TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction Article Swipe
Chentong Han
,
Xianghong Tang
,
Jianguang Lu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7231314/v1
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7231314/v1
Molecular property prediction plays a vital role in drug discovery, materials science, and chemical biology. Although molecular data are intrinsically multi-modal—comprising 1D sequences or fingerprints, 2D topological graphs, and 3D geometric conformations—conventional approaches often rely on single-modal inputs, thereby failing to leverage cross-modal complementarities and limiting predictive accuracy. To overcome this limitation, we propose TMolNet, a task-aware deep learning framework for adaptive multi-modal fusion. The architecture integrates modality-specific feature extractors to learn distinct representations from 1D, 2D, and 3D inputs, reducing the bias caused by incomplete or under-represented modalities. A contrastive learning scheme aligns the representations across modalities within a shared latent space, enhancing semantic consistency. Furthermore, a novel task-aware gating module dynamically modulates the contribution of each modality based on both data characteristics and task requirements. To promote balanced modality usage during training, we introduce a modality entropy regularization loss, which encourages diversity and stability in learned representations. Extensive evaluations on multiple benchmark datasets demonstrate that TMolNet consistently outperforms existing state-of-the-art methods in terms of both predictive accuracy and generalization. These findings validate the effectiveness of our task-aware fusion strategy and establish a new direction for multi-modal molecular property prediction.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-7231314/v1
- https://www.researchsquare.com/article/rs-7231314/latest.pdf
- OA Status
- gold
- References
- 41
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4412810127
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4412810127Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-7231314/v1Digital Object Identifier
- Title
-
TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property PredictionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-31Full publication date if available
- Authors
-
Chentong Han, Xianghong Tang, Jianguang LuList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-7231314/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-7231314/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-7231314/latest.pdfDirect OA link when available
- Concepts
-
Task (project management), Property (philosophy), Computer science, Artificial neural network, Artificial intelligence, Machine learning, Engineering, Systems engineering, Philosophy, EpistemologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
41Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4412810127 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-7231314/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-7231314/v1 |
| ids.openalex | https://openalex.org/W4412810127 |
| fwci | 0.0 |
| type | preprint |
| title | TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10211 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998000264167786 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1703 |
| topics[0].subfield.display_name | Computational Theory and Mathematics |
| topics[0].display_name | Computational Drug Discovery Methods |
| topics[1].id | https://openalex.org/T11948 |
| topics[1].field.id | https://openalex.org/fields/25 |
| topics[1].field.display_name | Materials Science |
| topics[1].score | 0.9994999766349792 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2505 |
| topics[1].subfield.display_name | Materials Chemistry |
| topics[1].display_name | Machine Learning in Materials Science |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2780451532 |
| concepts[0].level | 2 |
| concepts[0].score | 0.693026602268219 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[0].display_name | Task (project management) |
| concepts[1].id | https://openalex.org/C189950617 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6529635190963745 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q937228 |
