Pesticides benefit agriculture by increasing crop yield, quality, and security. However, pesticides may inadvertently harm bees, which are valuable as pollinators. Thus, candidate pesticides in development pipelines must be assessed for toxicity to bees. Leveraging a dataset of 382 molecules with toxicity labels from honey bee exposure experiments, we train a support vector machine (SVM) to predict the toxicity of pesticides to honey bees. We compare two representations of the pesticide molecules: (i) a random walk feature vector listing counts of length-L walks on the molecular graph with each vertex- and edge-label sequence and (ii) the Molecular ACCess System (MACCS) structural key fingerprint (FP), a bit vector indicating the presence/absence of a list of pre-defined subgraph patterns in the molecular graph. We explicitly construct the MACCS FPs but rely on the fixed-length-L random walk graph kernel (RWGK) in place of the dot product for the random walk representation. The L-RWGK-SVM achieves an accuracy, precision, recall, and F1 score (mean over 2000 runs) of 0.81, 0.68, 0.71, and 0.69, respectively, on the test data set—with L = 4 being the mode optimal walk length. The MACCS-FP-SVM performs on par/marginally better than the L-RWGK-SVM, lends more interpretability, but varies more in performance. We interpret the MACCS-FP-SVM by illuminating which subgraph patterns in the molecules tend to strongly push them toward the toxic/non-toxic side of the separating hyperplane.
REFERENCES
1.
F. P.
Carvalho
, “Agriculture, pesticides, food security and food safety
,” Environ. Sci. Policy
9
(7–8
), 685
–692
(2006
).2.
E.-C.
Oerke
, “Crop losses to pests
,” J. Agric. Sci.
144
(1
), 31
–43
(2006
).3.
J.
Popp
, K.
Pető
, and J.
Nagy
, “Pesticide productivity and food security. a review
,” Agron. Sustainable Dev.
33
(1
), 243
–255
(2013
).4.
J.
Cooper
and H.
Dobson
, “The benefits of pesticides to mankind and the environment
,” J. Crop Prot.
26
(9
), 1337
–1348
(2007
).5.
P.
Nicolopoulou-Stamati
, S.
Maipas
, C.
Kotampasi
, P.
Stamatis
, and L.
Hens
, “Chemical pesticides and human health: The urgent need for a new concept in agriculture
,” Front. Public Health
4
, 148
(2016
).6.
C.
Wilson
and C.
Tisdell
, “Why farmers continue to use pesticides despite environmental, health and sustainability costs
,” Ecol. Econ.
39
(3
), 449
–462
(2001
).7.
I.
Mahmood
, S. R.
Imadi
, K.
Shazadi
, A.
Gul
, and K. R.
Hakeem
, “Effects of pesticides on environment
,” in Plant, Soil and Microbes
(Springer
, 2016
), pp. 253
–269
.8.
D.
Tilman
, J.
Fargione
, B.
Wolff
, C.
D'Antonio
, A.
Dobson
, R.
Howarth
, D.
Schindler
, W. H.
Schlesinger
, D.
Simberloff
, and D.
Swackhamer
, “Forecasting agriculturally driven global environmental change
,” Science
292
(5515
), 281
–284
(2001
).9.
S.
Stehle
and R.
Schulz
, “Agricultural insecticides threaten surface waters at the global scale
,” Proc. Natl. Acad. Sci. U. S. A.
112
(18
), 5750
–5755
(2015
).10.
S.
Johnson
and G.
Preetha
, Pesticide Toxicity to Non-target Organisms
(Springer
, 2016
).11.
L. W.
Pisa
, V.
Amaral-Rogers
, L. P.
Belzunces
, J. M.
Bonmatin
, C. A.
Downs
, D.
Goulson
, D. P.
Kreutzweiser
, C.
Krupke
, M.
Liess
et al, “Effects of neonicotinoids and fipronil on non-target invertebrates
,” Environ. Sci. Pollut. Res.
22
(1
), 68
–102
(2015
). 12.
B. P.
Oldroyd
, “What’s killing American honey bees?
,” PLoS Biol.
5
(6
), e168
(2007
).13.
B. A.
Woodcock
, J. M.
Bullock
, R. F.
Shore
, M. S.
Heard
, M. G.
Pereira
, J.
Redhead
, L.
Ridding
, H.
Dean
, D.
Sleep
, P.
Henrys
et al, “Country-specific effects of neonicotinoid pesticides on honey bees and wild bees
,” Science
356
(6345
), 1393
–1395
(2017
).14.
