Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning Article Swipe

PDF

Ziteng Liu , Liqiang Lin , Qingqing Jia , Zheng Cheng , Yanyan Jiang , Yanwen Guo , Jing Ma ·

YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.26434/chemrxiv.12588170.v1

The development of efficient models for predicting specific properties through machine learning is of great importance for the innovation of chemistry and material science. However, predicting electronic structure properties like frontier molecular orbital HOMO and LUMO energy levels and their HOMO-LUMO gaps from the small-sized molecule data to larger molecules remains a challenge. Here we develop a multi-level attention strategy that enables chemical interpretable insights to be fused into multi-task learning of up to 110,000 records of data in QM9 for random split evaluation. The good transferability for predicting larger molecules outside the training set is demonstrated in both QM9 and Alchemy datasets. The efficient and accurate prediction of 12 properties including dipole moment, HOMO, and Gibbs free energy within chemical accuracy is achieved by using our specifically designed interpretable multi-level attention neural network, named as DeepMoleNet. Remarkably, the present multi-task deep learning model adopts the atom-centered symmetry functions (ACSFs) descriptor as one of the prediction targets, rather than using ACSFs as input in the conventional way. The proposed multi-level attention neural network is applicable to high-throughput screening of numerous chemical species to accelerate rational designs of drug, material, and chemical reactions.

Related Topics

Computer Science

Artificial Intelligence

Concepts

Computer science Artificial neural network Artificial intelligence HOMO/LUMO Machine learning Task (project management) Set (abstract data type) Quantum chemical Deep learning Molecular descriptor Quantitative structure–activity relationship Molecule Chemistry Economics Organic chemistry Management Programming language

Metadata

Type: preprint
Language: en
Landing Page: https://doi.org/10.26434/chemrxiv.12588170.v1
PDF: https://chemrxiv.org/ndownloader/files/23553335
OA Status: gold
Cited By: 12
Related Works: 10
OpenAlex ID: https://openalex.org/W4238485404

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4238485404

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.26434/chemrxiv.12588170.v1

Digital Object Identifier
Title: Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2020

Year of publication
Publication date: 2020-07-02

Full publication date if available
Authors: Ziteng Liu, Liqiang Lin, Qingqing Jia, Zheng Cheng, Yanyan Jiang, Yanwen Guo, Jing Ma

List of authors in order
Landing page: https://doi.org/10.26434/chemrxiv.12588170.v1

Publisher landing page
PDF URL: https://chemrxiv.org/ndownloader/files/23553335

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://chemrxiv.org/ndownloader/files/23553335

Direct OA link when available
Concepts: Computer science, Artificial neural network, Artificial intelligence, HOMO/LUMO, Machine learning, Task (project management), Set (abstract data type), Quantum chemical, Deep learning, Molecular descriptor, Quantitative structure–activity relationship, Molecule, Chemistry, Economics, Organic chemistry, Management, Programming language

Top concepts (fields/topics) attached by OpenAlex
Cited by: 12

Total citation count in OpenAlex
Citations by year (recent): 2024: 1, 2022: 3, 2021: 6, 2020: 2

