Systems, methods, and apparatus for processing documents to identify structures

• US 8,433,723 B2
• Filed: 05/03/2011
• Issued: 04/30/2013
• Est. Priority Date: 05/03/2010
• Status: Active Grant

• Current Assignee: Revvity Signals Software Incorporated
• Original Assignee: Cambridgesoft Corporation (Perkinelmer Incorporated)
• Inventors: Smith, Robin Y., Ballard, William B., Flicker, Scott G., Greenhow, Sean G.
• Primary Examiner(s): Beausoleil, Jr., Robert
• Assistant Examiner(s): Arjomandi, Noosha
• Application Number:
  US13/100,217
• Publication Number:
  US 20110276589A1
• Time in Patent Office: 728 Days
• Field of Search: 707/769, 707/754, 707/791, 707/803, 702/27, 702/32, 702/30, 715/513, 715/804, 706/20
• US Class Current: 707/769
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06V 30/422 Technical drawings; Geographical maps
• CPC Class Codes: G16C 20/40 Searching chemical structures or physicochemical data
• CPC Class Codes: G16C 20/80 Data visualisation
• CPC Class Codes: G16C 20/90 Programming languages; Computing architectures; Database systems; Data warehousing

Abstract

In various embodiments, multiple heterogeneous documents are processed to identify structures, such as chemical structures, contained therein, including non-embedded structures. Also described is a graphical user interface that permits a user to search for a structure or substructure within a set of electronic documents, then displays the matching structures as well as the actual pages of the documents on which the matching structures are found. Display of the actual pages allows the user to verify the matches and provides helpful context for the user.

Claims

1. An apparatus for electronically identifying and compiling chemical structures found in a storage facility comprising one or more electronic files, the apparatus comprising:

(a) a memory for storing a code defining a set of instructions; and

(b) a processor for executing the set of instructions, wherein the instructions, when executed by the processor, cause the processor to;

(i) identify a plurality of candidate chemical structures in at least a portion of the one or more electronic files of the storage facility, wherein

each electronic file of the portion of the one or more electronic files comprises at least one respective non-embedded image of a chemical structure, and

identifying a respective candidate chemical structure comprises identifying one or more graphical features common to chemical structures;

(ii) for each candidate chemical structure of the plurality of candidate chemical structures, derive a respective chemical structure object with an associated set of properties, wherein

one or more properties of the set of properties is derived from at least a portion of the one or more graphical features common to chemical structures,

a first property of the set of properties is a number of carbons, wherein the number of carbons is derived from the one or more graphical features common to chemical structures, and

a second property of the set of properties comprises one of the following;

(A) number of hetero atoms, (B) number of bonds, (C) number of bonds of a selected bond order, (D) number of rings, and (E) formula weight;

(iii) for each chemical structure object, apply one or more filters to at least one property of the associated set of properties, wherein

the one or more filters includes a filter configured to eliminate chemical structure objects having a value of the first property of the set of properties less than a predetermined number of carbons;

(iv) for each chemical structure object, compute a respective confidence factor value based on two or more properties of the set of properties associated with the chemical structure object;

wherein

one or more chemical structure objects are eliminated based on respective confidence factor values in order to reduce false positives; and

(v) provide, for storage in a searchable electronic compendium of identified chemical structure objects, chemical structure objects not eliminated by the one or more filters.

2. The apparatus of claim 1, wherein the storage facility comprises a plurality of electronic files of two or more different file types.

3. The apparatus of claim 2, wherein the two or more different file types comprise at least two members selected from the group consisting of PDF, Word, Tiff, Excel, Mol File, RXN File, RTF, PowerPoint, cdx, BMP, JPEG, Plain Text, and SDF.

4. The apparatus of claim 1, wherein the instructions cause the processor to, after applying the one or more filters, for each remaining chemical structure object, associate therewith identification of a respective electronic document in which the candidate chemical structure from which the respective chemical structure object was derived is located, and a page or portion thereof on which the candidate chemical structure is located, thereby facilitating identification of the origin of a particular chemical structure or substructure in the one or more electronic files during a search of the electronic compendium for the particular chemical structure or substructure.

5. The apparatus of claim 1, wherein, for at least one candidate chemical structure of the plurality of candidate chemical structures, a third property of the set of properties associated with a respective chemical structure object derived therefrom comprises stereochemistry.

6. The apparatus of claim 1, wherein the instructions, when executed, further cause the processor to:

(v) responsive to a search query, provide, for viewing by a user at a display device;

graphical user interface information, wherein the graphical user interface (GUI) information is configured, upon presentation, to provide;

(a) in a first designated location of a graphical user interface, one or more matching chemical structures, wherein

each of the one or more matching chemical structures corresponds to a respective chemical structure object in the searchable electronic compendium of identified chemical structure objects, and

each of the one or more matching chemical structures comprises a selectable control configured, upon selection, to present information pertaining to the respective matching chemical structure,

(b) in a second designated location of the graphical user interface, one or more selectable controls representing one or more electronic files from the storage facility, wherein each file of the one or more electronic files comprises at least one of the one or more matching chemical structures, and

(c) in a third designated location of the graphical user interface, a portion of a particular electronic file of the one or more electronic files, wherein the portion of the particular electronic file comprises at least one of the one or more matching chemical structures.

7. The apparatus of claim 1, wherein the each chemical structure object comprises a standardized molecule connection table.

8. The apparatus of claim 7, wherein a format of the standardized molecule connection table is compatible with a standardized chemical table file type.

9. A method for automated identification of graphical representations of chemical structures comprising:

identifying, by a processor of a computing device, within an electronic file comprising one or more non-embedded images of chemical structures, at least one candidate chemical structure, wherein the at least one candidate chemical structure is identified based at least in part on graphical image processing, wherein the graphical image processing comprises identifying one or more graphical features common to chemical structures;

for each of the at least one candidate chemical structure, deriving, by the processor, a respective chemical structure object, wherein

the respective chemical structure object comprises a set of properties, wherein

one or more properties of the set of properties is derived from at least a portion of the one or more graphical features common to chemical structures,

a first property of the set of properties is a number of carbons, and

a second property of the set of properties comprises one of the following;

(A) number of hetero atoms, (B) number of bonds, (C) number of bonds of a selected bond order, (D) number of rings, and (E) formula weight;

for each chemical structure object, applying, by the processor, one or more filters, wherein

each filter of the one or more filters is configured to compare one or more properties of the set of properties of a given chemical structure object to one or more predetermined values, and

a first filter of the one or more filters is configured to eliminate chemical structure objects based at least in part on a determination that the chemical structure object has fewer than a predetermined number of carbons;

for each chemical structure object, calculating a respective confidence factor value based on two or more properties of the set of properties associated with the chemical structure object, wherein

each chemical structure of the at least one confirmed chemical structure is identified based at least in part upon respective confidence score associated with the respective chemical structure object derived therefrom; and

identifying, by the processor, at least one confirmed chemical structure, wherein each chemical structure of the at least one confirmed chemical structure is identified based at least in part upon the respective chemical structure object derived therefrom avoiding elimination by the one or more filters.

10. The method of claim 9, wherein:

calculating the confidence score comprises applying a formula to at least three properties of the respective set of properties, wherein

the respective set of properties comprises two or more of number of nitrogen atoms, number of oxygen atoms, number of fluorine atoms, number of sulfur atoms, number of chlorine atoms, number of rings, number of aromatic rings, number of five-member rings, number of six-member rings, and number of reactive fragments.

11. The method of claim 9, wherein identifying the one or more non-embedded images of chemical structures comprises, for each page of the electronic file, successively segmenting the respective page into greater number of segments and identifying suspected chemical structures within each segment.

12. The method of claim 9, further comprising, for each confirmed chemical structure:

deriving molecular properties of the respective chemical structure, wherein

the molecular properties are accessed from a database, corporate registry, or corporate inventory system; and

associating the molecular properties with the respective chemical structure.

13. The method of claim 9, further comprising:

receiving a query comprising a specified chemical structure, wherein

applying the one or more filters comprises comparing the set of properties of a given chemical structure object to a plurality of known chemical properties of the chemical structure, and

identifying at least one confirmed chemical structure comprises identifying the at least one confirmed chemical structure as a suspected match to the specified chemical structure.

14. A non-transitory computer-readable medium having instructions stored thereon, wherein the instructions, when executed by a processor, cause the processor to:

identify, within an electronic file comprising one or more non-embedded images of chemical structures, at least one candidate chemical structure, wherein the at least one candidate chemical structure is identified based at least in part on graphical image processing, wherein

the graphical image processing comprises identifying one or more graphical features common to chemical structures;

for each of the at least one candidate chemical structure, derive a set of properties, wherein

one or more properties of the set of properties is derived from at least a portion of the one or more graphical features common to chemical structures,

a first property of the set of properties is a number of carbons, and

a second property of the set of properties comprises one of the following;

(A) number of hetero atoms, (B) number of bonds, (C) number of bonds of a selected bond order, (D) number of rings, and (E) formula weight;

for each candidate chemical structure, apply one or more filters, wherein

each filter of the one or more filters is configured to compare one or more properties of the set of properties of a given candidate chemical structure to one or more predetermined values, and

a first filter of the one or more filters is configured to eliminate candidate chemical structures based at least in part on a determination that the given candidate chemical structure has fewer than a predetermined number of carbons;

for each chemical structure object, calculate a respective confidence factor value based on two or more properties of the set of properties associated with the chemical structure object, wherein

each chemical structure of the at least one confirmed chemical structure is identified based at least in part upon respective confidence score associated with the respective chemical structure object derived therefrom; and

identify at least one confirmed chemical structure, wherein each chemical structure of the at least one confirmed chemical structure is identified based at least in part upon the candidate chemical structure avoiding elimination by the one or more filters.

15. The computer-readable medium of claim 14, wherein the instructions, when executed, further cause the processor to, for each confirmed chemical structure:

associate a respective electronic document in which the respective confirmed chemical structure is located and a respective location within the respective electronic document, wherein

the respective location identifies a location of the confirmed chemical structure.

16. The computer-readable medium of claim 15, wherein the respective position comprises a page number.

17. The computer-readable medium of claim 15, further comprising:

causing presentation of, on a display of a user device,

(i) in a first designated location of a graphical user interface (GUI), at least one of the one or more confirmed chemical structures, and

(ii) in a second designated location of the GUI, a portion of the electronic file, wherein the portion of the electronic file comprises the location of a confirmed chemical structure of the one or more confirmed chemical structures.

18. The computer-readable medium of claim 14, wherein the instructions, when executed, cause the processor to:

determine, based upon the one or more graphical features, that a first candidate chemical structure of the at least one candidate chemical structure lacks evidence of defined stereochemistry;

identify a bond center of the first candidate chemical structure;

analyze a plurality of sets of candidate bonds in relation to the first candidate chemical structure, wherein

each set of candidate bonds of the plurality of sets of candidate bonds is representative of a respective tetrahedral center, and

analyzing the plurality of sets of candidate bonds comprises identifying a matching stereo chemical configuration to the bond center of the first candidate chemical structure; and

assign, to the first candidate chemical structure, the matching stereo chemical configuration.

19. The computer-readable medium of claim 14, wherein a second filter of the one or more filters is configured to eliminate candidate chemical structures based at least in part on a determination that the given candidate chemical structure has a formula weight less than a minimum formula weight.