A. J.
Vanbergen
and the Insect Pollinators Initiative
, “Threats to an ecosystem service: Pressures on pollinators
,” Front. Ecol. Environ.
11
(5
), 251
–259
(2013
).15.
R. J.
Gill
, O.
Ramos-Rodriguez
, and N. E.
Raine
, “Combined pesticide exposure severely affects individual-and colony-level traits in bees
,” Nature
491
(7422
), 105
–108
(2012
).16.
D.
Goulson
, “REVIEW: An overview of the environmental risks posed by neonicotinoid insecticides
,” J. Appl. Ecol.
50
(4
), 977
–987
(2013
).17.
D.
VanEngelsdorp
, J.
Hayes
Jr., R. M.
Underwood
, and J.
Pettis
, “A survey of honey bee colony losses in the U.S., fall 2007 to spring 2008
,” PloS One
3
(12
), e4071
(2008
).18.
I.
Koh
, E. V.
Lonsdorf
, N. M.
Williams
, C.
Brittain
, R.
Isaacs
, J.
Gibbs
, and T. H.
Ricketts
, “Modeling the status, trends, and impacts of wild bee abundance in the United States
,” Proc. Natl. Acad. Sci. U. S. A.
113
(1
), 140
–145
(2016
).19.
S. A.
Cameron
, J. D.
Lozier
, J. P.
Strange
, J. B.
Koch
, N.
Cordes
, L. F.
Solter
, and T. L.
Griswold
, “Patterns of widespread decline in North American bumble bees
,” Proc. Natl. Acad. Sci. U. S. A.
108
(2
), 662
–667
(2011
).20.
M.
Spivak
, E.
Mader
, M.
Vaughan
, and N. H.
Euliss
, Jr., “The plight of the bees
,” Environ. Sci. Technol.
45
(1
), 34
–38
(2011
).21.
D.
Goulson
, E.
Nicholls
, C.
Botías
, and E. L.
Rotheray
, “Bee declines driven by combined stress from parasites, pesticides, and lack of flowers
,” Science
347
(6229
), 1255957
(2015
).22.
N.
Gallai
, J.-M.
Salles
, J.
Settele
, and B. E.
Vaissière
, “Economic valuation of the vulnerability of world agriculture confronted with pollinator decline
,” Ecol. Econ.
68
(3
), 810
–821
(2009
).23.
R.
Winfree
, N. M.
Williams
, H.
Gaines
, J. S.
Ascher
, and C.
Kremen
, “Wild bee pollinators provide the majority of crop visitation across land-use gradients in New Jersey and Pennsylvania, USA
,” J. Appl. Ecol.
45
(3
), 793
–802
(2008
).24.
A.-M.
Klein
, B. E.
Vaissiere
, J. H.
Cane
, I.
Steffan-Dewenter
, S. A.
Cunningham
, C.
Kremen
, and T.
Teja
, “Importance of pollinators in changing landscapes for world crops
,” Proc. R. Soc. B
274
(1608
), 303
–313
(2007
).25.
P. H.
Raven
, G. B.
Johnson
, J. B.
Losos
, K. A.
Mason
, and S. R.
Singer
, Biology
(McGraw-Hill Higher Education
, 2008
).26.
M. D.
Levin
, “Value of bee pollination to U.S. agriculture
,” Am. Entomol.
29
(4
), 50
–51
(1983
).27.
K. J.
Hung
, J. M.
Kingston
, M.
Albrecht
, D. A.
Holway
, and J. R.
Kohn
, “The worldwide importance of honey bees as pollinators in natural habitats
,” Proc. R. Soc. B
285
(1870
), 20172140
(2018
).28.
T. C.
Sparks
and R.
Nauen
, “IRAC: Mode of action classification and insecticide resistance management
,” Pestic. Biochem. Physiol.
121
, 122
–128
(2015
).29.
M. D. K.
Owen
and I. A.
Zelaya
, “Herbicide-resistant crops and weed resistance to herbicides
,” Pest Manage. Sci
61
(3
), 301
–311
(2005
).30.
J. A.
Lucas
, N. J.
Hawkins
, and B. A.
Fraaije
, “Chapter two - The evolution of fungicide resistance
,” in Advances in Applied Microbiology
, edited by S.
Sariaslani
and G.
Michael Gadd
(Academic Press
, 2015
), Vol. 90, pp. 29
–92
.31.
N.
Umetsu
and Y.
Shirai
, “Development of novel pesticides in the 21st century
,” J. Pestic. Sci.
45
(2
), 54
–74
(2020
).32.