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4238485404
doi	https://doi.org/10.26434/chemrxiv.12588170.v1
ids.doi	https://doi.org/10.26434/chemrxiv.12588170.v1
ids.openalex	https://openalex.org/W4238485404
fwci	0.94783949
type	preprint
title	Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11948
topics[0].field.id	https://openalex.org/fields/25
topics[0].field.display_name	Materials Science
topics[0].score	0.9995999932289124
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/2505
topics[0].subfield.display_name	Materials Chemistry
topics[0].display_name	Machine Learning in Materials Science
topics[1].id	https://openalex.org/T10211
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9983000159263611
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1703
topics[1].subfield.display_name	Computational Theory and Mathematics
topics[1].display_name	Computational Drug Discovery Methods
topics[2].id	https://openalex.org/T12327
topics[2].field.id	https://openalex.org/fields/16
topics[2].field.display_name	Chemistry
topics[2].score	0.9878000020980835
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1606
topics[2].subfield.display_name	Physical and Theoretical Chemistry
topics[2].display_name	Various Chemistry Research Topics
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.6148642897605896
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C50644808
concepts[1].level	2
concepts[1].score	0.5934466123580933
concepts[1].wikidata	https://www.wikidata.org/wiki/Q192776
concepts[1].display_name	Artificial neural network
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.561543345451355
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C14158195
concepts[3].level	3
concepts[3].score	0.5510436296463013
concepts[3].wikidata	https://www.wikidata.org/wiki/Q899637
concepts[3].display_name	HOMO/LUMO
concepts[4].id	https://openalex.org/C119857082
concepts[4].level	1
concepts[4].score	0.544803261756897
concepts[4].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[4].display_name	Machine learning
concepts[5].id	https://openalex.org/C2780451532
concepts[5].level	2
concepts[5].score	0.5139457583427429
concepts[5].wikidata	https://www.wikidata.org/wiki/Q759676
concepts[5].display_name	Task (project management)
concepts[6].id	https://openalex.org/C177264268
concepts[6].level	2
concepts[6].score	0.49257880449295044
concepts[6].wikidata	https://www.wikidata.org/wiki/Q1514741
concepts[6].display_name	Set (abstract data type)
concepts[7].id	https://openalex.org/C2991951333
concepts[7].level	3
concepts[7].score	0.4735243320465088
concepts[7].wikidata	https://www.wikidata.org/wiki/Q188403
concepts[7].display_name	Quantum chemical
concepts[8].id	https://openalex.org/C108583219
concepts[8].level	2
concepts[8].score	0.4370572566986084
concepts[8].wikidata	https://www.wikidata.org/wiki/Q197536
concepts[8].display_name	Deep learning
concepts[9].id	https://openalex.org/C164923092
concepts[9].level	3
concepts[9].score	0.42915040254592896
concepts[9].wikidata	https://www.wikidata.org/wiki/Q3705921
concepts[9].display_name	Molecular descriptor
concepts[10].id	https://openalex.org/C164126121
concepts[10].level	2
concepts[10].score	0.3843877911567688
concepts[10].wikidata	https://www.wikidata.org/wiki/Q766383
concepts[10].display_name	Quantitative structure–activity relationship
concepts[11].id	https://openalex.org/C32909587
concepts[11].level	2
concepts[11].score	0.3154640793800354
concepts[11].wikidata	https://www.wikidata.org/wiki/Q11369
concepts[11].display_name	Molecule
concepts[12].id	https://openalex.org/C185592680
concepts[12].level	0
concepts[12].score	0.3098561763763428
concepts[12].wikidata	https://www.wikidata.org/wiki/Q2329
concepts[12].display_name	Chemistry
concepts[13].id	https://openalex.org/C162324750
concepts[13].level	0
concepts[13].score	0.0
concepts[13].wikidata	https://www.wikidata.org/wiki/Q8134
concepts[13].display_name	Economics
concepts[14].id	https://openalex.org/C178790620
concepts[14].level	1
concepts[14].score	0.0
concepts[14].wikidata	https://www.wikidata.org/wiki/Q11351
concepts[14].display_name	Organic chemistry
concepts[15].id	https://openalex.org/C187736073
