Bayesian regression models outperform partial least squares methods for predicting milk components and technological properties using infrared spectral data

The aim of this study was to assess the performance of Bayesian models commonly used for genomic selection to predict "difficult-to-predict" dairy traits, such as milk fatty acid (FA) expressed as percentage of total fatty acids, and technological properties, such as fresh cheese yield and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of dairy science Jg. 98; H. 11; S. 8133
Hauptverfasser: Ferragina, A, de los Campos, G, Vazquez, A I, Cecchinato, A, Bittante, G
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.11.2015
Schlagworte:
ISSN:1525-3198, 1525-3198
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The aim of this study was to assess the performance of Bayesian models commonly used for genomic selection to predict "difficult-to-predict" dairy traits, such as milk fatty acid (FA) expressed as percentage of total fatty acids, and technological properties, such as fresh cheese yield and protein recovery, using Fourier-transform infrared (FTIR) spectral data. Our main hypothesis was that Bayesian models that can estimate shrinkage and perform variable selection may improve our ability to predict FA traits and technological traits above and beyond what can be achieved using the current calibration models (e.g., partial least squares, PLS). To this end, we assessed a series of Bayesian methods and compared their prediction performance with that of PLS. The comparison between models was done using the same sets of data (i.e., same samples, same variability, same spectral treatment) for each trait. Data consisted of 1,264 individual milk samples collected from Brown Swiss cows for which gas chromatographic FA composition, milk coagulation properties, and cheese-yield traits were available. For each sample, 2 spectra in the infrared region from 5,011 to 925 cm(-1) were available and averaged before data analysis. Three Bayesian models: Bayesian ridge regression (Bayes RR), Bayes A, and Bayes B, and 2 reference models: PLS and modified PLS (MPLS) procedures, were used to calibrate equations for each of the traits. The Bayesian models used were implemented in the R package BGLR (http://cran.r-project.org/web/packages/BGLR/index.html), whereas the PLS and MPLS were those implemented in the WinISI II software (Infrasoft International LLC, State College, PA). Prediction accuracy was estimated for each trait and model using 25 replicates of a training-testing validation procedure. Compared with PLS, which is currently the most widely used calibration method, MPLS and the 3 Bayesian methods showed significantly greater prediction accuracy. Accuracy increased in moving from calibration to external validation methods, and in moving from PLS and MPLS to Bayesian methods, particularly Bayes A and Bayes B. The maximum R(2) value of validation was obtained with Bayes B and Bayes A. For the FA, C10:0 (% of each FA on total FA basis) had the highest R(2) (0.75, achieved with Bayes A and Bayes B), and among the technological traits, fresh cheese yield R(2) of 0.82 (achieved with Bayes B). These 2 methods have proven to be useful instruments in shrinking and selecting very informative wavelengths and inferring the structure and functions of the analyzed traits. We conclude that Bayesian models are powerful tools for deriving calibration equations, and, importantly, these equations can be easily developed using existing open-source software. As part of our study, we provide scripts based on the open source R software BGLR, which can be used to train customized prediction equations for other traits or populations.
