MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling Article Swipe

PDF

Peter Eckmann , Dongxia Wu , Germano Heinzelmann , Michael K. Gilson , Rose Yu ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2402.10387

Current generative models for drug discovery primarily use molecular docking to evaluate the quality of generated compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. We propose a multi-fidelity approach, Multi-Fidelity Bind (MFBind), to achieve the optimal trade-off between accuracy and computational cost. MFBind integrates docking and binding free energy simulators to train a multi-fidelity deep surrogate model with active learning. Our deep surrogate model utilizes a pretraining technique and linear prediction heads to efficiently fit small amounts of high-fidelity data. We perform extensive experiments and show that MFBind (1) outperforms other state-of-the-art single and multi-fidelity baselines in surrogate modeling, and (2) boosts the performance of generative models with markedly higher quality compounds.

Related Topics

Artificial Intelligence

Pharmacology

Medicine

Concepts

Generative grammar Fidelity Drug Computer science Artificial intelligence Pharmacology Medicine Telecommunications

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2402.10387
PDF: https://arxiv.org/pdf/2402.10387
OA Status: green
Cited By: 3
Related Works: 10
OpenAlex ID: https://openalex.org/W4391940739

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4391940739

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2402.10387

Digital Object Identifier
Title: MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-02-16

Full publication date if available
Authors: Peter Eckmann, Dongxia Wu, Germano Heinzelmann, Michael K. Gilson, Rose Yu

List of authors in order
Landing page: https://arxiv.org/abs/2402.10387

Publisher landing page
PDF URL: https://arxiv.org/pdf/2402.10387

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2402.10387

Direct OA link when available
Concepts: Generative grammar, Fidelity, Drug, Computer science, Artificial intelligence, Pharmacology, Medicine, Telecommunications

