Autism Spectrum Disorder and Atypical Brain Connectivity: Novel Insights from Brain Connectivity-Associated Genes by Combining Random Forest and Support Vector Machine Algorithm
Restricted accessResearch articleFirst published online November, 2024
Autism Spectrum Disorder and Atypical Brain Connectivity: Novel Insights from Brain Connectivity-Associated Genes by Combining Random Forest and Support Vector Machine Algorithm
It is estimated that approximately one in every 100 children is diagnosed with autism spectrum disorder (ASD) around the globe. Currently, there are no curative pharmacological treatments for ASD. Discoveries on key molecular mechanisms of ASD are essential for precision medicine strategies. Considering that atypical brain connectivity patterns have been observed in individuals with ASD, this study examined the brain connectivity-associated genes and their putatively distinct expression patterns in brain samples from individuals diagnosed with ASD and using an iterative strategy based on random forest and support vector machine algorithms. We discovered a potential gene signature capable of differentiating ASD from control samples with a 92% accuracy. This gene signature comprised 14 brain connectivity-associated genes exhibiting enrichment in synapse-related terms. Of these genes, 11 were previously associated with ASD in varying degrees of evidence. Notably, NFKBIA, WNT10B, and IFT22 genes were identified as ASD-related for the first time in this study. Subsequent clustering analysis revealed the existence of two distinct ASD subtypes based on our gene signature. The expression levels of signature genes have the potential to influence brain connectivity patterns, potentially contributing to the manifestation of ASD. Further studies on the omics of ASD are called for so as to elucidate the molecular basis of ASD and for diagnostic and therapeutic innovations. Finally, we underscore that advances in ASD research can benefit from integrative bioinformatics and data science approaches.
Get full access to this article
View all access options for this article.
References
1.
AlhassenW, ChenS, VawterM, et al.Patterns of cilia gene dysregulations in major psychiatric disorders. Prog Neuropsychopharmacol Biol Psychiatry, 2021; 109:110255; doi: 10.1016/j.pnpbp.2021.110255
2.
APA. The Diagnostic and Statistical Manual of Mental Disorders. 5th ed. APA; 2013.
3.
Arnold AnteraperS, GuellX, D’MelloA, et al.Disrupted cerebrocerebellar intrinsic functional connectivity in young adults with high-functioning autism spectrum disorder: A data-driven, whole-brain, high-temporal resolution functional magnetic resonance imaging study. Brain Connect, 2019; 9(1):48–59; doi: 10.1089/brain.2018.0581
4.
BonoraE, GrazianoC, MinopoliF, et al.IMGSAC. Maternally inherited genetic variants of CADPS2 are present in autism spectrum disorders and intellectual disability patients. EMBO Mol Med, 2014; 6(6):795–809; doi: 10.1002/emmm.201303235
5.
BorgI, FreudeK, KübartS, et al.Disruption of netrin G1 by a balanced chromosome translocation in a girl with rett syndrome. Eur J Hum Genet, 2005; 13(8):921–927; doi: 10.1038/sj.ejhg.5201429
6.
BrandenburgC, GriswoldAJ, Van BoovenDJ, et al.Transcriptomic analysis of isolated and pooled human postmortem cerebellar purkinje cells in autism spectrum disorders. Front Genet, 2022; 13:944837; doi: 10.3389/fgene.2022.944837
7.
BreimanL. Random forests. Mach Learn, 2001; 45(1):5–32; doi: 10.1023/A:1010933404324
8.
CakirA, TuncerM, Taymaz-NikerelH, et al.Side effect prediction based on drug-induced gene expression profiles and random forest with iterative feature selection. Pharmacogenomics J, 2021; 21(6):673–681; doi: 10.1038/s41397-021-00246-4
9.
Celestino-SoperPB, SkinnerC, SchroerR, et al.Deletions in chromosome 6p22.3-P24.3, including ATXN1, are associated with developmental delay and autism spectrum disorders. Mol Cytogenet, 2012; 5:17; doi: 10.1186/1755-8166-5-17
10.
ChenZ, LongH, GuoJ, et al.Autism-risk gene Necab2 regulates psychomotor and social behavior as a neuronal modulator of mGluR1 signaling. Front Mol Neurosci, 2022; 15:901682; doi: 10.3389/fnmol.2022.901682
11.
ChenY, LunATL, and SmythGK. From reads to genes to pathways: Differential expression analysis of RNA-seq experiments using rsubread and the edger quasi-likelihood pipeline. F1000Res, 2016; 5:1438; doi: 10.12688/f1000research.8987.2
Di BenedettoD, Di VitaG, RomanoC, et al.6p22.3 deletion: Report of a patient with autism, severe intellectual disability and electroencephalographic anomalies. Mol Cytogenet, 2013; 6(1):4; doi: 10.1186/1755-8166-6-4
GeschwindDH, and VoineaguI. Genes dysregulated in autism as biomarkers and targets for therapeutic pathways. 2012.
16.
GoyalMS, and RaichleME. Gene expression-based modeling of human cortical synaptic density. Proc Natl Acad Sci U S A, 2013; 110(16):6571–6576; doi: 10.1073/pnas.1303453110
17.
GuoH, PengY, HuZ, et al.Genome-wide copy number variation analysis in a Chinese autism spectrum disorder cohort. Sci Rep, 2017; 7:44155; doi: 10.1038/srep44155
18.
HelsmoortelC, SwagemakersSMA, VandeweyerG, et al.Whole genome sequencing of a dizygotic twin suggests a role for the serotonin receptor HTR7 in autism spectrum disorder. Am J Med Genet B Neuropsychiatr Genet, 2016; 171(8):1049–1056; doi: 10.1002/ajmg.b.32473
19.
HillDS, CabreraR, Wallis SchultzD, et al.Autism-like behavior and epigenetic changes associated with autism as consequences of in utero exposure to environmental pollutants in a mouse model. Behav Neurol, 2015; 2015:426263; doi: 10.1155/2015/426263
20.
HongW, LuY, ZhouX, et al.Usefulness of random forest algorithm in predicting severe acute pancreatitis. Front Cell Infect Microbiol, 2022; 12:893294; doi: 10.3389/fcimb.2022.893294
21.
HuangH, McGarveyPB, SuzekBE, et al.A comprehensive protein-centric ID mapping service for molecular data integration. Bioinformatics, 2011; 27(8):1190–1191; doi: 10.1093/bioinformatics/btr101
22.
HuynhP-H, NguyenVH, and DoT-N. Improvements in the large p, small n classification issue. SN Comput Sci, 2020; 1(4):207; doi: 10.1007/s42979-020-00210-2
23.
JinY, LanA, DaiY, et al.Development and testing of a random forest-based machine learning model for predicting events among breast cancer patients with a poor response to neoadjuvant chemotherapy. Eur J Med Res, 2023; 28(1):394; doi: 10.1186/s40001-023-01361-7
24.
KaltschmidtB, HelwegLP, GreinerJFW, et al.NF-κB in neurodegenerative diseases: Recent evidence from human genetics. Front Mol Neurosci, 2022; 15:954541; doi: 10.3389/fnmol.2022.954541
25.
KolbergL, RaudvereU, KuzminI, et al.G:Profiler—Interoperable web service for functional enrichment analysis and gene identifier mapping (2023 Update). Nucleic Acids Res, 2023; 51(W1):W207–W212; doi: 10.1093/nar/gkad347
26.
KoldeR. Pheatmap. 2019.
27.
LinJC, HoW-H, GurneyA, et al.The netrin-G1 ligand NGL-1 promotes the outgrowth of thalamocortical axons. Nat Neurosci, 2003; 6(12):1270–1276; doi: 10.1038/nn1148
28.
LintasC, PicinelliC, PirasIS, et al.Copy Number variation in 19 Italian multiplex families with autism spectrum disorder: Importance of synaptic and neurite elongation genes. Am J Med Genet B Neuropsychiatr Genet, 2017; 174(5):547–556; doi: 10.1002/ajmg.b.32537
LoveMI, HuberW, and AndersS. Moderated estimation of fold change and dispersion for RNA-Seq data with DESeq2. Genome Biol, 2014; 15(12):550; doi: 10.1186/s13059-014-0550-8
31.
MasiA, DeMayoMM, GlozierN, et al.An overview of autism spectrum disorder, heterogeneity and treatment options. Neurosci Bull, 2017; 33(2):183–193; doi: 10.1007/s12264-017-0100-y
32.
MiczánV, KelemenK, GlavinicsJR, et al.NECAB1 and NECAB2 are prevalent calcium-binding proteins of CB1/CCK-positive GABAergic interneurons. Cereb Cortex, 2021; 31(3):1786–1806; doi: 10.1093/cercor/bhaa326
33.
MisraS, and LiH. noninvasive fracture characterization based on the classification of sonic wave travel times. In: Machine Learning for Subsurface Characterization. (MisraS, LiH, and HeJ, eds.) Gulf Professional Publishing, 2020, pp. 243–287; doi: 10.1016/B978-0-12-817736-5.00009-0
34.
NeulJL. The relationship of rett syndrome and MECP2 disorders to autism. Dialogues Clin Neurosci, 2012; 14(3):253–262.
35.
NewschafferCJ, CroenLA, DanielsJ, et al.The epidemiology of autism spectrum disorders. Annu Rev Public Health, 2007; 28(1):235–258; doi: 10.1146/annurev.publhealth.28.021406.144007
36.
ObergasteigerJ, ÜberbacherC, PramstallerPP, et al.CADPS2 gene expression is oppositely regulated by LRRK2 and Alpha-synuclein. Biochem Biophys Res Commun, 2017; 490(3):876–881; doi: 10.1016/j.bbrc.2017.06.134
O’RoakBJ, VivesL, GirirajanS, et al.Sporadic autism exomes reveal a highly interconnected protein network of de novo mutations. Nature, 2012; 485(7397):246–250; doi: 10.1038/nature10989
39.
PerkinsRS, SinghR, AbellAN, et al.The role of WNT10B in physiology and disease: A 10-year update. Front Cell Dev Biol, 2023; 11:1120365; doi: 10.3389/fcell.2023.1120365
40.
PintoD, DelabyE, MericoD, et al.Convergence of genes and cellular pathways dysregulated in autism spectrum disorders. Am J Hum Genet, 2014; 94(5):677–694; doi: 10.1016/j.ajhg.2014.03.018
41.
PisnerDA, and SchnyerDM. Support vector machine. In: Machine Learning. (MechelliA and VieiraS, eds.) Academic Press, 2020, pp. 101–121; doi: 10.1016/B978-0-12-815739-8.00006-7
42.
PragyaN, GovarthanPK, SinhaK, et al.Differential gene expression data analysis of ASD using random forest. Stud Health Technol Inform, 2023; 302:1047–1051; doi: 10.3233/SHTI230344
43.
RediesC, HertelN, and HübnerCA. Cadherins and neuropsychiatric disorders. Brain Res, 2012; 1470:130–144; doi: 10.1016/j.brainres.2012.06.020
44.
RichiardiJ, AltmannA, MilazzoA-C, et al.IMAGEN consortium. Correlated gene expression supports synchronous activity in brain networks. Science, 2015; 348(6240):1241–1244; doi: 10.1126/science.1255905
45.
SadakataT, KakegawaW, MizoguchiA, et al.Impaired cerebellar development and function in mice lacking CAPS2, a protein involved in neurotrophin release. J Neurosci, 2007a;27(10):2472–2482; doi: 10.1523/JNEUROSCI.2279-06.2007
46.
SadakataT, WashidaM, IwayamaY, et al.Autistic-like phenotypes in cadps2-knockout mice and aberrant CADPS2 splicing in autistic patients. J Clin Invest, 2007b;117(4):931–943; doi: 10.1172/JCI29031
47.
SakaiY, ShawCA, DawsonBC, et al.Protein interactome reveals converging molecular pathways among autism disorders. Sci Transl Med, 2011; 3(86):86ra49; doi: 10.1126/scitranslmed.3002166
48.
SandersSJ, Ercan-SencicekAG, HusV, et al.Multiple Recurrent de Novo CNVs, including duplications of the 7q11.23 williams syndrome region, are strongly associated with autism. Neuron, 2011; 70(5):863–885; doi: 10.1016/j.neuron.2011.05.002
49.
SchaeferGB, and MendelsohnNJ, Professional Practice and Guidelines Committee. Clinical genetics evaluation in identifying the etiology of autism spectrum disorders: 2013 guideline revisions. Genet Med, 2013; 15(5):399–407; doi: 10.1038/gim.2013.32
50.
SchmidtERE, and PolleuxF. Genetic mechanisms underlying the evolution of connectivity in the human cortex. Front Neural Circuits, 2021; 15:787164; doi: 10.3389/fnins.2021.797849
51.
ScullyC. 28—impairment and disability. In: Scully’s Medical Problems in Dentistry (Seventh Edition). (ScullyC, ed.) Churchill Livingstone: Oxford; 2014; pp. 676–686; doi: 10.1016/B978-0-7020-5401-3.00028-X
SmithKR, JonesKA, KopeikinaKJ, et al.Cadherin-10 maintains excitatory/inhibitory ratio through interactions with synaptic proteins. J Neurosci, 2017; 37(46):11127–11139; doi: 10.1523/JNEUROSCI.1153-17.2017
55.
StylesM, AlsharshaniD, SamaraM, et al.Risk factors, diagnosis, prognosis and treatment of autism. Front Biosci (Landmark Ed), 2020; 25(9):1682–1717; doi: 10.2741/4873
56.
SudharshanR, SinhaK, Manohari BalachanderG, et al.Comparing pertubagens from differential gene expression data analysis of ASD using random forest and statistical test. Curr Dir Biomed Eng, 2023; 9(1):682–685; doi: 10.1515/cdbme-2023-1171
57.
SunC, ZouM, WangX, et al.FADS1-FADS2 and ELOVL2 gene polymorphisms in susceptibility to autism spectrum disorders in chinese children. BMC Psychiatry, 2018; 18(1):283; doi: 10.1186/s12888-018-1868-7
58.
TeeuwJ, BrouwerRM, GuimarãesJ, et al.Genetic and environmental influences on functional connectivity within and between canonical cortical resting-state networks throughout adolescent development in boys and girls. Neuroimage, 2019; 202:116073; doi: 10.1016/j.neuroimage.2019.116073
ValléeA, and ValléeJ-N. Warburg effect hypothesis in autism spectrum disorders. Mol Brain, 2018; 11(1):1; doi: 10.1186/s13041-017-0343-6
61.
VissersME, XCohenM, and GeurtsHM. Brain connectivity and high functioning autism: A promising path of research that needs refined models, methodological convergence, and stronger behavioral links. Neurosci Biobehav Rev, 2012; 36(1):604–625; doi: 10.1016/j.neubiorev.2011.09.003
62.
WangK, ZhangH, MaD, et al.Common genetic variants on 5p14.1 associate with autism spectrum disorders. Nature, 2009; 459(7246):528–533; doi: 10.1038/nature07999
63.
Ward JrJH. Hierarchical grouping to optimize an objective function. J Am Stat Assoc, 1963; 58(301):236–244; doi: 10.1080/01621459.1963.10500845
64.
WeisnerPA, ChenC-Y, SunY, et al.A mouse mutation that dysregulates neighboring Galnt17 and Auts2 genes is associated with phenotypes related to the human AUTS2 syndrome. G3 (Bethesda), 2019; 9(11):3891–3906; doi: 10.1534/g3.119.400723
65.
WilliamsB, HalloinC, LöbelW, et al., et al.Data-driven model development for cardiomyocyte production experimental failure prediction. In: Computer Aided Chemical Engineering. (PierucciS, ManentiF, BozzanoGL, eds.). 30 European Symposium on Computer Aided Process Engineering Elsevier; 2020; pp. 1639–1644; doi: 10.1016/B978-0-12-823377-1.50274-3
66.
YangL, WuH, JinX, et al.Study of cardiovascular disease prediction model based on random forest in Eastern China. Sci Rep, 2020; 10(1):5245; doi: 10.1038/s41598-020-62133-5
67.
YoonSH, ChoiJ, LeeWJ, do, et al.Genetic and epigenetic etiology underlying autism spectrum disorder. J Clin Med, 2020; 9(4)i; doi: 10.3390/jcm9040966
68.
ZeidanJ, FombonneE, ScorahJ, et al.Global prevalence of autism: A systematic review update. Autism Res, 2022; 15(5):778–790; doi: 10.1002/aur.2696
69.
ZhangA, LiuL, ChangS, et al.Connectivity-based brain network supports restricted and repetitive behaviors in autism spectrum disorder across development. Front Psychiatry, 2022; 13:874090; doi: 10.3389/fpsyt.2022.874090
70.
ZhangX, XieY, TangJ, et al.Dissect relationships between gene Co-expression and functional connectivity in human brain. Front Neurosci, 2021; 15:797849; doi: 10.3389/fnins.2021.797849
71.
ZhuX, JooY, BossiS, et al.Tdrd3-null mice show post-transcriptional and behavioral impairments associated with neurogenesis and synaptic plasticity. Prog Neurobiol, 2024; 233:102568; doi: 10.1016/j.pneurobio.2024.102568
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
