Identifying Distinct Tourette Disorder Subtypes using Clinical Data

Identifying Distinct Tourette Disorder Subtypes using Clinical Data | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Identifying Distinct Tourette Disorder Subtypes using Clinical Data Subramanian Krishnamurthy , Tourette International Collaborative Genetics (TIC Genetics) , Robert A. King , Jay A. Tischfield , Gary A. Heiman , Jinchuan Xing doi: https://doi.org/10.1101/2025.11.09.25339700 Subramanian Krishnamurthy 1 Department of Genetics, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA 2 Human Genetics Institute of New Jersey, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA MS Find this author on Google Scholar Find this author on PubMed Search for this author on this site 1 Department of Genetics, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA Robert A. King 3 Yale Child Study Center, Yale School of Medicine , New Haven, CT 06510, USA MD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Jay A. Tischfield 1 Department of Genetics, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA 2 Human Genetics Institute of New Jersey, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site Gary A. Heiman 1 Department of Genetics, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA 2 Human Genetics Institute of New Jersey, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: heiman{at}rutgers.edu jinchuan.xing{at}rutgers.edu Jinchuan Xing 1 Department of Genetics, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA 2 Human Genetics Institute of New Jersey, Rutgers, The State University of New Jersey , Piscataway, NJ 08854, USA PhD Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: heiman{at}rutgers.edu jinchuan.xing{at}rutgers.edu Abstract Full Text Info/History Metrics Data/Code Preview PDF Abstract Tourette Disorder (TD), or Tourette Syndrome, is a highly heterogeneous childhood-onset neurodevelopmental disorder with a global prevalence of 0.5%. TD’s large phenotypic heterogeneity, variable heritability patterns, and frequent but varied comorbidity with other neurodevelopmental disorders indicate that different TD patients might have different etiologies. In this study, we performed unsupervised clustering of clinical data, such as categorical diagnoses and comorbidities, from 865 subjects with TD from the Tourette International Collaborative Genetics (TIC Genetics) study to detect Tourette Disorder subtypes. Using two different clustering methods, K-Means and Bayesian Hierarchical Clustering, we identified five distinct, clinically relevant subtypes. These subtypes are characterized by both previously described TD comorbidities, such as Obsessive-Compulsive Disorder (OCD) and Attention Deficit/Hyperactivity Disorder (ADHD), as well as other characteristics, such as sex and region. Defining clinically relevant TD subtypes could enable better diagnostics, treatment, and the understanding of TD etiology. In addition, stratified analysis of genetic data based on these phenotypic subtypes may help identify genes contributing to each TD subtype and provide insights into the disease variability. Introduction Tourette Disorder (TD), also called Tourette Syndrome, is characterized by multiple motor tics and at least one vocal tic, occurring many times a day (usually in bouts) nearly daily or intermittently for at least a year, with an onset before age 18 [ 1 ]. Most subjects with TD over the age of 10 report premonitory urges that are relieved by tics [ 2 ]. Coprophenomena (such as copropraxia or coprolalia) may occur when tics are most severe [ 2 ]. In addition, there are also sex-dependent differences in the phenotypic expression of TD, with males more often showing tic-related behaviors and females more often exhibiting Obsessive-Compulsive Symptoms/Behaviors (OCS/OCB) [ 3 , 4 ]. Twin and family studies have established that TD bears a strong genetic component with an unclear inheritance pattern, probably due to polygenic cause [ 5 , 6 ]. Large-scale genetic studies of TD have identified specific classes of genetic variation that contribute to the genetic risk of TD, including common variants [ 7 ], segregating variants, rare copy number variants, and de novo variants that impact protein-coding sequences [ 8 – 11 ]. Approximately 88% of TD subjects have one or more other Neurodevelopmental Disorders (NDDs) as comorbidities [ 12 ], such as Obsessive-Compulsive Disorder (OCD, ~30-50%), Attention Deficit/Hyperactivity Disorder (ADHD, ~50-60%) and to a lesser extent, Autism Spectrum Disorder (ASD, ~10%), as well as anxiety, depression, and other conditions [ 13 ]. Given the substantial genetic and phenotypic heterogeneity of TD, identifying distinct subtypes could assist in better diagnosis and treatment, as well as enable a better understanding of genetic architecture through stratified analysis of genetic data. Several prior studies (reviewed in [ 14 ]) have attempted to identify common factors and subtypes of TD. For example, one study examined heritability and polygenic load associated with TD, OCD, and ADHD using symptom-level factors [ 15 ]. Latent class analyses of subjects with TD identified three major TD-affected groups: 1) TD + OCS/OCB, 2) TD + OCD, and 3) TD + OCD + ADHD [ 16 ]. In two studies of TD comorbid disorder clusters and their heritability, TD + OCD and TD + OCD + ADHD were considered heritable while TD + ADHD was not [ 17 , 18 ]. In another study of clinical factors of 139 subjects with TD, two subtypes of tic disorders with severe (21.6%) and mild (78.4%) symptoms were identified [ 19 ]. A 6-factor exploratory factor analysis of forty-nine motor and phonic tics in 3,494 individuals (1,191 TS probands and 2,303 first-degree relatives) identified social disinhibition as a heritable subtype of TD [ 20 ]. Although these studies provided useful information, they had limited ability to comprehensively identify TD subtypes, because many of them were based on cohorts with either limited subsets of available phenotypic information (i.e., comorbidities or symptoms), small sample size, and/or subjects that were demographically homogeneous. In this study, we identified subsets with TD using unsupervised clustering of clinical and demographic data from the Tourette International Collaborative Genetics (TIC Genetics) study, a large international study with over 20 sites across the United States, Europe, Israel, and South Korea [ 21 ]. This large, uniformly assessed clinical dataset enabled us to identify five clinically relevant subtypes that will enhance the understanding of the heterogeneity of TD. Materials and Methods Clinical Data The clinical data were collected between 2011 and 2023 as a part of the TIC Genetics Study [ 21 ]. The Institutional Review Board approved the study protocol at each local site. Informed consent was obtained from all participants (or in the case of minors, from their parents). The clinical assessment methods and definitions of TD, OCD, ADHD, and Trichotillomania have been previously described in detail [ 21 ], and are based on the Diagnostic and Statistical Manual of Mental Disorders—Fourth edition, Text Revision (DSM-IV-TR) [ 22 ] or Fifth edition (DSM-5) [ 1 ]. Clinicians were trained to record all symptoms and perform diagnoses in a consistent manner to ensure quality and reliability across all sites. Detailed clinical data were acquired from an extensive written questionnaire which was completed by the participant or by the parent in the case of young probands. This information was validated in a semi-structured interview by an experienced clinician and recorded in a standardized fashion. Items included demographic information, details of tic, OCS/OCB/OCD, ADHD, and trichotillomania (including ages of onset), and other potentially relevant conditions. Based on the questionnaire and interview information, the clinician made lifetime diagnoses for 4,435 subjects, including probands with TD, both affected and unaffected parents, and some affected and unaffected siblings [ 21 ]. Data Preprocessing To improve the precision of subtype identification, we focused strictly on patients with TD diagnosis and excluded other tic disorders, such as other chronic, provisional, and transient forms. Among subjects that had TD, we excluded those that have any missing or “unable to rate” value for any of the Tic, Obsessive Compulsive, or Attention-disorder-Hyperactivity diagnoses. We also excluded subjects with potentially confounding factors flagged by clinicians, including “atypical presentation”, “psychosis”, “other severe neurological condition”, “congenital anomalies”, “genetic syndrome/chromosomal abnormality”, “other significant psychiatric history”, and “other significant medical history”. From each family, we selected only one member diagnosed with TD to minimize confounding effects of shared genetics. Twenty-two centers around the world were grouped into 3 regions: USA, Europe, and Asia. A description of the detailed clinical data variables for each subject included in this study is available in Supplementary Table S1. Some variables in our clinical dataset are mutually exclusive. For example, for OCD diagnosis, each subject belongs to one of the following categories: No OC disorder/symptoms, OC Subclinical, OC Symptoms, or OCD. In these cases, these mutually exclusive variables were combined into a single categorical variable (Supplementary Table S2). Because the age of onset for a given disorder was usually from parents’ recollection and the exact age has a high uncertainty, it was converted into two categories: “Early” ( 10y) based on the guidance from TD clinicians. In a few cases (<10%) where the age of onset was not available, age at diagnosis was used as a proxy. The age of onset of subjects with no diagnosis of the disorder was coded as “Never”. We used two categories for birth: “single” or “multiple” (>=2). After preprocessing, 14 categorical variables were selected for clustering (Supplementary Table S2). Exploratory data analysis and clustering method testing Characteristics and distribution of individual variables were analyzed to examine the dataset. Pairwise associations between variables were calculated as Cramer’s V statistics using the “CramersV” function in the R package “rcompanion” (version 2.5) [ 23 ]. Several clustering methods were tested (Supplementary Table S3), and two unsupervised clustering methods, K-Means and Bayesian Hierarchical Clustering (BHC) [ 24 ], were selected to identify TD subtypes. As the statistical methods chosen for our study are designed to handle highly correlated variables, we retained the correlated variables to provide additional insight into specific cluster characteristics. K-Means clustering K-means clustering is an unsupervised clustering method that partitions n observations into k clusters in which each observation belongs to the cluster with the closest cluster mean. Multiple Correspondence Analysis (MCA) [ 25 ] was used to convert categorical variables into principal components (PCs). This enabled us to: 1. reduce noise by removing less significant PCs with small contribution to the overall variance, and 2. use clustering methods that require continuous variables. K-means clustering was performed using the K-Means function in R using the “stats” package (version 4.4.3). The number of clusters (centers = k) from 2 to 20 were tested. To ensure robust convergence and reproducibility, the algorithm was run with 5,000 iterations and 1,000 random starts. Euclidean distance was used as the distance metric and the clustering method described by Hartigan and Wong (1979) [ 26 ]. The optimal number of clusters was identified based on the silhouette statistics, which combines cluster cohesion (how well each data point fits within its assigned cluster) and cluster separation (compared to other clusters) into a single, interpretable value. Bayesian Hierarchical Clustering (BHC) The BHC method performs bottom-up hierarchical clustering, using a Dirichlet Process (infinite mixture) to model uncertainty in the data and Bayesian model selection, to identify clusters that can be merged at each step [ 24 ]. This method works with categorical data and automatically optimizes Dirichlet process concentration variable to infer the optimal number of clusters. BHC clustering was performed using the BHC BioConductor package (version 1.56.0) in R with default variables. Cluster characteristics Variable importance was inferred using V-measure (or Normalized Mutual Information, calculated by “V-test” using “FactoMineR”, version 2.11, in R). V-measure is a single metric, computed based on percentage of the cluster that has a given characteristic and percentage of the population with a given characteristic that is in the cluster, which is an average of homogeneity and completeness. Key variables that define the cluster characteristics have high V-measure. The relative importance of each variable on each cluster was determined by Fisher’s exact test or V-Test. Tools R was used for all statistical analyses, and an overview of all R packages used in the analysis is listed in Supplementary Table S4. Data availability All data used in this study are provided in Supplementary Table S1. Results Data pre-processing and exploratory analyses An overview of the data processing and analysis pipeline is provided in Figure 1 . For clustering, we selected subjects diagnosed with TD (1,548) and excluded subjects with genetic abnormalities or severe psychiatric conditions (421) (see Methods for details). In addition, we excluded subjects with who were rated “Unable to rate” for Tic, Obsessive-compulsive, or Attention-deficit-Hyperactivity disorder diagnoses. To limit the effects of genetic relatedness, we selected one offspring from each family. The final data set used for identifying subtypes includes 865 offspring diagnosed with TD. Counts by category for each variable are included in the Supplementary Table S2. Download figure Open in new tab Figure 1. Analysis Pipeline overview. We first performed exploratory data analysis to understand the characteristics of data, such as variable distribution, completeness, and correlation. We then evaluated several unsupervised clustering methods (Supplementary Table S3) to identify methods that produce stable clusters. After testing, we selected two methods, K-Means and BHC for the final clustering and analysis of the data. After the cluster identification, we used V-Test to identify key factors that define the characteristics of each cluster and Fisher’s exact test to assess the impact of factors on each cluster. To understand the relationship between selected variables, we computed pairwise association among the variables using Cramer’s V statistic ( Supplemental Figure 1 ). The observed high association between OCD-related variables, ADHD-related variables, and Trichotillomania-related variables are expected. There were no other significant associations among the variables. After evaluating eight unsupervised clustering methods (Supplementary Table S3), and many different subsets of data (Supplementary Table S5), we selected two methods that produced stable clusters with our dataset: K-Means and Bayesian Hierarchical Clustering. Because these methods can accommodate correlated variables, we included correlated variables such as disease diagnosis, subtypes, and current symptom, in our analyses. K-Means Clustering To perform K-Means clustering, we used MCA to generate PCs from the dataset. When we provided all PCs to K-means clustering in our initial testing, it resulted in unstable clusters. These results are probably due to inherent variability in the clinical data. The later PCs capture mostly noise rather than meaningful structure in the clinical data. Therefore, we evaluated systematically excluding the least important PCs, one at a time, to reduce the noise in the dataset. For each set of PCs, we assessed the cluster number (K) from 2 to 20 and repeated the analysis 100 times to assess the stability. This resulted in the selection of the top three PCs (account for >35% of the variance), that produced five stable clusters (Silhouette Plot, Supplementary Figure 2 ). Though 7 clusters have a slightly higher silhouette width, there is a drop in width for 6 clusters. We chose 5 clusters based on biological relevance. Download figure Open in new tab Figure 2. K-Means Clusters. A . Major factors determining cluster characteristics. Positive values are positive correlations, while negative values are negative correlations. The larger the value, the stronger the correlation. B-D . Cluster plots on first three principal components. Each subject is shown as a dot, while the color of the dot corresponding to the cluster assignment. The centroid of each cluster is shown as a big dot. Next, we identified the variables that most significantly correlated (positively or negatively) with cluster identity ( Figure 2A ). For example, trichotillomania diagnosis is positively correlated only with cluster 2 (TrichDiag=TRUE), indicating grouping of subjects with trichotillomania in this cluster. ADHD is negatively correlated with cluster 3 (ADHDDiag=No ADHD). Plotting cluster memberships along the top three PCs confirmed clear separation of clusters along the three PCs, suggesting robust clustering and visually confirming the quality of clusters identified ( Figures 2B–D ). The detailed contribution and significance of each variable to each cluster are listed in Supplementary Data: K-Means.xlsx, including percentage of subjects in a category in each cluster, percentage of subjects in each cluster in a category, percentage of subjects in a category in the whole data set, and v-test for the significance of each variable. These results provide details for each statistically significant variable for each cluster, allowing us to fully understand the cluster characteristics. Overall, 12 out of 14 variables show statistically significant contribution to the clusters, including all variables associated with OCD, ADHD, trichotillomania, region, and sex (Supplementary Data: KMeans.xlsx – test.ch2 tab). Based on the variable contribution to the clusters and the individual membership of each cluster, we determined the defining characteristics of each cluster (Supplementary Table S6). To make the results more comprehensible, we describe all diagnosis variables for a given disorder as one category in the sections below (e.g., “ADHD” for “ADHD diagnosis” and “ADHD current symptom”) and included the p-value for the most statistically significant variable. Cluster 1 subjects (n=210) have ADHD (p=3.6E −71 ), early OCD age of onset (p=1.7E −46 ), no trichotillomania (p=1.1E −5 ), higher prevalence of males (p=2.2E −8 ) and ASD (p=7.9E −4 ). Cluster 2 subjects (n=40) have trichotillomania (p=6.7E −70 ), with higher prevalence of subjects from the USA (p=6.9E −4 ) and OCD (p=8.0E −4 ). Cluster 3 subjects (n=289) have high prevalence of OCD (p=4.0E −52 ), low levels of ADHD (p=4.0E −49 ), no trichotillomania (p=5.4E −8 ), higher prevalence of females (p=1.1E −6 ) and European subjects (p=1.8E −3 ). Cluster 4 subjects (n=229) have low NDD comorbidities, with no OCD (p=7.4E −127 ), very low ADHD (p=7.4E −45 ), no trichotillomania (p=3.3E −6 ), low prevalence of ASD (p=5.1E −6 ), and a high proportion of South Korean subjects (p=2.3E −6 ). Cluster 5 (n=97) comprises subjects with TD that have no OCD (p=5.6E −45 ), high prevalence of ADHD (p=2.6E −32 ), ASD (p=1.0E −3 ), and males (p=1.1E −4 ). BHC BHC clustering using the data set with 14 categorical variables identified six clusters. We identified the variables that most significantly correlated (positively or negatively) with cluster identity ( Figure 3A ). Plotting cluster memberships along the top three PCs confirmed clear separation, suggesting robust clustering ( Figures 3B-D ) and similarity between clustering produced by K-Means and BHC. The detailed contribution and significance of each variable to each cluster are listed in Supplementary Data BHC.xlsx. Like the K-mean clustering analysis, 11 out of 14 variables show a statistically significant contribution to the clusters (Supplementary Data: BHC.xlsx – test.ch2 tab). Download figure Open in new tab Figure 3. BHC Clusters. A. Cluster characteristics heatmap. Positive values are positive correlations, while negative values are negative correlations. The larger the value, the stronger the correlation. B-D . Cluster plots on first three principal components. Each subject is shown as a dot, while the color of the dot corresponding to the cluster assignment. The centroid of each cluster is shown as a big dot. Next, we examined the characteristics of each of the six clusters (Supplementary Table S7). Cluster 1 (n=120) comprises subjects with TD that have a high prevalence of ADHD (p=8E −44 ), no OCD (p=5.2E −57 ), and no trichotillomania (p=2.2E −3 ). Cluster 2 subjects (n=206) have low NDD comorbidities such as no OCD (p=7.9E −110 ), very low ADHD (p=7.3E −60 ), an absence of trichotillomania (p=1.4E −5 ), and a low prevalence of ASD (p=3.6E −5 ). Cluster 3 subjects (n=30) have trichotillomania (p=2.9E −47 ), with a higher prevalence of OCD (p=2.8E −8 ), and are more likely to be from the USA (p=1.2E −3 ). Cluster 4 subjects (n=10) have trichotillomania (p=1.4E −14 ) and no OCD (p=1.3E −3 ). Cluster 5 subjects (n=250) have a high prevalence of OCD (p=2.1E −49 ), low levels of ADHD (p=2.3E −64 ), an absence of trichotillomania (p=8.1E −7 ), and an increased proportion of females (p=4.2E −5 ). Cluster 6 subjects (n=249) have ADHD (p=3.4E −81 ), OCD (p=1.3E −42 ), no trichotillomania (p=8.7E −7 ), and a higher proportion of males (p=3.6E −5 ). Comparison of K-Means and BHC’s results K-Means uses a distance metric (Euclidean distance) and requires specification of the number of clusters. On the other hand, BHC uses an infinite mixture model to infer the optimal number of clusters and does not require specification of a distance metric. Fraction of members in each K-Means cluster that are in each BHC cluster is depicted in a heatmap in Figure 4 . Both methods resulted in four large clusters of similar sizes and characteristics, as illustrated in PC plots ( Figures 2 and 3 ) and Table 1 . These large clusters differ from each other only in minor characteristics and slightly varying memberships. Besides the four large clusters, K-Means clustered all trichotillomania patients together in one cluster, while BHC split them into two clusters (with and without OCD). View this table: View inline View popup Download powerpoint Table 1 Comparison of K-Means (KM) and BHC Clusters Download figure Open in new tab Figure 4. K-Means and BHC Cluster Comparison Fraction of K-Means cluster members in each BHC Cluster in descending order of overlap. For example, 75% and 25% of the K-Means cluster 2 members are in BHC cluster 3 and 4, respectively. As only 4.6% (40 of 865) of the subjects have trichotillomania and only 10 of those have OCD, we conclude that our study has identified five clinically relevant subtypes. Most significant variables (low p-value) that characterize each subtype and differentiate it from others are highlighted ( Table 1 ). Discussion Tourette disorder has high phenotypic heterogeneity, high comorbidity with other NDDs, and varying rates of shared heritability with other NDDs, suggesting distinct underlying genetic causes for different TD subjects. In this study, we performed unsupervised clustering analysis of clinical data from 865 TD subjects in the TIC Genetics study. The analyses identified five clinically relevant subtypes and highlighted shared characteristics among TD patients. Prior attempts to identify specific genes or alleles contributing to disease risk have yielded only two genes with rare damaging variants that confer large effects and a single common variant of small individual effect [ 8 , 9 ]. Stratified genetic analysis of TD subjects based on additional clinical features may help identify more genetically homogenous cohorts and improve power for gene discovery. Furthermore, identifying clinically relevant subtypes could enable better diagnostics and treatment. Earlier attempts to identify subtypes often relied on small sample sets from single cohort [ 2 , 16 , 28 , 29]. In addition, these studies usually relied on prior hypotheses regarding a subset of factors that were the cause of differentiation. To overcome these limitations, we performed unsupervised clustering analyses, using consistent clinical data from over 20 global sites, without filtering variables using prior hypothesis. This analysis enabled us to build on prior knowledge and identify novel TD subtypes. A major challenge in clinical data analysis lies in the presence of noise and occasional misclassification, which can compromise the reliability of findings. Therefore, data selection and cleanup are essential. In addition, we also evaluated several unsupervised clustering methods to identify the optimal methods for our data set (Supplementary Table S3). After evaluating a variety of data set selection criteria and clustering methods, we selected only TD subjects for our final dataset (Supplementary Table S1) and identified two methods, K-Means and BHC, that worked well with our dataset. Final dataset was selected to be as complete and homogeneous as possible and the methods were selected to ensure stable clustering. The two methods are quite different from each other. K-Means clustering was performed with PCs from MCA using the Euclidean Distance metric. The number of clusters was determined using Silhouette Statistics, coupled with the stability of the clusters generated. On the other hand, BHC differs from traditional distance-based agglomerative clustering algorithms in several ways: (1) it defines a probabilistic model to compute the probability of a subject belonging to any of the existing clusters in the tree; (2) it uses a model-based criterion to decide on merging clusters rather than an ad-hoc distance metric; and (3) the number of clusters is automatically determined [ 24 ]. In our analysis, K-means identified five clusters while BHC identified six clusters. The largest four clusters from both methods have similar size and characteristics. Because BHC used all the (categorical) data, while K-Means clustering used the first three PCs, this might account for the slight differences in cluster sizes and minor characteristics. Nevertheless, as we started without any assumption regarding the number of subtypes, the identification of similar sets of clinically relevant clusters by two different methods ( Table 1 ) increases our confidence in the results. In addition to confirming earlier findings on the importance of highly prevalent comorbidities such as ADHD and OCD [ 16 ], this large and diverse dataset identified new clusters that illustrate the importance of other clinically relevant factors such as trichotillomania and sex in TD subjects. Trichotillomania is an often debilitating psychiatric condition characterized by recurrent hair-pulling, which can lead to disfiguring hair loss and significant distress and social impairment, and has been associated with elevated rates of anxiety, depression, ADHD, and OCD (DSM-5) [ 1 ]. In DSM-5, it is classified under OCD-related Disorders. The condition has significant heritability according to twin studies, a shared genetic liability with OCD and other OCD-related factors, as well as a distinct factor specific to hair-pulling and skin-picking [ 27 ]. Our study found subjects with TD and comorbid trichotillomania appear more likely to have OCD, reaffirming the earlier results. Another advantage of the TIC Genetics cohort is its geographical diversity. Subjects were from the USA, Europe, Israel, and South Korea, which permitted us to assess the potential population-specific genetic contribution to TD subtypes. Subjects from TIC Genetics centers in South Korea include 69 Asians (~8.4% of the total TIC Genetics cohort). Only about 10% of all Asian subjects with a diagnosis of TD also had a diagnosis of OCD, as compared to 40-60% observed in Caucasian subjects with TD diagnosis. A prior cross-national study indicated a lower prevalence of OCD among Asians compared to the worldwide prevalence [ 28 ]. Determining whether the apparent difference in rates of OCD comorbidity among regions is due to genetic variation among populations or other factors is an important question requiring further study. In addition, there are higher proportion of TD subjects with minimal or no NDD comorbidity subjects from the USA and Europe than from South Korea, suggesting ancestry/genetic background and/or assessment differences might account for some of these findings. In addition, due to the uneven representation of different geographical regions in our study, further study with larger data sets is needed to confirm our observations based on population specific contributions. While our dataset is larger than most prior studies and has more variables, this study still has several limitations. First, compared with phase 1, TIC Genetics phase 2 focused on recruiting simplex trios. However, we confirmed that this did not affect the unsupervised clustering because adding study phase as a variable did not affect the clustering results (data not shown). Second, as subjects with TD made up the vast majority of the subjects with tic disorders in the study, we only included subjects with TD to improve cluster stability. A larger dataset, including more subjects with other tic disorder diagnoses, could permit better clustering despite the noisiness of the data and provide better grouping of tic disorder subtypes in addition to TD. Third, our dataset might not be large or varied enough to identify all the underlying subtypes with high accuracy. Larger data sets will enable us to effectively use machine learning and other methods (e.g., Variational Auto Encoders) for unsupervised clustering. Lastly, in addition to observations by the clinicians, a portion of the data is self-reported by the subject or their parents and might produce an uncertain level of errors. Even though the clinicians in the TIC Genetics study were trained to record the symptoms and diagnosis in a consistent manner, there may still be undetected variations between individual clinicians and sites. Despite all these limitations, the large and diverse TIC Genetics cohort enabled us to enhance the current understanding by identifying new and potentially relevant factors and subtypes. In the future, we will explore effective ways to include genetic data (e.g., SNP microarray and whole-exome sequencing data) available from the cohort to further identify subtypes. Another approach is to identify subtypes using genetic data and validate them using clinical data. The tools and methods we have evaluated and the workflow we developed here can also be used to evaluate hypotheses generated by domain experts. Ultimately, we plan to perform stratified analysis of genetic data based on the subtypes to identify new candidate genes and generate new insights into TD etiology, diagnosis, and treatment. Informed Consent and Institutional Review Board Statement All adult participants and parents of children provided written informed consent along with written or oral assent of their participating child. The Institutional Review Board (IRB) of each participating site approved the study. All methods were performed in accordance with the relevant guidelines and regulations. All adult participants and parents of children provided written informed consent along with written or oral assent of their participating child. As a part of the TIC Genetics Study, this study was approved by the Institutional Review Board at Rutgers, State University of New Jersey. Consortia Juliane Ball 51 , Leonie F. Becker 18,35 , Noa Benaroya-Milshtein 13,30 , Kate Bornais 15 , Danielle Cath 43,48 , Keun-Ah Cheon 59 , Barbara J. Coffey 60 , Lenrine Dalmeijer 39 , Erik M. Elster 12 , Dana Feldman 13,30 , Thomas V. Fernandez 57 , Carolin Fremer 8 , Lorena Garrote Espina 49,4 , Donald L. Gilbert 7 , Danea Glover 14 , Cristina Gómez Rapela 49 , Tammy Hedderly 27 , Gary A. Heiman 14 , Isobel Heyman 31 , Hyun Ju Hong 33 , Chaim Huijser 2,39 , Christina Kappler-Friedrichs 12 , Young Key Kim 23 , Young Shin Kim 53 , Robert A. King 58 , Nadine Kirchen 51 , Carolin Sophie Klages 8 , Yun-Joo Koh 38 , Florian Kraemer 51 , Subramanian Krishnamurthy 8 , Samuel Kuperman 20 , Bennett L. Leventhal 36 , Holan Liang 22,41 , Maria Loreta Lopez 60 , Marcos Madruga-Garrido 45,46 , Veronika Mailänder Zelger 51 , Osman Malik 28,47 , Marieke Messchendorp 52 , Malindi Mheen, van der 3,39,1 , Dararat Mingbunjerdsuk 54 , Pablo Mir 49,4 , Astrid Morer 11,34 , Kirsten Müller-Vahl 8 , Alexander Münchau 35 , Laura Muñoz-Delgado 49,4 , Tara L Murphy 31 , Cara Nasello 44,10,6 , Elena Ojeda-Lepe 49,4 , Veit Roessner 12 , Alyssa Rosen 24 , Guy Rouleau 16 , Simon Schmitt 8,21 , Chitra Shukla 24 , Sara Sopena 28 , Matthew W State 19 , Tamar Steinberg 13,30 , Frederika Tagwerker 51 , Zsanett Tarnok 56,26 , Joshua K. Thackray 44 , Meitar Timmor 13,30 , Jay A. Tischfield 14 , Max A. Tischfield 10,6 , Anne Uhlmann 12 , Ana Vigil-Pérez 11,34 , Frank Visscher 17 , Susanne Walitza 51 , Belinda Wang 19 , Jinchuan Xing 44 , and Samuel H. Zinner 55 . 1 Amsterdam Public Health Research Institute, Amsterdam UMC, Amsterdam, the Netherlands 2 Amsterdam UMC, Department of Child and Adolescent Psychiatry, Amsterdam, The Netherlands 3 Amsterdam UMC, location University of Amsterdam, department of Child and Adolescent Psychiatry, Amsterdam, the Netherlands 4 Centro de Investigación Biomédica en Red sobre Enfermedades Neurodegenerativas (CIBERNED), Instituto de Salud Carlos III, Madrid, Spain 5 Centro de Investigacion en Red de Salud Mental (CIBERSAM), Instituto Carlos III, Spain 6 Child Health Institute of New Jersey, Robert Wood Johnson Medical School, New Brunswick, NJ 08901 7 Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA 8 Clinic of Psychiatry, Social Psychiatry and Psychotherapy, Hannover Medical School, 8 Hannover, Germany 9 Departamento de Medicina, Facultad de Medicina, Universidad de Sevilla, Seville, Spain 10 Department of Cell Biology and Neuroscience, Rutgers University, Piscataway, NJ 08854 11 Department of Child and Adolescent Psychiatry and Psychology, Institute of Neurosciences, Hospital Clinic Universitari, Barcelona, Spain 12 Department of Child and Adolescent Psychiatry, Faculty of Medicine of the TU Dresden, Dresden, Germany 13 Department of Child Psychiatry, Feinberg Child Study Center, Schneider Children’s Medical Center of Israel, Petach Tikva 4920235, Israel 14 Department of Genetics and the Human Genetics Institute of New Jersey, Rutgers, the State University of New Jersey, Piscataway, NJ, 08854, USA 15 Department of Human Genetics, McGill University 16 Department of Neurology and Neurosurgery, Montreal Neurological Institute-Hospital, McGill University 17 Department of Neurology, Van Weel Bethesda Ziekenhuis, Dirksland, The Netherlands 18 Department of Pediatrics, University Hospital Medical Center Schleswig-Holstein, Campus Lübeck, Lübeck, Germany 19 Department of Psychiatry and Behavioral Sciences, UCSF Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, USA. 20 Department of Psychiatry, Professor of Child and Adolescent Psychiatry and Pediatrics, Emeritus MD, Carver College of Medicine, University of Iowa, Iowa City, IA, IA 52242, USA 21 Department of Psychiatry, Psychotherapy and Psychosomatics, RWTH Aachen University, Aachen, Germany 22 Department of Psychiatry, The University of Cambridge 23 Department of Psychiatry, Yonsei Bom Clinic, Seoul, 03330, KR 24 Division of Neonatology, Robert’s Center for Pediatric Research, Children’s Hospital of Philadelphia, Philadelphia, PA, USA. 25 Division of Neurology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA. 26 Egyenlito Diagnostic, Behavioral Therapy and Consultation Centre in Budapest, Hungary 27 Evelina London Children’s Hospital GSTT, Kings college London School of life sciences and medicine, London, UK 28 Evelina London Children’s Hospital GSTT, Kings Health Partners AHSC, London, UK 29 Evelina London Childrens Hospital, GSTT NHS Trust, Kings Health Partners AHSC, London, 30 Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv 6997801, Israel 31 Great Ormond Street Hospital for Children, and UCL Institute of Child Health, London, UK 32 Great Ormond Street UCL Institute of Child Health, London, UK 33 Hallym University Sacred Heart Hospital 34 Institut d’Investigacions Biomediques August Pi i Sunyer (IDIBAPS), Barcelona, Spain 35 Institute of Systems Motor Science, Center of Brain, Behavior and Metabolism, University of Lübeck, Lübeck, Germany 36 Irving B. Harris Professor of Child and Adolescent Psychiatry, emeritus, The University of Chicago 37 Korea Institute for Children’s Social Development and Rudolph Child Research Center, Seoul, South Korea 38 Korea Institute for Children’s Social Development, Seoul, South Korea 39 Levvel, Academic Center for Child and Adolescent Psychiatry, Amsterdam, the Netherlands 40 National Health Insurance Service Ilsan Hospital, Goyang-si, South Korea 41 North East London NHS Foundation Trust, UK 42 Quantitative Biosciences Institute, University of California, San Francisco, San Francisco, CA, USA. 43 Research department CMD MHC Drenthe, Assen, the Netherlands 44 Rutgers, the State University of New Jersey, Department of Genetics and the Human 45 Genetics Institute of New Jersey, Piscataway, NJ, USA 46 Sección de Neuropediatría, Hospital Viamed Santa Angela de la Cruz. Seville.Spain 47 Sección de Neuropediatría, Neurolinkia, Seville.Spain. 48 South London and Maudsley NHS Foundation Trust. 49 UMCG Groningen department of psychiatry & Rijksuniversity Groningen, the Netherlands 50 Unidad de Trastornos del Movimiento, Servicio de Neurología, Instituto de Biomedicina de Sevilla (IBiS), Hospital Universitario Virgen del Rocío/CSIC/Universidad de Sevilla. Seville, Spain 51 Universitat de Barcelona 52 University Hospital of Psychiatry Zurich; Child and Adolescent Psychiaty and Psychotherapy, Neumuensterallee 9, 8032 Zurich, Switzerland 53 University of Groningen, University Medical Center Groningen, Department of Child and Adolescent Psychiatry, Groningen, The Netherlands 54 University of Texas Austin, Dell Medical School 55 University of Washington and Seattle Children’s Hospital, Department of Neurology, Seattle, WA, USA 56 University of Washington School of Medicine, Department of Pediatrics, Division of Developmental Medicine, 1925 NE Pacific Street, Box 356524, Seattle, WA 98195 USA 57 Vadaskert Child and Adolescent Psychiatric Hospital, Budapest, Hungary 58 Yale Child Study Center and Department of Psychiatry, Yale University School of Medicine, New Haven, CT, USA 59 Yale Child Study Center, Yale University School of Medicine, New Haven, CT, 06510, USA 60 Yonsei University College of Medicine, Severance Hospital, Seoul, South Korea Department of Psychiatry and Behavioral Sciences, University of Miami, Miller School of Medicine Data Availability All data produced in the present work are contained in the manuscript. Conflicts of Interest Fernandez, T.V. has received research support or grants from the National Institutes of Health, Misophonia Research Fund, and Yale Child Study Center. He received an honorarium for participation in the 2025 Pediatric Psychopharmacology Update Institute by the American Academy of Child & Adolescent Psychiatry. He is paid for expert testimony and consultation by DLA Piper LLC. Dr. Gilbert has received compensation for expert testimony for the U.S. National Vaccine Injury Compensation Program, through the Department of Health and Human Services. He has received payment for medical expert opinions through TeladocHealth International. He has served as a paid consultant for PTC Therapeutics, Noema Pharma, and Emalex Biosciences and has received travel support to attend investigator meetings. He has provided educational lectures for Illumina, Inc and PTC Therapeutics, Inc. He has received salary compensation through Cincinnati Children’s for work as a clinical trial site investigator from Emalex Biosciences, Inc. (clinical trial, Tourette Syndrome), PTC Therapeutics (registry and clinical trial, Amino Acid Decarboxylase Deficiency), Neurocrine Biosciences (clinical trial, cerebral palsy), and Quince Therapeutics (clinical trial, ataxia telangiectasia). He has received book/publication royalties from Elsevier and Wolters Kluwer. Matthew State serves on the Scientific Advisory Board of MapLight Therapeutics. Funding This study was supported by grants from the National Institute of Mental Health (R01MH115958 to Gary Heiman and Jay Tischfield; R01MH115959 to Barbara J. Coffey; R01MH115960 to Alyssa Rosen; R01MH115961 to Samuel Kuperman; R01MH115962 to Donald L. Gilbert; R01MH115963 to Matthew State and Jeremy Willsey; and R01MH115993 to Samuel H. Zinner), from the Human Genetics Institute of New Jersey (to Gary Heiman and Jay Tischfield), and the New Jersey Center for Tourette Syndrome and Associated Disorders (to Gary Heiman and Jay Tischfield) and U24MH068457 (Jay Tischfield). Dr. Münchau has received grant from the Deutsche Forschungsgemeinschaft (DFG FOR 2698). Laura Muñoz-Delgado is financially supported by the “Juan Rodés” program (JR23/00016) from the Instituto de Salud Carlos III. Authors’ Roles Conceptualization, K.S., R.A.K., G.A.H., and J.X.; methodology, K.S and J.X.; formal analysis, K.S.; writing— original draft preparation, K.S.; editing, supervision, J.X. All authors have read and agreed to the published version of the manuscript. Supplementary Tables File: TD_SubTypes_SupplementaryTables.xlsx Supplementary Table S1 . TIC Genetics clinical data Supplementary Table S2. Variables used for clustering Supplementary Table S3 . Unsupervised clustering methods tested Supplementary Table S4 . R packages used in this study Supplementary Table S5 . Different data sets tested for identifying subtypes Supplementary Table S6 . K-Means Cluster Size and Characteristics Supplementary Table S7 . BHC Cluster Sizes and Characteristics Supplementary Figures Download figure Open in new tab Supplementary Figure S1. Pairwise variable association. Cramer’s V associations are shown, and empty cells (white) indicate no association. Download figure Open in new tab Supplementary Figure S2. Silhouette Plot for K-Means analysis with k=1 to 20 Supplementary Data K-Means.xlsx – Category Description – Complete Results BHC.xlsx – Category Description – Complete Results High or low prevalence of a variable represents a statistically significant difference between actual distribution phenotype in a cluster and compared to the expected distribution based on random sampling of our selected data set. R FactoMiner package [ 25 ] was used to generate the cluster characteristics and variable importance. Acknowledgments We thank the families who have participated in and contributed to this study. Bio samples are available through the NIMH Repository and Genomics Resource (U24MH068457 to J.A.T.). We gratefully acknowledge the contributions of Mayra Aldecoa, Diana Bok, Maria Cruz, Kayla Delapenha, Kristen Fleming, Laura Ibanez-Gomez, Jessica D. Leuchter, Adam Lombroso, Daniela Martinez, and Vessela Zaharieva to the TIC Genetics study. We are also grateful to the NJCTS for facilitating the inception and organization of the TIC Genetics study. Footnotes 1. Updated the "Informed Consent and Institutional Review Board Statement" 2. Updated Figure 4 References 1. ↵ American Psychiatric Association : Diagnostic and statistical manual of mental disorders, Fifth Edition (DSM5) . Washington DC : American Psychiatric Association ; 2013 . 2. ↵ Eapen V , Robertson MM : Are there distinct subtypes in Tourette syndrome? Pure-Tourette syndrome versus Tourette syndrome-plus, and simple versus complex tics . Neuropsychiatr Dis Treat 2015 , 11 : 1431 – 1436 . OpenUrl PubMed 3. ↵ Garcia-Delgar B , Servera M , Coffey BJ , Lazaro L , Openneer T , Benaroya-Milshtein N , Steinberg T , Hoekstra PJ , Dietrich A , Morer A , group Ec: Tic disorders in children and adolescents: does the clinical presentation differ in males and females? A report by the EMTICS group . Eur Child Adolesc Psychiatry 2022 , 31 : 1539 – 1548 . OpenUrl CrossRef PubMed 4. ↵ Dy-Hollins ME , Chibnik LB , Tracy NA , Osiecki L , Budman CL , Cath DC , Grados MA , King RA , Lyon GJ , Rouleau GA , et al : Sex Differences in Natural History and Health Outcomes Among Individuals With Tic Disorders . Neurology 2025 , 104 : e210249 . OpenUrl PubMed 5. ↵ O’Rourke JA , Scharf JM , Yu D , Pauls DL : The genetics of Tourette syndrome: a review . J Psychosom Res 2009 , 67 : 533 – 545 . OpenUrl CrossRef PubMed Web of Science 6. ↵ Price RA , Kidd KK , Cohen DJ , Pauls DL , Leckman JF : A twin study of Tourette syndrome . Arch Gen Psychiatry 1985 , 42 : 815 – 820 . OpenUrl CrossRef PubMed Web of Science 7. ↵ Akingbuwa WA , Hammerschlag AR , Bartels M , Middeldorp CM : Systematic Review: Molecular Studies of Common Genetic Variation in Child and Adolescent Psychiatric Disorders . J Am Acad Child Adolesc Psychiatry 2022 , 61 : 227 – 242 . OpenUrl PubMed 8. ↵ Willsey AJ , Fernandez TV , Yu D , King RA , Dietrich A , Xing J , Sanders SJ , Mandell JD , Huang AY , Richer P , et al : De Novo Coding Variants Are Strongly Associated with Tourette Disorder . Neuron 2017 , 94 : 486 – 499 e489 . OpenUrl CrossRef PubMed 9. ↵ Wang S , Mandell JD , Kumar Y , Sun N , Morris MT , Arbelaez J , Nasello C , Dong S , Duhn C , Zhao X , et al : De Novo Sequence and Copy Number Variants Are Strongly Associated with Tourette Disorder and Implicate Cell Polarity in Pathogenesis . Cell Reports 2018 , 24 : 3441 – 3454 .e3412. OpenUrl PubMed 10. Cao X , Zhang Y , Abdulkadir M , Deng L , Fernandez TV , Garcia-Delgar B , Hagstrom J , Hoekstra PJ , King RA , Koesterich J , et al : Whole-exome sequencing identifies genes associated with Tourette’s disorder in multiplex families . Mol Psychiatry 2021 , 26 : 6937 – 6951 . OpenUrl PubMed 11. ↵ de Haan MJ , Delucchi KL , Mathews CM , Cath DC : Tic symptom dimensions and their heritabilities in Tourette’s syndrome . Psychiatr Genet 2015 , 25 : 112 – 118 . OpenUrl PubMed 12. ↵ Pauls DL , Fernandez TV , Mathews CA , State MW , Scharf JM : The inheritance of Tourette Disorder: A review . Journal of Obsessive-Compulsive and Related Disorders 2014 , 3 : 380 – 385 . OpenUrl 13. ↵ Hirschtritt ME , Lee PC , Pauls DL , Dion Y , Grados MA , Illmann C , King RA , Sandor P , McMahon WM , Lyon GJ , et al : Lifetime prevalence, age of risk, and genetic relationships of comorbid psychiatric disorders in Tourette syndrome . JAMA Psychiatry 2015 , 72 : 325 – 333 . OpenUrl PubMed 14. ↵ Yang K , Lei T , Jun J , Yang Q , Li J , Wang M , Cui Y : Advances in Clustering and Classification of Tic Disorders: A Systematic Review . Neuropsychiatric Disease and Treatment 2024 , Volume 20 : 2663 – 2677 . OpenUrl 15. ↵ Hirschtritt ME , Darrow SM , Illmann C , Osiecki L , Grados M , Sandor P , Dion Y , King RA , Pauls D , Budman CL , et al : Genetic and phenotypic overlap of specific obsessive-compulsive and attention-deficit/hyperactive subtypes with Tourette syndrome . Psychol Med 2018 , 48 : 279 – 293 . OpenUrl CrossRef PubMed 16. ↵ Grados MA , Mathews CA , Tourette Syndrome Association International Consortium for G: Latent class analysis of gilles de la tourette syndrome using comorbidities: clinical and genetic implications . Biol Psychiatry 2008 , 64 : 219 – 225 . OpenUrl CrossRef PubMed Web of Science 17. ↵ Mathews CA , Grados MA : Familiality of Tourette syndrome, obsessive-compulsive disorder, and attention-deficit/hyperactivity disorder: heritability analysis in a large sib-pair sample . J Am Acad Child Adolesc Psychiatry 2011 , 50 : 46 – 54 . OpenUrl PubMed 18. ↵ Brainstorm C , Anttila V , Bulik-Sullivan B , Finucane HK , Walters RK , Bras J , Duncan L , Escott-Price V , Falcone GJ , Gormley P , et al : Analysis of shared heritability in common disorders of the brain . Science 2018 , 360 . 19. ↵ Yang K , Zhang W , Li Y , Wang X , Jiang Z , Hu S , Jun J , Yang Q , Li J , Hong X , et al : Subtypes of tic disorders in children and adolescents: based on clinical characteristics . BMC Pediatrics 2025 , 25 . 20. ↵ Hirschtritt ME , Darrow SM , Illmann C , Osiecki L , Grados M , Sandor P , Dion Y , King RA , Pauls DL , Budman CL , et al : Social disinhibition is a heritable subphenotype of tics in Tourette syndrome . Neurology 2016 , 87 : 497 – 504 . OpenUrl CrossRef PubMed 21. ↵ Dietrich A , Fernandez TV , King RA , State MW , Tischfield JA , Hoekstra PJ , Heiman GA , Group TICGC: The Tourette International Collaborative Genetics (TIC Genetics) study, finding the genes causing Tourette syndrome: objectives and methods . Eur Child Adolesc Psychiatry 2015 , 24 : 141 – 151 . OpenUrl PubMed 22. ↵ American Psychiatric Association : Diagnostic and statistical manual of mental disorders, 4th Edition Text Revision (DSM-IV-TR) . Washington DC : American Psychiatric Association ; 2000 . 23. ↵ Mangiafico SS : rcompanion: Functions to Support Extension Education Program Evaluation. 2.5.0 edition. Rutgers Cooperative Extension, New Brunswick, New Jersey ; 2025 . 24. ↵ Heller KA , Ghahramani Z : Bayesian hierarchical clustering. In ; 2005 . ACM Press ; 25. ↵ Le S , Josse J , Husson F : FactoMineR: An R package for multivariate analysis . Journal of Statistical Software 2008 , 25 : 1 – 18 . OpenUrl 26. ↵ Hartigan JA , Wong MA : Algorithm AS 136: A K-Means Clustering Algorithm . Applied Statistics 1979 , 28 . 27. ↵ Monzani B , Rijsdijk F , Harris J , Mataix-Cols D : The structure of genetic and environmental risk factors for dimensional representations of DSM-5 obsessive-compulsive spectrum disorders . JAMA psychiatry 2014 , 71 : 182 – 189 . OpenUrl PubMed 28. ↵ Weissman MM : Cross-national epidemiology of obsessive-compulsive disorder . CNS spectrums 1998 , 3 : 6 – 9 . OpenUrl View the discussion thread. Back to top Previous Next Posted March 15, 2026. Download PDF Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Identifying Distinct Tourette Disorder Subtypes using Clinical Data Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Identifying Distinct Tourette Disorder Subtypes using Clinical Data Subramanian Krishnamurthy , Tourette International Collaborative Genetics (TIC Genetics) , Robert A. King , Jay A. Tischfield , Gary A. Heiman , Jinchuan Xing medRxiv 2025.11.09.25339700; doi: https://doi.org/10.1101/2025.11.09.25339700 Share This Article: Copy Citation Tools Identifying Distinct Tourette Disorder Subtypes using Clinical Data Subramanian Krishnamurthy , Tourette International Collaborative Genetics (TIC Genetics) , Robert A. King , Jay A. Tischfield , Gary A. Heiman , Jinchuan Xing medRxiv 2025.11.09.25339700; doi: https://doi.org/10.1101/2025.11.09.25339700 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Neurology Subject Areas All Articles Addiction Medicine (568) Allergy and Immunology (863) Anesthesia (300) Cardiovascular Medicine (4435) Dentistry and Oral Medicine (444) Dermatology (382) Emergency Medicine (608) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1509) Epidemiology (15228) Forensic Medicine (30) Gastroenterology (1124) Genetic and Genomic Medicine (6599) Geriatric Medicine (668) Health Economics (997) Health Informatics (4536) Health Policy (1368) Health Systems and Quality Improvement (1613) Hematology (540) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15916) Intensive Care and Critical Care Medicine (1103) Medical Education (623) Medical Ethics (146) Nephrology (667) Neurology (6599) Nursing (346) Nutrition (998) Obstetrics and Gynecology (1144) Occupational and Environmental Health (957) Oncology (3332) Ophthalmology (974) Orthopedics (369) Otolaryngology (420) Pain Medicine (436) Palliative Medicine (130) Pathology (663) Pediatrics (1693) Pharmacology and Therapeutics (691) Primary Care Research (711) Psychiatry and Clinical Psychology (5447) Public and Global Health (9231) Radiology and Imaging (2198) Rehabilitation Medicine and Physical Therapy (1370) Respiratory Medicine (1196) Rheumatology (593) Sexual and Reproductive Health (712) Sports Medicine (530) Surgery (712) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a005fabaf9f4fbb0',t:'MTc3OTU1OTQyOA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();