concepts[15].level	1
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q2920921
concepts[15].display_name	Management
concepts[16].id	https://openalex.org/C199360897
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[16].display_name	Programming language
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.6148642897605896
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/artificial-neural-network
keywords[1].score	0.5934466123580933
keywords[1].display_name	Artificial neural network
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.561543345451355
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/homo/lumo
keywords[3].score	0.5510436296463013
keywords[3].display_name	HOMO/LUMO
keywords[4].id	https://openalex.org/keywords/machine-learning
keywords[4].score	0.544803261756897
keywords[4].display_name	Machine learning
keywords[5].id	https://openalex.org/keywords/task
keywords[5].score	0.5139457583427429
keywords[5].display_name	Task (project management)
keywords[6].id	https://openalex.org/keywords/set
keywords[6].score	0.49257880449295044
keywords[6].display_name	Set (abstract data type)
keywords[7].id	https://openalex.org/keywords/quantum-chemical
keywords[7].score	0.4735243320465088
keywords[7].display_name	Quantum chemical
keywords[8].id	https://openalex.org/keywords/deep-learning
keywords[8].score	0.4370572566986084
keywords[8].display_name	Deep learning
keywords[9].id	https://openalex.org/keywords/molecular-descriptor
keywords[9].score	0.42915040254592896
keywords[9].display_name	Molecular descriptor
keywords[10].id	https://openalex.org/keywords/quantitative-structure–activity-relationship
keywords[10].score	0.3843877911567688
keywords[10].display_name	Quantitative structure–activity relationship
keywords[11].id	https://openalex.org/keywords/molecule
keywords[11].score	0.3154640793800354
keywords[11].display_name	Molecule
keywords[12].id	https://openalex.org/keywords/chemistry
keywords[12].score	0.3098561763763428
keywords[12].display_name	Chemistry
language	en
locations[0].id	doi:10.26434/chemrxiv.12588170.v1
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by-nc-nd
locations[0].pdf_url	https://chemrxiv.org/ndownloader/files/23553335
locations[0].version	acceptedVersion
locations[0].raw_type	posted-content
locations[0].license_id	https://openalex.org/licenses/cc-by-nc-nd
locations[0].is_accepted	True
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	https://doi.org/10.26434/chemrxiv.12588170.v1
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5049087292
authorships[0].author.orcid	https://orcid.org/0000-0002-5791-6015
authorships[0].author.display_name	Ziteng Liu
authorships[0].author_position	first
authorships[0].raw_author_name	Ziteng Liu
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5085746619
authorships[1].author.orcid	https://orcid.org/0000-0003-2594-6495
authorships[1].author.display_name	Liqiang Lin
authorships[1].author_position	middle
authorships[1].raw_author_name	Liqiang Lin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100567325
authorships[2].author.orcid
authorships[2].author.display_name	Qingqing Jia
authorships[2].author_position	middle
authorships[2].raw_author_name	Qingqing Jia
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5108860079
authorships[3].author.orcid	https://orcid.org/0009-0007-7740-634X
authorships[3].author.display_name	Zheng Cheng
authorships[3].author_position	middle
authorships[3].raw_author_name	Zheng Cheng
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5044742951
authorships[4].author.orcid	https://orcid.org/0000-0002-7866-4689
authorships[4].author.display_name	Yanyan Jiang
authorships[4].author_position	middle
authorships[4].raw_author_name	Yanyan Jiang
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5009275869
authorships[5].author.orcid	https://orcid.org/0000-0002-7605-5206
authorships[5].author.display_name	Yanwen Guo
authorships[5].author_position	middle
authorships[5].raw_author_name	Yanwen Guo
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5020347295
authorships[6].author.orcid	https://orcid.org/0000-0001-5848-9775
authorships[6].author.display_name	Jing Ma
authorships[6].countries	CN
authorships[6].affiliations[0].institution_ids	https://openalex.org/I881766915
authorships[6].affiliations[0].raw_affiliation_string	Nanjing university
authorships[6].institutions[0].id	https://openalex.org/I881766915
authorships[6].institutions[0].ror	https://ror.org/01rxvg760
authorships[6].institutions[0].type	education
authorships[6].institutions[0].lineage	https://openalex.org/I881766915
authorships[6].institutions[0].country_code	CN
authorships[6].institutions[0].display_name	Nanjing University
authorships[6].author_position	last
authorships[6].raw_author_name	Jing Ma
authorships[6].is_corresponding	False
authorships[6].raw_affiliation_strings	Nanjing university
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://chemrxiv.org/ndownloader/files/23553335
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Transferable Multi-level Attention Neural Network for Accurate Prediction of Quantum Chemistry Properties via Multi-task Learning
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T11948
primary_topic.field.id	https://openalex.org/fields/25
primary_topic.field.display_name	Materials Science
primary_topic.score	0.9995999932289124
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2505
primary_topic.subfield.display_name	Materials Chemistry
primary_topic.display_name	Machine Learning in Materials Science
related_works	https://openalex.org/W2148009427, https://openalex.org/W1518515965, https://openalex.org/W1978931025, https://openalex.org/W3159291941, https://openalex.org/W2063120953, https://openalex.org/W2753230657, https://openalex.org/W2165637039, https://openalex.org/W2026843845, https://openalex.org/W2889092195, https://openalex.org/W2155827364
cited_by_count	12
counts_by_year[0].year	2024
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2022
counts_by_year[1].cited_by_count	3
counts_by_year[2].year	2021
counts_by_year[2].cited_by_count	6
counts_by_year[3].year	2020
counts_by_year[3].cited_by_count	2
locations_count	1
best_oa_location.id	doi:10.26434/chemrxiv.12588170.v1
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by-nc-nd
best_oa_location.pdf_url	https://chemrxiv.org/ndownloader/files/23553335
best_oa_location.version	acceptedVersion
best_oa_location.raw_type	posted-content
best_oa_location.license_id	https://openalex.org/licenses/cc-by-nc-nd
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/10.26434/chemrxiv.12588170.v1
primary_location.id	doi:10.26434/chemrxiv.12588170.v1
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by-nc-nd
primary_location.pdf_url	https://chemrxiv.org/ndownloader/files/23553335
primary_location.version	acceptedVersion
primary_location.raw_type	posted-content
primary_location.license_id	https://openalex.org/licenses/cc-by-nc-nd
primary_location.is_accepted	True
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	https://doi.org/10.26434/chemrxiv.12588170.v1
publication_date	2020-07-02
publication_year	2020
referenced_works_count	0
abstract_inverted_index.a	51, 56
abstract_inverted_index.12	109
abstract_inverted_index.as	135, 151, 161
abstract_inverted_index.be	66
abstract_inverted_index.by	124
abstract_inverted_index.in	78, 97, 163
abstract_inverted_index.is	12, 95, 122, 173
abstract_inverted_index.of	2, 13, 19, 71, 76, 108, 153, 178, 186
abstract_inverted_index.to	47, 65, 73, 175, 182
abstract_inverted_index.up	72
abstract_inverted_index.we	54
abstract_inverted_index.QM9	79, 99
abstract_inverted_index.The	0, 84, 103, 167
abstract_inverted_index.and	21, 34, 38, 100, 105, 115, 189
abstract_inverted_index.for	5, 16, 80, 87
abstract_inverted_index.one	152
abstract_inverted_index.our	126
abstract_inverted_index.set	94
abstract_inverted_index.the	17, 43, 92, 138, 145, 154, 164
abstract_inverted_index.HOMO	33
abstract_inverted_index.Here	53
abstract_inverted_index.LUMO	35
abstract_inverted_index.both	98
abstract_inverted_index.data	46, 77
abstract_inverted_index.deep	141
abstract_inverted_index.free	117
abstract_inverted_index.from	42
abstract_inverted_index.gaps	41
abstract_inverted_index.good	85
abstract_inverted_index.into	68
abstract_inverted_index.like	29
abstract_inverted_index.than	158
abstract_inverted_index.that	60
abstract_inverted_index.way.	166
abstract_inverted_index.ACSFs	160
abstract_inverted_index.Gibbs	116
abstract_inverted_index.HOMO,	114
abstract_inverted_index.drug,	187
abstract_inverted_index.fused	67
abstract_inverted_index.great	14
abstract_inverted_index.input	162
abstract_inverted_index.model	143
abstract_inverted_index.named	134
abstract_inverted_index.split	82
abstract_inverted_index.their	39
abstract_inverted_index.using	125, 159
abstract_inverted_index.adopts	144
abstract_inverted_index.dipole	112
abstract_inverted_index.energy	36, 118
abstract_inverted_index.larger	48, 89
abstract_inverted_index.levels	37
abstract_inverted_index.models	4
abstract_inverted_index.neural	132, 171
abstract_inverted_index.random	81
abstract_inverted_index.rather	157
abstract_inverted_index.within	119
abstract_inverted_index.(ACSFs)	149
abstract_inverted_index.110,000	74
abstract_inverted_index.Alchemy	101
abstract_inverted_index.designs	185
abstract_inverted_index.develop	55
abstract_inverted_index.enables	61
abstract_inverted_index.machine	10
abstract_inverted_index.moment,	113
abstract_inverted_index.network	172
abstract_inverted_index.orbital	32
abstract_inverted_index.outside	91
abstract_inverted_index.present	139
abstract_inverted_index.records	75
abstract_inverted_index.remains	50
abstract_inverted_index.species	181
abstract_inverted_index.through	9
abstract_inverted_index.However,	24
abstract_inverted_index.accuracy	121
abstract_inverted_index.accurate	106
abstract_inverted_index.achieved	123
abstract_inverted_index.chemical	62, 120, 180, 190
abstract_inverted_index.designed	128
abstract_inverted_index.frontier	30
abstract_inverted_index.insights	64
abstract_inverted_index.learning	11, 70, 142
abstract_inverted_index.material	22
abstract_inverted_index.molecule	45
abstract_inverted_index.network,	133
abstract_inverted_index.numerous	179
abstract_inverted_index.proposed	168
abstract_inverted_index.rational	184
abstract_inverted_index.science.	23
abstract_inverted_index.specific	7
abstract_inverted_index.strategy	59
abstract_inverted_index.symmetry	147
abstract_inverted_index.targets,	156
abstract_inverted_index.training	93
abstract_inverted_index.HOMO-LUMO	40
abstract_inverted_index.attention	58, 131, 170
abstract_inverted_index.chemistry	20
abstract_inverted_index.datasets.	102
abstract_inverted_index.efficient	3, 104
abstract_inverted_index.functions	148
abstract_inverted_index.including	111
abstract_inverted_index.material,	188
abstract_inverted_index.molecular	31
abstract_inverted_index.molecules	49, 90
abstract_inverted_index.screening	177
abstract_inverted_index.structure	27
abstract_inverted_index.accelerate	183
abstract_inverted_index.applicable	174
abstract_inverted_index.challenge.	52
abstract_inverted_index.descriptor	150
abstract_inverted_index.electronic	26
abstract_inverted_index.importance	15
abstract_inverted_index.innovation	18
abstract_inverted_index.multi-task	69, 140
abstract_inverted_index.predicting	6, 25, 88
abstract_inverted_index.prediction	107, 155
abstract_inverted_index.properties	8, 28, 110
abstract_inverted_index.reactions.	191
abstract_inverted_index.Remarkably,	137
abstract_inverted_index.development	1
abstract_inverted_index.evaluation.	83
abstract_inverted_index.multi-level	57, 130, 169
abstract_inverted_index.small-sized	44
abstract_inverted_index.DeepMoleNet.	136
abstract_inverted_index.conventional	165
abstract_inverted_index.demonstrated	96
abstract_inverted_index.specifically	127
abstract_inverted_index.atom-centered	146
abstract_inverted_index.interpretable	63, 129
abstract_inverted_index.high-throughput	176
abstract_inverted_index.transferability	86
cited_by_percentile_year.max	98
cited_by_percentile_year.min	90
countries_distinct_count	1
institutions_distinct_count	7
sustainable_development_goals[0].id	https://metadata.un.org/sdg/9
sustainable_development_goals[0].score	0.44999998807907104
sustainable_development_goals[0].display_name	Industry, innovation and infrastructure
citation_normalized_percentile.value	0.71535995
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False