Determining the association between drug and disease is important in drug development. However, existing approaches for drug–disease associations (DDAs) prediction are too homogeneous in terms of feature extraction. Here, a novel graph representation approach based on light gradient boosting machine (GRLGB) is proposed for prediction of DDAs. After the introduction of the protein into a heterogeneous network, nodes features were extracted from two perspectives: network topology and biological knowledge. Finally, the GRLGB classifier was applied to predict potential DDAs. GRLGB achieved satisfactory results on Bdataset and Fdataset through 10-fold cross-validation. To further prove the reliability of the GRLGB, case studies involving anxiety disorders and clozapine were conducted. The results suggest that GRLGB can identify novel DDAs.
Get full access to this article
View all access options for this article.
References
1.
BaiJ, LiY, LiJ, et al.Multinomial random forest. Pattern Recogn, 2022; 122:108331; doi: 10.1016/j.patcog.2021.108331
2.
ChanHCS, ShanH, DahounT, et al.Advancing drug discovery via artificial intelligence. Trends Pharmacol Sci, 2019; 40(10):801; doi: 10.1016/j.tips.2019.07.013
3.
ChenX, RenB, ChenM, et al.NLLSS: Predicting synergistic drug combinations based on semi-supervised learning. Wang E. ed. PLoS Comput Biol, 2016; 12(7):e1004975; doi: 10.1371/journal.pcbi.1004975
4.
GuoZ-H, YouZ-H, HuangD-S, et al.MeSHHeading2vec: A new method for representing MeSH headings as vectors based on graph embedding algorithm. Brief Bioinform, 2021; 22(2):2085–2095; doi: 10.1093/bib/bbaa037
5.
HuangC, WangS, PanX, et al.V-soft margin multi-task learning logistic regression. Int J Mach Learn Cyber, 2019; 10(2):369–383; doi: 10.1007/s13042-017-0721-5
6.
HuangL, LuoH, LiS, et al.Drug–drug similarity measure and its applications. Brief Bioinform, 2020; 24(4):bbaa265; doi: 10.1093/bib/bbaa265
7.
JiangH, HuangY. An effective drug-disease associations prediction model based on graphic representation learning over multi-biomolecular network. BMC Bioinformatics, 2022; 23(1):9; doi: 10.1186/s12859-021-04553-2
8.
JukicMM, SmithRL, HaslemoT, et al.Effect of CYP2D6 genotype on exposure and efficacy of risperidone and aripiprazole: A retrospective, cohort study. Lancet Psychiatry, 2019; 6(5):418–426; doi: 10.1016/S2215-0366(19)30088-4
9.
KonteB, WaltersJTR, RujescuD, et al.HLA-DQB1 6672G>C (Rs113332494) is associated with clozapine-induced neutropenia and agranulocytosis in individuals of European Ancestry. Transl Psychiatry, 2021; 11(1):214; doi: 10.1038/s41398-021-01322-w
10.
LandrumG. RDKit: Open-source cheminformatics from machine learning to chemical registration. Abstracts of Papers of the American Chemical Society;, 2019; 258.
11.
LiG, LuoJ, WangD, et al.Potential CircRNA-Disease Association Prediction Using DeepWalk and Network Consistency Projection. J Biomed Inform, 2020; 112:103624; doi: 10.1016/j.jbi.2020.103624
12.
LiangJ, BuY, TanK, et al.Estimation of stellar atmospheric parameters with light gradient boosting machine algorithm and principal component analysis. AJ, 2022; 163(4):153; doi: 10.3847/1538-3881/ac4d97
13.
LiangX, ZhangP, YanL, et al.LRSSL: Predict and interpret drug–disease associations based on data integration using sparse subspace learning. Berger B. ed. Bioinformatics, 2017; 33(8):1187–1196; doi: 10.1093/bioinformatics/btw770
14.
LiuB-M, GaoY-L, ZhangD-J, et al.A new framework for drug–disease association prediction combing light-gated message passing neural network and gated fusion mechanism. Brief Bioinform, 2022; 23(6):bbac457; doi: 10.1093/bib/bbac457
15.
López-GilX, BabotZ, Amargós-BoschM, et al.Clozapine and haloperidol differently suppress the MK-801-increased glutamatergic and serotonergic transmission in the medial prefrontal cortex of the rat. Neuropsychopharmacol, 2007; 32(10):2087–2097; doi: 10.1038/sj.npp.1301356
16.
LuoY, ZhaoX, ZhouJ, et al.A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous information. Nat Commun, 2017; 8(1):573; doi: 10.1038/s41467-017-00680-8
17.
MullerJE, KoenL, SeedatS, et al.Anxiety disorders and schizophrenia. Curr Psychiatry Rep, 2004; 6(4):255–261; doi: 10.1007/s11920-004-0074-0
18.
NesmerakK, ToropovAA, ToropovaAP, et al.SMILES-based quantitative structure–property relationships for half-wave potential of N-benzylsalicylthioamides. Eur J Med Chem, 2013; 67:111–114; doi: 10.1016/j.ejmech.2013.05.031
19.
SaberianN, PeyvandipourA, DonatoM, et al.A new computational drug repurposing method using established disease–drug pair knowledge. Kelso J. ed. Bioinformatics, 2019; 35(19):3672–3678; doi: 10.1093/bioinformatics/btz156
20.
WangL, YouZ-H, HuangD-S, et al.MGRCDA: Metagraph recommendation method for predicting CircRNA–disease association. IEEE Trans Cybern, 2023; 53(1):67–75; doi: 10.1109/TCYB.2021.3090756
21.
XuS. Bayesian Naïve Bayes classifiers to text classification. J Inform Sci, 2018; 44(1):48–59; doi: 10.1177/0165551516677946
22.
YanS, YangA, KongS, et al.Predictive intelligence powered attentional stacking matrix factorization algorithm for the computational drug repositioning. Appl Soft Comp, 2021; 110:107633; doi: 10.1016/j.asoc.2021.107633
23.
YuZ, HuangF, ZhaoX, et al.Predicting drug–disease associations through layer attention graph convolutional network. Brief Bioinform, 2021; 22(4):bbaa243; doi: 10.1093/bib/bbaa243
24.
YuanJ, Douzal-ChouakriaA, Varasteh YazdiS, et al.A large margin time series nearest neighbour classification under locally weighted time warps. Knowl Inf Syst, 2019; 59(1):117–135; doi: 10.1007/s10115-018-1184-z
25.
ZengX, ZhuS, LiuX, et al.DeepDR: A network-based deep learning approach to in silico drug repositioning. Cowen L. ed. Bioinformatics, 2019; 35(24):5191–5198; doi: 10.1093/bioinformatics/btz418
26.
ZhaoB-W, HuL, YouZ-H, et al.HINGRL: Predicting drug–disease associations with graph representation learning on heterogeneous information networks. Brief Bioinform, 2022; 23(1):bbab515; doi: 10.1093/bib/bbab515
27.
ZhouF, YinM-M, JiaoC-N, et al.Predicting MiRNA-disease associations through deep autoencoder with multiple kernel learning. IEEE Trans Neural Netw Learning Syst, 2021; 1–10; doi: 10.1109/TNNLS.2021.3129772
