Home

Useful links

• alternative parser http://fnl.es/medline-kung-fu.html
• Pubmed Open-Access (OA) dataset is available at http://www.ncbi.nlm.nih.gov/pmc/tools/ftp/
• the MEDLINE xmls are available here ftp://ftp.nlm.nih.gov/nlmdata/.medleasebaseline/gz/
• the MEDLINE xmls weekly updates are available here ftp://ftp.nlm.nih.gov/nlmdata/.medlease/gz/
• transform MEDLINE XML to json using node, https://github.com/ldbib/MEDLINEXMLToJSON

Here is a snippet from MEDLINE DTD. We can use it to see available tag from MEDLINE xml.

<!ELEMENT	MedlineCitationSet (MedlineCitation*, DeleteCitation?)>
<!ELEMENT	MedlineCitation (PMID, DateCreated, DateCompleted?, DateRevised?, Article, MedlineJournalInfo, ChemicalList?, SupplMeshList?,CitationSubset*, CommentsCorrectionsList?, GeneSymbolList?, MeshHeadingList?,NumberOfReferences?, PersonalNameSubjectList?, OtherID*, OtherAbstract*, KeywordList*, SpaceFlightMission*, InvestigatorList?, GeneralNote*)>
<!ATTLIST	MedlineCitation 
		Owner  (NLM | NASA | PIP | KIE | HSR | HMD | NOTNLM) "NLM"
		Status (Completed | In-Process | PubMed-not-MEDLINE |  In-Data-Review | Publisher | MEDLINE | OLDMEDLINE) #REQUIRED 
		VersionID CDATA #IMPLIED
		VersionDate CDATA #IMPLIED>
<!ELEMENT	Abstract (AbstractText+, CopyrightInformation?)>
<!ELEMENT	AbstractText (#PCDATA)>
<!ATTLIST	AbstractText
		Label CDATA #IMPLIED
		NlmCategory (BACKGROUND | OBJECTIVE | METHODS | RESULTS | CONCLUSIONS | UNASSIGNED) #IMPLIED>
<!ELEMENT	AccessionNumber (#PCDATA)>
<!ELEMENT	AccessionNumberList (AccessionNumber+)>
<!ELEMENT	Acronym (#PCDATA)>
<!ELEMENT	Affiliation (#PCDATA)>
<!ELEMENT	AffiliationInfo (Affiliation, Identifier*)>
<!ELEMENT	Agency (#PCDATA)>
<!ELEMENT	Article (Journal,ArticleTitle,((Pagination, ELocationID*) | ELocationID+),Abstract?,AuthorList?, Language+, DataBankList?, GrantList?,PublicationTypeList, VernacularTitle?, ArticleDate*)>
<!ATTLIST	Article 
		PubModel (Print | Print-Electronic | Electronic | Electronic-Print | Electronic-eCollection) #REQUIRED>
<!ELEMENT	ArticleDate (Year,Month,Day)>
<!ATTLIST	ArticleDate DateType CDATA  #FIXED "Electronic">
<!ELEMENT	ArticleTitle (#PCDATA)>
<!ELEMENT	Author (((LastName, ForeName?, Initials?, Suffix?) | CollectiveName), Identifier*, AffiliationInfo*)>
<!ATTLIST	Author ValidYN (Y | N) "Y">
<!ELEMENT	AuthorList (Author+)>
<!ATTLIST	AuthorList CompleteYN (Y | N) "Y">
<!ELEMENT	Chemical (RegistryNumber,NameOfSubstance)>
<!ELEMENT	ChemicalList (Chemical+)>
<!ELEMENT	CitationSubset (#PCDATA)>
<!ELEMENT	CollectiveName (#PCDATA)>
<!ELEMENT	CommentsCorrections (RefSource,PMID?,Note?)>
<!ATTLIST	CommentsCorrections 
		RefType (AssociatedDataset | AssociatedPublication | CommentOn | CommentIn | ErratumIn | ErratumFor | PartialRetractionIn | PartialRetractionOf | RepublishedFrom | RepublishedIn | RetractionOf | RetractionIn | UpdateIn | UpdateOf | SummaryForPatientsIn | OriginalReportIn | ReprintOf | ReprintIn | Cites) #REQUIRED >
<!ELEMENT	CommentsCorrectionsList (CommentsCorrections+)>
<!ELEMENT	CopyrightInformation (#PCDATA)>
<!ELEMENT	Country (#PCDATA)>
<!ELEMENT	DataBank (DataBankName, AccessionNumberList?)>
<!ELEMENT	DataBankList (DataBank+)>
<!ATTLIST	DataBankList CompleteYN (Y | N) "Y">
<!ELEMENT	DataBankName (#PCDATA)>
<!ELEMENT	DateCompleted (Year,Month,Day)>
<!ELEMENT	DateCreated (Year,Month,Day)>
<!ELEMENT	DateRevised (Year,Month,Day)>
<!ELEMENT	Day (#PCDATA)>
<!ELEMENT	DescriptorName (#PCDATA)>
<!ATTLIST	DescriptorName 
		MajorTopicYN (Y | N) "N"
		Type (Geographic) #IMPLIED
		UI CDATA #REQUIRED>
<!ELEMENT	ELocationID (#PCDATA)>
<!ATTLIST	ELocationID EIdType (doi | pii) #REQUIRED 
		ValidYN  (Y | N) "Y">
<!ELEMENT	EndPage (#PCDATA)>
<!ELEMENT	ForeName (#PCDATA)>
<!ELEMENT	GeneSymbol (#PCDATA)>
<!ELEMENT	GeneSymbolList (GeneSymbol+)>
<!ELEMENT	GeneralNote (#PCDATA)>
<!ATTLIST	GeneralNote
		Owner (NLM | NASA | PIP | KIE | HSR | HMD) "NLM">
<!ELEMENT	Grant (GrantID?, Acronym?, Agency, Country)>
<!ELEMENT	GrantID (#PCDATA)>
<!ELEMENT	GrantList (Grant+)>
<!ATTLIST	GrantList CompleteYN (Y | N) "Y">
<!ELEMENT	Identifier (#PCDATA)>
<!ATTLIST	Identifier 
		Source CDATA #REQUIRED >
<!ELEMENT	ISOAbbreviation (#PCDATA)>
<!ELEMENT	ISSN (#PCDATA)>
<!ATTLIST	ISSN 
		IssnType  (Electronic | Print) #REQUIRED>
<!ELEMENT	ISSNLinking (#PCDATA)>
<!ELEMENT	Initials (#PCDATA)>
<!ELEMENT	Investigator (LastName, ForeName?, Initials?, Suffix?, Identifier*, AffiliationInfo*)>
<!ATTLIST	Investigator 
		ValidYN (Y | N) "Y">
<!ELEMENT	InvestigatorList (Investigator+)>
<!ELEMENT	Issue (#PCDATA)>
<!ELEMENT	Journal (ISSN?, JournalIssue, Title?, ISOAbbreviation?)>
<!ELEMENT	JournalIssue (Volume?, Issue?, PubDate)>
<!ATTLIST	JournalIssue 
		CitedMedium (Internet | Print) #REQUIRED>
<!ELEMENT	Keyword (#PCDATA)>
<!ATTLIST	Keyword 
		MajorTopicYN (Y | N) "N">
<!ELEMENT	KeywordList (Keyword+)>
<!ATTLIST	KeywordList 
		Owner (NLM | NLM-AUTO | NASA | PIP | KIE | NOTNLM | HHS) "NLM">
<!ELEMENT	Language (#PCDATA)>
<!ELEMENT	LastName (#PCDATA)>
<!ELEMENT	MedlineDate (#PCDATA)>
<!ELEMENT	MedlineJournalInfo (Country?, MedlineTA, NlmUniqueID?, ISSNLinking?)>
<!ELEMENT	MedlinePgn (#PCDATA)>
<!ELEMENT	MedlineTA (#PCDATA)>
<!ELEMENT	MeshHeading (DescriptorName, QualifierName*)>
<!ELEMENT	MeshHeadingList (MeshHeading+)>
<!ELEMENT	Month (#PCDATA)>
<!ELEMENT	NameOfSubstance (#PCDATA)>
<!ATTLIST	NameOfSubstance 
		UI CDATA #REQUIRED>
<!ELEMENT	NlmUniqueID (#PCDATA)>
<!ELEMENT	Note (#PCDATA)>
<!ELEMENT	NumberOfReferences (#PCDATA)>
<!ELEMENT	OtherAbstract (AbstractText+, CopyrightInformation?)>
<!ATTLIST	OtherAbstract 
		Type (AAMC | AIDS | KIE | PIP | NASA | Publisher) #REQUIRED
		Language CDATA "eng">
<!ELEMENT	OtherID (#PCDATA)>
<!ATTLIST	OtherID 
		Source (NASA | KIE | PIP | POP | ARPL | CPC | IND | CPFH | CLML | NRCBL | NLM | QCIM) #REQUIRED>
<!ELEMENT	PMID (#PCDATA)>
<!ATTLIST	PMID 
		Version CDATA #REQUIRED>
<!ELEMENT	Pagination ((StartPage, EndPage?, MedlinePgn?) | MedlinePgn)>
<!ELEMENT	PersonalNameSubject (LastName, ForeName?, Initials?, Suffix?)>
<!ELEMENT	PersonalNameSubjectList (PersonalNameSubject+)>
<!ELEMENT	PubDate ((Year, ((Month, Day?) | Season)?) | MedlineDate)>
<!ELEMENT	PublicationType (#PCDATA)>
<!ATTLIST	PublicationType 
		UI CDATA #REQUIRED>
<!ELEMENT	PublicationTypeList (PublicationType+)>
<!ELEMENT	QualifierName (#PCDATA)>
<!ATTLIST	QualifierName 
		MajorTopicYN (Y | N) "N"
		UI CDATA #REQUIRED>
<!ELEMENT	RefSource (#PCDATA)>
<!ELEMENT	RegistryNumber (#PCDATA)>
<!ELEMENT	Season (#PCDATA)>
<!ELEMENT	SpaceFlightMission (#PCDATA)>
<!ELEMENT	StartPage (#PCDATA)>
<!ELEMENT	Suffix (#PCDATA)>
<!ELEMENT	SupplMeshList (SupplMeshName+)>
<!ELEMENT	SupplMeshName (#PCDATA)>
<!ATTLIST	SupplMeshName 
		Type (Disease | Protocol) #REQUIRED
		UI CDATA #REQUIRED>
<!ELEMENT	Title (#PCDATA)>
<!ELEMENT	VernacularTitle (#PCDATA)>
<!ELEMENT	Volume (#PCDATA)>
<!ELEMENT	Year (#PCDATA)>
<!ELEMENT	DeleteCitation (PMID+)>