Given a gene, identify the world experts http://biostar.stackexchange.com/questions/4296

BioStar4296.java

/**
 * Author: Pierre Lindenbaum PhD
 * WWW: http://plindenbaum.blogspot.com
 * Motivation:
 * 	Given a gene, identify the world experts
 * 	http://biostar.stackexchange.com/questions/4296
 */
import java.net.URLEncoder;
import java.text.Collator;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashSet;
import java.util.List;
import java.util.Locale;
import java.util.Set;
import java.util.TreeSet;
import java.util.logging.Level;
import java.util.logging.Logger;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.stream.XMLOutputFactory;
import javax.xml.stream.XMLStreamWriter;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;


public class BioStar4296
	{
	private Logger LOG=Logger.getLogger(BioStar4296.class.getName());
	private String organism="Homo Sapiens";
	private DocumentBuilder docBuilder;
	private XPath xpath;
	private Collator collator;
	
	
	static class Author
		{
		String suffix="";
		String firstName="";
		String lastName="";
		String initials="";
		Set<String> mails=new HashSet<String>();
		Set<Integer> pmids=new TreeSet<Integer>();
		int factor=1;
		Set<String> affilitations=new HashSet<String>();
		@Override
		public int hashCode() {
			final int prime = 31;
			int result = 1;
			result = prime * result
					+ ((firstName == null) ? 0 : firstName.hashCode());
			result = prime * result
					+ ((lastName == null) ? 0 : lastName.hashCode());
			return result;
		}
		@Override
		public boolean equals(Object obj) {
			if (this == obj)
				return true;
			if (obj == null)
				return false;
			if (getClass() != obj.getClass())
				return false;
			Author other = (Author) obj;
			if (firstName == null) {
				if (other.firstName != null)
					return false;
			} else if (!firstName.equals(other.firstName))
				return false;
			if (lastName == null) {
				if (other.lastName != null)
					return false;
			} else if (!lastName.equals(other.lastName))
				return false;
			return true;
		}
		@Override
		public String toString() {
			return firstName+" "+lastName+" lab:"+this.affilitations+" mails:"+this.mails;
			}
		
		void write(XMLStreamWriter w)
			throws Exception
			{
			w.writeStartElement("Person");
			w.writeCharacters("\n");
			
			w.writeStartElement("firstName");
			w.writeCharacters(firstName);
			w.writeEndElement();
			w.writeCharacters("\n");
			
			w.writeStartElement("lastName");
			w.writeCharacters(lastName);
			w.writeEndElement();
			w.writeCharacters("\n");
			
			for(Integer s:pmids)
				{
				w.writeStartElement("pmid");
				w.writeCharacters(String.valueOf(s));
				w.writeEndElement();
				w.writeCharacters("\n");
				}
			
			for(String s:mails)
				{
				w.writeStartElement("mail");
				w.writeCharacters(s);
				w.writeEndElement();
				w.writeCharacters("\n");
				}
			for(String s:affilitations)
				{
				w.writeStartElement("affilitation");
				w.writeCharacters(s);
				w.writeEndElement();
				w.writeCharacters("\n");
				}
			
			w.writeEndElement();
			w.writeCharacters("\n");
			}
		}
	
	private BioStar4296() throws Exception
		{
		LOG.setLevel(Level.OFF);
		
		DocumentBuilderFactory f=DocumentBuilderFactory.newInstance();
		f.setNamespaceAware(false);
		f.setCoalescing(true);
		f.setIgnoringComments(true);
		f.setIgnoringElementContentWhitespace(true);
		f.setValidating(false);
		this.docBuilder=f.newDocumentBuilder();
		