Top concepts (fields/topics) attached by OpenAlex
Cited by: 3

Total citation count in OpenAlex
Citations by year (recent): 2025: 1, 2024: 2

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

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4391940739
doi	https://doi.org/10.48550/arxiv.2402.10387
ids.doi	https://doi.org/10.48550/arxiv.2402.10387
ids.openalex	https://openalex.org/W4391940739
fwci
type	preprint
title	MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling
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	0.3946000039577484
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/T10621
topics[1].field.id	https://openalex.org/fields/13
topics[1].field.display_name	Biochemistry, Genetics and Molecular Biology
topics[1].score	0.3756999969482422
topics[1].domain.id	https://openalex.org/domains/1
topics[1].domain.display_name	Life Sciences
topics[1].subfield.id	https://openalex.org/subfields/1312
topics[1].subfield.display_name	Molecular Biology
topics[1].display_name	Gene Regulatory Network Analysis
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C39890363
concepts[0].level	2
concepts[0].score	0.6651642322540283
concepts[0].wikidata	https://www.wikidata.org/wiki/Q36108
concepts[0].display_name	Generative grammar
concepts[1].id	https://openalex.org/C2776459999
concepts[1].level	2
concepts[1].score	0.6393904685974121
concepts[1].wikidata	https://www.wikidata.org/wiki/Q2119376
concepts[1].display_name	Fidelity
concepts[2].id	https://openalex.org/C2780035454
concepts[2].level	2
concepts[2].score	0.5597737431526184
concepts[2].wikidata	https://www.wikidata.org/wiki/Q8386
concepts[2].display_name	Drug
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.5490666627883911
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.2951642870903015
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C98274493
concepts[5].level	1
concepts[5].score	0.1984507441520691
concepts[5].wikidata	https://www.wikidata.org/wiki/Q128406
concepts[5].display_name	Pharmacology
concepts[6].id	https://openalex.org/C71924100
concepts[6].level	0
concepts[6].score	0.18572530150413513
concepts[6].wikidata	https://www.wikidata.org/wiki/Q11190
concepts[6].display_name	Medicine
concepts[7].id	https://openalex.org/C76155785
concepts[7].level	1
concepts[7].score	0.0
concepts[7].wikidata	https://www.wikidata.org/wiki/Q418
concepts[7].display_name	Telecommunications
keywords[0].id	https://openalex.org/keywords/generative-grammar
keywords[0].score	0.6651642322540283
keywords[0].display_name	Generative grammar
keywords[1].id	https://openalex.org/keywords/fidelity
keywords[1].score	0.6393904685974121
keywords[1].display_name	Fidelity
keywords[2].id	https://openalex.org/keywords/drug
keywords[2].score	0.5597737431526184
keywords[2].display_name	Drug
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.5490666627883911
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.2951642870903015
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/pharmacology
keywords[5].score	0.1984507441520691
keywords[5].display_name	Pharmacology
keywords[6].id	https://openalex.org/keywords/medicine
keywords[6].score	0.18572530150413513
keywords[6].display_name	Medicine
language	en
locations[0].id	pmh:oai:arXiv.org:2402.10387
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2402.10387
locations[0].version	submittedVersion
locations[0].raw_type
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2402.10387
locations[1].id	doi:10.48550/arxiv.2402.10387
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2402.10387
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101771743
authorships[0].author.orcid	https://orcid.org/0000-0002-5388-9451
authorships[0].author.display_name	Peter Eckmann
authorships[0].author_position	first
authorships[0].raw_author_name	Eckmann, Peter
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100943740
authorships[1].author.orcid	https://orcid.org/0009-0005-5059-2395
authorships[1].author.display_name	Dongxia Wu
authorships[1].author_position	middle
authorships[1].raw_author_name	Wu, Dongxia
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5026255015
authorships[2].author.orcid	https://orcid.org/0000-0001-7168-6941
authorships[2].author.display_name	Germano Heinzelmann
authorships[2].author_position	middle
authorships[2].raw_author_name	Heinzelmann, Germano
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5049982297
authorships[3].author.orcid	https://orcid.org/0000-0002-3375-1738
authorships[3].author.display_name	Michael K. Gilson
authorships[3].author_position	middle
authorships[3].raw_author_name	Gilson, Michael K
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5057778679
authorships[4].author.orcid	https://orcid.org/0000-0002-8491-7937
authorships[4].author.display_name	Rose Yu
authorships[4].author_position	last
authorships[4].raw_author_name	Yu, Rose
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2402.10387
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-02-20T00:00:00
display_name	MFBind: a Multi-Fidelity Approach for Evaluating Drug Compounds in Practical Generative Modeling
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
