nala:自然语言突变的文本挖掘提到_https_github_其他

<html xmlns="http://www.w3.org/1999/xhtml"><head><meta charset="utf-8"><meta name="generator" content="pdf2htmlEX"><meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"><link rel="stylesheet" href="https://csdnimg.cn/release/download_crawler_static/css/base.min.css"><link rel="stylesheet" href="https://csdnimg.cn/release/download_crawler_static/css/fancy.min.css"><link rel="stylesheet" href="https://csdnimg.cn/release/download_crawler_static/19137102/raw.css"><script src="https://csdnimg.cn/release/download_crawler_static/js/compatibility.min.js"></script><script src="https://csdnimg.cn/release/download_crawler_static/js/pdf2htmlEX.min.js"></script><script>try{pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({});}catch(e){}</script><title></title></head><body><div id="sidebar" style="display: none"><div id="outline"></div></div><div id="pf1" class="pf w0 h0" data-page-no="1"><div class="pc pc1 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://csdnimg.cn/release/download_crawler_static/19137102/bg1.jpg"><div class="t m0 x1 h2 y1 ff1 fs0 fc0 sc0 ls0 ws0">April 28, 2007 13:18 WSPC/INSTRUCTION FILE annotation˙guidelines</div><div class="t m0 x2 h3 y2 ff2 fs1 fc0 sc0 ls0 ws0">1</div><div class="t m0 x3 h4 y3 ff3 fs0 fc0 sc0 ls0 ws0">Appendix A. Annotation Guidelines</div><div class="t m0 x3 h2 y4 ff1 fs0 fc0 sc0 ls0 ws0">The corpus used in the development of MutationFinder</div><div class="t m0 x4 h5 y5 ff4 fs2 fc0 sc0 ls0 ws0">a</div><div class="t m0 x5 h2 y4 ff1 fs0 fc0 sc0 ls0 ws0">is annotated using the</div><div class="t m0 x3 h2 y6 ff1 fs0 fc0 sc0 ls0 ws0">Knowtator plugin for the Protege Ontology Editor and Knowledge Acquisition</div><div class="t m0 x3 h2 y7 ff1 fs0 fc0 sc0 ls0 ws0">System. (See Figure 1.) A new “mutation ontology” has been developed for this</div><div class="t m0 x3 h2 y8 ff1 fs0 fc0 sc0 ls0 ws0">purp ose , the components of which are summarized as follows:</div><div class="t m0 x6 h2 y9 ff5 fs0 fc0 sc0 ls0 ws0">• mutation event</div><div class="t m0 x7 h2 ya ff3 fs0 fc0 sc0 ls0 ws0">– deletion (subclass)</div><div class="t m0 x8 h2 yb ff5 fs0 fc0 sc0 ls0 ws0">∗ deleted element (slot for biological sequence element, biological</div><div class="t m0 x9 h2 yc ff6 fs0 fc0 sc0 ls0 ws0">subsequence, or biological sequence position)</div><div class="t m0 x7 h2 yd ff3 fs0 fc0 sc0 ls0 ws0">– insertion (subclass)</div><div class="t m0 x8 h2 ye ff5 fs0 fc0 sc0 ls0 ws0">∗ inserted element (slot for biological sequence or biological sequence</div><div class="t m0 x9 h2 yf ff6 fs0 fc0 sc0 ls0 ws0">element)</div><div class="t m0 x8 h2 y10 ff5 fs0 fc0 sc0 ls0 ws0">∗ insertion start (slot for biological sequence position)</div><div class="t m0 x7 h2 y11 ff3 fs0 fc0 sc0 ls0 ws0">– substitution (subclass)</div><div class="t m0 x8 h2 y12 ff5 fs0 fc0 sc0 ls0 ws0">∗ wild type element (slot for biological sequence element, biological</div><div class="t m0 x9 h2 y13 ff6 fs0 fc0 sc0 ls0 ws0">sequence position, or biological subsequence)</div><div class="t m0 x8 h2 y14 ff5 fs0 fc0 sc0 ls0 ws0">∗ mutant element (slot for biological sequence element or biological</div><div class="t m0 x9 h2 y15 ff6 fs0 fc0 sc0 ls0 ws0">sequence)</div><div class="t m0 x6 h2 y16 ff5 fs0 fc0 sc0 ls0 ws0">• biological sequence</div><div class="t m0 x7 h2 y17 ff3 fs0 fc0 sc0 ls0 ws0">– polypeptide sequence (subclass)</div><div class="t m0 x7 h2 y18 ff3 fs0 fc0 sc0 ls0 ws0">– sequence (slot for string)</div><div class="t m0 x6 h2 y19 ff5 fs0 fc0 sc0 ls0 ws0">• biological sequence position</div><div class="t m0 x6 h2 y1a ff5 fs0 fc0 sc0 ls0 ws0">• biological sequence element</div><div class="t m0 x7 h2 y1b ff3 fs0 fc0 sc0 ls0 ws0">– amino acid (subclass)</div><div class="t m0 x8 h2 y1c ff5 fs0 fc0 sc0 ls0 ws0">∗ Alanine, Ala, A</div><div class="t m0 x8 h2 y1d ff5 fs0 fc0 sc0 ls0 ws0">∗ Glycine, Gly, G</div><div class="t m0 x8 h2 y1e ff5 fs0 fc0 sc0 ls0 ws0">∗ etc.