S. F.
Sousa
, P. A.
Fernandes
, and M. J.
Ramos
, “Protein–ligand docking: Current status and future challenges
,” Proteins
65
(1
), 15
–26
(2006
).33.
F.
Gang
, X.
Li
, C.
Yang
, L.
Han
, H.
Qian
, S.
Wei
, W.
Wu
, and J.
Zhang
, “Synthesis and insecticidal activity evaluation of virtually screened phenylsulfonamides
,” J. Agric. Food Chem.
68
(42
), 11665
–11671
(2020
).34.
T.
Harada
, Y.
Nakagawa
, T.
Ogura
, Y.
Yamada
, T.
Ohe
, and H.
Miyagawa
, “Virtual screening for ligands of the insect molting hormone receptor
,” J. Chem. Inf. Model.
51
(2
), 296
–305
(2011
).35.
X.
Hu
, B.
Yin
, K.
Cappelle
, L.
Swevers
, G.
Smagghe
, X.
Yang
, and L.
Zhang
, “Identification of novel agonists and antagonists of the ecdysone receptor by virtual screening
,” J. Mol. Graphics Modell.
81
, 77
–85
(2018
).36.
T.-T.
Yao
, S.-W.
Fang
, Z.-S.
Li
, D.-X.
Xiao
, J.-L.
Cheng
, H.-Z.
Ying
, Y.-J.
Ying
, J.-H.
Zhao
, and X.-W.
Dong
, “Discovery of novel succinate dehydrogenase inhibitors by the integration of in silico library design and pharmacophore mapping
,” J. Agric. Food Chem.
65
(15
), 3204
–3211
(2017
).37.
S.
Horoiwa
, T.
Yokoi
, S.
Masumoto
, S.
Minami
, C.
Ishizuka
, H.
Kishikawa
, S.
Ozaki
, S.
Kitsuda
, Y.
Nakagawa
, and H.
Miyagawa
, “Structure-based virtual screening for insect ecdysone receptor ligands using MM/PBSA
,” Bioorg. Med. Chem.
27
(6
), 1065
–1075
(2019
).38.
G. J.
Correy
, D.
Zaidman
, A.
Harmelin
, S.
Carvalho
, P. D.
Mabbitt
, V.
Calaora
, P. J.
James
, A. C.
Kotze
, C. J.
Jackson
, and N.
London
, “Overcoming insecticide resistance through computational inhibitor design
,” Proc. Natl. Acad. Sci. U. S. A.
116
(42
), 21012
–21021
(2019
).39.
K.
Teralı
, “An evaluation of neonicotinoids’ potential to inhibit human cholinesterases: Protein–ligand docking and interaction profiling studies
,” J. Mol. Graphics Modell.
84
, 54
–63
(2018
).40.
A.
Decourtye
, M.
Henry
, and N.
Desneux
, “Overhaul pesticide testing on bees
,” Nature
497
(7448
), 188
(2013
).41.
See https://www.epa.gov/pollinator-protection/pollinator-risk-assessment-guidance for United States Environmental Protection Agency. Pollinator risk assessment guidance; accessed 20 February 2022.
42.
G. J.
Myatt
, E.
Ahlberg
, Y.
Akahori
, D.
Allen
, Amberg
A.
, L. T.
Anger
, A.
Aptula
, S.
Auerbach
, L.
Beilke
, P.
Bellion
, R.
Benigni
, J.
Bercu
, E. D.
Booth
, D.
Bower
, A.
Brigo
, N.
Burden
, Cammerer
Z.
, M. T. D.
Cronin
, K. P.
Cross
, L.
Custer
, M.
Dettwiler
, K.
Dobo
, K. A.
Ford
, M. C.
Fortin
, S. E.
Gad-McDonald
, N.
Gellatly
, V.
Gervais
, K. P.
Glover
, Glowienke
S.
, J.
Van Gompel
, S.
Gutsell
, B.
Hardy
, J. S.
Harvey
, J.
Hillegass
, M.
Honma
, J.-H.
Hsieh
, C.-W.
Hsu
, K.
Hughes
, C.
Johnson
, R.
Jolly
, D.
Jones
, R.
Kemper
, M. O.
Kenyon
, M. T.
Kim
, N. L.
Kruhlak
, S. A.
Kulkarni
, K.
Kümmerer
, P.
Leavitt
, B.
Majer
, S.
Masten
, S.
Miller
, J.
Moser
, M.
Mumtaz
, W.
Muster
, L.
Neilson
, T. I.
Oprea
, G.
