 bioRxiv
Show abstract

RNA Dependent RNA Polymerase (RdRP) catalyzes the replication of RNA from an RNA template and is mostly found in Viruses. We have collected over 161 viral RdRP FASTA Sequences from the NCBI protein database using python script. Each of these sequences was transformed with TfidfVectorizer using sklearn module, with the "one Letter" word, because each Letter belongs to one Amino acid. These transformed data were sent to Hierarchical clustering using scipy library and visualized data using Dendrogram. These Machine Learning technique is able to classify or segment similar RdRp into one cluster. Each of these clusters was tested for their multiple sequence alignment with COBALT of NCBI. We observed that these clusters predicted similar RdRP among various viruses. These techniques can be further improved to segment or classify various proteins. These Machine Learning or Artificial Intelligence techniques need more improvement in their algorithms to solve genomics and proteomics. RepositoryPrograms and Datasets : https://github.com/DSPavan/RdRP

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.