Ex Parte Lightner et al

Patent Trial and Appeal Board

Feb 28, 2019

12780066 (P.T.A.B. Feb. 28, 2019)

UNITED STA TES p A TENT AND TRADEMARK OFFICE
APPLICATION NO. FILING DATE
12/780,066 05/14/2010
23377 7590 03/04/2019
Baker Hostetler
Cira Centre 12th Floor
2929 Arch Street
Philadelphia, PA 19104-2891
FIRST NAMED INVENTOR
Jonathan E. Lightner
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
ATTORNEY DOCKET NO. CONFIRMATION NO.
102003.000017/2268 9864
EXAMINER
BRUSCA, JOHNS
ART UNIT PAPER NUMBER
1631
NOTIFICATION DATE DELIVERY MODE
03/04/2019 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):
eofficemonitor@bakerlaw.com
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte JONATHAN E. LIGHTNER, FEDERICO VALVERDE, and
STEVEN L. WRIGHT
Appeal2018-000866
Application 12/780,066
Technology Center 1600
Before JEFFREY N. FREDMAN, DEBORAH KATZ, and JOHN G. NEW,
Administrative Patent Judges.
FREDMAN, Administrative Patent Judge.
DECISION ON APPEAL
This is an appeal 1,2 under 35 U.S.C. § 134(a) involving claims to
predicting characteristics of a plant based on spectral data. The Examiner
rejected the claims as directed to patent-ineligible subject matter and
obvious. We have jurisdiction under 35 U.S.C. § 6(b). We AFFIRM.
1 Appellants identify the Real Party in Interest as Pioneer Hi-Bred
International, Inc. (see Supp. App. Br. 1 ).
2 We have considered and herein refer to the Specification of May 14, 2010
("Spec."); Final Office Action of Feb. 10, 2017 ("Final Act."); Appeal Brief
of July 5, 2017 ("App. Br."); Examiner's Answer of Sep. 5, 2017 ("Ans.");
and Reply Brief of Nov. 1, 2017 ("Reply Br.").
Appeal2018-000866
Application 12/780,066
Statement of the Case
Background
"Remote sensing usually refers to the use of imaging sensor
technology. The imaging sensor can involve passive collection to detect
natural energy (e.g., radiation) that is emitted or reflected by the object or
surrounding area being observed" (Spec. ,r 77). "Application of remote
sensing data for plant breeding and plant advancement experiments has
centered on classical modeling relative to phenotypes of interest." (Spec.
,r 11 ).
"Classical" or "reverse" predictive modeling "starts with certain a
priori information and/or assumptions ( e.g., that a plant's spectrum taken at
a certain wavelength is indicative of the plant's yield because of a certain
reflective parameter of chlorophyll) and then goes back (i.e., 'reverses') and
builds a model based on the assumptions" (Spec. ,r 5). "[R]everse or
classical modeling requires the time and resources to come up with functions
relating inputs needed to make a prediction. The processes to identify those
functions can be laborious." (Spec. ,r 9). Also, "classical or reverse
modeling may not take into account, and may completely miss, important
factors involved in leaf chlorophyll concentration" (Spec. ,r 10).
"[T]he general inverse method is a different approach from classical
or reverse modeling approaches .... Multivariate analysis provides reliable
prediction of needed information at the right time for acceptable cost from
indirect observation measurements even despite selectivity problems,
interference, and mistakes" (Spec. ,r,r 177-178)
2
Appeal2018-000866
Application 12/780,066
The Claims
Claims 1-32 are on appeal. Independent claim 1 is representative and
reads as follows:
1. A method of estimating a plant characteristic, comprising:
a. using a computer processor, constructing a predictive
model for the plant characteristic,
the predictive model comprising a calibration constructed
from:
i. a first set of whole-plant spectroscopic
absorbance data from a first plant population, and
ii. a corresponding measured plant characteristic
data set from the first plant population, and,
the calibration being a multivariate relation between the
whole-plant spectroscopic absorbance data and the measured
plant characteristic data set, the multivariate relation
maximizing covariance between the first set of whole-plant
spectroscopic absorbance data and the measured plant
characteristic data set; and,
b. applying the predictive model to a second set of
whole-plant spectroscopic data from a second plant, a second
plant population, or both, so as to estimate the plant
characteristic in the second plant, the second plant population,
or both, and
c. selecting or removing the second plant for use in a
plant breeding program based on the second plant's estimated
plant characteristic.