		XPathFactory factory=XPathFactory.newInstance();
		this.xpath=factory.newXPath();
		
		this.collator= Collator.getInstance(Locale.FRENCH);
		this.collator.setStrength(Collator.PRIMARY);
		}
	
	private int search(XMLStreamWriter w,String geneName)
		throws Exception
		{
		w.writeCharacters("\n");
		w.writeStartElement("gene");
		w.writeAttribute("name", geneName);
		String url= "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=gene&term="+
			URLEncoder.encode(geneName+"[PREF] \""+this.organism+"\"[ORGN]", "UTF-8");
		LOG.info(url);
		Document dom=this.docBuilder.parse(url);
		NodeList list=(NodeList)this.xpath.evaluate(
			"/eSearchResult/IdList/Id",
			dom,XPathConstants.NODESET);
		if(list.getLength()==0)
			{
			w.writeComment("Cannot find any entry for "+geneName);
			w.writeEndElement();
			return -1;
			}
		else if(list.getLength()!=1)
			{
			w.writeComment("Ambigous name "+geneName);
			w.writeEndElement();
			return -1;
			}
		String geneId= list.item(0).getTextContent();
		LOG.info("GeneId:"+geneId);
		w.writeAttribute("geneId", geneId);
		
		url="http://www.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=gene&id="+
			geneId+
			"&rettype=text&retmode=xml";
		LOG.info(url);
		dom=this.docBuilder.parse(url);
		list=(NodeList)this.xpath.evaluate(
				"//PubMedId",
				dom,XPathConstants.NODESET);
		if(list.getLength()==0)
			{
			w.writeComment("No pubmed for "+geneName);
			w.writeEndElement();
			return -1;
			}
		List<Author> authors=new ArrayList<Author>();
		Set<Integer> pmidSet=new TreeSet<Integer>();
		for(int articleIdx=0;articleIdx< list.getLength();++articleIdx)
			{
			String pmid= list.item(articleIdx).getTextContent();
			LOG.info("PMID:"+pmid);
			pmidSet.add(Integer.parseInt(pmid));
			}
		w.writeAttribute("count-pmids",String.valueOf(pmidSet.size()));
		w.writeCharacters("\n");
		
		for(Integer pmid: pmidSet)
			{
			
			LOG.info("PMID:"+pmid);
			url="http://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id="+pmid+"&retmode=xml";
			LOG.info("url:"+url);
			dom=this.docBuilder.parse(url);
			Node n=(Node)this.xpath.evaluate("//Affiliation", dom,XPathConstants.NODE);
			if(n==null) continue;
			String affiliation=n.getTextContent();
			String adressFragments[]=affiliation.split("[ \t\\:\\<,\\>\\(\\)]");
			LOG.info("affiliation:"+affiliation);
			NodeList authorList=(NodeList)this.xpath.evaluate(
					"//AuthorList/Author",
					dom,XPathConstants.NODESET);
			LOG.info("Authors:"+authorList.getLength());
			if(authorList.getLength()==0) continue;
			
			for(int j=0;j< authorList.getLength();++j)
				{
				boolean collective=false;
				Author author=new Author();
				for(Node c1=authorList.item(j).getFirstChild();c1!=null;c1=c1.getNextSibling())
					{
					if(c1.getNodeType()!=Node.ELEMENT_NODE) continue;
					String tag=c1.getNodeName();
					String content= c1.getTextContent();
					if(tag.equals("LastName"))
						{
						author.lastName= content;
						}
					else if(tag.equals("FirstName") || tag.equals("ForeName"))
						{
						author.firstName= content;
						}
					else if(tag.equals("Initials"))
						{
						author.initials= content;
						}
					
					else if(tag.equals("CollectiveName"))
						{
						collective=true;
						break;
						}
					else if(tag.equals("Suffix"))
						{
						author.suffix= content;
						}
					}
				if(collective) continue;
				LOG.info("Make New Author:"+author);
				int k=0;
				for(k=0;k< authors.size();++k)
					{
					Author p=authors.get(k);
					if( !p.firstName.isEmpty() && 
						this.collator.compare(p.firstName,author.firstName)==0 &&
						this.collator.compare(p.lastName,author.lastName)==0)
						{
						LOG.info("Same: "+p+" "+author);
						author=p;
						break;
						}
					}
				
				if(k==authors.size())
					{
					k=0;
					for(k=0;k< authors.size();++k)
						{
						Author p=authors.get(k);
						if( 
							(
							(!author.initials.isEmpty() && p.firstName.toLowerCase().startsWith(author.initials.toLowerCase())) ||
							(!p.initials.isEmpty() && author.firstName.toLowerCase().startsWith(p.initials) )||
							this.collator.compare(p.initials,author.initials)==0 )&&
							this.collator.compare(p.lastName,author.lastName)==0)
							{
							LOG.info("Same: "+p+" "+author);
							if(p.firstName.length()< author.firstName.length())
								{
								p.firstName=author.firstName;
								}
							author=p;
							break;
							}
						}
					}
				