Patlewicz
, A.
Paulino
, E.
Lo Piparo
, M.
Powley
, D. P.
Quigley
, M. V.
Reddy
, A.-N.
Richarz
, P.
Ruiz
, B.
Schilter
, R.
Serafimova
, W.
Simpson
, L.
Stavitskaya
, R.
Stidl
, D.
Suarez-Rodriguez
, D. T.
Szabo
, A.
Teasdale
, A.
Trejo-Martin
, J.-P.
Valentin
, A.
Vuorinen
, B. A.
Wall
, P.
Watts
, A. T.
White
, J.
Wichard
, K. L.
Witt
, A.
Woolley
, D.
Woolley
, C.
Zwickl
, and C.
Hasselgren
, “In silico toxicology protocols
,” Regul. Toxicol. Pharmacol.
96
, 1
–17
(2018
).43.
A. B.
Raies
and V. B.
Bajic
, “In silico toxicology: Computational methods for the prediction of chemical toxicity
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
6
(2
), 147
–172
(2016
).44.
F. A.
Quintero
, S. J.
Patel
, F.
Muñoz
, and M.
Sam Mannan
, “Review of existing QSAR/QSPR models developed for properties used in hazardous chemicals classification system
,” Ind. Eng. Chem. Res.
51
(49
), 16101
–16115
(2012
).45.
I.
Takao
, N.
Motoyama
, J. T.
Ambrose
, and R. M.
Roe
, “Mechanism for the differential toxicity of neonicotinoid insecticides in the honey bee, Apis mellifera
,” J. Crop Prot.
23
(5
), 371
–378
(2004
).46.
D.
Laurino
, M.
Porporato
, A.
Patetta
, A.
Manino
et al, “Toxicity of neonicotinoid insecticides to honey bees: Laboratory tests
,” Bull. Insectology
64
(1
), 107
–113
(2011
).47.
F.
Sanchez-Bayo
and K.
Goka
, “Pesticide residues and bees – A risk assessment
,” PLoS One
9
(4
), e94482
(2014
).48.
E. L.
Atkins
and D.
Kellum
, “Comparative morphogenic and toxicity studies on the effect of pesticides on honeybee brood
,” J. Apic. Res.
25
(4
), 242
–255
(1986
).49.
H. M.
Thompson
, “Assessing the exposure and toxicity of pesticides to bumblebees (Bombus sp.)
,” Apidologie
32
(4
), 305
–321
(2001
).50.
Y.-T.
Hu
, T.-C.
Wu
, E.-C.
Yang
, P.-C.
Wu
, P.-T.
Lin
, and Y.-L.
Wu
, “Regulation of genes related to immune signaling and detoxification in Apis mellifera by an inhibitor of histone deacetylation
,” Sci. Rep.
7
(1
), 41255
–41314
(2017
).51.
K.
Pohorecka
, T.
Szczęsna
, M.
Witek
, A.
Miszczak
, and P.
Sikorski
, “The exposure of honey bees to pesticide residues in the hive environment with regard to winter colony losses
,” J. Apic. Sci.
61
(1
), 105
–125
(2017
).52.
C. A.
Mullin
, M.
Frazier
, J. L.
Frazier
, S.
Ashcraft
, R.
Simonds
, D.
VanEngelsdorp
, and J. S.
Pettis
, “High levels of miticides and agrochemicals in North American apiaries: Implications for honey bee health
,” PLoS One
5
(3
), e9754
(2010
).53.
A.
Decourtye
, J.
Devillers
, E.
Genecque
, K. L.
Menach
, H.
Budzinski
, S.
Cluzeau
, and M. H.
Pham-Delègue
, “Comparative sublethal toxicity of nine pesticides on olfactory learning performances of the honeybee Apis mellifera
,” Arch. Environ. Contam. Toxicol.
48
(2
), 242
–250
(2005
).54.
T. S.
Bovi
, R.
Zaluski
, and R. O.
Orsi
, “Toxicity and motor changes in Africanized honey bees (Apis mellifera L.) exposed to fipronil and imidacloprid
,” An. Acad. Bras. Cienc.
90
, 239
–245
(2018
).55.
M. E. I.
Badawy
, H. M.
Nasr
, and E. I.
Rabea
, “Toxicity and biochemical changes in the honey bee Apis mellifera exposed to four insecticides under laboratory conditions
,” Apidologie
46
(2
), 177
–193
(2015
).56.
N.
Tsvetkov
, O.
Samson-Robert
, K.
Sood
, H. S.
Patel
, D. A.
Malena
, P. H.
Gajiwala
, P.
Maciukiewicz
, V.
Fournier
, and A.
Zayed
, “Chronic exposure to neonicotinoids reduces honey bee health near corn crops
,” Science
356
(6345
), 1395
–1397
(2017
).57.
J. T.
Moreira-Filho
, R. C.
Braga
, J. M.
Lemos
, V. M.
Alves
, J. V. V. B.
Borba
, W. S.
Costa
, N.
Kleinstreuer
, E. N.
Muratov
, C. H.
Andrade
, and B. J.
Neves
, “BeeToxAI: An artificial intelligence-based web app to assess acute toxicity of chemicals to honey bees
,” Artif. Intell. Life Sci.
1
, 100013
(2021
).58.
F.
Wang
, J.-F.
Yang
, M.-Y.
Wang
, C.-Y.
Jia
, X.-X.
Shi
, G.-F.
Hao
, and G.-F.
Yang
, “Graph attention convolutional neural network model for chemical poisoning of honey bees’ prediction
,” Sci. Bull.
65
(14
), 1184
–1191
(2020
).59.
E.
Carnesecchi
, A. A.
Toropov
, A. P.
Toropova
, N.
Kramer
, C.
Svendsen
, J. L.
Dorne
, and E.
Benfenati
, “Predicting acute contact toxicity of organic binary mixtures in honey bees (A. mellifera) through innovative QSAR models
,” Sci. Total Environ.
704
, 135302
(2020
).60.
M.
Hamadache
, O.
Benkortbi
, S.
Hanini
, and A.
Amrane
, “QSAR modeling in ecotoxicological risk assessment: Application to the prediction of acute contact toxicity of pesticides on bees (Apis mellifera L.)
,” Environ. Sci. Pollut. Res.
25
(1
), 896
–907
(2017
).61.
F.
Como
, E.
Carnesecchi
, S.
Volani
, J. L.
Dorne
, J.
Richardson
, A.
Bassan
, M.
Pavan
, and E.
Benfenati
, “Predicting acute contact toxicity of pesticides in honeybees (Apis mellifera) through a k-nearest neighbor model
,” Chemosphere
166
, 438
–444
(2017
).62.
X.
Xu
, P.
Zhao
, Z.
Wang
, X.
Zhang
, Z.
Wu
, W.
Li
, Y.
Tang
, and G.
Liu
, “In silico prediction of chemical acute contact toxicity on honey bees via machine learning methods
,” Toxicol. In Vitro
72
, 105089
(2021
).63.
X.
Li
, Y.
Zhang
, H.
Chen
, H.
Li
, and Y.
Zhao
, “Insights into the molecular basis of the acute contact toxicity of diverse organic chemicals in the honey bee
,” J. Chem. Inf. Model.
57
(12
), 2948
–2957
(2017
).64.
K. T.
Butler
, D. W.
Davies
, H.
Cartwright
, O.
Isayev
, and A.
Walsh
, “Machine learning for molecular and materials science
,” Nature
559
(7715
), 547
–555
(2018
).65.
L.
David
, A.
Thakkar
, R.
Mercado
, and O.
Engkvist
, “Molecular representations in AI-driven drug discovery: A review and practical guide
,” J. Cheminformatics
12
(1
), 56
(2020
).66.
D. S.
Wigh
, J. M.
Goodman
, and A. A.
Lapkin
, “A review of molecular representation in the age of machine learning
,” Wiley Interdiscip. Rev.: Comput. Mol. Sci.
(published online 2022
).67.
L.
Pattanaik
and C. W.
Coley
, “Molecular representation: Going long on fingerprints
,” Chem
6
(6
), 1204
–1207
(2020
).68.
L.
Pattanaik
, O.-E.
Ganea
, I.
Coley
, K. F.
Jensen
, W. H.
Green
, and C. W.
Coley
, “Message passing networks for molecules with tetrahedral chirality
,” in Machine Learning for Molecules Workshop at NeurIPS 2020, available at https://ml4molecules.github.io/papers2020/ML4Molecules_2020_paper_36.pdf.69.
T.
Le
, V. C.
Epa
, F. R.
Burden
, and D. A.
Winkler
, “Quantitative structure – Property relationship modeling of diverse materials properties
,” Chem. Rev.
112
(5
), 2889
–2919
(2012
).70.
A.
Simon
, D.
Schwalbe-Koda
, S.
Mohapatra
, D.
James
, K. P.
Greenman
, and R.
Gómez-Bombarelli
, “Learning matter: Materials design with machine learning and atomistic simulations
,” Acc. Mater. Res.
3
(3
), 343
–357
(2022
).71.
A.
Cereto-Massagué
, M. J.
Ojeda
, Valls
, C.
, M.
Mulero
, S.
Garcia-Vallvé
, and G.
Pujadas
, “Molecular fingerprint similarity search in virtual screening
,” Methods
71
, 58
–63
(2015
).72.
S.
Kearnes
, K.
McCloskey
, M.
Berndl
, V.
Pande
, and P.
Riley
, “Molecular graph convolutions: Moving beyond fingerprints
,” J. Comput.-Aided Mol. Des.
30
(8
), 595
–608
(2016
).73.
J. L.
Durant
, B. A.
Leland
, D. R.
Henry
, and J. G.
Nourse
, “Reoptimization of MDL keys for use in drug discovery
,” J. Chem. Inf. Comput. Sci.
42
(6
), 1273
–1280
(2002
).74.
W. L.
Hamilton
, R.
Ying
, and J.
Leskovec
, “Representation learning on graphs: Methods and applications
,” IEEE Data Eng. Bull.
40
(3
), 52
–74
(2017
).75.
J.
Gilmer
, S. S.
Schoenholz
, P. F.
Riley
, O.
Vinyals
, and G. E.
Dahl
, “Neural message passing for quantum chemistry
,” in International Conference on Machine Learning
(PMLR
, 2017
), pp. 1263
–1272
.76.
Z.
Wu
, S.
Pan
, F.
Chen
, G.
Long
, C.
Zhang
, and P. S.
Yu
, “A comprehensive survey on graph neural networks
,” IEEE Trans. Neural Networks Learn. Syst.
32
(1
), 4
–24
(2020
).77.
S. V. N.
Vishwanathan
, N. N.
Schraudolph
, R.
Kondor
, and K. M.
Borgwardt
, “Graph kernels
,” J. Mach. Learn. Res.
11
(40
), 1201
–1242
(2010
).78.
M.
Rupp
and G.
Schneider
, “Graph kernels for molecular similarity
,” Mol. Inf.
29
(4
), 266
–273
(2010
).79.
K.
Borgwardt
, E.
Ghisu
, F.
Llinares-López
, L.
O’Bray
, and B.
Rieck
, “Graph kernels: State-of-the-art and future challenges
,” in Now Foundations and Trends, 2020, available at https://ieeexplore.ieee.org/document/9307216.80.
J.
Ramon
and T.
Gärtner
, “Expressivity versus efficiency of graph kernels
,” in Proceedings of the First International Workshop on Mining Graphs, Trees and Sequences
(2003
), pp. 65
–74
.81.
L.
Ralaivola
, S. J.
Swamidass
, H.
Saigo
, and P.
Baldi
, “Graph kernels for chemical informatics
,” Neural Networks
18
(8
), 1093
–1110
(2005
).82.
G.
Nikolentzos
, G.
Siglidis
, and M.
Vazirgiannis
, “Graph kernels: A survey
,” J. Artif. Intell. Res.
72
, 943
–1027
(2021
).83.
84.
C.
Cortes
and V.
Vapnik
, “Support-vector networks
,” Mach. Learn.
20
(3
), 273
–297
(1995
).85.
C. E.
Rasmussen
and C. K. I.
Williams
, “Gaussian processes for machine learning
,” in Adaptive Computation and Machine Learning
(MIT Press
, 2006
).86.
S. S.
Du
, K.
Hou
, R. R.
Salakhutdinov
, B.
Poczos
, R.
Wang
, and K.
Xu
, “Graph neural tangent kernel: Fusing graph neural networks with graph kernels
,” Adv. Neural Inf. Process. Syst.
32
, (2019
).87.
Y.
Xiang
, Y.-H.
Tang
, G.
Lin
, and H.
Sun
, “A comparative study of marginalized graph kernel and message-passing neural network
,” J. Chem. Inf. Model.
61
(11
), 5414
–5424
(2021
).88.
See https://www.epa.gov/sites/default/files/2014-06/documents/pollinator_risk_assessment_guidance_06_19_14.pdf for Office of Pesticide Programs; United States Environmental Protection Agency. Guidance for assessing pesticide risks to bees, 2014; accessed 3 May 2022.
89.
Z.
Yin
, H.
Ai
, L.
Zhang
, G.
Ren
, Y.
Wang
, Q.
Zhao
, and H.
Liu
, “Predicting the cytotoxicity of chemicals using ensemble learning methods and molecular fingerprints
,” J. Appl. Toxicol.
