Towards Enhancing Manufacturing Process Performance Through Multivariate Data Mining View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2011-07-25

AUTHORS

Salim Charaniya , Huong Le , Keri Mills , Kevin Johnson , George Karypis , Wei-Shou Hu

ABSTRACT

Several newly approved protein-based therapeutics in the past decade are manufactured in modern production plants with automated systems for process control and comprehensive data archival. The hundreds of process parameters and key output variables for several production batches in the vast historical databases provide a valuable resource to improve process understanding and robustness. Multivariate data analysis is a critical process analytical technology tool to unearth any hidden patterns within process trends and identify key parameters for enhancing process performance and product quality. Cell culture process data from more than hundred “trains” comprising production as well as inoculum bioreactors was investigated in this study. Each batch encompasses over 130 on-line and off-line temporal parameters. A maximum margin support vector algorithm was coupled with a kernel-based machine learning approach to develop multivariate predictive models for critical cell culture performance parameters. A differential weighting scheme was incorporated in the model to prioritize the process parameters with strong associations with process outcome and to identify key performance indicators at every stage of the production train. Model evaluations indicate that cell culture performance can be accurately predicted several days before harvest and downstream purification. Further, multiple parameters in the inoculum and early stages of production bioreactors were identified as precocious markers of the final process outcome. This process-data driven approach for knowledge discovery in manufacturing processes represents an important step towards implementing a real-time decision making scheme based on critical product and process traits. More... »

