*** Call for Participation for GenoVarDis at IberLEF 2024 ***
GenoVarDis: NER in Genomic Variants and related Diseases at IberLEF 2024
https://codalab.lisn.upsaclay.fr/competitions/17733
We look forward to your participation in advancing Spanish biomedical text processing through the GenoVarDis challenge at IberLEF 2024.
This task addresses the shortage of resources for Spanish in the domain of NER and genomic variants. The first one of this kind. By leveraging a unique corpus of a wider spectrum of mutations and variant-related entities (including gene, disease and symptom) in Spanish (mainly, translating from English and curated by human-experts), we aim to provide valuable data for training and evaluating NER models in this low-resource domain.
Description of the task:
* Given a text (sequence of tokens), identify the named entities as spans in the text and
classify them according to one of: Variant on DNA sequence, RS number, Allele on DNA sequence, Wild type and mutant, Variant with insufficient information, and transcript IDs. Metrics will include precision, recall, and F1 scores for the task (F-score is the primary metric), considering exact matches.
Example of text:
Neurofibromatosis tipo I. Mutación de splicing detectada por MLPA y secuenciación en la Argentina La neurofibromatosis tipo 1 (NF1) es un desorden genético autosómico dominante, con una prevalencia de 1 en 2500-3000 nacidos vivos. La dificultad diagnóstica se debe al tamaño extenso del gen NF1 con pocos sitios hot-spot, la ausencia de una clara relación genotipo-fenotipo y rasgos clínicos con un espectro muy heterogéneo. Un caso sospechoso de NF1 procedente de la provincia de Jujuy fue analizado por MLPA (multiplex ligation-dependent probe amplification) en nuestro laboratorio. Mujer, adolescente mestiza (Amerindia/Europea), con un osteoma maxilar, lordosis lumbar, neurofibromas cutáneos y manchas café con leche. Por MLPA se detectó una alteración en el exón 13 del gen NF1. Por secuenciación del exón 13 se identificó una mutación “missense” en la posición 1466 del ARNm (NM_000267.3:c.1466A>G) que introduce un sitio de splicing aberrante.
#pmid start end term entity
25919870 0 24 Neurofibromatosis tipo I Disease
25919870 101 125 neurofibromatosis tipo 1 Disease
25919870 127 130 NF1 Gene
25919870 291 294 NF1 Gene
25919870 447 450 NF1 Gene
25919870 640 655 Osteoma maxilar Disease
25919870 657 672 Lordosis lumbar Disease
25919870 674 696 Neurofibromas cutáneos Disease
25919870 699 721 Manchas café con leche Disease
25919870 747 771 Alteración en el exón 13 OtherMutation
25919870 780 783 NF1 Gene
25919870 833 872 Mutación “missense” en la posición 1466 OtherMutation
25919870 883 894 NM_000267.3 Transcript
25919870 895 904 c.1466A>G DNAMutation
How to participate:
If you want to participate in this task, please join our Codalab competition: https://codalab.lisn.upsaclay.fr/competitions/17733
Important Dates:
* March 22, 2024: release training corpus.
* May 24, 2024: release test corpus.
* June 7, 2024: publication of results.
* June 17, 2024: paper submission.
* June 28, 2024: notification of acceptance.
* July 3, 2024: camera ready paper submission.
* September, 2024: IberLEF 202 Workshop.