3
Appeal2018-000866
Application 12/780,066
The Re} ections
A. The Examiner rejected claims 1-11 under 35 U.S.C. § I03(a) as
obvious over Jacquemoud, 3 Orr, 4 and Hansen5 (Final Act. 10-13).
B. The Examiner rejected claims 1, 12-15, 24, 25, and 29-31 under 35
U.S.C. § I03(a) as obvious over Jacquemoud, Orr, Hansen, and Stewart6
(Final Act. 13-15).
C. The Examiner rejected claims 1, 16-18, 24, 26-28, and 32 under 35
U.S.C. § I03(a) as obvious over Jacquemoud, Orr, Hansen, Stewart, and
Halfuill7 (Final Act. 15-17).
D. The Examiner rejected claims 19 and 21 under 35 U.S.C. § I03(a) as
obvious over Jacquemoud, Orr, Hansen, and Anser8 (Final Act. 17-18).
E. The Examiner rejected claims 22 and 23 under 35 U.S.C. § I03(a) as
obvious over Jacquemoud, Orr, Hansen, Anser, and Free 9 (Final Act. 18-
20).
3 Jacquemoud et al., Comparison of Four Radiative Transfer Models to
Stimulate Plant Canopies Reflectance: Direct and Inverse Mode, 74
REMOTE SENSING ENV'T 471-81 (2000)
4 Orr et al., US 5,764,819, issued June 9, 1998
5 Hansen et al., Reflectance measurement of canopy biomass and nitrogen
status in wheat crops using normalized difference vegetation indices and
partial least squares regression, 86 REMOTE SENSING ENV'T 542-53 (2003)
6 Stewart Jr., Monitoring the presence and expression of trans genes in living
plants, IO TRENDS IN PLANT SCI. 390-96 (2005)
7 Halfhill et al., Additive transgene expression and genetic introgression in
multiple green-fluorescent protein transgenic crop x weed hybrid
generations, 107 THEOR. APPL. GENET. 1553--40 (2003)
8 Anser et al., Drought stress and carbon uptake in an Amazon forest
measured with spaceborne imaging spectroscopy, 101 PROC. NAT'L ACAD.
SCI. 6039--44 (2004)
9 Free, US 2006/0190137 Al, published Aug. 24, 2006
4
Appeal2018-000866
Application 12/780,066
F. The Examiner rejected claim 20 under 35 U.S.C. § 103(a) as obvious
over Jacquemoud, Orr, Hansen, Anser, and Cheng 10 (Final Act. 20-21).
G. The Examiner rejected claims 1-32 under 35 U.S.C. § 101 as directed
to an abstract idea (Final Act. 5-9).
A-F. 35 U.S.C. § 103(a)
Because these rejections all rely on the combination of Jacquemoud,
Orr, and Hansen, and because Appellants do not separately argue limitations
in the dependent claims to which rejections B-F are addressed, we will
consider all of the rejections together.
The Examiner finds Jacquemoud teaches "a process of using
reflectance spectra measurements of plant populations to develop inverse
models for determining chlorophyll content and leaf area index" (Final Act.
11 ). The Examiner finds that Jacquemoud teaches "three validated inverse
models were applied to field spectroscopic measurements of soybean and
com plants" (Final Act. 12). The Examiner finds that Jacquemoud does "not
show selecting a second plant for breeding, measuring spectroscopic
absorbance data and a corresponding measured plant characteristic from the
same plant population, or partial least square regression analysis" (id.).