AbstractList The aim of this study was to assess the performance of Bayesian models commonly used for genomic selection to predict "difficult-to-predict" dairy traits, such as milk fatty acid (FA) expressed as percentage of total fatty acids, and technological properties, such as fresh cheese yield and protein recovery, using Fourier-transform infrared (FTIR) spectral data. Our main hypothesis was that Bayesian models that can estimate shrinkage and perform variable selection may improve our ability to predict FA traits and technological traits above and beyond what can be achieved using the current calibration models (e.g., partial least squares, PLS). To this end, we assessed a series of Bayesian methods and compared their prediction performance with that of PLS. The comparison between models was done using the same sets of data (i.e., same samples, same variability, same spectral treatment) for each trait. Data consisted of 1,264 individual milk samples collected from Brown Swiss cows for which gas chromatographic FA composition, milk coagulation properties, and cheese-yield traits were available. For each sample, 2 spectra in the infrared region from 5,011 to 925 cm(-1) were available and averaged before data analysis. Three Bayesian models: Bayesian ridge regression (Bayes RR), Bayes A, and Bayes B, and 2 reference models: PLS and modified PLS (MPLS) procedures, were used to calibrate equations for each of the traits. The Bayesian models used were implemented in the R package BGLR (http://cran.r-project.org/web/packages/BGLR/index.html), whereas the PLS and MPLS were those implemented in the WinISI II software (Infrasoft International LLC, State College, PA). Prediction accuracy was estimated for each trait and model using 25 replicates of a training-testing validation procedure. Compared with PLS, which is currently the most widely used calibration method, MPLS and the 3 Bayesian methods showed significantly greater prediction accuracy. Accuracy increased in moving from calibration to external validation methods, and in moving from PLS and MPLS to Bayesian methods, particularly Bayes A and Bayes B. The maximum R(2) value of validation was obtained with Bayes B and Bayes A. For the FA, C10:0 (% of each FA on total FA basis) had the highest R(2) (0.75, achieved with Bayes A and Bayes B), and among the technological traits, fresh cheese yield R(2) of 0.82 (achieved with Bayes B). These 2 methods have proven to be useful instruments in shrinking and selecting very informative wavelengths and inferring the structure and functions of the analyzed traits. We conclude that Bayesian models are powerful tools for deriving calibration equations, and, importantly, these equations can be easily developed using existing open-source software. As part of our study, we provide scripts based on the open source R software BGLR, which can be used to train customized prediction equations for other traits or populations.The aim of this study was to assess the performance of Bayesian models commonly used for genomic selection to predict "difficult-to-predict" dairy traits, such as milk fatty acid (FA) expressed as percentage of total fatty acids, and technological properties, such as fresh cheese yield and protein recovery, using Fourier-transform infrared (FTIR) spectral data. Our main hypothesis was that Bayesian models that can estimate shrinkage and perform variable selection may improve our ability to predict FA traits and technological traits above and beyond what can be achieved using the current calibration models (e.g., partial least squares, PLS). To this end, we assessed a series of Bayesian methods and compared their prediction performance with that of PLS. The comparison between models was done using the same sets of data (i.e., same samples, same variability, same spectral treatment) for each trait. Data consisted of 1,264 individual milk samples collected from Brown Swiss cows for which gas chromatographic FA composition, milk coagulation properties, and cheese-yield traits were available. For each sample, 2 spectra in the infrared region from 5,011 to 925 cm(-1) were available and averaged before data analysis. Three Bayesian models: Bayesian ridge regression (Bayes RR), Bayes A, and Bayes B, and 2 reference models: PLS and modified PLS (MPLS) procedures, were used to calibrate equations for each of the traits. The Bayesian models used were implemented in the R package BGLR (http://cran.r-project.org/web/packages/BGLR/index.html), whereas the PLS and MPLS were those implemented in the WinISI II software (Infrasoft International LLC, State College, PA). Prediction accuracy was estimated for each trait and model using 25 replicates of a training-testing validation procedure. Compared with PLS, which is currently the most widely used calibration method, MPLS and the 3 Bayesian methods showed significantly greater prediction accuracy. Accuracy increased in moving from calibration to external validation methods, and in moving from PLS and MPLS to Bayesian methods, particularly Bayes A and Bayes B. The maximum R(2) value of validation was obtained with Bayes B and Bayes A. For the FA, C10:0 (% of each FA on total FA basis) had the highest R(2) (0.75, achieved with Bayes A and Bayes B), and among the technological traits, fresh cheese yield R(2) of 0.82 (achieved with Bayes B). These 2 methods have proven to be useful instruments in shrinking and selecting very informative wavelengths and inferring the structure and functions of the analyzed traits. We conclude that Bayesian models are powerful tools for deriving calibration equations, and, importantly, these equations can be easily developed using existing open-source software. As part of our study, we provide scripts based on the open source R software BGLR, which can be used to train customized prediction equations for other traits or populations.
