Heterozygous Variants in KMT2E Cause a Spectrum of Neurodevelopmental Disorders and Epilepsy
AMERICAN JOURNAL OF HUMAN GENETICS(2019)
Harvard Med Sch | Broad Center for Mendelian Genomics | Division of Evolution & Genomic Sciences | Department of Systems Biology | Univ Oxford | Division of Neurology | Department of Molecular Medicine and Surgery | Institute of Medical Genetics | McGill Univ | Pediatric Neurology | Univ Amsterdam | Institute of Medical Genetics and Applied Genomics | Laboratoire de Génétique Moléculaire et Génomique | Division of Genetics | Department of Genetics | West Midlands Regional Clinical Genetics Service | Univ Med Ctr Utrecht | Medical Genetics | Childrens Hosp Philadelphia | Centre de Génétique Chromosomique | Department of Clinical Genetics | Medical Genetic Unit | Oxford National Institute for Health Research Biomedical Research Centre | Division of Neurology and Department of Biomedical and Health Informatics | Univ Siena | GeneDx | Univ Calif San Diego | Service de Génétique Médicale | Division of Genetics and Metabolism | Mendelics Genomic Analysis | Department of Medical Genetics | IRCCS Ist Giannina Gaslini | Ludwig Institute for Cancer Research | Division of Medical Genetics and Genomics | Amsterdam Univ Med Ctr | Division of Clinical and Metabolic Genetics | Department of Neuropediatrics | Neuropediatric Unit | Department of Pediatrics | Section of Pediatric Neurology | Center for Pediatric Genomic Medicine | Department of Neurology and Epileptology | EA7364 Rares du Developpement Embryonnaire et du Metabolisme | Division of Child Neurology and Inherited Metabolic Diseases | Univ Florida | School of Medicine | Pediatric Neurology and Neurophysiology | Univ Fed Sao Paulo | Azienda Osped Univ Senese | Childrens Mercy Hosp & Clin | Scripps Res Inst | Aarhus Univ Hosp | Univ Toronto | UnivToronto | Univ Tuspacing | Wellcome Sanger Inst | Ctr Hosp Univ Nantes | Italian Hosp Lugano | Univ Leipzig | Spectrum Hlth | Univ Zurich | Univ Genoa | Karolinska Inst | Univ Penn | Rady Childrens Hosp | Univ Chile | Univ S Florida | Cook Childrens Phys Network | Christian Albrechts Univ Kiel | Natl Hlth Serv Fdn Trust
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

被引用117 | 浏览
被引用20 | 浏览
被引用92 | 浏览
被引用1858 | 浏览
被引用43 | 浏览
被引用159 | 浏览
被引用75 | 浏览
被引用1169 | 浏览
被引用120 | 浏览
被引用194 | 浏览
被引用152 | 浏览