| concepts[1].display_name | Property (philosophy) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6380165815353394 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C50644808 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5588405728340149 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[3].display_name | Artificial neural network |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4690946340560913 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C119857082 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3326554298400879 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[5].display_name | Machine learning |
| concepts[6].id | https://openalex.org/C127413603 |
| concepts[6].level | 0 |
| concepts[6].score | 0.09006562829017639 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[6].display_name | Engineering |
| concepts[7].id | https://openalex.org/C201995342 |
| concepts[7].level | 1 |
| concepts[7].score | 0.043304115533828735 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[7].display_name | Systems engineering |
| concepts[8].id | https://openalex.org/C138885662 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[8].display_name | Philosophy |
| concepts[9].id | https://openalex.org/C111472728 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9471 |
| concepts[9].display_name | Epistemology |
| keywords[0].id | https://openalex.org/keywords/task |
| keywords[0].score | 0.693026602268219 |
| keywords[0].display_name | Task (project management) |
| keywords[1].id | https://openalex.org/keywords/property |
| keywords[1].score | 0.6529635190963745 |
| keywords[1].display_name | Property (philosophy) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6380165815353394 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[3].score | 0.5588405728340149 |
| keywords[3].display_name | Artificial neural network |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4690946340560913 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/machine-learning |
| keywords[5].score | 0.3326554298400879 |
| keywords[5].display_name | Machine learning |
| keywords[6].id | https://openalex.org/keywords/engineering |
| keywords[6].score | 0.09006562829017639 |
| keywords[6].display_name | Engineering |
| keywords[7].id | https://openalex.org/keywords/systems-engineering |
| keywords[7].score | 0.043304115533828735 |
| keywords[7].display_name | Systems engineering |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-7231314/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-7231314/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-7231314/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5108896765 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Chentong Han |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I178232147 |
| authorships[0].affiliations[0].raw_affiliation_string | Guizhou University |
| authorships[0].institutions[0].id | https://openalex.org/I178232147 |
| authorships[0].institutions[0].ror | https://ror.org/02wmsc916 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I178232147 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Guizhou University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | cao han |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Guizhou University |
| authorships[1].author.id | https://openalex.org/A5103060458 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3961-5649 |
| authorships[1].author.display_name | Xianghong Tang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I178232147 |
| authorships[1].affiliations[0].raw_affiliation_string | Guizhou University |
| authorships[1].institutions[0].id | https://openalex.org/I178232147 |
| authorships[1].institutions[0].ror | https://ror.org/02wmsc916 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I178232147 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Guizhou University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xianghong Tang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Guizhou University |
| authorships[2].author.id | https://openalex.org/A5037067067 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2191-1570 |
| authorships[2].author.display_name | Jianguang Lu |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I178232147 |
| authorships[2].affiliations[0].raw_affiliation_string | Guizhou University |
| authorships[2].institutions[0].id | https://openalex.org/I178232147 |
| authorships[2].institutions[0].ror | https://ror.org/02wmsc916 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I178232147 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Guizhou University |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Jianguang Lu |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Guizhou University |
