155 lines
7.2 KiB
Text
155 lines
7.2 KiB
Text
<!DOCTYPE html>
|
|
<html lang="en-US">
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html; charset=utf-8">
|
|
<title>NCBI Datasets and Software</title>
|
|
<link href="https://fonts.googleapis.com/css?family=Roboto:400,400i" rel="stylesheet">
|
|
<style>
|
|
body { font-family:Roboto,Arial;margin:3%;padding:0px;text-align:center; }
|
|
table { width:800px;margin-left:auto;margin-right:auto; }
|
|
h1 { border-bottom:dotted 1px #000000;margin-bottom:0px;font-size:23px; }
|
|
h2 { margin-bottom:0px;font-size:15px;font-weight:bold; }
|
|
h3 { padding-top:10px;color:#555555;padding-bottom:0px;margin-bottom:0px;font-size:13px;font-weight:normal; }
|
|
a:link, a:visited { color:#b2b2b2;text-decoration:none;font-size:9pt;font-weight:bold; }
|
|
a:hover, a:active { color:#b2b2b2;text-decoration:underline;font-size:9pt;font-weight:bold; }
|
|
a.PDF:link, a.PDF:visited { color:#b2b2b2;text-decoration:none;font-size:9pt;font-weight:normal; }
|
|
a.PDF:hover, a.PDF:active { color:#b2b2b2;text-decoration:underline;font-size:9pt;font-weight:normal; }
|
|
ul { margin-top:0;margin-bottom:0; }
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<br><br>
|
|
<center>
|
|
|
|
<table>
|
|
<tr><td>
|
|
<h1>
|
|
Datasets and Software
|
|
</h1>
|
|
</td></tr>
|
|
</table>
|
|
|
|
<br>
|
|
|
|
<table>
|
|
<!--stopwords-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;">Stopwords for biomedical literature:</span> <a href="ftp://ftp.ncbi.nlm.nih.gov/pub/wilbur/stopwords.zip">[DOWNLOAD]</a><br>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
</ul>
|
|
</td></tr>
|
|
<!--PubMed Phrases-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;">PubMed Phrases:</span> <a href="ftp://ftp.ncbi.nlm.nih.gov/pub/lu/PubMedPhrase/PubMed_Phrases.tar.gz">[DOWNLOAD]</a><br>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>PubMed Phrases are coherent text segments that are beneficial for information retrieval and human comprehension.</li>
|
|
<li>PubMed Phrases, an open set of coherent phrases for searching biomedical literature, S. Kim, L. Yeganova, D. C. Comeau, W. J. Wilbur and Z. Lu, <span style="font-style:italic;">Scientific Data</span>, 5, 180104, 2018.</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
<!--word2vec for PubMed-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;">Word embeddings for PubMed:</span> <a href="ftp://ftp.ncbi.nlm.nih.gov/pub/wilbur/EMBED/pubmed_s100w10_min.bin.gz">[DOWNLOAD]</a><br>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>Word vectors (in <a style="color:#555555;font-size:13px;font-style:italic;font-weight:normal;" href="https://code.google.com/archive/p/word2vec">word2vec</a> binary format) trained on all PubMed abstracts (Mar. 2016).</li>
|
|
<li>Bridging the gap: incorporating a semantic similarity measure for effectively mapping PubMed queries to documents, S. Kim, N. Fiorini, W. J. Wilbur and Z. Lu, <span style="font-style:italic;">Journal of Biomedical Informatics</span>, 75, pp. 122-127, 2017 (original version in <a class="PDF" href="https://arxiv.org/abs/1608.01972v1">arXiv</a>).</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
<!--BioNLP NCBITextLib-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;">NCBITextLib:</span> <a href="https://github.com/ncbi-nlp/NCBITextLib">[LINK]</a>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>Software library for building a large-scale data infrastructure for text mining.</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
<!--Meshable Dataset-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;"><i>Meshable</i> dataset (MeSH terms):</span> <a href="ftp://ftp.ncbi.nlm.nih.gov/pub/wilbur/Meshable/meshable.txt.gz">[DOWNLOAD]</a><br>
|
|
<span style="color:#333333;"><i>Meshable</i> dataset (MeSH term/subheading combinations):</span> <a href="ftp://ftp.ncbi.nlm.nih.gov/pub/wilbur/Meshable/meshable.sub.txt.gz">[DOWNLOAD]</a>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>MeSH terms (sorted by document set size) and their top 100 topic terms with alpha scores. The PubMed set used to obtain topic terms was collected in Oct. 2015.</li>
|
|
<li>Meshable: searching PubMed abstracts by utilizing MeSH and MeSH-derived topical terms, S. Kim, L. Yeganova and W. J. Wilbur, <span style="font-style:italic;">Bioinformatics</span>, 32(19), pp. 3044-3046, 2016.</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
<!--EMNLP PMID-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;"><i>Cystic fibrosis</i>, <i>Deafness</i>, <i>DiGeorge syndrome</i>, <i>Autism</i> and <i>Hypertrophic cardiomyopathy</i> datasets:</span> <a href="https://www.ncbi.nlm.nih.gov/CBBresearch/Wilbur/IRET/PAVEM/">[LINK]</a>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>PubMed IDs used for evaluating the PAV-EM thematic clustering algorithm.</li>
|
|
<li>Summarizing topical contents from PubMed documents using a thematic analysis, S. Kim, L. Yeganova, and W. J. Wilbur, <span style="font-style:italic;">Conference on Empirical Methods on Natural Language Processing (EMNLP)</span>, pp. 805-810, 2015.</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
<!--JBI DDI-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;">Feature generation tool for DDIExtraction corpora:</span> <a href="https://www.ncbi.nlm.nih.gov/IRET/DDI/">[LINK]</a>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>The tool creates a feature set for the DDIExtraction 2013 corpus.</li>
|
|
<li>Extracting drug-drug interactions from literature using a rich feature-based linear kernel approach, S. Kim, H. Liu, L. Yeganova, and W. J. Wilbur, <span style="font-style:italic;">Journal of Biomedical Informatics</span>, 55, pp. 23-30, 2015.</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
<!--BioNLP Gene-->
|
|
<tr><td>
|
|
<h2>
|
|
<span style="color:#333333;"><i>Disease</i>, <i>CellLine</i> and <i>Reptiles</i> datasets:</span> <a href="https://www.ncbi.nlm.nih.gov/CBBresearch/Wilbur/IRET/bionlp.zip">[DOWNLOAD]</a>
|
|
</h2>
|
|
<ul style="list-style-type:disc">
|
|
<h3>
|
|
<li>Gene names annotated for PubMed documents.</li>
|
|
<li>Classifying gene sentences in biomedical literature by combining high-precision gene identifiers, S. Kim, W. Kim, D. Comeau, and W. J. Wilbur, <span style="font-style:italic;">NAACL 2012 Workshop on Biomedical Natural Language Processing (BioNLP)</span>, pp. 185-192, 2012.</li>
|
|
</h3>
|
|
</ul>
|
|
</td></tr>
|
|
</table>
|
|
|
|
<br>
|
|
|
|
<table>
|
|
<tr><td>
|
|
<span style="font-size:10pt;font-style:italic;font-weight:bold;color:#333333;text-decoration:underline;">Public Domain Notice</span>
|
|
</td></tr>
|
|
<tr><td>
|
|
<ul>
|
|
<span style="font-size:10pt;color:#555555;">
|
|
This work is a United States Government Work under the terms of the United States Copyright Act. It was written as part of the authors' official duties as a United States Government employee and thus cannot be copyrighted within the United States. The data is freely available to the public for use. The National Library of Medicine and the U.S. Government have not placed any restriction on its use or reproduction.
|
|
<br><br>
|
|
Although all reasonable efforts have been taken to ensure the accuracy and reliability of the data and its source code, the NLM and the U.S. Government do not and cannot warrant the performance or results that may be obtained by using it. The NLM and the U.S. Government disclaim all warranties, express or implied, including warranties of performance, merchantability or fitness for any particular purpose.
|
|
</span>
|
|
</ul>
|
|
</td></tr>
|
|
</table>
|
|
|
|
<br>
|
|
|
|
<table>
|
|
<tr><td>
|
|
<span style="font-family:Roboto,Arial;font-size:10pt;font-style:italic;font-weight:normal;color:#b2b2b2;">Contact us: </span><a href="mailto:sun.kim@nih.gov"><span style="font-family:Roboto,Sans-serif;font-size:10pt;font-style:italic;font-weight:normal;color:#b2b2b2;">sun.kim@nih.gov</span></a>
|
|
</td></tr>
|
|
</table>
|
|
</center>
|
|
</body>
|
|
</html>
|