The Examiner finds Orr teaches "remote sensing to select plants for
breeding" (Final Act. 12). The Examiner finds Hansen teaches
"hyperspectral reflectance data was used to determine plant characteristics,
and that partial least squares regression improved the prediction of some
1° Cheng et al., A Novel Integrated PCA and FLD Method on Hyperspectral
Image Feature Extraction for Cucumber Chilling Damage Inspection, 4 7
AM. Soc. AGRIC. ENGINEERS 1313-20 (2004)
5
Appeal2018-000866
Application 12/780,066
characteristics" (id.). The Examiner finds Hansen teaches measuring canopy
reflectance using a spectrophometer and sampling the analyzed plants to
assay plant characteristics (see id.). The Examiner further finds that Hansen
teaches a "multivariate analysis of the plant spectra" using multiple
wavelengths (id.).
The Examiner determines it would have been:
obvious to modify the spectral data used by Jacquemoud [] to
include a partial least squares regression analysis because
Hansen [] shows that partial least squares regression analysis
produces equivalent or better results for a number of measured
plant characteristics, and to perform spectroscopic and plant
characteristic analysis on the same plants because Hansen []
shows developing a predictive model by use of those
techniques, and because it is obvious to use a known technique
to improve a similar method
(App. Br. 13).
The issue with respect to this rejection is: Does a preponderance of the
evidence of record support the Examiner's conclusion that claim 1 would
have been obvious?
Findings of Fact ("FF'')
1. J acquemoud teaches comparing existing models for remote
sensing in agriculture using model inversion by iterative optimization
( J acquemoud 4 71).
2. J acquemoud teaches the successful testing of" [ n] ew methods
to extract information from remote sensing data, such as multispectral
analysis, lookup tables, [] neural networks" and "model inversion by
iterative optimization techniques" (Jacquemoud 471--472).
6
Appeal2018-000866
Application 12/780,066
3. J acquemoud teaches that there are several critical elements for a
successful model, including: physical meaning, good fit, running time on a
given computer, and input parameters representing quantities measureable in
the field and interpretable in terms of plant biophysical characteristics (see
Jacquemoud 472).
4. Jacquemoud teaches testing the models against synthetic data
and field data, including remote sensing of 20 soybean and 20 com parcels
(see Jacquemoud 476-477 "About 20 soybean (Glycine max) and 20 com
(Zea mays L.) parcels were overflown by CASI on five different dates
covering the growing season, giving rise to an impressive data set, with 200
spectra available together with some canopy biophysical characteristics like
the green LAI or Cab· LAI and Cab.")
5. Orr teaches classifying plants by remote sensing and image
analysis technology for "evaluating plants and for selecting plants for a plant
breeding program" (Orr Abstract).
6. Orr teaches a classifying method including the steps of:
1. Simultaneously collect remote sensing data in the form of an
image on a first set of phenotypic traits from a group of plant
genotypes of the same species generally from relatively small
geographical areas, in particular, subplots of land in which
plants are growing ....
In some cases, one may wish to obtain information on the
environment (E) in which the plants are growing so that the
genotypic effects (G) can be separated from the total phenotype
(P) where (P=G+E).
2. Develop a descriptor by performing operations on the raw
data obtained by remote sensing.
7
Appeal2018-000866
Application 12/780,066
3. Use the descriptor to classify the plants; the descriptor may
also be used to predict values for a second set of commercially
valuable traits.
(Orr 5:21--40).
7. Hansen teaches "[h]yperspectral reflectance (438 to 884 nm)
data were recorded at five different growth stages of winter wheat in a field
experiment" (Hansen Abstract).
8. Hansen teaches that partial least squares regression ("PLS")
"may provide a useful exploratory and predictive tool when applied on
hyperspectral reflectance data" (Hansen Abstract).
9. Hansen teaches:
The objective of the present investigation was to compare the
predictive power of (i) models based on predefined short and
broadbands for a normalized difference type of index, (ii) the
best combination of narrow wavebands for a normalized
difference type of vegetation index, and (iii) partial least
squares regression (PLS) using all available wavebands
(Hansen 543).
10. Hansen teaches an experimental design that coordinated
measurements of canopy reflectance with an effective measurement range of
438-833 nm, with corresponding green plant samplings to measure green
biomass ("GBM"), nitrogen concentration ("Nconc'') and density ("N