Mapping Medline papers, genes, and proteins related to melanoma research

Abstract

What is the structure of the research reported on melanoma? How has it evolved over the last 40 years? Which parts of this research field are correlated with the study of genes and proteins? Are there sudden increases in the number of occurrences of certain gene or protein names, reflecting a surge of interest? How are genes, protein and papers interconnected via co-occurrence patterns? This paper aims to provide answers to these questions by analyzing a data set consisting of papers from Medline, genes from the Entrez Gene database, and proteins from UniProt. Word burst detection and cooccurrence analyses were both performed. The spatial layout algorithm VxOrd was applied to create the very first map that shows papers, genes, and proteins and their co-occurrence relationships. The results were validated by five domain experts leading to a number of interesting facts pertaining to structure and dynamics of the melanoma research field. 1.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 18 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.