				if(k==authors.size())
					{
					LOG.info("Adding: "+author);
					authors.add(author);
					}
				author.factor*=j;
				author.affilitations.add(affiliation);
				author.pmids.add(pmid);
				
				if(affiliation.indexOf('@')!=-1)
					{
					for(String mail: adressFragments)
						{							
						mail.replaceAll("\\{\\}", "");
						if(mail.endsWith(".")) mail= mail.substring(0,mail.length()-1);
						int index=mail.indexOf('@');
						if(index==-1) continue;
						String mailPrefix=mail.substring(0,index).toLowerCase();

						if(mailPrefix.contains(author.lastName.toLowerCase()) ||
								collator.compare(mailPrefix, author.lastName)==0)
							{
							LOG.info("Adding: "+mail+" to "+author);
							author.mails.add(mail.toLowerCase());
							}
						else if( author.firstName.length()>1 &&
								(mailPrefix.contains( author.firstName.toLowerCase()) ||
							collator.compare(mailPrefix, author.firstName)==0))
							{
							LOG.info("Adding: "+mail+" to "+author);
							author.mails.add(mail.toLowerCase());
							}
						}
					}
				}	
			}
					
		if(authors.isEmpty())
			{
			w.writeComment("No Author found");
			w.writeEndElement();
			return -1;
			}
		
		Collections.sort(authors,new Comparator<Author>()
				{
				@Override
				public int compare(Author o1, Author o2)
					{
					int i= o2.pmids.size()-o1.pmids.size();
					if(i!=0) return i;
					i= o2.factor-o1.factor;//later is more interesting ? not sure...
					return i;
					}
				});
		
		
		authors.get(0).write(w);
		
		w.writeEndElement();
		return 0;
		}
	
	public static void main(String[] args)
		{
		try {
			BioStar4296 app= new BioStar4296();
			int optind=0;
			while(optind<args.length)
				{
				if(args[optind].equals("-h"))
					{
					System.err.println("Pierre Lindenbaum");
					System.err.println("Options:");
					System.err.println(" -o <organism> ["+app.organism+"]");
					System.err.println(" -v show logs");
					return;
					}
				else if(args[optind].equals("-o"))
					{
					app.organism=args[++optind];
					}
				else if(args[optind].equals("-v"))
					{
					app.LOG.setLevel(Level.ALL);
					}
				else if(args[optind].equals("--"))
					{
					optind++;
					break;
					}
				else if(args[optind].startsWith("-"))
					{
					System.err.println("Unnown option: "+args[optind]);
					return;
					}
				else
					{
					break;
					}
				++optind;
				}
		if(optind==args.length)
			{
			System.err.println("Gene Name missing");
			}
		else
			{
			XMLOutputFactory xmlfactory= XMLOutputFactory.newInstance();
			XMLStreamWriter w= xmlfactory.createXMLStreamWriter(System.out,"UTF-8");
			w.writeStartDocument("UTF-8","1.0");
			w.writeCharacters("\n");
			w.writeStartElement("experts");
			w.writeCharacters("\n");
			while(optind < args.length)
				{
				app.search(w,args[optind]);
				optind++;
				w.writeCharacters("\n");
				}
			w.writeEndElement();
			w.writeEndDocument();
			w.flush();
			}
		} catch (Exception e)
			{
			e.printStackTrace();
			}
		}
	}

experts.xml

<?xml version="1.0" encoding="UTF-8"?>
<experts>

<gene name="ZC3H7B" geneId="23264" count-pmids="13">
<Person>
<firstName>Sumio</firstName>
<lastName>Sugano</lastName>
<pmid>8125298</pmid>
<pmid>9373149</pmid>
<pmid>14702039</pmid>
<affilitation>International and Interdisciplinary Studies, The University of Tokyo, Japan.</affilitation>
<affilitation>Institute of Medical Science, University of Tokyo, Japan.</affilitation>
<affilitation>Helix Research Institute, 1532-3 Yana, Kisarazu, Chiba 292-0812, Japan.</affilitation>
</Person>
</gene>

