GestaltMatcher

Overcoming the limits of rare disease matching using facial phenotypic descriptors

GestaltMatcher API (GM API) is a REST API to provide the GestaltMatcher service. GestaltMatcher is a next-generation phenotyping approach that can predict the disorder/gene by analyzing the frontal image (T.-C. Hsieh et al., 2022; Hustinx et al., 2023). Users can send the image via GM API and obtain the gestalt scores of 449 disorders/genes predicted by GestaltMatcher. It can also be further integrated into user’s variant prioritization platform to facilitate the exome variants prioritization, such as PEDIA approach (T. C. Hsieh et al., 2019). To access GM API, please contact Prof. Peter Krawitz via email (pkrawitz@uni-bonn.de). For technical assistance or to arrange a demo meeting, please contact Dr. Tzung-Chien Hsieh (thsieh@uni-bonn.de).

Usage

1. Authentication

Request example:
POST https:/api.gestaltmatcher.org/api/auth?user=xxx&key=yyy
Response:
200 {token: zzz} - please use this token to authenticate the following two steps. 
    The token is only valid for 10 minutes. 
    Please redo the authentication (Step 1), once it is expired.
400 {msg: Unauthorized.}

2. Send image

Request example:
POST https:/api.gestaltmatcher.org/api/images
{
  "images": [
  {"base64": "cGlj...yZQ=="}
  ],
}
Response:
200
{
    "msg": "Image is uploaded successfully.",
    "service_id": 1234
}
401
{
    "msg": "Token expired."
}
{
    "msg": "Invalid token."
}
400
{
    "msg": "Invalid file."
}

3. Fetch prediction result

Request example:
GET https:/api.gestaltmatcher.org/api/get_results?service_id=xxx
Please replace xxx with the service id you received in the previous step.
Response:
You will receive a list of predicted syndromes with gestalt score and syndrome information. Because the gestalt score is the distance, the smaller distance indicates a higher probability. Image id is the nearest image of the syndrome, you can further check this patient in GestaltMatcher Database to verify whether the predicted syndrome/patient is similar to your patient.
{
  "results": [
      {
          "distance": 0.492,
          "gestalt_score": 0.492,
          "image_id": "4992",
          "omim_id": 194050,
          "subject_id": 3631,
          "syndrome_id": 1,
          "syndrome_name": "WILLIAMS-BEUREN SYNDROME; WBS"
      },
      {
          "distance": 0.711,
          "gestalt_score": 0.711,
          "image_id": "6103",
          "omim_id": 610954,
          "subject_id": 4336,
          "syndrome_id": 15,
          "syndrome_name": "PITT-HOPKINS SYNDROME; PTHS"
      },...
  ],
  "service_id": "5",
  "version": "1.0.3"
}

Usage

References

  • Hsieh, T.-C., Bar-Haim, A., Moosa, S., Ehmke, N., Gripp, K. W., Pantel, J. T., Danyel, M., Mensah, M. A., Horn, D., Rosnev, S., Fleischer, N., Bonini, G., Hustinx, A., Schmid, A., Knaus, A., Javanmardi, B., Klinkhammer, H., Lesmann, H., Sivalingam, S., … Krawitz, P. M. (2022). GestaltMatcher facilitates rare disease matching using facial phenotype descriptors. Nature Genetics, 54(3), 349–357. https://doi.org/10.1038/s41588-021-01010-x
  • Hsieh, T. C., Mensah, M. A., Pantel, J. T., Aguilar, D., Bar, O., Bayat, A., Becerra-Solano, L., Bentzen, H. B., Biskup, S., Borisov, O., Braaten, O., Ciaccio, C., Coutelier, M., Cremer, K., Danyel, M., Daschkey, S., Eden, H. D., Devriendt, K., Wilson, S., … Krawitz, P. M. (2019). PEDIA: prioritization of exome data by image analysis. Genetics in Medicine: Official Journal of the American College of Medical Genetics , 21(12), 2807–2814. https://doi.org/10.1038/s41436-019-0566-2
  • Hustinx, A., Hellmann, F., Sumer, O., Javanmardi, B., Andre, E., Krawitz, P., & Hsieh, T.-C. (2023, January). Improving deep facial phenotyping for ultra-rare disorder verification using model ensembles. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) . 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA. https://doi.org/10.1109/wacv56688.2023.00499