| 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-7231314/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10211 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998000264167786 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1703 |
| primary_topic.subfield.display_name | Computational Theory and Mathematics |
| primary_topic.display_name | Computational Drug Discovery Methods |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W4387369504, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W4283697347 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-7231314/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-7231314/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-7231314/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-7231314/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-7231314/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-7231314/v1 |
| publication_date | 2025-07-31 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W1988037271, https://openalex.org/W3201677331, https://openalex.org/W4293199734, https://openalex.org/W2973264305, https://openalex.org/W1981276685, https://openalex.org/W4396678548, https://openalex.org/W4386012785, https://openalex.org/W3198212015, https://openalex.org/W3034806393, https://openalex.org/W4213077304, https://openalex.org/W4390936165, https://openalex.org/W4390608578, https://openalex.org/W4399884408, https://openalex.org/W4390338971, https://openalex.org/W6600194071, https://openalex.org/W4388191982, https://openalex.org/W4323644140, https://openalex.org/W3036441178, https://openalex.org/W3210813272, https://openalex.org/W4399781535, https://openalex.org/W4297179162, https://openalex.org/W4387079109, https://openalex.org/W4390452972, https://openalex.org/W4388423863, https://openalex.org/W4388571136, https://openalex.org/W2064675550, https://openalex.org/W3097145107, https://openalex.org/W2221103459, https://openalex.org/W2200017991, https://openalex.org/W2527189750, https://openalex.org/W2963677766, https://openalex.org/W2619383789, https://openalex.org/W3030948478, https://openalex.org/W2594183968, https://openalex.org/W3120618935, https://openalex.org/W4365455552, https://openalex.org/W4367172783, https://openalex.org/W4321227311, https://openalex.org/W4385969371, https://openalex.org/W4394770110, https://openalex.org/W4407319601 |
| referenced_works_count | 41 |
| abstract_inverted_index.A | 90 |
| abstract_inverted_index.a | 5, 56, 100, 108, 137, 184 |
| abstract_inverted_index.1D | 22 |
| abstract_inverted_index.2D | 26 |
| abstract_inverted_index.3D | 30, 79 |
| abstract_inverted_index.To | 49, 128 |
| abstract_inverted_index.by | 85 |
| abstract_inverted_index.in | 8, 147, 164 |
| abstract_inverted_index.of | 117, 166, 177 |
| abstract_inverted_index.on | 36, 121, 152 |
| abstract_inverted_index.or | 24, 87 |
| abstract_inverted_index.to | 41, 71 |
| abstract_inverted_index.we | 53, 135 |
| abstract_inverted_index.1D, | 76 |
| abstract_inverted_index.2D, | 77 |
| abstract_inverted_index.The | 65 |
| abstract_inverted_index.and | 13, 29, 45, 78, 125, 145, 170, 182 |
| abstract_inverted_index.are | 19 |
| abstract_inverted_index.for | 61, 187 |
| abstract_inverted_index.new | 185 |
| abstract_inverted_index.our | 178 |
| abstract_inverted_index.the | 82, 95, 115, 175 |
| abstract_inverted_index.bias | 83 |
| abstract_inverted_index.both | 122, 167 |
| abstract_inverted_index.data | 18, 123 |
| abstract_inverted_index.deep | 58 |
| abstract_inverted_index.drug | 9 |
| abstract_inverted_index.each | 118 |
| abstract_inverted_index.from | 75 |
| abstract_inverted_index.rely | 35 |
| abstract_inverted_index.role | 7 |
| abstract_inverted_index.task | 126 |
| abstract_inverted_index.that | 157 |
| abstract_inverted_index.this | 51 |
| abstract_inverted_index.These | 172 |
| abstract_inverted_index.based | 120 |
| abstract_inverted_index.learn | 72 |
| abstract_inverted_index.loss, | 141 |
| abstract_inverted_index.novel | 109 |
| abstract_inverted_index.often | 34 |
| abstract_inverted_index.plays | 4 |
| abstract_inverted_index.terms | 165 |
| abstract_inverted_index.usage | 132 |
| abstract_inverted_index.vital | 6 |
| abstract_inverted_index.which | 142 |
| abstract_inverted_index.across | 97 |
| abstract_inverted_index.aligns | 94 |
| abstract_inverted_index.caused | 84 |
| abstract_inverted_index.during | 133 |
| abstract_inverted_index.fusion | 180 |
| abstract_inverted_index.gating | 111 |
| abstract_inverted_index.latent | 102 |
| abstract_inverted_index.module | 112 |
