Catalogo dei prodotti della ricerca

Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural networks (NN). The main score used to compare the methods was the Area Under the ROC Curve (AUC) statistics. The impact of quality control (QC), imputing and coding methods on LR results showed that QC methods and imputation of missing genotypes may artificially increase the scores. At the opposite, neither the patient/control ratio nor marker preselection or coding strategies significantly affected the results. LR methods, including Lasso, Ridge and ElasticNet provided similar results with a maximum AUC of 0.80. GBT methods like XGBoost, LightGBM and CatBoost, together with dense NN with one or more hidden layers, provided similar AUC values, suggesting limited epistatic effects in the genetic architecture of the trait. ML methods detected near all the genetic variants previously identified by GWAS among the best predictors plus additional predictors with lower effects. The robustness and complementarity of the different methods are also studied. Compared to LR, non-linear models such as GBT or NN may provide robust complementary approaches to identify and classify genetic markers.

Comparative performances of machine learning methods for classifying Crohn disease patients using genome-wide genotyping data / Romagnoni, A.; Jegou, S.; Van Steen, K.; Wainrib, G.; Hugot, J. -P.; Peyrin-Biroulet, L.; Chamaillard, M.; Colombel, J. -F.; Cottone, M.; D'Amato, M.; D'Inca, R.; Halfvarson, J.; Henderson, P.; Karban, A.; Kennedy, N. A.; Khan, M. A.; Lemann, M.; Levine, A.; Massey, D.; Milla, M.; Ng, S. M. E.; Oikonomou, I.; Peeters, H.; Proctor, D. D.; Rahier, J. -F.; Rutgeerts, P.; Seibold, F.; Stronati, L.; Taylor, K. M.; Torkvist, L.; Ublick, K.; Van Limbergen, J.; Van Gossum, A.; Vatn, M. H.; Zhang, H.; Zhang, W.; Andrews, J. M.; Bampton, P. A.; Barclay, M.; Florin, T. H.; Gearry, R.; Krishnaprasad, K.; Lawrance, I. C.; Mahy, G.; Montgomery, G. W.; Radford-Smith, G.; Roberts, R. L.; Simms, L. A.; Hanigan, K.; Croft, A.; Amininijad, L.; Cleynen, I.; Dewit, O.; Franchimont, D.; Georges, M.; Laukens, D.; Peeters, H.; Rahier, J. -F.; Rutgeerts, P.; Theatre, E.; Van Gossum, A.; Vermeire, S.; Aumais, G.; Baidoo, L.; Barrie, A. M.; Beck, K.; Bernard, E. -J.; Binion, D. G.; Bitton, A.; Brant, S. R.; Cho, J. H.; Cohen, A.; Croitoru, K.; Daly, M. J.; Datta, L. W.; Deslandres, C.; Duerr, R. H.; Dutridge, D.; Ferguson, J.; Fultz, J.; Goyette, P.; Greenberg, G. R.; Haritunians, T.; Jobin, G.; Katz, S.; Lahaie, R. G.; Mcgovern, D. P.; Nelson, L.; Ng, S. M.; Ning, K.; Oikonomou, I.; Pare, P.; Proctor, D. D.; Regueiro, M. D.; Rioux, J. D.; Ruggiero, E.; Schumm, L. P.; Schwartz, M.; Scott, R.; Sharma, Y.; Silverberg, M. S.; Spears, D.; Steinhart, A. H.; Stempak, J. M.; Swoger, J. M.; Tsagarelis, C.; Zhang, W.; Zhang, C.; Zhao, H.; Aerts, J.; Ahmad, T.; Arbury, H.; Attwood, A.; Auton, A.; Ball, S. G.; Balmforth, A. J.; Barnes, C.; Barrett, J. C.; Barroso, I.; Barton, A.; Bennett, A. J.; Bhaskar, S.; Blaszczyk, K.; Bowes, J.; Brand, O. J.; Braund, P. S.; Bredin, F.; Breen, G.; Brown, M. J.; Bruce, I. N.; Bull, J.; Burren, O. S.; Burton, J.; Byrnes, J.; Caesar, S.; Cardin, N.; Clee, C. M.; Coffey, A. J.; MC Connell, J.; Conrad, D. F.; Cooper, J. D.; Dominiczak, A. F.; Downes, K.; Drummond, H. E.; Dudakia, D.; Dunham, A.; Ebbs, B.; Eccles, D.; Edkins, S.; Edwards, C.; Elliot, A.; Emery, P.; Evans, D. M.; Evans, G.; Eyre, S.; Farmer, A.; Ferrier, I. N.; Flynn, E.; Forbes, A.; Forty, L.; Franklyn, J. A.; Frayling, T. M.; Freathy, R. M.; Giannoulatou, E.; Gibbs, P.; Gilbert, P.; Gordon-Smith, K.; Gray, E.; Green, E.; Groves, C. J.; Grozeva, D.; Gwilliam, R.; Hall, A.; Hammond, N.; Hardy, M.; Harrison, P.; Hassanali, N.; Hebaishi, H.; Hines, S.; Hinks, A.; Hitman, G. A.; Hocking, L.; Holmes, C.; Howard, E.; Howard, P.; Howson, J. M. M.; Hughes, D.; Hunt, S.; Isaacs, J. D.; Jain, M.; Jewell, D. P.; Johnson, T.; Jolley, J. D.; Jones, I. R.; Jones, L. A.; Kirov, G.; Langford, C. F.; Lango-Allen, H.; Lathrop, G. M.; Lee, J.; Lee, K. L.; Lees, C.; Lewis, K.; Lindgren, C. M.; Maisuria-Armer, M.; Maller, J.; Mansfield, J.; Marchini, J. L.; Martin, P.; Massey, D. C.; Mcardle, W. L.; Mcguffin, P.; Mclay, K. E.; Mcvean, G.; Mentzer, A.; Mimmack, M. L.; Morgan, A. E.; Morris, A. P.; Mowat, C.; Munroe, P. B.; Myers, S.; Newman, W.; Nimmo, E. R.; O'Donovan, M. C.; Onipinla, A.; Ovington, N. R.; Owen, M. J.; Palin, K.; Palotie, A.; Parnell, K.; Pearson, R.; Pernet, D.; Perry, J. R.; Phillips, A.; Plagnol, V.; Prescott, N. J.; Prokopenko, I.; Quail, M. A.; Rafelt, S.; Rayner, N. W.; Reid, D. M.; Renwick, A.; Ring, S. M.; Robertson, N.; Robson, S.; Russell, E.; Clair, D. S.; Sambrook, J. G.; Sanderson, J. D.; Sawcer, S. J.; Schuilenburg, H.; Scott, C. E.; Scott, R.; Seal, S.; Shaw-Hawkins, S.; Shields, B. M.; Simmonds, M. J.; Smyth, D. J.; Somaskantharajah, E.; Spanova, K.; Steer, S.; Stephens, J.; Stevens, H. E.; Stirrups, K.; Stone, M. A.; Strachan, D. P.; Su, Z.; Symmons, D. P. M.; Thompson, J. R.; Thomson, W.; Tobin, M. D.; Travers, M. E.; Turnbull, C.; Vukcevic, D.; Wain, L. V.; Walker, M.; Walker, N. M.; Wallace, C.; Warren-Perry, M.; Watkins, N. A.; Webster, J.; Weedon, M. N.; Wilson, A. G.; Woodburn, M.; Wordsworth, B. P.; Yau, C.; Young, A. H.; Zeggini, E.; Brown, M. A.; Burton, P. R.; Caulfield, M. J.; Compston, A.; Farrall, M.; Gough, S. C. L.; Hall, A. S.; Hattersley, A. T.; Hill, A. V. S.; Mathew, C. G.; Pembrey, M.; Satsangi, J.; Stratton, M. R.; Worthington, J.; Hurles, M. E.; Duncanson, A.; Ouwehand, W. H.; Parkes, M.; Rahman, N.; Todd, J. A.; Samani, N. J.; Kwiatkowski, D. P.; Mccarthy, M. I.; Craddock, N.; Deloukas, P.; Donnelly, P.; Blackwell, J. M.; Bramon, E.; Casas, J. P.; Corvin, A.; Jankowski, J.; Markus, H. S.; Palmer, C. N.; Plomin, R.; Rautanen, A.; Trembath, R. C.; Viswanathan, A. C.; Wood, N. W.; Spencer, C. C. A.; Band, G.; Bellenguez, C.; Freeman, C.; Hellenthal, G.; Giannoulatou, E.; Pirinen, M.; Pearson, R.; Strange, A.; Blackburn, H.; Bumpstead, S. J.; Dronov, S.; Gillman, M.; Jayakumar, A.; Mccann, O. T.; Liddle, J.; Potter, S. C.; Ravindrarajah, R.; Ricketts, M.; Waller, M.; Weston, P.; Widaa, S.; Whittaker, P.. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - 9:1(2019), p. 10351. [10.1038/s41598-019-46649-z]

Comparative performances of machine learning methods for classifying Crohn disease patients using genome-wide genotyping data

Stronati L.;Schwartz M.;Scott R.;Zhang W.;Zhao H.;Cardin N.;Edwards C.;Evans G.;Flynn E.;Hall A.;Howard P.;Hughes D.;Scott R.;Su Z.;
2019

Abstract

Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural networks (NN). The main score used to compare the methods was the Area Under the ROC Curve (AUC) statistics. The impact of quality control (QC), imputing and coding methods on LR results showed that QC methods and imputation of missing genotypes may artificially increase the scores. At the opposite, neither the patient/control ratio nor marker preselection or coding strategies significantly affected the results. LR methods, including Lasso, Ridge and ElasticNet provided similar results with a maximum AUC of 0.80. GBT methods like XGBoost, LightGBM and CatBoost, together with dense NN with one or more hidden layers, provided similar AUC values, suggesting limited epistatic effects in the genetic architecture of the trait. ML methods detected near all the genetic variants previously identified by GWAS among the best predictors plus additional predictors with lower effects. The robustness and complementarity of the different methods are also studied. Compared to LR, non-linear models such as GBT or NN may provide robust complementary approaches to identify and classify genetic markers.
2019
Crohn's disease, genetics, genome wide association
01 Pubblicazione su rivista::01a Articolo in rivista
Comparative performances of machine learning methods for classifying Crohn disease patients using genome-wide genotyping data / Romagnoni, A.; Jegou, S.; Van Steen, K.; Wainrib, G.; Hugot, J. -P.; Peyrin-Biroulet, L.; Chamaillard, M.; Colombel, J. -F.; Cottone, M.; D'Amato, M.; D'Inca, R.; Halfvarson, J.; Henderson, P.; Karban, A.; Kennedy, N. A.; Khan, M. A.; Lemann, M.; Levine, A.; Massey, D.; Milla, M.; Ng, S. M. E.; Oikonomou, I.; Peeters, H.; Proctor, D. D.; Rahier, J. -F.; Rutgeerts, P.; Seibold, F.; Stronati, L.; Taylor, K. M.; Torkvist, L.; Ublick, K.; Van Limbergen, J.; Van Gossum, A.; Vatn, M. H.; Zhang, H.; Zhang, W.; Andrews, J. M.; Bampton, P. A.; Barclay, M.; Florin, T. H.; Gearry, R.; Krishnaprasad, K.; Lawrance, I. C.; Mahy, G.; Montgomery, G. W.; Radford-Smith, G.; Roberts, R. L.; Simms, L. A.; Hanigan, K.; Croft, A.; Amininijad, L.; Cleynen, I.; Dewit, O.; Franchimont, D.; Georges, M.; Laukens, D.; Peeters, H.; Rahier, J. -F.; Rutgeerts, P.; Theatre, E.; Van Gossum, A.; Vermeire, S.; Aumais, G.; Baidoo, L.; Barrie, A. M.; Beck, K.; Bernard, E. -J.; Binion, D. G.; Bitton, A.; Brant, S. R.; Cho, J. H.; Cohen, A.; Croitoru, K.; Daly, M. J.; Datta, L. W.; Deslandres, C.; Duerr, R. H.; Dutridge, D.; Ferguson, J.; Fultz, J.; Goyette, P.; Greenberg, G. R.; Haritunians, T.; Jobin, G.; Katz, S.; Lahaie, R. G.; Mcgovern, D. P.; Nelson, L.; Ng, S. M.; Ning, K.; Oikonomou, I.; Pare, P.; Proctor, D. D.; Regueiro, M. D.; Rioux, J. D.; Ruggiero, E.; Schumm, L. P.; Schwartz, M.; Scott, R.; Sharma, Y.; Silverberg, M. S.; Spears, D.; Steinhart, A. H.; Stempak, J. M.; Swoger, J. M.; Tsagarelis, C.; Zhang, W.; Zhang, C.; Zhao, H.; Aerts, J.; Ahmad, T.; Arbury, H.; Attwood, A.; Auton, A.; Ball, S. G.; Balmforth, A. J.; Barnes, C.; Barrett, J. C.; Barroso, I.; Barton, A.; Bennett, A. J.; Bhaskar, S.; Blaszczyk, K.; Bowes, J.; Brand, O. J.; Braund, P. S.; Bredin, F.; Breen, G.; Brown, M. J.; Bruce, I. N.; Bull, J.; Burren, O. S.; Burton, J.; Byrnes, J.; Caesar, S.; Cardin, N.; Clee, C. M.; Coffey, A. J.; MC Connell, J.; Conrad, D. F.; Cooper, J. D.; Dominiczak, A. F.; Downes, K.; Drummond, H. E.; Dudakia, D.; Dunham, A.; Ebbs, B.; Eccles, D.; Edkins, S.; Edwards, C.; Elliot, A.; Emery, P.; Evans, D. M.; Evans, G.; Eyre, S.; Farmer, A.; Ferrier, I. N.; Flynn, E.; Forbes, A.; Forty, L.; Franklyn, J. A.; Frayling, T. M.; Freathy, R. M.; Giannoulatou, E.; Gibbs, P.; Gilbert, P.; Gordon-Smith, K.; Gray, E.; Green, E.; Groves, C. J.; Grozeva, D.; Gwilliam, R.; Hall, A.; Hammond, N.; Hardy, M.; Harrison, P.; Hassanali, N.; Hebaishi, H.; Hines, S.; Hinks, A.; Hitman, G. A.; Hocking, L.; Holmes, C.; Howard, E.; Howard, P.; Howson, J. M. M.; Hughes, D.; Hunt, S.; Isaacs, J. D.; Jain, M.; Jewell, D. P.; Johnson, T.; Jolley, J. D.; Jones, I. R.; Jones, L. A.; Kirov, G.; Langford, C. F.; Lango-Allen, H.; Lathrop, G. M.; Lee, J.; Lee, K. L.; Lees, C.; Lewis, K.; Lindgren, C. M.; Maisuria-Armer, M.; Maller, J.; Mansfield, J.; Marchini, J. L.; Martin, P.; Massey, D. C.; Mcardle, W. L.; Mcguffin, P.; Mclay, K. E.; Mcvean, G.; Mentzer, A.; Mimmack, M. L.; Morgan, A. E.; Morris, A. P.; Mowat, C.; Munroe, P. B.; Myers, S.; Newman, W.; Nimmo, E. R.; O'Donovan, M. C.; Onipinla, A.; Ovington, N. R.; Owen, M. J.; Palin, K.; Palotie, A.; Parnell, K.; Pearson, R.; Pernet, D.; Perry, J. R.; Phillips, A.; Plagnol, V.; Prescott, N. J.; Prokopenko, I.; Quail, M. A.; Rafelt, S.; Rayner, N. W.; Reid, D. M.; Renwick, A.; Ring, S. M.; Robertson, N.; Robson, S.; Russell, E.; Clair, D. S.; Sambrook, J. G.; Sanderson, J. D.; Sawcer, S. J.; Schuilenburg, H.; Scott, C. E.; Scott, R.; Seal, S.; Shaw-Hawkins, S.; Shields, B. M.; Simmonds, M. J.; Smyth, D. J.; Somaskantharajah, E.; Spanova, K.; Steer, S.; Stephens, J.; Stevens, H. E.; Stirrups, K.; Stone, M. A.; Strachan, D. P.; Su, Z.; Symmons, D. P. M.; Thompson, J. R.; Thomson, W.; Tobin, M. D.; Travers, M. E.; Turnbull, C.; Vukcevic, D.; Wain, L. V.; Walker, M.; Walker, N. M.; Wallace, C.; Warren-Perry, M.; Watkins, N. A.; Webster, J.; Weedon, M. N.; Wilson, A. G.; Woodburn, M.; Wordsworth, B. P.; Yau, C.; Young, A. H.; Zeggini, E.; Brown, M. A.; Burton, P. R.; Caulfield, M. J.; Compston, A.; Farrall, M.; Gough, S. C. L.; Hall, A. S.; Hattersley, A. T.; Hill, A. V. S.; Mathew, C. G.; Pembrey, M.; Satsangi, J.; Stratton, M. R.; Worthington, J.; Hurles, M. E.; Duncanson, A.; Ouwehand, W. H.; Parkes, M.; Rahman, N.; Todd, J. A.; Samani, N. J.; Kwiatkowski, D. P.; Mccarthy, M. I.; Craddock, N.; Deloukas, P.; Donnelly, P.; Blackwell, J. M.; Bramon, E.; Casas, J. P.; Corvin, A.; Jankowski, J.; Markus, H. S.; Palmer, C. N.; Plomin, R.; Rautanen, A.; Trembath, R. C.; Viswanathan, A. C.; Wood, N. W.; Spencer, C. C. A.; Band, G.; Bellenguez, C.; Freeman, C.; Hellenthal, G.; Giannoulatou, E.; Pirinen, M.; Pearson, R.; Strange, A.; Blackburn, H.; Bumpstead, S. J.; Dronov, S.; Gillman, M.; Jayakumar, A.; Mccann, O. T.; Liddle, J.; Potter, S. C.; Ravindrarajah, R.; Ricketts, M.; Waller, M.; Weston, P.; Widaa, S.; Whittaker, P.. - In: SCIENTIFIC REPORTS. - ISSN 2045-2322. - 9:1(2019), p. 10351. [10.1038/s41598-019-46649-z]
01a Articolo in rivista
File allegati a questo prodotto
File Dimensione Formato  
Romagnoni_Comparative performances_2019.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.04 MB
Formato Adobe PDF
3.04 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1399970
Citazioni
  • ???jsp.display-item.citation.pmc??? 37
  • Scopus 80
  • ???jsp.display-item.citation.isi??? 71
social impact