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	0.3946000039577484
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/W2748952813, https://openalex.org/W2381850946, https://openalex.org/W4380449851, https://openalex.org/W3125091513, https://openalex.org/W4318832338, https://openalex.org/W2380075625, https://openalex.org/W2390279801, https://openalex.org/W2358668433, https://openalex.org/W2376932109, https://openalex.org/W2001405890
cited_by_count	3
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2024
counts_by_year[1].cited_by_count	2
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2402.10387
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2402.10387
best_oa_location.version	submittedVersion
best_oa_location.raw_type
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2402.10387
primary_location.id	pmh:oai:arXiv.org:2402.10387
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2402.10387
primary_location.version	submittedVersion
primary_location.raw_type
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2402.10387
publication_date	2024-02-16
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	64, 69, 95, 108
abstract_inverted_index.We	67, 123
abstract_inverted_index.as	47
abstract_inverted_index.do	33
abstract_inverted_index.in	24, 63, 139
abstract_inverted_index.of	14, 120, 147
abstract_inverted_index.to	10, 61, 75, 93, 115
abstract_inverted_index.(1)	131
abstract_inverted_index.(2)	143
abstract_inverted_index.Our	103
abstract_inverted_index.and	82, 88, 111, 127, 136, 142
abstract_inverted_index.are	20, 57
abstract_inverted_index.but	55
abstract_inverted_index.fit	117
abstract_inverted_index.for	3, 42
abstract_inverted_index.not	22, 34
abstract_inverted_index.the	12, 77, 145
abstract_inverted_index.too	58
abstract_inverted_index.use	7, 62
abstract_inverted_index.Bind	73
abstract_inverted_index.More	39
abstract_inverted_index.deep	97, 104
abstract_inverted_index.drug	4
abstract_inverted_index.even	27
abstract_inverted_index.free	52, 90
abstract_inverted_index.high	30
abstract_inverted_index.show	36, 128
abstract_inverted_index.such	18, 46
abstract_inverted_index.that	129
abstract_inverted_index.they	56
abstract_inverted_index.with	29, 100, 150
abstract_inverted_index.based	50
abstract_inverted_index.cost.	84
abstract_inverted_index.data.	122
abstract_inverted_index.heads	114
abstract_inverted_index.model	99, 106
abstract_inverted_index.often	21
abstract_inverted_index.other	133
abstract_inverted_index.small	118
abstract_inverted_index.train	94
abstract_inverted_index.MFBind	85, 130
abstract_inverted_index.active	101
abstract_inverted_index.boosts	144
abstract_inverted_index.energy	53, 91
abstract_inverted_index.exist,	45
abstract_inverted_index.higher	152
abstract_inverted_index.linear	112
abstract_inverted_index.model.	66
abstract_inverted_index.models	2, 19, 149
abstract_inverted_index.scores	32
abstract_inverted_index.single	135
abstract_inverted_index.useful	23
abstract_inverted_index.Current	0
abstract_inverted_index.achieve	76
abstract_inverted_index.amounts	119
abstract_inverted_index.because	26
abstract_inverted_index.between	80
abstract_inverted_index.binding	51, 89
abstract_inverted_index.docking	9, 31, 87
abstract_inverted_index.methods	41
abstract_inverted_index.optimal	78
abstract_inverted_index.perform	124
abstract_inverted_index.propose	68
abstract_inverted_index.quality	13, 153
abstract_inverted_index.However,	17
abstract_inverted_index.accuracy	81
abstract_inverted_index.accurate	40
abstract_inverted_index.activity	43
abstract_inverted_index.dynamics	49
abstract_inverted_index.evaluate	11
abstract_inverted_index.markedly	151
abstract_inverted_index.practice	25
abstract_inverted_index.utilizes	107
abstract_inverted_index.(MFBind),	74
abstract_inverted_index.activity.	38
abstract_inverted_index.approach,	71
abstract_inverted_index.baselines	138
abstract_inverted_index.compounds	28
abstract_inverted_index.discovery	5
abstract_inverted_index.expensive	60
abstract_inverted_index.extensive	125
abstract_inverted_index.generated	15
abstract_inverted_index.learning.	102
abstract_inverted_index.modeling,	141
abstract_inverted_index.molecular	8, 48
abstract_inverted_index.primarily	6
abstract_inverted_index.surrogate	98, 105, 140
abstract_inverted_index.technique	110
abstract_inverted_index.trade-off	79
abstract_inverted_index.compounds.	16, 154
abstract_inverted_index.generative	1, 65, 148
abstract_inverted_index.integrates	86
abstract_inverted_index.prediction	44, 113
abstract_inverted_index.simulators	92
abstract_inverted_index.efficiently	116
abstract_inverted_index.experiments	126
abstract_inverted_index.outperforms	132
abstract_inverted_index.performance	146
abstract_inverted_index.pretraining	109
abstract_inverted_index.consistently	35
abstract_inverted_index.experimental	37
abstract_inverted_index.calculations,	54
abstract_inverted_index.computational	83
abstract_inverted_index.high-fidelity	121
abstract_inverted_index.Multi-Fidelity	72
abstract_inverted_index.multi-fidelity	70, 96, 137
abstract_inverted_index.computationally	59
abstract_inverted_index.state-of-the-art	134
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile