Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling Article Swipe
Mingda Li
,
Mouyang Cheng
,
Weiliang Luo
,
Hao Tang
,
Bowen Yu
,
Yongqiang Cheng
,
Weiwei Xie
,
Ju Li
,
Heather J. Kulik
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7228011/v1
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7228011/v1
Diffusion-based deep generative models have emerged as powerful tools for inverse materials design. Yet, many existing approaches overlook essential chemical constraints such as oxidation state balance, which can lead to chemically invalid structures. Here we introduce CrysVCD (Crystal generator with Valence-Constrained Design), a modular framework that integrates chemical rules directly into the generative process. CrysVCD first employs a transformer-based elemental language model to generate valence-balanced compositions, followed by a diffusion model to generate crystal structures. The valence constraint enables orders-of-magnitude more efficient chemical valence checking, compared to pure data-driven approaches with post-screening. When fine-tuned on stability metrics, CrysVCD achieves 85% thermodynamic stability and 68% phonon stability. Moreover, CrysVCD supports conditional generation of functional materials, enabling discovery of candidates such as high thermal conductivity semiconductors and high-κ dielectric compounds. Designed as a general-purpose plugin, CrysVCD can be integrated into diverse generative pipeline to promote chemical validity, offering a reliable, scientifically grounded path for materials discovery.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-7228011/v1
- https://www.researchsquare.com/article/rs-7228011/latest.pdf
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4413968093
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4413968093Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-7228011/v1Digital Object Identifier
- Title
-
Enhancing Materials Discovery with Valence Constrained Design in Generative ModelingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-03Full publication date if available
- Authors
-
Mingda Li, Mouyang Cheng, Weiliang Luo, Hao Tang, Bowen Yu, Yongqiang Cheng, Weiwei Xie, Ju Li, Heather J. KulikList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-7228011/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-7228011/latest.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.researchsquare.com/article/rs-7228011/latest.pdfDirect OA link when available
- Concepts
-
Generative grammar, Valence (chemistry), Computer science, Biochemical engineering, Data science, Chemistry, Engineering, Artificial intelligence, Organic chemistryTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4413968093 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-7228011/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-7228011/v1 |
| ids.openalex | https://openalex.org/W4413968093 |
| fwci | 0.0 |
| type | article |
| title | Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11159 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9465000033378601 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2209 |
| topics[0].subfield.display_name | Industrial and Manufacturing Engineering |
| topics[0].display_name | Manufacturing Process and Optimization |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C39890363 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6852060556411743 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[0].display_name | Generative grammar |
| concepts[1].id | https://openalex.org/C168900304 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5601581931114197 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q171407 |
| concepts[1].display_name | Valence (chemistry) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.4077119827270508 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C183696295 |
| concepts[3].level | 1 |
| concepts[3].score | 0.33790576457977295 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2487696 |
| concepts[3].display_name | Biochemical engineering |
| concepts[4].id | https://openalex.org/C2522767166 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3207097351551056 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2374463 |
| concepts[4].display_name | Data science |
| concepts[5].id | https://openalex.org/C185592680 |
| concepts[5].level | 0 |
| concepts[5].score | 0.27494946122169495 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[5].display_name | Chemistry |
| concepts[6].id | https://openalex.org/C127413603 |
| concepts[6].level | 0 |
| concepts[6].score | 0.22893399000167847 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[6].display_name | Engineering |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.21768048405647278 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C178790620 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11351 |
| concepts[8].display_name | Organic chemistry |
| keywords[0].id | https://openalex.org/keywords/generative-grammar |
| keywords[0].score | 0.6852060556411743 |
| keywords[0].display_name | Generative grammar |
| keywords[1].id | https://openalex.org/keywords/valence |
| keywords[1].score | 0.5601581931114197 |
| keywords[1].display_name | Valence (chemistry) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.4077119827270508 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/biochemical-engineering |
| keywords[3].score | 0.33790576457977295 |
| keywords[3].display_name | Biochemical engineering |
| keywords[4].id | https://openalex.org/keywords/data-science |
| keywords[4].score | 0.3207097351551056 |
| keywords[4].display_name | Data science |
| keywords[5].id | https://openalex.org/keywords/chemistry |
| keywords[5].score | 0.27494946122169495 |
| keywords[5].display_name | Chemistry |
| keywords[6].id | https://openalex.org/keywords/engineering |
| keywords[6].score | 0.22893399000167847 |
| keywords[6].display_name | Engineering |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.21768048405647278 |
