Comparing BioKDE search engine with those of PubMed, Google Scholar and Semantic Scholar
The search function at BioKDE performs better than those of PubMed (https://pubmed.ncbi.nlm.nih.gov/), Google Scholar (https://scholar.google.com) and Semantic Scholar (https://semanticscholar.org) based on our preliminary comparisons. Below are some examples. We only compare articles returned on the first page (top 20 relevant articles).
“cancer”:
-
PubMed returned relatively new review articles related to cancer in general.
-
Google Scholar returned many articles related to cancer statistics of different times with mostly old articles.
-
Semantic Scholar returned papers not as important as BioKDE returned in terms of article type, publication time and citations.
-
BioKDE returned relatively new highly cited review articles related to cancer. BioKDE results take citation an article received into account and return highly cited articles more favorable than less cited articles.
“breast cancer”:
-
PubMed returned many articles without abstracts, which is kind of strange. Readers will not know much about the articles when they click the link since there is no abstract to read.
-
Google Scholar returned mostly old articles with high citations with no articles published after 2010. When clicking sorting by dates, many latest conference abstracts showed up, which are likely not one would like to find. Very few highly cited review articles were returned, which are probably what users really like to read.
-
Semantic Scholar returned relatively old articles without using time as a query condition. When limiting only recent articles, such as last 5 years, it still returned relatively old articles not as important as those BioKDE returned in terms of publication time, article type and citations.
-
BioKDE returned new highly cited review articles related to breast cancer.
“breast cancer chemotherapy”:
-
PubMed returned a good number of recently review articles, but again the results contains many articles without abstracts. The top ranked article titled “Breast cancer targeted therapy: successes and challenges.” is actually not very relevant to breast cancer chemotherapy.
-
Google Scholar again returned mostly old articles with high citations. Sorting by dates returned many conference abstracts.
-
Semantic Scholar returned articles not as relevant as BioKDE returned.
-
BioKDE returned many recently published highly cited articles or highly cited review articles related to breast cancer chemotherapy.
“breast cancer chemotherapy and immunotherapy”:
The user may want to find out article related to combining chemotherapy and immunotherapy or comparison between chemotherapy and immunotherapy.
-
PubMed returned a small number of articles truly related to both breast cancer chemotherapy and immunotherapy.
-
Google Scholar only returned on recently published article related to both chemotherapy and immunotherapy.
-
Semantic Scholar returned articles similar to those of PubMed about only one type of treatment instead of both treatments.
-
BioKDE returned articles related to both breast cancer chemotherapy and immunotherapy.
“gene expression biomarkers for breast cancer chemotherapy response”:
PubMed, Google Scholar, Semantic Scholar and BioKDE returned quite different results. It is obvious that BioKDE returned many more relevant articles than PubMed, Google Scholar and Semantic Scholar.
For long sentences, PubMed often returned no results. Our Sentence search function will guarantee returning some article as relevant as possible.
If you have done any comparison and find examples for which PubMed, Google Scholar or Semantic Scholar performs better than BioKDE, please let us know (contact@insilicom.com).