The aim of this study was to assess the performance of Bayesian models commonly used for genomic selection to predict "difficult-to-predict" dairy traits, such as milk fatty acid (FA) expressed as percentage of total fatty acids, and technological properties, such as fresh cheese yield and protein recovery, using Fourier-transform infrared (FTIR) spectral data. Our main hypothesis was that Bayesian models that can estimate shrinkage and perform variable selection may improve our ability to predict FA traits and technological traits above and beyond what can be achieved using the current calibration models (e.g., partial least squares, PLS). To this end, we assessed a series of Bayesian methods and compared their prediction performance with that of PLS. The comparison between models was done using the same sets of data (i.e., same samples, same variability, same spectral treatment) for each trait. Data consisted of 1,264 individual milk samples collected from Brown Swiss cows for which gas chromatographic FA composition, milk coagulation properties, and cheese-yield traits were available. For each sample, 2 spectra in the infrared region from 5,011 to 925 cm(-1) were available and averaged before data analysis. Three Bayesian models: Bayesian ridge regression (Bayes RR), Bayes A, and Bayes B, and 2 reference models: PLS and modified PLS (MPLS) procedures, were used to calibrate equations for each of the traits. The Bayesian models used were implemented in the R package BGLR (http://cran.r-project.org/web/packages/BGLR/index.html), whereas the PLS and MPLS were those implemented in the WinISI II software (Infrasoft International LLC, State College, PA). Prediction accuracy was estimated for each trait and model using 25 replicates of a training-testing validation procedure. Compared with PLS, which is currently the most widely used calibration method, MPLS and the 3 Bayesian methods showed significantly greater prediction accuracy. Accuracy increased in moving from calibration to external validation methods, and in moving from PLS and MPLS to Bayesian methods, particularly Bayes A and Bayes B. The maximum R(2) value of validation was obtained with Bayes B and Bayes A. For the FA, C10:0 (% of each FA on total FA basis) had the highest R(2) (0.75, achieved with Bayes A and Bayes B), and among the technological traits, fresh cheese yield R(2) of 0.82 (achieved with Bayes B). These 2 methods have proven to be useful instruments in shrinking and selecting very informative wavelengths and inferring the structure and functions of the analyzed traits. We conclude that Bayesian models are powerful tools for deriving calibration equations, and, importantly, these equations can be easily developed using existing open-source software. As part of our study, we provide scripts based on the open source R software BGLR, which can be used to train customized prediction equations for other traits or populations.
Author Ferragina, A
de los Campos, G
Bittante, G
Vazquez, A I
Cecchinato, A
Author_xml – sequence: 1
  givenname: A
  surname: Ferragina
  fullname: Ferragina, A
  organization: Department of Agronomy, Food, Natural Resources, Animals and Environment (DAFNAE), University of Padova, Viale dell'Università 16, 35020 Legnaro, Italy
– sequence: 2
  givenname: G
  surname: de los Campos
  fullname: de los Campos, G
  organization: Epidemiology and Biostatistics Department, Michigan State University, East Lansing 48824; Department of Statistics and Probability, Michigan State University, East Lansing 48824
– sequence: 3
  givenname: A I
  surname: Vazquez
  fullname: Vazquez, A I
  organization: Epidemiology and Biostatistics Department, Michigan State University, East Lansing 48824
– sequence: 4
  givenname: A
  surname: Cecchinato
  fullname: Cecchinato, A
  email: alessio.cecchinato@unipd.it
  organization: Department of Agronomy, Food, Natural Resources, Animals and Environment (DAFNAE), University of Padova, Viale dell'Università 16, 35020 Legnaro, Italy. Electronic address: alessio.cecchinato@unipd.it
– sequence: 5
  givenname: G
  surname: Bittante
  fullname: Bittante, G
  organization: Department of Agronomy, Food, Natural Resources, Animals and Environment (DAFNAE), University of Padova, Viale dell'Università 16, 35020 Legnaro, Italy
BackLink https://www.ncbi.nlm.nih.gov/pubmed/26387015$$D View this record in MEDLINE/PubMed
BookMark eNpNkLtOAzEQRS0EghAoaZFLmgU_9pUSEC8JiQbqaGLPJg679sbjLfgXPhYjQKK6U5w5urrHbN8Hj4ydSXGpZd1ebS1dKiHLYiFLvcdmslJVoeWi3f93H7Fjoq0QSipRHbIjVeu2EbKasc8b-EBy4HnEdUQiFzwfgsWeeJjSiLELceAjxOSg5z0CJU67CTLLB0ybYIlnhI8RrTPJ-TUfXP_OTRjG3NQn4uAtT2g2PvRh7UzWjDFkc3LZMdH3i_NdzErLaUSTYkYsJDhhBx30hKe_OWdv93evt4_F88vD0-31c2HKuk2FtnUHWKumNgsArNRKVQKghLYrW6NKRKUtGJUZ3bZiIaBRAhurjdGA2qg5u_jx5l67CSktB0cG-x48homWslG6qeq6KTN6_otOqwHtcoxugPix_FtUfQFNDH-o
CitedBy_id crossref_primary_10_3389_fnut_2024_1327301
crossref_primary_10_1002_tpg2_70050
crossref_primary_10_3168_jds_2024_25970
crossref_primary_10_3168_jds_2021_20640
crossref_primary_10_3389_fgene_2020_563393
crossref_primary_10_1016_j_compag_2025_110889
crossref_primary_10_1186_s40104_020_00445_2
crossref_primary_10_3390_ani14060900
crossref_primary_10_3389_fvets_2022_1012251
crossref_primary_10_3168_jds_2015_9596
crossref_primary_10_1016_j_scitotenv_2018_09_101
crossref_primary_10_3168_jds_2021_21661
crossref_primary_10_3389_fpls_2022_871943
crossref_primary_10_3390_ani13040763
crossref_primary_10_3168_jds_2016_11662
crossref_primary_10_3168_jds_2020_19031
crossref_primary_10_1016_j_foodchem_2019_125480
crossref_primary_10_1029_2021GB007160
crossref_primary_10_1186_s12711_021_00620_7
crossref_primary_10_3168_jds_2015_9803
crossref_primary_10_3168_jds_2023_23772
crossref_primary_10_3390_foods12244517
crossref_primary_10_2135_cropsci2017_01_0007
crossref_primary_10_3168_jds_2014_9146
crossref_primary_10_3168_jds_2018_15109
crossref_primary_10_1371_journal_pone_0236853
crossref_primary_10_3390_app142310916
crossref_primary_10_3389_fgene_2020_00923
crossref_primary_10_1186_s13007_018_0314_7
crossref_primary_10_3390_ani10091654
crossref_primary_10_1016_j_foodchem_2024_142631
crossref_primary_10_3168_jds_2017_14111
crossref_primary_10_3168_jds_2016_12226
crossref_primary_10_3168_jds_2020_19861
crossref_primary_10_1016_j_foodchem_2022_134403
crossref_primary_10_3168_jds_2018_14464
crossref_primary_10_3389_fanim_2022_889797
crossref_primary_10_3168_jds_2021_20267
crossref_primary_10_1038_s41598_020_65011_2
crossref_primary_10_3168_jds_2019_16770
crossref_primary_10_3390_molecules28145379
crossref_primary_10_3390_foods10020450
crossref_primary_10_3168_jds_2021_20395
crossref_primary_10_3390_foods14060969
crossref_primary_10_1017_S1751731117001471
crossref_primary_10_3168_jds_2017_13874
crossref_primary_10_1111_1471_0307_12859
crossref_primary_10_3168_jds_2017_14289
crossref_primary_10_3168_jds_2024_25269
crossref_primary_10_1186_s13007_016_0154_2
crossref_primary_10_1016_j_foodchem_2024_142465
crossref_primary_10_3390_ani9090663
crossref_primary_10_1039_D4AY02250E
crossref_primary_10_3168_jds_2020_18321
crossref_primary_10_1080_1828051X_2022_2158953
crossref_primary_10_1038_s41598_020_64575_3
crossref_primary_10_3168_jds_2015_9629
crossref_primary_10_3168_jds_2021_20499
crossref_primary_10_3168_jds_2019_16320
crossref_primary_10_1016_j_meatsci_2021_108518
crossref_primary_10_3168_jds_2023_23349
crossref_primary_10_3168_jds_2015_10078
crossref_primary_10_3390_ani10020336
crossref_primary_10_1038_s41598_021_93457_5
crossref_primary_10_3168_jds_2017_13647
crossref_primary_10_1016_j_meatsci_2019_108017
crossref_primary_10_3168_jds_2021_21079
crossref_primary_10_3168_jds_2020_19491
crossref_primary_10_3168_jds_2024_24701
crossref_primary_10_1186_s40104_021_00555_5
crossref_primary_10_3168_jds_2016_11199
crossref_primary_10_3168_jds_2016_12203
crossref_primary_10_3168_jds_2023_23827
crossref_primary_10_3390_pr13051320
ContentType Journal Article
Copyright Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.3168/jds.2014-9143
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Agriculture
EISSN 1525-3198
ExternalDocumentID 26387015
Genre Research Support, U.S. Gov't, Non-P.H.S
Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NIGMS NIH HHS
  grantid: R01GM101219
– fundername: NIDDK NIH HHS
  grantid: 7-R01-DK-062148-10-S1
– fundername: NIDDK NIH HHS
  grantid: R01 DK062148
– fundername: NIGMS NIH HHS
  grantid: R01 GM101219
– fundername: NIGMS NIH HHS
  grantid: R01 GM099992
– fundername: NIGMS NIH HHS
  grantid: R01GM09992
GroupedDBID ---
--K
-~X
.GJ
0R~
186
18M
1B1
29K
2WC
36B
4.4
457
4G.
53G
5GY
5VS
7-5
7X2
7X7
7XC
88E
8FE
8FG
8FH
8FI
8FJ
8FW
8R4
8R5
8VB
AAEDT
AAEDW
AAFWJ
AAHBH
AALRI
AAQFI
AAQXK
AAWRB
AAXUO
AAYWO
ABCQX
ABJCF
ABUWG
ABWVN
ACGFO
ACGFS
ACIWK
ACRPL
ACVFH
ADBBV
ADCNI
ADMHG
ADMUD
ADNMO
ADVLN
AEGXH
AENEX
AEUPX
AEUYN
AFJKZ
AFKRA
AFPKN
AFPUW
AFRAH
AFTJW
AGQPQ
AHMBA
AI.
AIAGR
AIGII
AITUG
AKBMS
AKRWK
AKYEP
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
APXCP
ASPBG
ATCPS
AVWKF
AZFZN
BELOY
BENPR
BGLVJ
BHPHI
BPHCQ
BVXVI
C1A
CCPQU
CGR
CS3
CUY
CVF
D-I
DU5
E3Z
EBS
ECM
EIF
EJD
F5P
FDB
FEDTE
FGOYB
FYUFA
GBLVA
GROUPED_DOAJ
GX1
HCIFZ
HMCUK
HVGLF
HZ~
K1G
L6V
L7B
M0K
M1P
M41
M7S
N9A
NHB
NPM
O9-
OK1
P2P
PATMY
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
PQQKQ
PROAC
PSQYO
PTHSS
PYCSY
Q2X
QII
QWB
R2-
ROL
RWL
S0X
SEL
SES
SSZ
TAE
TDS
TWZ
U5U
UHB
UKHRP
VH1
WOQ
XH2
XOL
ZGI
ZL0
ZXP
~KM
7X8
ID FETCH-LOGICAL-c468t-3d6fae6276c9aae52b250aa4a8f48c24ee23dac2ae6388090a720e7d3cc3ae3c2
IEDL.DBID 7X8
ISICitedReferencesCount 80
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000363495400066&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1525-3198
IngestDate Thu Oct 02 08:28:45 EDT 2025
Mon Jul 21 05:59:23 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 11
Keywords fatty acid
cheese yield
milk trait
Bayesian method
infrared spectroscopy
Language English
License Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c468t-3d6fae6276c9aae52b250aa4a8f48c24ee23dac2ae6388090a720e7d3cc3ae3c2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink http://www.journalofdairyscience.org/article/S0022030215006645/pdf
PMID 26387015
PQID 1723756674
PQPubID 23479
ParticipantIDs proquest_miscellaneous_1723756674
pubmed_primary_26387015
PublicationCentury 2000
PublicationDate 2015-11-01
PublicationDateYYYYMMDD 2015-11-01
PublicationDate_xml – month: 11
  year: 2015
  text: 2015-11-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of dairy science
PublicationTitleAlternate J Dairy Sci
PublicationYear 2015
References 24094531 - J Dairy Sci. 2013;96(12):7952-65
23831101 - J Dairy Sci. 2013 Sep;96(9):5933-42
16537952 - J Dairy Sci. 2006 Apr;89(4):1189-94
23021752 - J Dairy Sci. 2012 Dec;95(12):6843-70
19762848 - J Dairy Sci. 2009 Oct;92(10):5304-13
25108864 - J Dairy Sci. 2014 Oct;97(10):6560-72
21787950 - J Dairy Sci. 2011 Aug;94(8):4152-63
21948610 - J Anim Sci. 2012 Feb;90(2):429-38
17881671 - J Dairy Sci. 2007 Oct;90(10):4499-512
20804166 - Chem Rev. 2010 Oct 13;110(10):6144-68
19923625 - J Dairy Sci. 2009 Dec;92(12):6202-9
23141823 - J Dairy Sci. 2013 Jan;96(1):50-62
20338453 - J Dairy Sci. 2010 Apr;93(4):1743-8
22999289 - J Dairy Sci. 2012 Nov;95(11):6362-71
23031721 - Animal. 2013 Feb;7(2):348-54
25958274 - J Dairy Sci. 2015 Jul;98(7):4914-27
24440251 - J Dairy Sci. 2014 Mar;97(3):1171-86
10764056 - J Anim Sci. 2000 Mar;78(3):515-22
22440358 - Animal. 2011 Aug;5(10):1653-8
24268398 - J Dairy Sci. 2014;97(1):17-35
23810593 - J Dairy Sci. 2013 Sep;96(9):5991-6006
16899705 - J Dairy Sci. 2006 Sep;89(9):3690-5
11290733 - Genetics. 2001 Apr;157(4):1819-29
19762790 - J Dairy Sci. 2009 Oct;92(10):4745-55
21426953 - J Dairy Sci. 2011 Apr;94(4):1657-67
23636739 - Genetics. 2013 Jul;194(3):573-96
22745228 - Genetics. 2013 Feb;193(2):327-45
24094539 - J Dairy Sci. 2013;96(12):7966-79
23708544 - Talanta. 2013 Aug 15;112:101-10
18292278 - J Dairy Sci. 2008 Mar;91(3):1209-13
24094534 - J Dairy Sci. 2013;96(12):7980-90
25009151 - Genetics. 2014 Oct;198(2):483-95
22999290 - J Dairy Sci. 2012 Nov;95(11):6806-19
20338450 - J Dairy Sci. 2010 Apr;93(4):1722-8
21787956 - J Dairy Sci. 2011 Aug;94(8):4205-13
19762788 - J Dairy Sci. 2009 Oct;92 (10 ):4730-7
20855022 - J Dairy Sci. 2010 Oct;93(10):4872-82
22192224 - J Dairy Sci. 2012 Jan;95(1):450-4
18255558 - IEEE Trans Neural Netw. 1996;7(1):56-72
References_xml – reference: 24268398 - J Dairy Sci. 2014;97(1):17-35
– reference: 18292278 - J Dairy Sci. 2008 Mar;91(3):1209-13
– reference: 22999289 - J Dairy Sci. 2012 Nov;95(11):6362-71
– reference: 20804166 - Chem Rev. 2010 Oct 13;110(10):6144-68
– reference: 19923625 - J Dairy Sci. 2009 Dec;92(12):6202-9
– reference: 22745228 - Genetics. 2013 Feb;193(2):327-45
– reference: 23636739 - Genetics. 2013 Jul;194(3):573-96
– reference: 23031721 - Animal. 2013 Feb;7(2):348-54
– reference: 23708544 - Talanta. 2013 Aug 15;112:101-10
– reference: 20338453 - J Dairy Sci. 2010 Apr;93(4):1743-8
– reference: 20338450 - J Dairy Sci. 2010 Apr;93(4):1722-8
– reference: 23831101 - J Dairy Sci. 2013 Sep;96(9):5933-42
– reference: 22440358 - Animal. 2011 Aug;5(10):1653-8
– reference: 24094534 - J Dairy Sci. 2013;96(12):7980-90
– reference: 25958274 - J Dairy Sci. 2015 Jul;98(7):4914-27
– reference: 24094539 - J Dairy Sci. 2013;96(12):7966-79
– reference: 22192224 - J Dairy Sci. 2012 Jan;95(1):450-4
– reference: 19762790 - J Dairy Sci. 2009 Oct;92(10):4745-55
– reference: 24094531 - J Dairy Sci. 2013;96(12):7952-65
– reference: 16537952 - J Dairy Sci. 2006 Apr;89(4):1189-94
– reference: 10764056 - J Anim Sci. 2000 Mar;78(3):515-22
– reference: 11290733 - Genetics. 2001 Apr;157(4):1819-29
– reference: 18255558 - IEEE Trans Neural Netw. 1996;7(1):56-72
– reference: 17881671 - J Dairy Sci. 2007 Oct;90(10):4499-512
– reference: 21948610 - J Anim Sci. 2012 Feb;90(2):429-38
– reference: 21787956 - J Dairy Sci. 2011 Aug;94(8):4205-13
– reference: 19762848 - J Dairy Sci. 2009 Oct;92(10):5304-13
– reference: 23021752 - J Dairy Sci. 2012 Dec;95(12):6843-70
– reference: 19762788 - J Dairy Sci. 2009 Oct;92 (10 ):4730-7
– reference: 25108864 - J Dairy Sci. 2014 Oct;97(10):6560-72
– reference: 21787950 - J Dairy Sci. 2011 Aug;94(8):4152-63
– reference: 25009151 - Genetics. 2014 Oct;198(2):483-95
– reference: 20855022 - J Dairy Sci. 2010 Oct;93(10):4872-82
– reference: 21426953 - J Dairy Sci. 2011 Apr;94(4):1657-67
– reference: 22999290 - J Dairy Sci. 2012 Nov;95(11):6806-19
– reference: 23810593 - J Dairy Sci. 2013 Sep;96(9):5991-6006
– reference: 24440251 - J Dairy Sci. 2014 Mar;97(3):1171-86
– reference: 16899705 - J Dairy Sci. 2006 Sep;89(9):3690-5
– reference: 23141823 - J Dairy Sci. 2013 Jan;96(1):50-62
SSID ssj0021205
Score 2.462328
Snippet The aim of this study was to assess the performance of Bayesian models commonly used for genomic selection to predict "difficult-to-predict" dairy traits, such...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 8133
SubjectTerms Animals
Bayes Theorem
Calibration
Cattle
Cheese - analysis
Fatty Acids - analysis
Female
Least-Squares Analysis
Milk - chemistry
Milk Proteins - analysis
Principal Component Analysis
Regression Analysis
Spectroscopy, Fourier Transform Infrared - veterinary
Title Bayesian regression models outperform partial least squares methods for predicting milk components and technological properties using infrared spectral data
URI https://www.ncbi.nlm.nih.gov/pubmed/26387015
https://www.proquest.com/docview/1723756674
Volume 98
WOSCitedRecordID wos000363495400066&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELaAMsDA-1FeMhJr1NZx43hCBVGxUHUAqVvk2pcKKEmatEj8F34sd0kKExISS6aLYzmfz6fzd_cxdmWpMqajnReOtfUkItgbgyIxM-tUDEYHYEuxCTUYhKORHtYJt6KmVS59YumoXWopR97Cg9ZXGHsoeZ3NPFKNotvVWkJjlTV8DGWI0qVG37cI6JVLCiNJ_KCv0WHVY5Okmlovjnp1dyRudirY-S26LE-Z_vZ_57fDtur4kvcqQOyyFUj22GZvktc9NmCffd6YD6DaSZ7DpKLBJrxUxCl4uphnVSkBzwhUONSU1H14MVtQpRKvFKcLjiY8y-mWh3jT_O15-sqJnp4mxMzgJnF8vszaEw7QOM2Iw41jENd-whHaObHfeVnsmaMJsVUP2FP_7vH23qtFGjwrg3Du-S6IDQRCBVYbA10xxqDKGGnCWIZWSADhO2MF2lDfGd02SrRBOd9a34BvxSFbS3Bux4ybIHCO8kZOdkgYTRsRyyBuuzbEGuKwyS6XSx_hJqCbDZNAuiiin8VvsqPq_0VZ1a0jEvhdhUHPyR_ePmUbCIpuVWt4xhoxugA4Z-v2ff5c5BcluvA5GD58AU5D4JI
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Bayesian+regression+models+outperform+partial+least+squares+methods+for+predicting+milk+components+and+technological+properties+using+infrared+spectral+data&rft.jtitle=Journal+of+dairy+science&rft.au=Ferragina%2C+A&rft.au=de+los+Campos%2C+G&rft.au=Vazquez%2C+A+I&rft.au=Cecchinato%2C+A&rft.date=2015-11-01&rft.issn=1525-3198&rft.eissn=1525-3198&rft.volume=98&rft.issue=11&rft.spage=8133&rft_id=info:doi/10.3168%2Fjds.2014-9143&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1525-3198&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1525-3198&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1525-3198&client=summon