<gene name="eif4G1" geneId="1981" count-pmids="106">
<Person>
<firstName>Nahum</firstName>
<lastName>Sonenberg</lastName>
<pmid>7651417</pmid>
<pmid>7935836</pmid>
<pmid>8449919</pmid>
<pmid>8521827</pmid>
<pmid>9372926</pmid>
<pmid>9418880</pmid>
<pmid>9857202</pmid>
<pmid>9878069</pmid>
<pmid>10523622</pmid>
<pmid>10753870</pmid>
<pmid>10872469</pmid>
<pmid>10996799</pmid>
<pmid>15193258</pmid>
<pmid>15234964</pmid>
<pmid>15314020</pmid>
<pmid>15961545</pmid>
<pmid>16698552</pmid>
<pmid>19114555</pmid>
<pmid>19203580</pmid>
<pmid>20053821</pmid>
<affilitation>Department of Biochemistry and McGill Cancer Center, McGill University, Montreal, H3G 1Y6, Quebec, Canada.</affilitation>
<affilitation>Department of Biochemistry, McGill University, Montreal, Quebec, Canada.</affilitation>
<affilitation>Laboratories of Molecular Biophysics, The Rockefeller University, New York, New York 10021, USA.</affilitation>
<affilitation>Molecular Histology Unit, San Raffaele Institute, 20132 Milan, Italy.</affilitation>
<affilitation>Department of Biochemistry McGill University, Montréal, Québec, Canada. gingras@med.mcgill.ca</affilitation>
<affilitation>Department of Biochemistry and McGill Cancer Cancer Center, McGill University, 3655 Drummond Street, Montréal, Québec, H3G 1Y6 Canada.</affilitation>
<affilitation>Department of Biochemistry and McGill Cancer Centre, McGill University, Montreal, Quebec, Canada.</affilitation>
<affilitation>Department of Biological Chemistry and Molecular Pharmacology, Harvard Medical School, Boston, MA, USA. amarint@bu.edu</affilitation>
<affilitation>Dana-Farber Cancer Institute, Harvard Medical School, Boston, Massachusetts 02115, USA.</affilitation>
<affilitation>Department of Biochemistry, University of California, Riverside, Riverside, California 92521, USA.</affilitation>
<affilitation>Department of Biochemistry, McGill University, Montréal, Quebec, Canada.</affilitation>
<affilitation>Department of Biochemistry and McGill Cancer Center, McGill University, Montréal, Québec, Canada.</affilitation>
<affilitation>Department of Biochemistry and McGill Cancer Centre, McGill University, Drummond Street 3655, Montreal, Quebec, Canada H3G 1Y6.</affilitation>
<affilitation>Department of Biochemistry, McGill Cancer Center, McGill University, Montreal, Quebec, Canada H3G 1Y6.</affilitation>
<affilitation>Department of Biochemistry and Molecular Genetics, University of Illinois at Chicago, 60607, USA. nhay@uic.edu</affilitation>
<affilitation>Department of Biochemistry, McGill University, Montréal, Québec, Canada.</affilitation>
<affilitation>Department of Medicine, University of Minnesota, Minneapolis, MN 55455, USA.</affilitation>
<affilitation>Department of Biochemistry, Case Western Reserve University, Cleveland, Ohio 44106.</affilitation>
</Person>
</gene>

<gene name="PRNP" geneId="5621" count-pmids="429">
<Person>
<firstName>John</firstName>
<lastName>Collinge</lastName>
<pmid>1352724</pmid>
<pmid>1677164</pmid>
<pmid>2159587</pmid>
<pmid>2567794</pmid>
<pmid>8364585</pmid>
<pmid>11283320</pmid>
<pmid>11704923</pmid>
<pmid>12514748</pmid>
<pmid>12621436</pmid>
<pmid>12690204</pmid>
<pmid>15123682</pmid>
<pmid>15539564</pmid>
<pmid>16099923</pmid>
<pmid>16156720</pmid>
<pmid>16342955</pmid>
<pmid>16824036</pmid>
<pmid>16847141</pmid>
<pmid>16925523</pmid>
<pmid>17709704</pmid>
<pmid>18638557</pmid>
<pmid>19081515</pmid>
<pmid>19218199</pmid>
<pmid>19321423</pmid>
<pmid>19369250</pmid>
<pmid>19923577</pmid>
<pmid>20109837</pmid>
<pmid>20583301</pmid>
<mail>j.collinge@ic.ac.uk</mail>
<affilitation>MRC Prion Unit, Department of Neurodegenerative Disease, Institute of Neurology, Queen Square, London WC1N 3BG, UK.</affilitation>
<affilitation>CNS Infection and Immunity Group, Department of Neurogenetics, Division of Neurosciences and Psychological Medicine, Faculty of Medicine, Imperial College, Norfolk Place, London W2 1PG, UK.</affilitation>
<affilitation>Krebs Institute for Biomolecular Research, Department of Molecular Biology and Biotechnology, University of Sheffield, Sheffield S10 2TN, UK.</affilitation>
<affilitation>MRC Prion Unit and Department of Neurogenetics, Imperial College School of Medicine at St. Mary's, London, United Kingdom. J.Collinge@ic.ac.uk</affilitation>
<affilitation>Division of Neuroscience (Neurophysiology), Medical School, University of Birmingham, Edgbaston, Birmingham, UK. sratte@pitt.edu</affilitation>
<affilitation>Division of Psychiatry, Clinical Research Centre, Harrow, Middlesex, UK.</affilitation>
<affilitation>MRC Prion Unit and National Prion Clinic, UCL Institute of Neurology and National Hospital for Neurology and Neurosurgery, London, UK.</affilitation>
<affilitation>Medical Research Council Prion Unit and Department of Neurodegenerative Disease, Institute of Neurology, Queen Square, London, UK.</affilitation>
<affilitation>MRC Prion Unit and Department of Neurodegenerative Disease, UCL Institute of Neurology, National Hospital for Neurology and Neurosurgery, Queen Square, London WC1N 3BG, UK.</affilitation>
<affilitation>MRC Prion Unit, Department of Neurodegenerative Disease, UCL Institute of Neurology, National Hospital for Neurology and Neurosurgery, Queen Square, London, WC1N 3BG, UK.</affilitation>
<affilitation>MRC Prion Unit, Department of Neurodegenerative Disease, Institute of Neurology, University College London, Queen Square, London WC1N 3BG, UK.</affilitation>
<affilitation>MRC Prion Unit and Department of Neurogenetics, Imperial College, St. Mary's Hospital, London, United Kingdom.</affilitation>
<affilitation>Medical Research Council Prion Unit, Department of Neurodegenerative Disease, Institute of Neurology, University College London, Queen Square, London WC1N 3BG, United Kingdom.</affilitation>
<affilitation>Medical Research Council (MRC) Prion Unit and Department of Neurodegenerative Disease, Institute of Neurology, University College London, Queen Square, London WC1N 3BG, UK.</affilitation>
<affilitation>MRC Prion Unit and National Prion Clinic, Institute of Neurology and National Hospital for Neurology and Neurosurgery, Queen Square, London, UK. l.l.hosszu@shef.ac.uk</affilitation>
<affilitation>MRC Prion Unit, Department of Neurodegenerative Diseases, Institute of Neurology, University College London, Queen Square, London WC1N 3BG, UK.</affilitation>
<affilitation>Medical Research Council Prion Unit, Institute of Neurology, Queen Square, London WC1N 3BG, United Kingdom.</affilitation>
<affilitation>Division of Psychiatry, Clinical Research Centre, Harrow, Middlesex, U.K.</affilitation>
<affilitation>Medical Research Council Prion Unit, Department of Neurodegenerative Disease, University College London Institute of Neurology, United Kingdom.</affilitation>
<affilitation>Division of Psychiatry, Clinical Research Centre, Harrow, UK.</affilitation>
<affilitation>Department of Biochemistry and Molecular Genetics, St Mary's Hospital Medical School, London, UK.</affilitation>
<affilitation>Department of Biochemistry and Molecular Genetics, St. Mary's Hospital Medical School, Norfolk Place, London, UK.</affilitation>
<affilitation>MRC Prion Unit and Department of Neurodegenerative Disease, Institute of Neurology, Queen Square, London, UK.</affilitation>
<affilitation>Medical Research Council Prion Unit, and Department of Neurodegenerative Disease, Institute of Neurology, University College, Queen Square, London WC1N 3BG, UK.</affilitation>
</Person>
</gene>
</experts>