| keywords[7].display_name | Artificial intelligence |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-7228011/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-7228011/latest.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-7228011/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5000005685 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-7055-6368 |
| authorships[0].author.display_name | Mingda Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Mingda Li |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5068026713 |
| authorships[1].author.orcid | https://orcid.org/0009-0001-7014-2464 |
| authorships[1].author.display_name | Mouyang Cheng |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mouyang Cheng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5025482903 |
| authorships[2].author.orcid | https://orcid.org/0009-0005-6150-2797 |
| authorships[2].author.display_name | Weiliang Luo |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Weiliang Luo |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100662192 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-6877-0226 |
| authorships[3].author.display_name | Hao Tang |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I63966007 |
| authorships[3].affiliations[0].raw_affiliation_string | Massachusetts Institute of Technology |
| authorships[3].institutions[0].id | https://openalex.org/I63966007 |
| authorships[3].institutions[0].ror | https://ror.org/042nb2s44 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I63966007 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | Massachusetts Institute of Technology |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hao Tang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Massachusetts Institute of Technology |
| authorships[4].author.id | https://openalex.org/A5100604886 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6804-1859 |
| authorships[4].author.display_name | Bowen Yu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Bowen Yu |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5033156106 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3263-4812 |
| authorships[5].author.display_name | Yongqiang Cheng |
| authorships[5].countries | US |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I1289243028 |
| authorships[5].affiliations[0].raw_affiliation_string | Oak Ridge National Lab |
| authorships[5].institutions[0].id | https://openalex.org/I1289243028 |
| authorships[5].institutions[0].ror | https://ror.org/01qz5mb56 |
| authorships[5].institutions[0].type | facility |
| authorships[5].institutions[0].lineage | https://openalex.org/I1289243028, https://openalex.org/I1330989302, https://openalex.org/I39565521, https://openalex.org/I4210159294 |
| authorships[5].institutions[0].country_code | US |
| authorships[5].institutions[0].display_name | Oak Ridge National Laboratory |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Yongqiang Cheng |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Oak Ridge National Lab |
| authorships[6].author.id | https://openalex.org/A5028350211 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-5500-8195 |
| authorships[6].author.display_name | Weiwei Xie |
| authorships[6].countries | US |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I87216513 |
| authorships[6].affiliations[0].raw_affiliation_string | Michigan State University |
| authorships[6].institutions[0].id | https://openalex.org/I87216513 |
| authorships[6].institutions[0].ror | https://ror.org/05hs6h993 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I87216513 |
| authorships[6].institutions[0].country_code | US |
| authorships[6].institutions[0].display_name | Michigan State University |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Weiwei Xie |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Michigan State University |
| authorships[7].author.id | https://openalex.org/A5100609041 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-7841-8058 |
| authorships[7].author.display_name | Ju Li |
| authorships[7].countries | US |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I63966007 |
| authorships[7].affiliations[0].raw_affiliation_string | Massachusetts Institute of Technology |
| authorships[7].institutions[0].id | https://openalex.org/I63966007 |
| authorships[7].institutions[0].ror | https://ror.org/042nb2s44 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I63966007 |
| authorships[7].institutions[0].country_code | US |
| authorships[7].institutions[0].display_name | Massachusetts Institute of Technology |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Ju Li |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | Massachusetts Institute of Technology |
| authorships[8].author.id | https://openalex.org/A5050671822 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-9342-0191 |
| authorships[8].author.display_name | Heather J. Kulik |
| authorships[8].countries | US |
| authorships[8].affiliations[0].institution_ids | https://openalex.org/I63966007 |
| authorships[8].affiliations[0].raw_affiliation_string | Massachusetts Institute of Technology |
| authorships[8].institutions[0].id | https://openalex.org/I63966007 |
| authorships[8].institutions[0].ror | https://ror.org/042nb2s44 |
| authorships[8].institutions[0].type | education |
| authorships[8].institutions[0].lineage | https://openalex.org/I63966007 |
| authorships[8].institutions[0].country_code | US |
| authorships[8].institutions[0].display_name | Massachusetts Institute of Technology |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Heather Kulik |
| authorships[8].is_corresponding | False |
| authorships[8].raw_affiliation_strings | Massachusetts Institute of Technology |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.researchsquare.com/article/rs-7228011/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Enhancing Materials Discovery with Valence Constrained Design in Generative Modeling |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11159 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9465000033378601 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2209 |