</div><div class="t m0 x7 h2 y1f ff3 fs0 fc0 sc0 ls0 ws0">– position in sequence (slot for biological sequence position)</div><div class="t m0 x6 h2 y20 ff5 fs0 fc0 sc0 ls0 ws0">• biological subsequence</div><div class="t m0 x7 h2 y21 ff3 fs0 fc0 sc0 ls0 ws0">– polypeptide subsequence (subclass)</div><div class="t m0 x3 h6 y22 ff7 fs3 fc0 sc0 ls0 ws0">a</div><div class="t m0 xa h3 y23 ff2 fs1 fc0 sc0 ls0 ws0">At present, MutationFinder leverages only a subset of the annotation data in the annotated</div><div class="t m0 x3 h3 y24 ff2 fs1 fc0 sc0 ls0 ws0">corpus. (The MutationFinder distribution includes data ﬁles that have been generated from the</div><div class="t m0 x3 h3 y25 ff2 fs1 fc0 sc0 ls0 ws0">Knowtator projects used in this annotation task, but have been preprocessed to simplify their</div><div class="t m0 x3 h3 y26 ff2 fs1 fc0 sc0 ls0 ws0">contents.) As of this writing, the data sets provided with MutationFinder include only ordered</div><div class="t m0 x3 h3 y27 ff2 fs1 fc0 sc0 ls0 ws0">lists of substitution events. Insertion and deletion events are not currently supported by the tool,</div><div class="t m0 x3 h3 y28 ff2 fs1 fc0 sc0 ls0 ws0">and all information relating to how speciﬁc spans of text are associated with each substitution is</div><div class="t m0 x3 h3 y29 ff2 fs1 fc0 sc0 ls0 ws0">absent. While the MutationFinder system itself is capable of conveying basic positional information</div><div class="t m0 x3 h3 y2a ff2 fs1 fc0 sc0 ls0 ws0">about where substitution-event mentions begin and end in piece of text, the system’s output cannot</div><div class="t m0 x3 h3 y2b ff2 fs1 fc0 sc0 ls0 ws0">currently be used to automate the full annotation process described here.</div></div><div class="pi" data-data='{"ctm":[1.568627,0.000000,0.000000,1.568627,0.000000,0.000000]}'></div></div></body></html>

<div id="pf2" class="pf w0 h0" data-page-no="2"><div class="pc pc2 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://csdnimg.cn/release/download_crawler_static/19137102/bg2.jpg"><div class="t m0 x1 h2 y1 ff1 fs0 fc0 sc0 ls0 ws0">April 28, 2007 13:18 WSPC/INSTRUCTION FILE annotation˙guidelines</div><div class="t m0 xb h3 y2c ff2 fs1 fc0 sc0 ls0 ws0">2 Authors’ Names</div><div class="t m0 xc h2 y2d ff3 fs0 fc0 sc0 ls0 ws0">– start element (slot for biological sequence element or a biological se-</div><div class="t m0 xd h2 y2e ff6 fs0 fc0 sc0 ls0 ws0">quence position)</div><div class="t m0 xc h2 y2f ff3 fs0 fc0 sc0 ls0 ws0">– end element (slot for biological sequence element or a biological se-</div><div class="t m0 xd h2 y30 ff6 fs0 fc0 sc0 ls0 ws0">quence position)</div><div class="t m0 xa h2 y31 ff1 fs0 fc0 sc0 ls0 ws0">A generic biological sequence may be thought of as a sequence of sequence ele-</div><div class="t m0 xb h2 y32 ff6 fs0 fc0 sc0 ls0 ws0">ments. Mutation events are simply changes to these sequence elements. The ontology</div><div class="t m0 xb h2 y33 ff1 fs0 fc0 sc0 ls0 ws0">as presented here is capable of capturing only amino-acid sequences that appear in</div><div class="t m0 xb h2 y34 ff1 fs0 fc0 sc0 ls0 ws0">nature and the ways in which these sequences have been modiﬁed (mutated) ex-</div><div class="t m0 xb h2 y35 ff1 fs0 fc0 sc0 ls0 ws0">perimentally. However, the ontology class structure outlined above is designed to</div><div class="t m0 xb h2 y36 ff1 fs0 fc0 sc0 ls0 ws0">accommodate generic biological sequences. In the future, nucleotide subclasses may</div><div class="t m0 xb h2 y37 ff1 fs0 fc0 sc0 ls0 ws0">easily be added to allow modeling of mutations at the pre-translational level. This</div><div class="t m0 xb h2 y38 ff1 fs0 fc0 sc0 ls0 ws0">focus in the current ontology merely reﬂects the initial focus of the MutationFinder</div><div class="t m0 xb h2 y39 ff1 fs0 fc0 sc0 ls0 ws0">project on proteins.</div><div class="t m0 xa h2 y3a ff1 fs0 fc0 sc0 ls0 ws0">Thus, your task at present is to identify text elements that describe a mutation</div><div class="t m0 xb h2 y3b ff1 fs0 fc0 sc0 ls0 ws0">in a protein sequence. Any references to nucleic-acid mutations or sequences or</div><div class="t m0 xb h2 y3c ff1 fs0 fc0 sc0 ls0 ws0">sequence elements should not be captured during this annotation task.</div><div class="t m0 xa h2 y3d ff1 fs0 fc0 sc0 ls0 ws0">To make this task less tedious, much of the text you review will have been pre-</div><div class="t m0 xb h2 y3e ff1 fs0 fc0 sc0 ls0 ws0">processed to contain text elements that have already been annotated automatically.</div><div class="t m0 xb h2 y3f ff1 fs0 fc0 sc0 ls0 ws0">It is important for you to verify each of these automatic annotations in addition to</div><div class="t m0 xb h2 y40 ff1 fs0 fc0 sc0 ls0 ws0">identifying mutation content that was missed by the automated process.</div><div class="t m0 xb h7 y41 ff3 fs0 fc0 sc0 ls0 ws0">A.1. Elements of the Ontology</div><div class="t m0 xb h2 y42 ff1 fs0 fc0 sc0 ls0 ws0">We now describe the various components of the mutation ontology in more detail. In</div><div class="t m0 xb h2 y43 ff1 fs0 fc0 sc0 ls0 ws0">the forthcoming discussion, we will refer several times to the following text sample:</div><div class="t m0 xe h2 y44 ff1 fs0 fc0 sc0 ls0 ws0">In this study, the structural characterization of the nitrogenase Fe</div><div class="t m0 xe h2 y45 ff1 fs0 fc0 sc0 ls0 ws0">protein with Asp at position 39 substituted by Pro provides an</div><div class="t m0 xe h2 y46 ff1 fs0 fc0 sc0 ls0 ws0">explanation. . . .</div><div class="t m0 xb h2 y47 ff1 fs0 fc0 sc0 ls0 ws0">A.1.1. Biological sequence position</div><div class="t m0 xb h2 y48 ff1 fs0 fc0 sc0 ls0 ws0">This class is used to capture the sequence position in the text. In our text sample</div><div class="t m0 xb h2 y49 ff1 fs0 fc0 sc0 ls0 ws0">above, for example, the string 39 should be annotated as a sequence position. This</div><div class="t m0 xb h2 y4a ff1 fs0 fc0 sc0 ls0 ws0">class has no slots (attributes). Use this class to annotate the position in the sequence</div><div class="t m0 xb h2 y4b ff1 fs0 fc0 sc0 ls0 ws0">only. The text spanned by this class should not include any information about what</div><div class="t m0 xb h2 y4c ff1 fs0 fc0 sc0 ls0 ws0">resides at this position. For example, confronted with the</div><div class="t m0 xe h2 y4d ff1 fs0 fc0 sc0 ls0 ws0">The experiment has shown Asp-213 of the L subunit (Asp-213) to</div><div class="t m0 xe h2 y4e ff1 fs0 fc0 sc0 ls0 ws0">be important. . . .</div><div class="t m0 xb h2 y4f ff1 fs0 fc0 sc0 ls0 ws0">text string, you should create two biological sequence position annotations, each</div><div class="t m0 xb h2 y50 ff1 fs0 fc0 sc0 ls0 ws0">spanning one of the strings 213. There should not be an annotation spanning L and</div><div class="t m0 xb h2 y2b ff6 fs0 fc0 sc0 ls0 ws0">213 or Asp-213.</div></div><div class="pi" data-data='{"ctm":[1.568627,0.000000,0.000000,1.568627,0.000000,0.000000]}'></div></div>