39
(10
), 1366
–1377
(2019
).90.
X.
Li
, L.
Chen
, F.
Cheng
, Z.
Wu
, H.
Bian
, C.
Xu
, W.
Li
, G.
Liu
, X.
Shen
, and Y.
Tang
, “In silico prediction of chemical acute oral toxicity using multi-classification methods
,” J. Chem. Inf. Model.
54
(4
), 1061
–1069
(2014
).91.
D.-S.
Cao
, Y.-N.
Yang
, J.-C.
Zhao
, J.
Yan
, S.
Liu
, Q.-N.
Hu
, Q.-S.
Xu
, and Y.-Z.
Liang
, “Computer-aided prediction of toxicity with substructure pattern and random forest
,” J. Chemom.
26
(1–2
), 7
–15
(2012
).92.
C.
Zhang
, F.
Cheng
, W.
Li
, G.
Liu
, Pw.
Lee
, and Y.
Tang
, “In silico prediction of drug induced liver toxicity using substructure pattern recognition method
,” Mol. Inf.
35
(3–4
), 136
–144
(2016
).93.
G.
Landrum
et al, “RDKit: A software suite for cheminformatics, computational chemistry, and predictive modeling
,” rdkit.org (2013
).94.
See https://github.com/rdkit/rdkit/blob/master/rdkit/Chem/MACCSkeys.py for RDKit. RDKit source code for MACCS fingerprint; accessed May 23 2022.
95.
D. J.
Klein
, J. L.
Palacios
, M.
Randić
, and N.
Trinajstić
, “Random walks and chemical graph theory
,” J. Chem. Inf. Comput. Sci.
44
(5
), 1521
–1525
(2004
).96.
T.
Gärtner
, P.
Flach
, and S.
Wrobel
, “On graph kernels: Hardness results and efficient alternatives
,” in Learning Theory and Kernel Machines
(Springer
, 2003
), pp. 129
–143
.97.
N. M.
Kriege
, M.
Neumann
, C.
Morris
, K.
Kersting
, and P.
Mutzel
, “A unifying view of explicit and implicit feature maps of graph kernels
,” Data Min. Knowl. Discovery
33
(6
), 1505
–1547
(2019
).98.
H.
Kashima
, K.
Tsuda
, and A.
Inokuchi
, “Marginalized kernels between labeled graphs
,” in Proceedings of the 20th International Conference on Machine Learning
(ICML-03
, 2003
), pp. 321
–328
.99.
M. N.
Kriege
, F. D.
Johansson
, and C.
Morris
, “A survey on graph kernels
,” Appl. Networks Sci.
5
, 6
(2020
).100.
C. M.
Bishop
and N. M.
Nasrabadi
, Pattern Recognition and Machine Learning
(Springer
, 2006
), Vol. 4.101.
A.
Ben-Hur
and J.
Weston
, “A user’s guide to support vector machines
,” in Data Mining Techniques for the Life Sciences
(Springer
, 2010
), pp. 223
–239
.102.
M.
Meilă
, “Data centering in feature space
,” in International Workshop on Artificial Intelligence and Statistics
(PMLR
, 2003
), pp. 209
–216
.103.
B.
Schölkopf
, A.
Smola
, and Müller
, K.-R.
, “Nonlinear component analysis as a kernel eigenvalue problem
,” Neural Comput.
10
(5
), 1299
–1319
(1998
).104.
T.
Saito
and M.
Rehmsmeier
, “The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets
,” PloS One
10
(3
), e0118432
(2015
).105.
F.
Pedregosa
, G.
Varoquaux
, A.
Gramfort
, V.
Michel
, B.
Thirion
, O.
Grisel
, M.
Blondel
, P.
Prettenhofer
, R.
Weiss
, V.
Dubourg
, J.
Vanderplas
, A.
Passos
, D.
Cournapeau
, M.
Brucher
, M.
Perrot
, and E.
Duchesnay
, “Scikit-learn: Machine learning in Python
,” J. Mach. Learn. Res.
12
(85
), 2825
–2830
(2011
).106.
W.
Samek
and K.-R.
Müller
, “Towards explainable artificial intelligence
,” in Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
(Springer
, 2019
), pp. 5
–22
.107.
G. P.
Wellawatte
, A.
Seshadri
, and A. D.
White
, “Model agnostic generation of counterfactual explanations for molecules
,” Chem. Sci.
13
(13
), 3697
–3705
(2022
).108.
X.
Jia
, A.
Lynch
, Y.
Huang
, M.