| abstract_inverted_index.scheme | 93 |
| abstract_inverted_index.shared | 101 |
| abstract_inverted_index.space, | 103 |
| abstract_inverted_index.within | 99 |
| abstract_inverted_index.TMolNet | 158 |
| abstract_inverted_index.entropy | 139 |
| abstract_inverted_index.failing | 40 |
| abstract_inverted_index.feature | 69 |
| abstract_inverted_index.fusion. | 64 |
| abstract_inverted_index.graphs, | 28 |
| abstract_inverted_index.inputs, | 38, 80 |
| abstract_inverted_index.learned | 148 |
| abstract_inverted_index.methods | 163 |
| abstract_inverted_index.promote | 129 |
| abstract_inverted_index.propose | 54 |
| abstract_inverted_index.thereby | 39 |
| abstract_inverted_index.Although | 16 |
| abstract_inverted_index.TMolNet, | 55 |
| abstract_inverted_index.accuracy | 169 |
| abstract_inverted_index.adaptive | 62 |
| abstract_inverted_index.balanced | 130 |
| abstract_inverted_index.biology. | 15 |
| abstract_inverted_index.chemical | 14 |
| abstract_inverted_index.datasets | 155 |
| abstract_inverted_index.distinct | 73 |
| abstract_inverted_index.existing | 161 |
| abstract_inverted_index.findings | 173 |
| abstract_inverted_index.learning | 59, 92 |
| abstract_inverted_index.leverage | 42 |
| abstract_inverted_index.limiting | 46 |
| abstract_inverted_index.modality | 119, 131, 138 |
| abstract_inverted_index.multiple | 153 |
| abstract_inverted_index.overcome | 50 |
| abstract_inverted_index.property | 2, 190 |
| abstract_inverted_index.reducing | 81 |
| abstract_inverted_index.science, | 12 |
| abstract_inverted_index.semantic | 105 |
| abstract_inverted_index.strategy | 181 |
| abstract_inverted_index.validate | 174 |
| abstract_inverted_index.Extensive | 150 |
| abstract_inverted_index.Molecular | 1 |
| abstract_inverted_index.accuracy. | 48 |
| abstract_inverted_index.benchmark | 154 |
| abstract_inverted_index.direction | 186 |
| abstract_inverted_index.diversity | 144 |
| abstract_inverted_index.enhancing | 104 |
| abstract_inverted_index.establish | 183 |
| abstract_inverted_index.framework | 60 |
| abstract_inverted_index.geometric | 31 |
| abstract_inverted_index.introduce | 136 |
| abstract_inverted_index.materials | 11 |
| abstract_inverted_index.modulates | 114 |
| abstract_inverted_index.molecular | 17, 189 |
| abstract_inverted_index.sequences | 23 |
| abstract_inverted_index.stability | 146 |
| abstract_inverted_index.training, | 134 |
| abstract_inverted_index.approaches | 33 |
| abstract_inverted_index.discovery, | 10 |
| abstract_inverted_index.encourages | 143 |
| abstract_inverted_index.extractors | 70 |
| abstract_inverted_index.incomplete | 86 |
| abstract_inverted_index.integrates | 67 |
| abstract_inverted_index.modalities | 98 |
| abstract_inverted_index.prediction | 3 |
| abstract_inverted_index.predictive | 47, 168 |
| abstract_inverted_index.task-aware | 57, 110, 179 |
| abstract_inverted_index.contrastive | 91 |
| abstract_inverted_index.cross-modal | 43 |
| abstract_inverted_index.demonstrate | 156 |
| abstract_inverted_index.dynamically | 113 |
| abstract_inverted_index.evaluations | 151 |
| abstract_inverted_index.limitation, | 52 |
| abstract_inverted_index.modalities. | 89 |
| abstract_inverted_index.multi-modal | 63, 188 |
| abstract_inverted_index.outperforms | 160 |
| abstract_inverted_index.prediction. | 191 |
| abstract_inverted_index.topological | 27 |
| abstract_inverted_index.Furthermore, | 107 |
| abstract_inverted_index.architecture | 66 |
| abstract_inverted_index.consistency. | 106 |
| abstract_inverted_index.consistently | 159 |
| abstract_inverted_index.contribution | 116 |
| abstract_inverted_index.single-modal | 37 |
| abstract_inverted_index.effectiveness | 176 |
| abstract_inverted_index.fingerprints, | 25 |
| abstract_inverted_index.intrinsically | 20 |
| abstract_inverted_index.requirements. | 127 |
| abstract_inverted_index.regularization | 140 |
| abstract_inverted_index.characteristics | 124 |
| abstract_inverted_index.generalization. | 171 |
| abstract_inverted_index.representations | 74, 96 |
| abstract_inverted_index.representations. | 149 |
| abstract_inverted_index.state-of-the-art | 162 |
| abstract_inverted_index.complementarities | 44 |
| abstract_inverted_index.modality-specific | 68 |
| abstract_inverted_index.under-represented | 88 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| abstract_inverted_index.multi-modal—comprising | 21 |
| abstract_inverted_index.conformations—conventional | 32 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.31905488 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |