Finally, random forests allowed convenient access to the features' relative importance, which was numerically provided as mean decrease in classification accuracy when the respective feature (gene locus) was omitted from forest building (Fig. 3). The feature ranking pointed at TRPA1 variants as most important, whereas the first TRPV1 variants figured only at rank 7 among the classification-relevant gene loci. This observation accompanied the results of the classic χ2-based genotype vs phenotype association analysis, in which only the 2 TRPA1 variants X8.72934391.SNV and X8.72969263.SNV differed in allelic distribution between phenotype groups, however, only at the uncorrected α level (Fig. 3). These variants could also be used for phenotype class association; however, when eliminating them from the data set, a phenotype association was still consistently better than chance (Table 3 and Fig. 3B), which supports that a complex genotype rather than a single variant modulated the phenotype.
In the present analysis, several different methods of data analysis pointed toward a contribution of human TRP channel genotypes to the individual susceptibility to capsaicin-induced hypersensitization to heat stimuli. This was firstly hinted at by a high-dimensional pattern that emerged in the genotypes and could be statistically significantly associated with the 2 generated phenotype classes. Subsequently and most importantly, an importance of TRP genotypes for the heat pain–related phenotypes could be supported by the consistently better prediction of phenotypes from the genetic information than by chance, which was similarly observed across all machine-learned methods applied that always outperformed the phenotype class prediction when using randomly permuted genetic markers. Thus, the results can be summarized as an association of a complex TRP channel–related NGS genotype with the phenotype of the individual sensitivity to heat pain–related phenotypes.
Along this line, to further assess the biological plausibility of a functional consequence of the present machine-learned derived selection of gene loci, the 31 selected variants were queried in the genome-wide annotation of variants tool (GWAVA, https://www.sanger.ac.uk/sanger/StatGen_Gwava). This web-based tool produces a prediction of the functional impact of noncoding genetic variants that are based on machine learning from a wide range of annotations of noncoding elements for which the functional consequences are known. For this task, it uses a tailored random-forest algorithm that builds 3 different classifiers, the so-called GWAVA scores named “region score,” “TSS score,” and “unmatched” score and all scaled in the range [0,…,1], by using all available annotations to discriminate between disease variants and variants from 3 control data sets.62 Specifically, the “unmatched” classifier bases on a random selection of single-nucleotide variations (SNVs) from across the genome to get a reasonable sample of the background, the “TSS score” includes genome-wide variants matched for distance to the nearest transcription start site and the “region score” is composed of all variants in the 1 kb surrounding each of the disease variants. The machine-learned algorithm is trained with a set of variants with known function and learns to predict the function of further variants from their location within the gene. A high GWAVA score means more active functionality with respect to a low GWAVA score. The quality of the prediction was addressed in the original publication62 where the authors showed that the classifier for each training set could usefully discriminate between disease and control variants. The area under the receiver operating characteristic curves were 0.97, 0.88, and 0.71, respectively, where a value of 0.5 denotes a bad classifier and 1 denotes an excellent classifier.
The pattern of variant alleles differed between phenotype groups in the direction that carriers of fewer variant alleles were underrepresented in the phenotype group with less pronounced changes of HPTs after topical application of capsaicin. Both directions of changes would seem biological plausible, and in particular, gain-of-function mutations in ion channels may lead to increased agonist sensitivity or altered gating properties, and may render the channel constitutively active.5 For example, an autosomal-dominant hereditary form of high-pain sensitivity, the so-called familial episodic pain syndrome, FEPS1 (accession number 615040 in the Online Mendelian Inheritance in Man (OMIM) database; http://www.ncbi.nlm.nih.gov/omim), which is characterized by episodes of debilitating upper-body pain, triggered by fasting and physical stress, is caused by a gain-of-function SNP (rs398123010) in the TRPA1 gene.37 In carriers, QST showed normal baseline sensory thresholds but enhanced secondary hyperalgesia to punctate stimuli after treatment with mustard oil.37 Accordingly, this mutation increases the chemical sensitivity of TRPA1, but leaves the voltage sensitivity unchanged. Other gain-of-function mutations, rs753375978 and rs575489206, located in the analogous region of the TRPV1 gene, severely affect all aspects of channel activation and lead to spontaneous activity.5
The more important role of TRPA1 as compared to that of TRPV1 in the sensitivity to heat or the hypersensitization response to capsaicin bears implications for the development of novel analgesic treatments56 involving TRP channel inhibitors. Specifically, a query of the Thomson Reuters “Drugs and Biologics Search Tool” (http://integrity.thomsonpharma.com) in August 2017 indicated (Table 4) that by far, the most frequently regarded TRP channel family member in analgesic drug development is TRPV1, for which are 29 agonists or antagonists are currently under active development. TRPA1 agonists or antagonists figured with only 7 entries. If, based on the present results, the functional impact of TRPA1 variants exceeds TRPV1 variants, TRPA1 may play a greater role in pain including neuropathic pain when considering that topical capsaicin can induce a neuropathy-like QST results pattern in a small subgroup of healthy subjects.46
The authors have no conflict of interest to declare.
This work has been funded by the European Union Seventh Framework Programme (FP7/2013) under grant agreement no. 602919 (J.L., GLORIA) and by the Landesoffensive zur Entwicklung wissenschaftlich-ökonomischer Exzellenz (LOEWE), LOEWE-Zentrum für Translationale Medizin und Pharmakologie (G.G. and J.L.).
Supplemental digital content
Supplemental digital content associated with this article can be found online at http://links.lww.com/PAIN/A561.
. Backes C, Harz C, Fischer U, Schmitt J, Ludwig N, Petersen BS, Mueller SC, Kim YJ, Wolf NM, Katus HA, Meder B, Furtwängler R, Franke A, Bohle R, Henn W, Graf N, Keller A, Meese E. New insights into the genetics of glioblastoma multiforme by familial exome sequencing. Oncotarget 2015;6:5918–31.
. Bayes M, Price M. An essay towards solving a problem in the doctrine of chances. By the late rev. Mr. Bayes, F. R. S. Communicated by Mr. Price, in a Letter to John Canton, A. M. F. R. S. Philosophical Trans 1763;53:370–418.
. Bonferroni CE. Teoria statistica delle classi e calcolo delle probabilita. Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commerciali di Firenze 1936;8:3–62.
. Borg I, Groenen P. Modern multidimensional scaling: theory and applications. New York: Springer, 2005.
. Boukalova S, Touska F, Marsakova L, Hynkova A, Sura L, Chvojka S, Dittert I, Vlachova V. Gain-of-function mutations in the transient receptor potential channels TRPV1 and TRPA1: how painful? Physiol Res 2014;63(suppl 1):S205–213.
. Breiman L. Random forests. Mach Learn 2001;45:5–32.
. Breimann L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. Boca Raton: Chapman and Hall, 1993.
. Campbell CM, Edwards RR, Carmona C, Uhart M, Wand G, Carteret A, Kim YK, Frost J, Campbell JN. Polymorphisms in the GTP cyclohydrolase gene (GCH1) are associated with ratings of capsaicin pain. PAIN 2009;141:114–18.
. Clapham DE. TRP channels as cellular sensors. Nature 2003;426:517–24.
. Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995;20:273–97.
. Cover T, Hart P. Nearest neighbor pattern classification. IEEE Trans Inf Theor 1967;13:21–7.
. Craw S. Manhattan distance. In: Sammut C, Webb GI, editors. Encyclopedia of machine learning
. Boston: Springer US, 2010. p. 639.
. Cross SA. Pathophysiology of pain. Mayo Clin Proc 1994;69:375–83.
. Culp M, Johnson K, Michailides G. ada: an R package for stochastic boosting. J Stat Softw 2006;17:27.
. Davis JB, Gray J, Gunthorpe MJ, Hatcher JP, Davey PT, Overend P, Harries MH, Latcham J, Clapham C, Atkinson K, Hughes SA, Rance K, Grau E, Harper AJ, Pugh PL, Rogers DC, Bingham S, Randall A, Sheardown SA. Vanilloid receptor-1 is essential for inflammatory thermal hyperalgesia. Nature 2000;405:183–7.
. Delaney A, Keighren M, Fleetwood-Walker SM, Jackson IJ. Involvement of the melanocortin-1 receptor in acute pain and pain of inflammatory but not neuropathic origin. PLoS One 2010;5:e12498.
. Demartines P, Hérault J. CCA: “Curvilinear component analysis”. Proceedings of the Proc 15° Colloque sur le traitement du signal et des images, Vol. 199: GRETSI, Groupe d'Etudes du Traitement du Signal et des Images, 1995.
. Dhar V. Data science
and prediction. Commun ACM 2013;56:64–73.
. Diatchenko L, Nackley AG, Tchivileva IE, Shabalina SA, Maixner W. Genetic architecture of human
pain perception. Trends Genet 2007;23:605–13.
. Fischer MJ, Balasuriya D, Jeggle P, Goetze TA, McNaughton PA, Reeh PW, Edwardson JM. Direct evidence for functional TRPV1/TRPA1 heteromers. Pflugers Arch 2014;466:2229–41.
. Fisher RA. On the interpretation of Chi square from contingency tables, and the calculation of P. J R Stat Soc 1922;85:87–94.
. Fung KL, Gottesman MM. A synonymous polymorphism in a common MDR1 (ABCB1) haplotype shapes protein function. Biochim Biophys Acta 2009;1794:860–71.
. Fung KL, Pan J, Ohnuma S, Lund PE, Pixley JN, Kimchi-Sarfaty C, Ambudkar SV, Gottesman MM. MDR1 synonymous polymorphisms alter transporter specificity and protein stability in a stable epithelial monolayer. Cancer Res 2014;74:598–608.
. Good PI. Resampling methods: a practical guide to data analysis. Boston: Birkhäuser, 2006.
. Graffelman J. Exploring diallelic genetic markers: the HardyWeinberg package. J Stat Softw 2015;64:1–23.
. Hardy GH. Mendelian proportions in a mixed population. Science 1908;28:49–50.
. Herrmann L, Ultsch A. The architecture of ant-based clustering to improve topographic mapping. In: M, M, C, M, T, AFT, editors. Ant colony optimization and swarm intelligence. 6th International Conference, ANTS 2008, Brussels, Belgium, 22–24 September, 2008 Proceedings. Berlin: Springer Berlin Heidelberg, 2008. p. 379–86.
. Ho KW, Ward NJ, Calkins DJ. TRPV1: a stress response protein in the central nervous system. Am J Neurodegener Dis 2012;1:1–14.
. Horjales-Araujo E, Dahl JB. Is the experience of thermal pain genetics dependent? Biomed Res Int 2015;2015:349584.
. Julius D, Basbaum AI. Molecular mechanisms of nociception. Nature 2001;413:203–10.
. Juran JM. The non-pareto principle; Mea culpa. Qual Prog 1975;8:8–9.
. Karatzoglou A, Smola A, Hornik K, Zeileis A. Kernlab—an S4 package for kernel methods in R. J Stat Softw 2004;11:1–20.
. Kearns M, Valiant LG. Crytographic limitations on learning Boolean formulae and finite automata. Proceedings of the 21st annual ACM symposium on Theory of computing. Seattle, WA: ACM, 1989. p. 433–44.
. Khurana E, Fu Y, Chakravarty D, Demichelis F, Rubin MA, Gerstein M. Role of non-coding sequence variants in cancer. Nat Rev Genet 2016;17:93–108.
. Kim H, Mittal DP, Iadarola MJ, Dionne RA. Genetic predictors for acute experimental cold and heat pain sensitivity in humans. J Med Genet 2006;43:e40.
. Kim H, Neubert JK, San Miguel A, Xu K, Krishnaraju RK, Iadarola MJ, Goldman D, Dionne RA. Genetic influence on variability in human
acute experimental pain sensitivity associated with gender, ethnicity and psychological temperament. PAIN 2004;109:488–96.
. Kremeyer B, Lopera F, Cox JJ, Momin A, Rugiero F, Marsh S, Woods CG, Jones NG, Paterson KJ, Fricker FR, Villegas A, Acosta N, Pineda-Trujillo NG, Ramirez JD, Zea J, Burley MW, Bedoya G, Bennett DL, Wood JN, Ruiz-Linares A. A gain-of-function mutation in TRPA1 causes familial episodic pain syndrome. Neuron 2010;66:671–80.
. Kringel D, Sisignano M, Zinn S, Lötsch J. Next-generation sequencing
of the human
TRPV1 gene and the regulating co-players LTB4R and LTB4R2 based on a custom AmpliSeq panel. PLoS One 2017;12:e0180116.
. Kringel D, Ultsch A, Zimmermann M, Jansen JP, Ilias W, Freynhagen R, Griessinger N, Kopf A, Stein C, Doehring A, Resch E, Lötsch J. Emergent biomarker derived from next-generation sequencing
to identify pain patients requiring uncommonly high opioid doses. Pharmacogenomics J 2017;17:419–26.
. Lariviere WR, McBurney DH, Frot M, Balaban CD. Tonic, phasic, and integrator components of psychophysical responses to topical capsaicin account for differences of location and sex. J Pain 2005;6:777–81.
. Liaw A, Wiener M. Classification and regression by randomForest. R News 2002;2:18–22.
. Lötsch J, Dimova V, Hermens H, Zimmermann M, Geisslinger G, Oertel BG, Ultsch A. Pattern of neuropathic pain induced by topical capsaicin application in healthy subjects. PAIN 2015;156:405–14.
. Lötsch J, Dimova V, Lieb I, Zimmermann M, Oertel BG, Ultsch A. Multimodal distribution of human
cold pain thresholds. PLoS One 2015;10:e0125822.
. Lötsch J, Doehring A, Mogil JS, Arndt T, Geisslinger G, Ultsch A. Functional genomics of pain in analgesic drug development and therapy. Pharmacol Ther 2013;139:60–70.
. Lötsch J, Fluhr K, Neddermayer T, Doehring A, Geisslinger G. The consequence of concomitantly present functional genetic variants for the identification of functional genotype-phenotype associations in pain. Clin Pharmacol Ther 2009;85:25–30.
. Lötsch J, Geisslinger G, Heinemann S, Lerch F, Oertel BG, Ultsch A. QST response patterns to capsaicin- and UV-B-induced local skin hypersensitization in healthy subjects: a machine-learned analysis. PAIN 2018;159:11–24.
. Lötsch J, Kringel D. Use of computational functional genomics in drug discovery and repurposing for analgesic indications. Clin Pharmacol Ther 2017. doi: . [Epub ahead of print].
. Lötsch J, Lippmann C, Kringel D, Ultsch A. Integrated computational analysis of genes associated with human
hereditary insensitivity to pain. A drug repurposing perspective. Front Neurosci 2017;10:252.
. Lotsch J, Ultsch A. Machine learning
in pain research. PAIN 2018;159:623–30.
. Lötsch J, Ultsch A. A machine-learned knowledge discovery method for associating complex phenotypes with complex genotypes. Application to pain. J Biomed Inform 2013;46:921–8.
. Lötsch J, Ultsch A. Exploiting the structures of the U-matrix. In: Villmann T, Schleif FM, Kaden M, Lange M, editors. Advances in intelligent systems and computing. Vol. 295. Heidelberg: Springer, 2014. p. 248–57.
. Magerl W, Krumova EK, Baron R, Tolle T, Treede RD, Maier C. Reference data for quantitative sensory testing (QST): refined stratification for age and a novel method for statistical comparison of group data. PAIN 2010;151:598–605.
. Mogil JS, Sorge RE, LaCroix-Fralish ML, Smith SB, Fortin A, Sotocinal SG, Ritchie J, Austin JS, Schorscher-Petcu A, Melmed K, Czerminski J, Bittong RA, Mokris JB, Neubert JK, Campbell CM, Edwards RR, Campbell JN, Crawley JN, Lariviere WR, Wallace MR, Sternberg WF, Balaban CD, Belfer I, Fillingim RB. Pain sensitivity and vasopressin analgesia are mediated by a gene-sex-environment interaction. Nat Neurosci 2011;14:1569–73.
. Murphy KP. Machine learning
: a probabilistic perspective. Cambridge, MA: The MIT Press, 2012.
. Pareto V. Manuale di economia politica, Milan: Società editrice libraria, revised and translated into French as Manuel d'économie politique. Paris: Giard et Briére, 1909.
. Patapoutian A, Tate S, Woolf CJ. Transient receptor potential channels: targeting pain at the source. Nat Rev Drug Discov 2009;8:55–68.
. Pearson K. On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Philosophical Mag Series 5 1900;50:157–75.
. Petersen KL, Rowbotham MC. A new human
experimental pain model: the heat/capsaicin sensitization model. Neuroreport 1999;10:1511–16.
. Pfau D, Klein T, Blunk JA, Geber C, Krumova E, Limbeck C, Magerl W, Maier C, Westermann A, Schuh-Hofer S, Tiede W, Treede RD. QST Quantitative sensorische Testung, Handanweisung für den Untersucher, Eine standardisierte Testbatterie für die Quantitative Sensorische Testung nach den Regeln des Deutschen Forschungsverbundes Neuropathischer Schmerz (DFNS). In: Rolke R, Andrews A, Magerl W, Treede RD, editors. Mannheim, Germany: Lehrstuhl für Neurophysiologie, Universitätsmedizin Mannheim, 2010.
. R Development Core Team. R: a language and environment for statistical computing. Vienna: 2008.
. Reubish D, Emerling D, Defalco J, Steiger D, Victoria C, Vincent F. Functional assessment of temperature-gated ion-channel activity using a real-time PCR machine. Biotechniques 2009;47:iii–ix.
. Ritchie GR, Dunham I, Zeggini E, Flicek P. Functional annotation of noncoding sequence variants. Nat Methods 2014;11:294–6.
. Rolke R, Baron R, Maier C, Tolle TR, Treede RD, Beyer A, Binder A, Birbaumer N, Birklein F, Botefur IC, Braune S, Flor H, Huge V, Klug R, Landwehrmeyer GB, Magerl W, Maihofner C, Rolko C, Schaub C, Scherens A, Sprenger T, Valet M, Wasserka B. Quantitative sensory testing in the German Research Network on Neuropathic Pain (DFNS): standardized protocol and reference values. PAIN 2006;123:231–43.
. Rolke R, Magerl W, Campbell KA, Schalber C, Caspari S, Birklein F, Treede RD. Quantitative sensory testing: a comprehensive protocol for clinical trials. Eur J Pain 2006;10:77–88.
. Sauna ZE, Kimchi-Sarfaty C. Understanding the contribution of synonymous mutations to human
disease. Nat Rev Genet 2011;12:683–91.
. Schapire RE, Freund Y. A short introduction to boosting. J Jpn Soc Artif Intelligence 1999;14:771–80.
. Schapire RE, Freund Y. Boosting: foundations and algorithms. Cambridge, MA: The MIT Press, 2012.
. Schütz M, Oertel BG, Heimann D, Doehring A, Walter C, Dimova V, Geisslinger G, Lötsch J. Consequences of a human
TRPA1 genetic variant on the perception of nociceptive and olfactory stimuli. PLoS One 2014;9:e95592.
. Shannon CE. A mathematical theory of communication. Bell Syst Techn J 1951;30:50–64.
. Smirnov N. Table for estimating the goodness of fit of empirical distributions. Ann Math Statist 1948;19:279–81.
. Smolensky P. On the proper treatment of connectionism. Behav Brain Sci 2010;11:1–23.
. Story GM, Peier AM, Reeve AJ, Eid SR, Mosbacher J, Hricik TR, Earley TJ, Hergarden AC, Andersson DA, Hwang SW, McIntyre P, Jegla T, Bevan S, Patapoutian A. ANKTM1, a TRP-like channel expressed in nociceptive neurons, is activated by cold temperatures. Cell 2003;112:819–29.
. Swets JA. The relative operating characteristic in psychology: a technique for isolating effects of response bias finds wide use in the study of perception and cognition. Science 1973;182:990–1000.
. Teslovich TM, Musunuru K, Smith AV, Edmondson AC, Stylianou IM, Koseki M, Pirruccello JP, Ripatti S, Chasman DI, Willer CJ, Johansen CT, Fouchier SW, Isaacs A, Peloso GM, Barbalic M, Ricketts SL, Bis JC, Aulchenko YS, Thorleifsson G, Feitosa MF, Chambers J, Orho-Melander M, Melander O, Johnson T, Li X, Guo X, Li M, Shin Cho Y, Jin Go M, Jin Kim Y, Lee JY, Park T, Kim K, Sim X, Twee-Hee Ong R, Croteau-Chonka DC, Lange LA, Smith JD, Song K, Hua Zhao J, Yuan X, Luan Ja, Lamina C, Ziegler A, Zhang W, Zee RYL, Wright AF, Witteman JCM, Wilson JF, Willemsen G, Wichmann HE, Whitfield JB, Waterworth DM, Wareham NJ, Waeber G, Vollenweider P, Voight BF, Vitart V, Uitterlinden AG, Uda M, Tuomilehto J, Thompson JR, Tanaka T, Surakka I, Stringham HM, Spector TD, Soranzo N, Smit JH, Sinisalo J, Silander K, Sijbrands EJG, Scuteri A, Scott J, Schlessinger D, Sanna S, Salomaa V, Saharinen J, Sabatti C, Ruokonen A, Rudan I, Rose LM, Roberts R, Rieder M, Psaty BM, Pramstaller PP, Pichler I, Perola M, Penninx BWJH, Pedersen NL, Pattaro C, Parker AN, Pare G, Oostra BA, O'Donnell CJ, Nieminen MS, Nickerson DA, Montgomery GW, Meitinger T, McPherson R, McCarthy MI, McArdle W, Masson D, Martin NG, Marroni F, Mangino M, Magnusson PKE, Lucas G, Luben R, Loos RJF, Lokki ML, Lettre G, Langenberg C, Launer LJ, Lakatta EG, Laaksonen R, Kyvik KO, Kronenberg F, König IR, Khaw KT, Kaprio J, Kaplan LM, Johansson A, Jarvelin MR, Janssens ACJW, Ingelsson E, Igl W, Kees Hovingh G, Hottenga JJ, Hofman A, Hicks AA, Hengstenberg C, Heid IM, Hayward C, Havulinna AS, Hastie ND, Harris TB, Haritunians T, Hall AS, Gyllensten U, Guiducci C, Groop LC, Gonzalez E, Gieger C, Freimer NB, Ferrucci L, Erdmann J, Elliott P, Ejebe KG, Döring A, Dominiczak AF, Demissie S, Deloukas P, de Geus EJC, de Faire U, Crawford G, Collins FS, Chen YD, Caulfield MJ, Campbell H, Burtt NP, Bonnycastle LL, Boomsma DI, Boekholdt SM, Bergman RN, Barroso I, Bandinelli S, Ballantyne CM, Assimes TL, Quertermous T, Altshuler D, Seielstad M, Wong TY, Tai ES, Feranil AB, Kuzawa CW, Adair LS, Taylor HA, Borecki IB, Gabriel SB, Wilson JG, Holm H, Thorsteinsdottir U, Gudnason V, Krauss RM, Mohlke KL, Ordovas JM, Munroe PB, Kooner JS, Tall AR, Hegele RA, Kastelein JJP, Schadt EE, Rotter JI, Boerwinkle E, Strachan DP, Mooser V, Stefansson K, Reilly MP, Samani NJ, Schunkert H, Cupples LA, Sandhu MS, Ridker PM, Rader DJ, van Duijn CM, Peltonen L, Abecasis GR, Boehnke M, Kathiresan S. Biological, clinical and population relevance of 95 loci for blood lipids. Nature 2010;466:707–13.
. Thrun MC. Projection-based clustering through self-organization and swarm intelligence: combining cluster analysis with the visualization of high-dimensional data. Wiesbaden, Germany: Springer Fachmedien Wiesbaden, 2018.
. Thrun MC, Lerch F, Lötsch J, Ultsch A. Visualization and 3D printing of multivariate data of biomarkers. Proceedings of the International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. 2016. p. 7–16.
. Treutlein J, Cichon S, Ridinger M, Wodarz N, Soyka M, Zill P, Maier W, Moessner R, Gaebel W, Dahmen N, Fehr C, Scherbaum N, Steffens M, Ludwig KU, Frank J, Wichmann HE, Schreiber S, Dragano N, Sommer WH, Leonardi-Essmann F, Lourdusamy A, Gebicke-Haerter P, Wienker TF, Sullivan PF, Nothen MM, Kiefer F, Spanagel R, Mann K, Rietschel M. Genome-wide association study of alcohol dependence. Arch Gen Psychiatry 2009;66:773–84.
. Uhl GR, Walther D, Behm FM, Rose JE. Menthol preference among smokers: association with TRPA1 variants. Nicotine Tob Res 2011;13:1311–15.
. Ultsch A. Visualisation and classification with artificial life. In: Kiers HAL, Rasson JP, Groenen PJF, Schader M, editors. Data analysis, classification, and related methods. Berlin: Springer Berlin Heidelberg, 2000. p. 229–34.
. Ultsch A. Pareto density estimation: a density estimation for knowledge discovery. In: D, KD, editors. Innovations in classification, data science
, and information Systems. Proceedings of the 27th Annual Conference of the German Classification Society (GfKL), Cottbus, March 12-14, 2003. Heidelberg, Berlin: Springer Verlag, 2003.
. Ultsch A, Kringel D, Kalso E, Mogil JS, Lötsch J. A data science
approach to candidate gene selection of pain regarded as a process of learning and neural plasticity. PAIN 2016;157:2747–57.
. Ultsch A, Lötsch J. Computed ABC analysis for rational selection of most informative variables in multivariate data. PLoS One 2015;10:e0129767.
. Ultsch A, Lötsch J. Machine-learned cluster identification in high-dimensional data. J Biomed Inform 2017;66:95–104.
. Ultsch A, Sieman HP. Kohonen's self organizing feature maps for exploratory data analysis. Proceedings of the INNC'90, Int Neural Network Conference, International Neural Network Conference, July 9–13, 1990, Palais des Congres, Paris, France. Kluwer, 1990. p. 305–8.
. Ultsch A, Thrun MC, Hansen-Goos O, Lötsch J. Identification of molecular fingerprints in human
heat pain thresholds by use of an interactive mixture model R toolbox (AdaptGauss). Int J Mol Sci 2015;16:25897–911.
. Valdes AM, De Wilde G, Doherty SA, Lories RJ, Vaughn FL, Laslett LL, Maciewicz RA, Soni A, Hart DJ, Zhang W, Muir KR, Dennison EM, Wheeler M, Leaverton P, Cooper C, Spector TD, Cicuttini FM, Chapman V, Jones G, Arden NK, Doherty M. The Ile585Val TRPV1 variant is involved in risk of painful knee osteoarthritis. Ann Rheum Dis 2011;70:1556–61.
. van der Maaten LJP, Hinton GE. Visualizing high-dimensional data using t-SNE. J Mach Learn Res 2008;9:2579–605.
. Venna J, Peltonen J, Nybo K, Aidos H, Kaski S. Information retrieval perspective to Nonlinear dimensionality reduction for data visualization. J Mach Learn Res 2010;11:451–90.
. Vriens J, Owsianik G, Hofmann T, Philipp Stephan E, Stab J, Chen X, Benoit M, Xue F, Janssens A, Kerselaers S, Oberwinkler J, Vennekens R, Gudermann T, Nilius B, Voets T. TRPM3 is a nociceptor channel involved in the detection of noxious heat. Neuron 2011;70:482–94.
. Walker SH, Duncan DB. Estimation of the probability of an event as a function of several independent variables. Biometrika 1967;54:167–79.
. Ward JH Jr. Hierarchical grouping to optimize an objective function. J Am Stat Assoc 1963;58:236–44.
. Wild A. Best practice in inventory management. New York: Wiley, 1997.
. You FM, Deal KR, Wang J, Britton MT, Fass JN, Lin D, Dandekar AM, Leslie CA, Aradhya M, Luo MC, Dvorak J. Genome-wide SNP discovery in walnut with an AGSNP pipeline updated for SNP discovery in allogamous organisms. BMC Genomics 2012;13:354.