Danielson
, I.
Lang’at
, A.
Milder
, A. E.
Ruby
, H.
Wang
, S. A.
Friedler
, A. J.
Norquist
, and J.
Schrier
, “Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis
,” Nature
573
(7773
), 251
–255
(2019
).109.
D. P.
Kovács
, W.
McCorkindale
, and A. A.
Lee
, “Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias
,” Nat. Commun.
12
, 1695
(2021
).110.
S.
Amos
, “When training and test sets are different: Characterizing learning transfer
,” in Dataset Shift in Machine Learning
, edited by J.
Quiñonero-Candela
, M.
Sugiyama
, A.
Schwaighofer
, and N. D.
Lawrence
(MIT Press
, 2009
), pp. 3-28.111.
M. P.
Preeja
and K. P.
Soman
, “Walk-based graph kernel for drug discovery: A review
,” Int. J. Comput. Appl.
94
(16
), 1
–7
(2014
).112.
K. M.
Borgwardt
, C. S.
Ong
, S.
Schönauer
, S. V.
Vishwanathan
, A. J.
Smola
, and H. P.
Kriegel
, “Protein function prediction via graph kernels
,” Bioinformatics
21
(suppl. 1
), i47
–i56
(2005
).113.
C.
Geng
, Y.
Jung
, N.
Renaud
, V.
Honavar
, A. M. J. J.
Bonvin
, and L. C.
Xue
, “iScore: a novel graph kernel-based function for scoring protein–protein docking models
,” Bioinformatics
36
(1
), 112
–121
(2019
).114.
H.
Ohno
and Y.
Mukae
, “Machine learning approach for prediction and search: Application to methane storage in a metal–organic framework
,” J. Phys. Chem. C
120
(42
), 23963
–23968
(2016
).115.
Y.-H.
Tang
and W. A.
de Jong
, “Prediction of atomization energy using graph kernel and active learning
,” J. Chem. Phys.
150
(4
), 044107
(2019
).116.
G.
Ferré
, T.
Haut
, and K.
Barros
, “Learning molecular energies using localized graph kernels
,” J. Chem. Phys.
146
(11
), 114107
(2017
).117.
Y.
Xiang
, Y.-H.
Tang
, H.
Liu
, G.
Lin
, and H.
Sun
, “Predicting single-substance phase diagrams: A kernel approach on graph representations of molecules
,” J. Phys. Chem. A
125
(20
), 4488
–4497
(2021
).118.
P.
Mahé
, N.
Ueda
, T.
Akutsu
, J.-L.
Perret
, and J.-P.
Vert
, “Extensions of marginalized graph kernels
,” in Proceedings of the Twenty-first International conference on Machine learning
(2004
), p. 70
.119.
K. M.
Borgwardt
and H.-P.
Kriegel
, “Shortest-path kernels on graphs
,” in Fifth IEEE International Conference on Data Mining (ICDM’05)
(IEEE
, 2005
), p. 8
.120.
N.
Shervashidze
, S. V. N.
Vishwanathan
, T.
Petri
, K.
Mehlhorn
, and K.
Borgwardt
, “Efficient graphlet kernels for large graph comparison
,” in Artificial Intelligence and Statistics
(PMLR
, 2009
), pp. 488
–495
.121.
T.
Horváth
, T.
Gärtner
, and S.
Wrobel
, “Cyclic pattern kernels for predictive graph mining
,” in Proceedings of the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
(2004
), pp. 158
–167
.122.
P.
Mahé
and J.-P.
Vert
, “Graph kernels based on tree patterns for molecules
,” Mach. Learn.
75
(1
), 3
–35
(2009
).123.
H.
Fröhlich
, J. K.
Wegner
, F.
Sieker
, and A.
Zell
, “Optimal assignment kernels for attributed molecular graphs
,” in Proceedings of the 22nd International Conference on Machine Learning
(2005
), pp. 225
–232
.124.
P.
Yang
and C.
Simon
, “SimonEnsemble/graph-kernel-SVM-for-toxicity-of-pesticides-to-bees
,” https://github.com/SimonEnsemble/graph-kernel-SVM-for-toxicity-of-pesticides-to-bees (2022
).125.
F.
Oviedo
, J. L.
Ferres
, T.
Buonassisi
, and K. T.
Butler
, “Interpretable and explainable machine learning for materials science and chemistry
,” Acc. Mater. Res.
(published online 2022
).© 2022 Author(s). Published under an exclusive license by AIP Publishing.
2022
Author(s)
You do not currently have access to this content.