PAGES

285-294

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-94-007-0884-6_43

DOI

http://dx.doi.org/10.1007/978-94-007-0884-6_43

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1009357787


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Genentech, Inc., 92056, Oceanside, CA, USA", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Genentech, Inc., 92056, Oceanside, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Charaniya", 
        "givenName": "Salim", 
        "id": "sg:person.01052763265.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01052763265.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Chemical Engineering and Materials Science, University of Minnesota, 55455, Minneapolis, MN, USA", 
          "id": "http://www.grid.ac/institutes/grid.17635.36", 
          "name": [
            "Department of Chemical Engineering and Materials Science, University of Minnesota, 55455, Minneapolis, MN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Le", 
        "givenName": "Huong", 
        "id": "sg:person.0710004312.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0710004312.25"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Genentech, Inc, 95688, Vacaville, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.418158.1", 
          "name": [
            "Genentech, Inc, 95688, Vacaville, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mills", 
        "givenName": "Keri", 
        "id": "sg:person.01140461312.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01140461312.07"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Genentech, Inc, 95688, Vacaville, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.418158.1", 
          "name": [
            "Genentech, Inc, 95688, Vacaville, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Johnson", 
        "givenName": "Kevin", 
        "id": "sg:person.01206574512.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01206574512.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Computer Science and Engineering, University of Minnesota, 55455, Minneapolis, MN, USA", 
          "id": "http://www.grid.ac/institutes/grid.17635.36", 
          "name": [
            "Department of Computer Science and Engineering, University of Minnesota, 55455, Minneapolis, MN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Karypis", 
        "givenName": "George", 
        "id": "sg:person.01200652334.04", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01200652334.04"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Chemical Engineering and Materials Science, University of Minnesota, 55455, Minneapolis, MN, USA", 
          "id": "http://www.grid.ac/institutes/grid.17635.36", 
          "name": [
            "Department of Chemical Engineering and Materials Science, University of Minnesota, 55455, Minneapolis, MN, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Hu", 
        "givenName": "Wei-Shou", 
        "id": "sg:person.01064261433.49", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01064261433.49"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2011-07-25", 
    "datePublishedReg": "2011-07-25", 
    "description": "Several newly approved protein-based therapeutics in the past decade are manufactured in modern production plants with automated systems for process control and comprehensive data archival. The hundreds of process parameters and key output variables for several production batches in the vast historical databases provide a valuable resource to improve process understanding and robustness. Multivariate data analysis is a critical process analytical technology tool to unearth any hidden patterns within process trends and identify key parameters for enhancing process performance and product quality. Cell culture process data from more than hundred \u201ctrains\u201d comprising production as well as inoculum bioreactors was investigated in this study. Each batch encompasses over 130 on-line and off-line temporal parameters. A maximum margin support vector algorithm was coupled with a kernel-based machine learning approach to develop multivariate predictive models for critical cell culture performance parameters. A differential weighting scheme was incorporated in the model to prioritize the process parameters with strong associations with process outcome and to identify key performance indicators at every stage of the production train. Model evaluations indicate that cell culture performance can be accurately predicted several days before harvest and downstream purification. Further, multiple parameters in the inoculum and early stages of production bioreactors were identified as precocious markers of the final process outcome. This process-data driven approach for knowledge discovery in manufacturing processes represents an important step towards implementing a real-time decision making scheme based on critical product and process traits.", 
    "editor": [
      {
        "familyName": "Jenkins", 
        "givenName": "Nigel", 
        "type": "Person"
      }, 
      {
        "familyName": "Barron", 
        "givenName": "Niall", 
        "type": "Person"
      }, 
      {
        "familyName": "Alves", 
        "givenName": "Paula", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-94-007-0884-6_43", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-94-007-0883-9", 
        "978-94-007-0884-6"
      ], 
      "name": "Proceedings of the 21st Annual Meeting of the European Society for Animal Cell Technology (ESACT), Dublin, Ireland, June 7-10, 2009", 
      "type": "Book"
    }, 
    "keywords": [
      "kernel-based machine", 
      "real-time decisions", 
      "support vector algorithm", 
      "modern production plants", 
      "final process outcome", 
      "multivariate data mining", 
      "knowledge discovery", 
      "data mining", 
      "data archival", 
      "vector algorithm", 
      "technology tools", 
      "process data", 
      "key performance indicators", 
      "historical database", 
      "weighting scheme", 
      "process trends", 
      "process control", 
      "output variables", 
      "manufacturing process performance", 
      "differential weighting schemes", 
      "scheme", 
      "data analysis", 
      "process outcomes", 
      "performance", 
      "performance indicators", 
      "predictive model", 
      "performance parameters", 
      "multiple parameters", 
      "mining", 
      "process performance", 
      "important step", 
      "algorithm", 
      "critical products", 
      "machine", 
      "model evaluation", 
      "product quality", 
      "robustness", 
      "manufacturing process", 
      "database", 
      "production plant", 
      "valuable resource", 
      "resources", 
      "tool", 
      "temporal parameters", 
      "model", 
      "archival", 
      "system", 
      "process understanding", 
      "multivariate data analysis", 
      "decisions", 
      "past decade", 
      "hundreds", 
      "quality", 
      "parameters", 
      "process analytical technology (PAT) tool", 
      "discovery", 
      "step", 
      "train", 
      "key parameters", 
      "data", 
      "production batches", 
      "evaluation", 
      "batch", 
      "process", 
      "production train", 
      "key output variables", 
      "control", 
      "stage", 
      "early stages", 
      "process parameters", 
      "decades", 
      "analysis", 
      "patterns", 
      "trends", 
      "variables", 
      "understanding", 
      "lines", 
      "precocious marker", 
      "products", 
      "indicators", 
      "multivariate predictive model", 
      "production bioreactor", 
      "study", 
      "plants", 
      "outcomes", 
      "traits", 
      "protein-based therapeutics", 
      "cell culture performance", 
      "production", 
      "days", 
      "association", 
      "harvest", 
      "markers", 
      "downstream purification", 
      "bioreactor", 
      "strong association", 
      "approach", 
      "culture performance", 
      "therapeutics", 
      "purification", 
      "inoculum", 
      "comprehensive data archival", 
      "vast historical databases", 
      "critical process analytical technology tool", 
      "analytical technology tool", 
      "Cell culture process data", 
      "culture process data", 
      "inoculum bioreactors", 
      "line temporal parameters", 
      "maximum margin support vector algorithm", 
      "margin support vector algorithm", 
      "critical cell culture performance parameters", 
      "cell culture performance parameters", 
      "culture performance parameters", 
      "process traits"
    ], 
    "name": "Towards Enhancing Manufacturing Process Performance Through Multivariate Data Mining", 
    "pagination": "285-294", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1009357787"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-94-007-0884-6_43"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-94-007-0884-6_43", 
      "https://app.dimensions.ai/details/publication/pub.1009357787"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:16", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_281.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-94-007-0884-6_43"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-94-007-0884-6_43'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-94-007-0884-6_43'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-94-007-0884-6_43'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-94-007-0884-6_43'


 

This table displays all metadata directly associated to this object as RDF triples.

232 TRIPLES      23 PREDICATES      141 URIs      133 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-94-007-0884-6_43 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 anzsrc-for:0806
4 schema:author N84f51e2871f0499ba270e7703759f616
5 schema:datePublished 2011-07-25
6 schema:datePublishedReg 2011-07-25
7 schema:description Several newly approved protein-based therapeutics in the past decade are manufactured in modern production plants with automated systems for process control and comprehensive data archival. The hundreds of process parameters and key output variables for several production batches in the vast historical databases provide a valuable resource to improve process understanding and robustness. Multivariate data analysis is a critical process analytical technology tool to unearth any hidden patterns within process trends and identify key parameters for enhancing process performance and product quality. Cell culture process data from more than hundred “trains” comprising production as well as inoculum bioreactors was investigated in this study. Each batch encompasses over 130 on-line and off-line temporal parameters. A maximum margin support vector algorithm was coupled with a kernel-based machine learning approach to develop multivariate predictive models for critical cell culture performance parameters. A differential weighting scheme was incorporated in the model to prioritize the process parameters with strong associations with process outcome and to identify key performance indicators at every stage of the production train. Model evaluations indicate that cell culture performance can be accurately predicted several days before harvest and downstream purification. Further, multiple parameters in the inoculum and early stages of production bioreactors were identified as precocious markers of the final process outcome. This process-data driven approach for knowledge discovery in manufacturing processes represents an important step towards implementing a real-time decision making scheme based on critical product and process traits.
8 schema:editor Nad099c83ef20439f9b57a0eed4f85ebf
9 schema:genre chapter
10 schema:inLanguage en
11 schema:isAccessibleForFree false
12 schema:isPartOf Nb11508e0eeb64a019ec540694840862d
13 schema:keywords Cell culture process data
14 algorithm
15 analysis
16 analytical technology tool
17 approach
18 archival
19 association
20 batch
21 bioreactor
22 cell culture performance
23 cell culture performance parameters
24 comprehensive data archival
25 control
26 critical cell culture performance parameters
27 critical process analytical technology tool
28 critical products
29 culture performance
30 culture performance parameters
31 culture process data
32 data
33 data analysis
34 data archival
35 data mining
36 database
37 days
38 decades
39 decisions
40 differential weighting schemes
41 discovery
42 downstream purification
43 early stages
44 evaluation
45 final process outcome
46 harvest
47 historical database
48 hundreds
49 important step
50 indicators
51 inoculum
52 inoculum bioreactors
53 kernel-based machine
54 key output variables
55 key parameters
56 key performance indicators
57 knowledge discovery
58 line temporal parameters
59 lines
60 machine
61 manufacturing process
62 manufacturing process performance
63 margin support vector algorithm
64 markers
65 maximum margin support vector algorithm
66 mining
67 model
68 model evaluation
69 modern production plants
70 multiple parameters
71 multivariate data analysis
72 multivariate data mining
73 multivariate predictive model
74 outcomes
75 output variables
76 parameters
77 past decade
78 patterns
79 performance
80 performance indicators
81 performance parameters
82 plants
83 precocious marker
84 predictive model
85 process
86 process analytical technology (PAT) tool
87 process control
88 process data
89 process outcomes
90 process parameters
91 process performance
92 process traits
93 process trends
94 process understanding
95 product quality
96 production
97 production batches
98 production bioreactor
99 production plant
100 production train
101 products
102 protein-based therapeutics
103 purification
104 quality
105 real-time decisions
106 resources
107 robustness
108 scheme
109 stage
110 step
111 strong association
112 study
113 support vector algorithm
114 system
115 technology tools
116 temporal parameters
117 therapeutics
118 tool
119 train
120 traits
121 trends
122 understanding
123 valuable resource
124 variables
125 vast historical databases
126 vector algorithm
127 weighting scheme
128 schema:name Towards Enhancing Manufacturing Process Performance Through Multivariate Data Mining
129 schema:pagination 285-294
130 schema:productId N831f8cf7002443e2b391790850beefb4
131 Nedc2fd549cd4471ea8ba90a73e653429
132 schema:publisher N5652d7b5f06841e381bc7491ac46eea5
133 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009357787
134 https://doi.org/10.1007/978-94-007-0884-6_43
135 schema:sdDatePublished 2022-01-01T19:16
136 schema:sdLicense https://scigraph.springernature.com/explorer/license/
137 schema:sdPublisher Ned3097237f344777911cbb8629e3ac6c
138 schema:url https://doi.org/10.1007/978-94-007-0884-6_43
139 sgo:license sg:explorer/license/
140 sgo:sdDataset chapters
141 rdf:type schema:Chapter
142 N06edbed42f134026baf0adca0dfc30a8 rdf:first sg:person.01140461312.07
143 rdf:rest N8707dc2050d945fb9f5546b2b46dd6d8
144 N40187f339e234a96bbbf85da935dd3ff rdf:first sg:person.01200652334.04
145 rdf:rest Nb20b9332aefc4b43920d87d519fb6863
146 N5652d7b5f06841e381bc7491ac46eea5 schema:name Springer Nature
147 rdf:type schema:Organisation
148 N5a0a555bf3e145808ef797549d3382e4 schema:familyName Jenkins
149 schema:givenName Nigel
150 rdf:type schema:Person
151 N831f8cf7002443e2b391790850beefb4 schema:name doi
152 schema:value 10.1007/978-94-007-0884-6_43
153 rdf:type schema:PropertyValue
154 N84f51e2871f0499ba270e7703759f616 rdf:first sg:person.01052763265.65
155 rdf:rest Na462aa073f504ddb99420d97df16c3f0
156 N8707dc2050d945fb9f5546b2b46dd6d8 rdf:first sg:person.01206574512.22
157 rdf:rest N40187f339e234a96bbbf85da935dd3ff
158 N988c53481447484ab921fba1b1e595d0 schema:familyName Barron
159 schema:givenName Niall
160 rdf:type schema:Person
161 Na462aa073f504ddb99420d97df16c3f0 rdf:first sg:person.0710004312.25
162 rdf:rest N06edbed42f134026baf0adca0dfc30a8
163 Nad099c83ef20439f9b57a0eed4f85ebf rdf:first N5a0a555bf3e145808ef797549d3382e4
164 rdf:rest Nc9d032c663e446a5b27606a40d12cd30
165 Nb11508e0eeb64a019ec540694840862d schema:isbn 978-94-007-0883-9
166 978-94-007-0884-6
167 schema:name Proceedings of the 21st Annual Meeting of the European Society for Animal Cell Technology (ESACT), Dublin, Ireland, June 7-10, 2009
168 rdf:type schema:Book
169 Nb20b9332aefc4b43920d87d519fb6863 rdf:first sg:person.01064261433.49
170 rdf:rest rdf:nil
171 Nc382e55e1bce42749647f9d891ed3377 schema:familyName Alves
172 schema:givenName Paula
173 rdf:type schema:Person
174 Nc9d032c663e446a5b27606a40d12cd30 rdf:first N988c53481447484ab921fba1b1e595d0
175 rdf:rest Ndf81a04c354a4172940b7cf02e6831ef
176 Ndf81a04c354a4172940b7cf02e6831ef rdf:first Nc382e55e1bce42749647f9d891ed3377
177 rdf:rest rdf:nil
178 Ned3097237f344777911cbb8629e3ac6c schema:name Springer Nature - SN SciGraph project
179 rdf:type schema:Organization
180 Nedc2fd549cd4471ea8ba90a73e653429 schema:name dimensions_id
181 schema:value pub.1009357787
182 rdf:type schema:PropertyValue
183 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
184 schema:name Information and Computing Sciences
185 rdf:type schema:DefinedTerm
186 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
187 schema:name Artificial Intelligence and Image Processing
188 rdf:type schema:DefinedTerm
189 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
190 schema:name Information Systems
191 rdf:type schema:DefinedTerm
192 sg:person.01052763265.65 schema:affiliation grid-institutes:None
193 schema:familyName Charaniya
194 schema:givenName Salim
195 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01052763265.65
196 rdf:type schema:Person
197 sg:person.01064261433.49 schema:affiliation grid-institutes:grid.17635.36
198 schema:familyName Hu
199 schema:givenName Wei-Shou
200 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01064261433.49
201 rdf:type schema:Person
202 sg:person.01140461312.07 schema:affiliation grid-institutes:grid.418158.1
203 schema:familyName Mills
204 schema:givenName Keri
205 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01140461312.07
206 rdf:type schema:Person
207 sg:person.01200652334.04 schema:affiliation grid-institutes:grid.17635.36
208 schema:familyName Karypis
209 schema:givenName George
210 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01200652334.04
211 rdf:type schema:Person
212 sg:person.01206574512.22 schema:affiliation grid-institutes:grid.418158.1
213 schema:familyName Johnson
214 schema:givenName Kevin
215 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01206574512.22
216 rdf:type schema:Person
217 sg:person.0710004312.25 schema:affiliation grid-institutes:grid.17635.36
218 schema:familyName Le
219 schema:givenName Huong
220 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0710004312.25
221 rdf:type schema:Person
222 grid-institutes:None schema:alternateName Genentech, Inc., 92056, Oceanside, CA, USA
223 schema:name Genentech, Inc., 92056, Oceanside, CA, USA
224 rdf:type schema:Organization
225 grid-institutes:grid.17635.36 schema:alternateName Department of Chemical Engineering and Materials Science, University of Minnesota, 55455, Minneapolis, MN, USA
226 Department of Computer Science and Engineering, University of Minnesota, 55455, Minneapolis, MN, USA
227 schema:name Department of Chemical Engineering and Materials Science, University of Minnesota, 55455, Minneapolis, MN, USA
228 Department of Computer Science and Engineering, University of Minnesota, 55455, Minneapolis, MN, USA
229 rdf:type schema:Organization
230 grid-institutes:grid.418158.1 schema:alternateName Genentech, Inc, 95688, Vacaville, CA, USA
231 schema:name Genentech, Inc, 95688, Vacaville, CA, USA
232 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...