INTERNATIONAL BUSINESS MACHINES CORPORATION

Patent Trials and Appeals Board

Aug 2, 2021

2020003402 (P.T.A.B. Aug. 2, 2021)

UNITED STATES PATENT AND TRADEMARK OFFICE
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
14/279,617 05/16/2014 Qi He ARC920130135US1 1086
48915 7590 08/02/2021
CANTOR COLBURN LLP-IBM YORKTOWN
20 Church Street
22nd Floor
Hartford, CT 06103
EXAMINER
SMITH, BRIAN M
ART UNIT PAPER NUMBER
2122
NOTIFICATION DATE DELIVERY MODE
08/02/2021 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
usptopatentmail@cantorcolburn.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte QI HE, MING JI, and W. SCOTT SPANGLER
Appeal 2020-003402
Application 14/279,617
Technology Center 2100
Before ALLEN R. MacDONALD, IRVIN E. BRANCH, and
PHILLIP A. BENNETT, Administrative Patent Judges.
BENNETT, Administrative Patent Judge.
DECISION ON APPEAL
STATEMENT OF THE CASE
Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the
Examiner’s decision to reject claims 1, 4–11, and 14–18. We have
jurisdiction under 35 U.S.C. § 6(b).
We affirm.

1 “Appellant” refers to “applicant” as defined in 37 C.F.R. § 1.42(a).
Appellant identifies the real party in interest as International Business
Machines Corporation. Appeal Br. 1.
Appeal 2020-003402
Application 14/279,617

2
CLAIMED SUBJECT MATTER
The claims are directed to discovering entity relationships. Claim 1,
reproduced below, is illustrative of the claimed subject matter:
1. A computer-implemented method for discovering entity
relationships comprising:
receiving data associated with a co-occurrence graph
among heterogeneous entities, said co-occurrence graph
comprising a plurality of nodes, each node representing an entity
in said heterogeneous entities, wherein any two nodes in said co-
occurrence graph are connected by an edge when they co-occur
in a knowledge base, with a weight of said edge being equal to
the number of times entities associated with said two nodes co-
occur in said knowledge base, said data associated with said co-
occurrence graph is built from a plurality of the following: US
Food and Drug Administration approved drugs, diseases
extracted from human disease ontology, chemical compounds
with drug indications from a first database, terms in a tree used
as a metadata to index documents in a second database, and
targets made up of four sub-types: tissue, cell-line, protein, and
organism;
receiving a query comprising a query entity name and a
target entity type, the query entity name comprising a disease
name and the target entity type comprising a "Drug";
receiving a plurality of meta paths to constrain co-
occurrence scope of any two heterogeneous entities in said co-
occurrence graph, the received meta paths specifying a complete
path from a source to a destination in the co-occurrence graph,
each meta path m of length l in the plurality of meta paths given
by: , where, for K types of predefined
entities E1, ..., EK, xy [1, K], y [1, l], and where
defines a composite correlation between two entity types
;

Appeal 2020-003402
Application 14/279,617

3
generating a subgraph of said co-occurrence graph with
path instances of said received meta paths;
identifying a plurality of entities from said subgraph as
newly discovered entity relationships; and
outputting entities from said subgraph as newly discovered
entity relationships, the output entities belonging to said target
entity type and having relevance with said query entity name
based on a probabilistic context-aware relevance model, where
said relevance is constrained by said received meta paths.
Appeal Br. 13 (Claims Appendix).
REFERENCES2
The prior art relied upon by the Examiner is:
Name Reference Date
Busa US 2002/0004792 A1 Jan. 10, 2002
Chen et al., Assessing Drug Target Association Using Semantic Linked
Data, PLOS COMPUTATIONAL BIO 8(7): e1002574. doi:10.1371 (July 5, 2012)
Shi et al., Relevance Search in Heterogeneous Networks, EDBT 2012,
(March 26–30, 2012)
Orphanet, the Portal for rare diseases and orphan drugs,
http://orpha.net/consor/cgi-bin/index.php, archived at web.archive.org on
(Feb. 12, 2014)
Gramatica et al., Graph Theory Enables Drug Repurposing - How a
Mathematical Model Can Drive the Discovery of Hidden Mechanisms of
Action, PLOS ONE 9(1): e84912. doi:10.1371 (January 9, 2014)

REJECTIONS
Claims 1, 5, 6, and 9 stand rejected under 35 U.S.C. § 103 as being
unpatentable over Gramatica, Shi, and Orphanet. Final Act. 3–9.

2 Citations to the references are to the first named inventor/author only.
Appeal 2020-003402
Application 14/279,617

4
Claim 4 stands rejected under 35 U.S.C. § 103 as being unpatentable
over Gramatica, Shi, Orphanet, and Chen. Final Act. 9–10.
Claims 7 and 8 stand rejected under 35 U.S.C. § 103 as being
unpatentable over Gramatica, Shi, Orphanet, and Busa. Final Act. 10–11.
Claims 10, 11, 15, and 16 stand rejected under 35 U.S.C. § 103 as
being unpatentable over Gramatica and Shi. Final Act. 11–17.
Claim 14 stands rejected under 35 U.S.C. § 103 as being unpatentable
over Gramatica, Shi, and Chen. Final Act. 17–18.
Claims 17 and 18 stand rejected under 35 U.S.C. § 103 as being
unpatentable over Gramatica, Shi, and Busa. Final Act. 18–19.
ISSUE
Has the Examiner erred in finding Gramatica and Shi teach or suggest
the disputed limitation:
receiving a plurality of meta paths to constrain co-occurrence
scope of any two heterogeneous entities in said co-occurrence
graph, the received meta paths specifying a complete path from
a source to a destination in the co-occurrence graph, each meta
path m of length l m the plurality of meta paths given by:
, where, for K types of predefined entities
E1, ..., EK, xy [1, K], y [1, l], and where defines a
composite correlation between two entity types ;
as recited in claim 1?
ANALYSIS
We have reviewed the Examiner's rejections in light of Appellant's
arguments set forth in the Appeal Brief.3 We are not persuaded by

3 No Reply Brief was filed.
Appeal 2020-003402
Application 14/279,617

5
Appellant's arguments. We adopt as our own: (1) the findings and reasons
set forth by the Examiner in the action from which this appeal is taken (Final
Act. 2–19) and (2) the findings, reasons, and explanations set forth by the
Examiner in the Examiner's Answer in response to Appellant’s Brief
(Ans. 2-5) and concur with the conclusions reached by the Examiner. We
highlight the following for emphasis.
In rejecting claim 1, the Examiner finds that Gramatica teaches the
disputed limitation (Final Act. 5–6 (citing Gramatica p.3, first column, first
paragraph)), except for “the received meta paths specifying a complete path
from a source to a destination in the co-occurrence graph” (Final Act. 7).
(“The meta paths of Gramatica consist of a single link between types of
entity nodes, and thus Gramatica does not teach the pre-specified meta paths
specifying a complete path from a source to a destination in the co-
occurrence graph.”). The Examiner relies on Shi for specifying the complete
path. (Final Act. 7, emphasis omitted (citing Shi p.4, first column, second
paragraph)). The Examiner explains:
Shi, like Gramatica, teaches a relevance model for entities in a
heterogeneous graph, where entities are proscribed by pre-
determined meta paths. (Shi, pg. 4, 1st column, 2nd paragraph,
'Relevance path'). Further, the relevance paths/meta paths of Shi
denote a complete path from a source to a destination (Shi, pg. 4,
[1]st column, last paragraph, “Given a relevance path between
two objects,” Shi computes a relevance between the two objects
as HeteSim) and the meta paths of Shi further fit the claimed
definition, specifying entity types along the path (Shi, pg. 4, 1st
column, 3rd paragraph, “For simplicity, we can also use type
names denoting the relevance path if there are no multiple
relations between the same pair of types”).
Final Act. 7 (emphasis omitted).
Appeal 2020-003402
Application 14/279,617

6
Appellant argues that the references are deficient. Specifically,
Appellant offers agreement with the Examiner that Gramatica does not teach
the disputed limitation, and “respectfully disagrees with the Examiner’s
contention that these features are shown in the secondary reference, i.e.,
Shi.” Appeal Br. 9. Appellant asserts that Shi does not teach that meta
paths are received, nor does Shi teach the received meta paths are used to
“constrain co-occurrence scope of any two heterogeneous entities in said co-
occurrence graph.” Appeal Br. 9–10.
In the Answer, the Examiner responds at length to Appellant’s
arguments. With respect to Appellant’s assertion that the Examiner found
Gramatica fails to disclose the disputed limitation, the Examiner reiterates
that Gramatica teaches most of the disputed limitation, and that “Gramatica
only fails to teach the received meta paths specifying a complete path from a
source to a destination in the co-occurrence graph.” Ans. 3–4 (emphasis
omitted). The Examiner provides a detailed explanation for how Shi’s
teachings would have made it obvious to modify Gramatica noting that “the
complete linked MoA corresponding to peptide-cell-receptor-process-
disease, while never specifically described as such in Gramatica,
corresponds to a relevance path of Shi.” Ans. 5 (emphasis omitted). The
Examiner thus determines that “describing the allowable links of Gramatica
as such a complete relevance path, as does Shi, precisely teaches the meta
paths of the claimed invention.” Ans. 5 (emphasis omitted).
The Examiner further addresses Appellant’s argument that Shi fails to
teach that meta paths are received. Specifically, the Examiner notes that
Gramatica teaches the “receiving” of the meta paths. Ans. 5. The Examiner
further notes that Gramatica also teaches that the paths be used to “constrain
Appeal 2020-003402
Application 14/279,617

7
the co-occurrence scope of any two heterogeneous entities” because
Gramatica teaches that “we consider specific interactions (links) among
nodes, filtering out unwanted information ... thus only links in the form cell
receptor-process or cell receptor-protein are allowed.” Ans. 5 (emphasis
omitted) (citing Gramatica p.3, first column).
Appellant did not file a Reply Brief to address the detailed
explanations and findings set forth in the Answer. As such, the Examiner’s
analysis, which we find reasonable, stands unchallenged in this record.
Accordingly, Appellant has not persuaded us the Examiner erred in rejecting
claim 1, and we sustain its rejection under § 103.
Remaining Claims
Appellant presents no separate arguments for patentability of any
other claims. Accordingly, we sustain the Examiner’s rejections of these
claims for the reasons stated with respect to the independent claims from
which they depend. See 37 C.F.R. § 41.37(c)(1)(iv).
CONCLUSION
We affirm the Examiner’s decision to reject the claims.

Appeal 2020-003402
Application 14/279,617

8
DECISION SUMMARY
Claims
Rejected
35 U.S.C.
§
Reference(s)/Basis Affirmed Reversed
1, 5, 6, 9 103 Gramatica, Shi,
Orphanet
1, 5, 6, 9
4 103 Gramatica, Shi,
Orphanet, Chen
4
7, 8 103 Gramatica, Shi,
Orphanet, Busa
7, 8
10, 11, 15,
16
103 Gramatica, Shi 10, 11, 15,
16

14 103 Gramatica, Shi,
Chen
14
17, 18 103 Gramatica, Shi,
Busa
17, 18
Overall
Outcome
1, 4–11, 14–
18

TIME PERIOD FOR RESPONSE
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R.
§ 1.136(a)(1)(iv).
AFFIRMED