| primary_topic.subfield.display_name | Industrial and Manufacturing Engineering |
| primary_topic.display_name | Manufacturing Process and Optimization |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2380075625, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-7228011/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.researchsquare.com/article/rs-7228011/latest.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7228011/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-7228011/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-7228011/latest.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7228011/v1 |
| publication_date | 2025-09-03 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 43, 58, 69, 131, 147 |
| abstract_inverted_index.as | 7, 23, 120, 130 |
| abstract_inverted_index.be | 136 |
| abstract_inverted_index.by | 68 |
| abstract_inverted_index.of | 112, 117 |
| abstract_inverted_index.on | 95 |
| abstract_inverted_index.to | 30, 63, 72, 87, 142 |
| abstract_inverted_index.we | 35 |
| abstract_inverted_index.68% | 104 |
| abstract_inverted_index.85% | 100 |
| abstract_inverted_index.The | 76 |
| abstract_inverted_index.and | 103, 125 |
| abstract_inverted_index.can | 28, 135 |
| abstract_inverted_index.for | 10, 152 |
| abstract_inverted_index.the | 52 |
| abstract_inverted_index.Here | 34 |
| abstract_inverted_index.When | 93 |
| abstract_inverted_index.Yet, | 14 |
| abstract_inverted_index.deep | 2 |
| abstract_inverted_index.have | 5 |
| abstract_inverted_index.high | 121 |
| abstract_inverted_index.into | 51, 138 |
| abstract_inverted_index.lead | 29 |
| abstract_inverted_index.many | 15 |
| abstract_inverted_index.more | 81 |
| abstract_inverted_index.path | 151 |
| abstract_inverted_index.pure | 88 |
| abstract_inverted_index.such | 22, 119 |
| abstract_inverted_index.that | 46 |
| abstract_inverted_index.with | 40, 91 |
| abstract_inverted_index.first | 56 |
| abstract_inverted_index.model | 62, 71 |
| abstract_inverted_index.rules | 49 |
| abstract_inverted_index.state | 25 |
| abstract_inverted_index.tools | 9 |
| abstract_inverted_index.which | 27 |
| abstract_inverted_index.models | 4 |
| abstract_inverted_index.phonon | 105 |
| abstract_inverted_index.CrysVCD | 37, 55, 98, 108, 134 |
| abstract_inverted_index.crystal | 74 |
| abstract_inverted_index.design. | 13 |
| abstract_inverted_index.diverse | 139 |
| abstract_inverted_index.emerged | 6 |
| abstract_inverted_index.employs | 57 |
| abstract_inverted_index.enables | 79 |
| abstract_inverted_index.high-κ | 126 |
| abstract_inverted_index.invalid | 32 |
| abstract_inverted_index.inverse | 11 |
| abstract_inverted_index.modular | 44 |
| abstract_inverted_index.plugin, | 133 |
| abstract_inverted_index.promote | 143 |
| abstract_inverted_index.thermal | 122 |
| abstract_inverted_index.valence | 77, 84 |
| abstract_inverted_index.(Crystal | 38 |
| abstract_inverted_index.Design), | 42 |
| abstract_inverted_index.Designed | 129 |
| abstract_inverted_index.achieves | 99 |
| abstract_inverted_index.balance, | 26 |
| abstract_inverted_index.chemical | 20, 48, 83, 144 |
| abstract_inverted_index.compared | 86 |
| abstract_inverted_index.directly | 50 |
| abstract_inverted_index.enabling | 115 |
| abstract_inverted_index.existing | 16 |
| abstract_inverted_index.followed | 67 |
| abstract_inverted_index.generate | 64, 73 |
| abstract_inverted_index.grounded | 150 |
| abstract_inverted_index.language | 61 |
| abstract_inverted_index.metrics, | 97 |
| abstract_inverted_index.offering | 146 |
| abstract_inverted_index.overlook | 18 |
| abstract_inverted_index.pipeline | 141 |
| abstract_inverted_index.powerful | 8 |
| abstract_inverted_index.process. | 54 |
| abstract_inverted_index.supports | 109 |
| abstract_inverted_index.Moreover, | 107 |
| abstract_inverted_index.checking, | 85 |
| abstract_inverted_index.diffusion | 70 |
| abstract_inverted_index.discovery | 116 |
| abstract_inverted_index.efficient | 82 |
| abstract_inverted_index.elemental | 60 |
| abstract_inverted_index.essential | 19 |
| abstract_inverted_index.framework | 45 |
| abstract_inverted_index.generator | 39 |
| abstract_inverted_index.introduce | 36 |
| abstract_inverted_index.materials | 12, 153 |
| abstract_inverted_index.oxidation | 24 |
| abstract_inverted_index.reliable, | 148 |
| abstract_inverted_index.stability | 96, 102 |
| abstract_inverted_index.validity, | 145 |
| abstract_inverted_index.approaches | 17, 90 |
| abstract_inverted_index.candidates | 118 |
| abstract_inverted_index.chemically | 31 |
| abstract_inverted_index.compounds. | 128 |
| abstract_inverted_index.constraint | 78 |
| abstract_inverted_index.dielectric | 127 |
| abstract_inverted_index.discovery. | 154 |
| abstract_inverted_index.fine-tuned | 94 |
| abstract_inverted_index.functional | 113 |
| abstract_inverted_index.generation | 111 |
| abstract_inverted_index.generative | 3, 53, 140 |
| abstract_inverted_index.integrated | 137 |
| abstract_inverted_index.integrates | 47 |
| abstract_inverted_index.materials, | 114 |
| abstract_inverted_index.stability. | 106 |
| abstract_inverted_index.conditional | 110 |
| abstract_inverted_index.constraints | 21 |
| abstract_inverted_index.data-driven | 89 |
| abstract_inverted_index.structures. | 33, 75 |
| abstract_inverted_index.conductivity | 123 |
| abstract_inverted_index.compositions, | 66 |
| abstract_inverted_index.thermodynamic | 101 |
| abstract_inverted_index.scientifically | 149 |
| abstract_inverted_index.semiconductors | 124 |
| abstract_inverted_index.Diffusion-based | 1 |
| abstract_inverted_index.general-purpose | 132 |
| abstract_inverted_index.post-screening. | 92 |
| abstract_inverted_index.valence-balanced | 65 |
| abstract_inverted_index.transformer-based | 59 |
| abstract_inverted_index.Valence-Constrained | 41 |
| abstract_inverted_index.orders-of-magnitude | 80 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile.value | 0.52357553 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |