All Publications

  • CAGI, the Critical Assessment of Genome Interpretation, establishes progress and prospects for computational genetic variant interpretation methods GENOME BIOLOGY Jain, S., Bakolitsa, C., Brenner, S. E., Radivojac, P., Moult, J., Repo, S., Hoskins, R. A., Andreoletti, G., Barsky, D., Chellapan, A., Chu, H., Dabbiru, N., Kollipara, N. K., Ly, M., Neumann, A. J., Pal, L. R., Odell, E., Pandey, G., Peters-Petrulewicz, R. C., Srinivasan, R., Yee, S. F., Yeleswarapu, S., Zuhl, M., Adebali, O., Patra, A., Beer, M. A., Hosur, R., Peng, J., Bernard, B. M., Berry, M., Dong, S., Boyle, A. P., Adhikari, A., Chen, J., Hu, Z., Wang, R., Wang, Y., Miller, M., Wang, Y., Bromberg, Y., Turina, P., Capriotti, E., Han, J. J., Ozturk, K., Carter, H., Babbi, G., Bovo, S., Di Lena, P., Martelli, P., Savojardo, C., Casadio, R., Cline, M. S., De Baets, G., Bonache, S., Diez, O., Gutierrez-Enriquez, S., Fernandez, A., Montalban, G., Ootes, L., Ozkan, S., Padilla, N., Riera, C., De la Cruz, X., Diekhans, M., Huwe, P. J., Wei, Q., Xu, Q., Dunbrack, R. L., Gotea, V., Elnitski, L., Margolin, G., Fariselli, P., Kulakovskiy, I. V., Makeev, V. J., Penzar, D. D., Vorontsov, I. E., Favorov, A. V., Forman, J. R., Hasenahuer, M., Fornasari, M. S., Parisi, G., Avsec, Z., Celik, M. H., Thi Yen Duong Nguyen, Gagneur, J., Shi, F., Edwards, M. D., Guo, Y., Tian, K., Zeng, H., Gifford, D. K., Goke, J., Zaucha, J., Gough, J., Ritchie, G. S., Frankish, A., Mudge, J. M., Harrow, J., Young, E. L., Yu, Y., Huff, C. D., Murakami, K., Nagai, Y., Imanishi, T., Mungall, C. J., Jacobsen, J. B., Kim, D., Jeong, C., Jones, D. T., Li, M., Guthrie, V., Bhattacharya, R., Chen, Y., Douville, C., Fan, J., Kim, D., Masica, D., Niknafs, N., Sengupta, S., Tokheim, C., Turner, T. N., Yeo, H., Karchin, R., Shin, S., Welch, R., Keles, S., Li, Y., Kellis, M., Corbi-Verge, C., Strokach, A. V., Kim, P. M., Klein, T. E., Mohan, R., Sinnott-Armstrong, N. A., Wainberg, M., Kundaje, A., Gonzaludo, N., Mak, A. Y., Chhibber, A., Lam, H. K., Dahary, D., Fishilevich, S., Lancet, D., Lee, I., Bachman, B., Katsonis, P., Lua, R. C., Wilson, S. J., Lichtarge, O., Bhat, R. R., Sundaram, L., Viswanath, V., Bellazzi, R., Nicora, G., Rizzo, E., Limongelli, I., Mezlini, A. M., Chang, R., Kim, S., Lai, C., O'Connor, R., Topper, S., van den Akker, J., Zhou, A. Y., Zimmer, A. D., Mishne, G., Bergquist, T. R., Breese, M. R., Guerrero, R. F., Jiang, Y., Kiga, N., Li, B., Mort, M., Pagel, K. A., Pejaver, V., Stamboulian, M. H., Thusberg, J., Mooney, S. D., Teerakulkittipong, N., Cao, C., Kundu, K., Yin, Y., Yu, C., Kleyman, M., Lin, C., Stackpole, M., Mount, S. M., Eraslan, G., Mueller, N. S., Naito, T., Rao, A. R., Azaria, J. R., Brodie, A., Ofran, Y., Garg, A., Pal, D., Hawkins-Hooker, A., Kenlay, H., Reid, J., Mucaki, E. J., Rogan, P. K., Schwarz, J. M., Searls, D. B., Lee, G., Seok, C., Kramer, A., Shah, S., Huang, C. V., Kirsch, J. F., Shatsky, M., Cao, Y., Chen, H., Karimi, M., Moronfoye, O., Sun, Y., Shen, Y., Shigeta, R., Ford, C. T., Nodzak, C., Uppal, A., Shi, X., Joseph, T., Kotte, S., Rana, S., Rao, A., Saipradeep, V. G., Sivadasan, N., Sunderam, U., Stanke, M., Su, A., Adzhubey, I., Jordan, D. M., Sunyaev, S., Rousseau, F., Schymkowitz, J., Van Durme, J., Tavtigian, S. V., Carraro, M., Giollo, M., Tosatto, S. E., Adato, O., Carmel, L., Cohen, N. E., Fenesh, I., Holtzer, I., Juven-Gershon, T., Unger, R., Niroula, A., Olatubosun, A., Valiaho, J., Yang, Y., Vihinen, M., Wahl, M. E., Chang, B., Chong, K., Hu, I., Sun, R., Wu, W., Xia, X., Zee, B. C., Wang, M. H., Wang, M., Wu, C., Lu, Y., Chen, K., Yang, Y., Yates, C. M., Kreimer, A., Yan, Z., Yosef, N., Zhao, H., Wei, Z., Yao, Z., Zhou, F., Folkman, L., Zhou, Y., Daneshjou, R., Altman, R. B., Inoue, F., Ahituv, N., Arkin, A. P., Lovisa, F., Bonvini, P., Bowdin, S., Gianni, S., Mantuano, E., Minicozzi, V., Novak, L., Pasquo, A., Pastore, A., Petrosino, M., Puglisi, R., Toto, A., Veneziano, L., Chiaraluce, R., Ball, M. P., Bobe, J. R., Church, G. M., Consalvi, V., Mort, M., Cooper, D. N., Buckley, B. A., Sheridan, M. B., Cutting, G. R., Scaini, M., Cygan, K. J., Fredericks, A. M., Glidden, D. T., Neil, C., Rhine, C. L., Fairbrother, W. G., Alontaga, A. Y., Fenton, A. W., Matreyek, K. A., Starita, L. M., Fowler, D. M., Loescher, B., Franke, A., Adamson, S. I., Graveley, B. R., Gray, J. W., Malloy, M. J., Kane, J. P., Kousi, M., Katsanis, N., Schubach, M., Kircher, M., Tang, P. F., Kwok, P., Lathrop, R. H., Clark, W. T., Yu, G. K., LeBowitz, J. H., Benedicenti, F., Bettella, E., Bigoni, S., Cesca, F., Mammi, I., Marino-Bus-Ije, C., Milani, D., Peron, A., Polli, R., Sartori, S., Stanzial, F., Ioldo, I., Turolla, L., Aspromonte, M. C., Bellini, M., Leonardi, E., Liu, X., Marshall, C., McCombie, W., Elefanti, L., Menin, C., Meyn, M., Murgia, A., Nadeau, K. Y., Neuhausen, S. L., Nussbaum, R. L., Pirooznia, M., Potash, J. B., Dimster-Denk, D. F., Rine, J. D., Sanford, J. R., Snyder, M., Tavtigian, S. V., Cole, A. G., Sun, S., Verby, M. W., Weile, J., Roth, F. P., Tewhey, R., Sabeti, P. C., Campagna, J., Refaat, M. M., Wojciak, J., Grubb, S., Schmitt, N., Shendure, J., Spurdle, A. B., Stavropoulos, D. J., Walton, N. A., Zandi, P. P., Ziv, E., Burke, W., Chen, F., Carr, L. R., Martinez, S., Paik, J., Harris-Wai, J., Yarborough, M., Fullerton, S. M., Koenig, B. A., McInnes, G., Shigaki, D., Chandonia, J., Furutsuki, M., Kasak, L., Yu, C., Chen, R., Cline, M. S., Pandey, G., Friedberg, I., Getz, G. A., Cong, Q., Kinch, L. N., Zhang, J., Grishin, N. V., Voskanian, A., Kann, M. G., Clark, W. T., Tran, E., Ioannidis, N. M., Hunter, J. M., Udani, R., Cai, B., Morgan, A. A., Sokolov, A., Stuart, J. M., Tavtigian, S. V., Minervini, G., Monzon, A. M., Batzoglou, S., Butte, A. J., Church, G. M., Greenblatt, M. S., Hart, R. K., Hernandez, R., Hubbard, T. P., Kahn, S., O'Donnell-Luria, A., Ng, P. C., Shon, J., Tavtigian, S. V., Veltman, J., Zook, J. M., Critical Assessment Genome 2024; 25 (1): 53


    The Critical Assessment of Genome Interpretation (CAGI) aims to advance the state-of-the-art for computational prediction of genetic variant impact, particularly where relevant to disease. The five complete editions of the CAGI community experiment comprised 50 challenges, in which participants made blind predictions of phenotypes from genetic data, and these were evaluated by independent assessors.Performance was particularly strong for clinical pathogenic variants, including some difficult-to-diagnose cases, and extends to interpretation of cancer-related variants. Missense variant interpretation methods were able to estimate biochemical effects with increasing accuracy. Assessment of methods for regulatory variants and complex trait disease risk was less definitive and indicates performance potentially suitable for auxiliary use in the clinic.Results show that while current methods are imperfect, they have major utility for research and clinical applications. Emerging methods and increasingly large, robust datasets for training and assessment promise further progress ahead.

    View details for DOI 10.1186/s13059-023-03113-6

    View details for Web of Science ID 001184832400002

    View details for PubMedID 38389099

    View details for PubMedCentralID PMC10882881

  • Academic machine learning researchers' ethical perspectives on algorithm development for health care: a qualitative study. Journal of the American Medical Informatics Association : JAMIA Kasun, M., Ryan, K., Paik, J., Lane-McKinley, K., Dunn, L. B., Roberts, L. W., Kim, J. P. 2023


    We set out to describe academic machine learning (ML) researchers' ethical considerations regarding the development of ML tools intended for use in clinical care.We conducted in-depth, semistructured interviews with a sample of ML researchers in medicine (N = 10) as part of a larger study investigating stakeholders' ethical considerations in the translation of ML tools in medicine. We used a qualitative descriptive design, applying conventional qualitative content analysis in order to allow participant perspectives to emerge directly from the data.Every participant viewed their algorithm development work as holding ethical significance. While participants shared positive attitudes toward continued ML innovation, they described concerns related to data sampling and labeling (eg, limitations to mitigating bias; ensuring the validity and integrity of data), and algorithm training and testing (eg, selecting quantitative targets; assessing reproducibility). Participants perceived a need to increase interdisciplinary training across stakeholders and to envision more coordinated and embedded approaches to addressing ethics issues.Participants described key areas where increased support for ethics may be needed; technical challenges affecting clinical acceptability; and standards related to scientific integrity, beneficence, and justice that may be higher in medicine compared to other industries engaged in ML innovation. Our results help shed light on the perspectives of ML researchers in medicine regarding the range of ethical issues they encounter or anticipate in their work, including areas where more attention may be needed to support the successful development and integration of medical ML tools.

    View details for DOI 10.1093/jamia/ocad238

    View details for PubMedID 38069455

  • Reports from the fifth edition of CAGI: The Critical Assessment of Genome Interpretation HUMAN MUTATION Andreoletti, G., Pal, L. R., Moult, J., Brenner, S. E. 2019; 40 (9): 1197-1201


    Interpretation of genomic variation plays an essential role in the analysis of cancer and monogenic disease, and increasingly also in complex trait disease, with applications ranging from basic research to clinical decisions. Many computational impact prediction methods have been developed, yet the field lacks a clear consensus on their appropriate use and interpretation. The Critical Assessment of Genome Interpretation (CAGI, /'kā-jē/) is a community experiment to objectively assess computational methods for predicting the phenotypic impacts of genomic variation. CAGI participants are provided genetic variants and make blind predictions of resulting phenotype. Independent assessors evaluate the predictions by comparing with experimental and clinical data. CAGI has completed five editions with the goals of establishing the state of art in genome interpretation and of encouraging new methodological developments. This special issue ( comprises reports from CAGI, focusing on the fifth edition that culminated in a conference that took place 5 to 7 July 2018. CAGI5 was comprised of 14 challenges and engaged hundreds of participants from a dozen countries. This edition had a notable increase in splicing and expression regulatory variant challenges, while also continuing challenges on clinical genomics, as well as complex disease datasets and missense variants in diseases ranging from cancer to Pompe disease to schizophrenia. Full information about CAGI is at

    View details for DOI 10.1002/humu.23876

    View details for Web of Science ID 000483662200001

    View details for PubMedID 31334884

    View details for PubMedCentralID PMC7329230

  • In the twilight: Life in the margins between sick and well JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION Goldstein, J. 2001; 285 (1): 92
  • No one an island: The geography of the whole patient JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION PAik, J. E. 2000; 284 (13): 1704

    View details for DOI 10.1001/jama.284.13.1704-a

    View details for Web of Science ID 000089501900034

    View details for PubMedID 11015804

  • The feminization of medicine JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION Paik, J. E. 2000; 283 (5): 666

    View details for DOI 10.1001/jama.283.5.666-a

    View details for Web of Science ID 000084956500035

    View details for PubMedID 10665709

  • Grief Journal of General Internal Medicine Elgart, J. L. 1998; 13 (6): 399