STICI: Split-Transformer with integrated convolutions for genotype imputation
Abstract Despite advances in sequencing technologies, genome-scale datasets often contain missing bases and genomic segments, hindering downstream analyses. Genotype imputation addresses this issue and has been a cornerstone pre-processing step in genetic and genomic studies. Although various method...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-56273-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571549386801152 |
|---|---|
| author | Mohammad Erfan Mowlaei Chong Li Oveis Jamialahmadi Raquel Dias Junjie Chen Benyamin Jamialahmadi Timothy Richard Rebbeck Vincenzo Carnevale Sudhir Kumar Xinghua Shi |
| author_facet | Mohammad Erfan Mowlaei Chong Li Oveis Jamialahmadi Raquel Dias Junjie Chen Benyamin Jamialahmadi Timothy Richard Rebbeck Vincenzo Carnevale Sudhir Kumar Xinghua Shi |
| author_sort | Mohammad Erfan Mowlaei |
| collection | DOAJ |
| description | Abstract Despite advances in sequencing technologies, genome-scale datasets often contain missing bases and genomic segments, hindering downstream analyses. Genotype imputation addresses this issue and has been a cornerstone pre-processing step in genetic and genomic studies. Although various methods have been widely adopted for genotype imputation, it remains challenging to impute certain genomic regions and large structural variants. Here, we present a transformer-based framework, named STICI, for accurate genotype imputation. STICI models automatically learn genome-wide patterns of linkage disequilibrium, evidenced by much higher imputation accuracy in regions with highly linked variants. Our imputation results on the human 1000 Genomes Project and non-human genomes show that STICI can achieve high imputation accuracy comparable to the state-of-the-art genotype imputation methods, with the additional capability to impute multi-allelic variants and various types of genetic variants. STICI can be trained for any collection of genomes automatically using self-supervision. Moreover, STICI shows excellent performance without needing any special presuppositions about the underlying patterns in collections of non-human genomes, pointing to adaptability and applications of STICI to impute missing genotypes in any species. |
| format | Article |
| id | doaj-art-dcd7ac33d3ef481a9763a66e811c2b55 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-dcd7ac33d3ef481a9763a66e811c2b552025-02-02T12:33:29ZengNature PortfolioNature Communications2041-17232025-01-0116111410.1038/s41467-025-56273-3STICI: Split-Transformer with integrated convolutions for genotype imputationMohammad Erfan Mowlaei0Chong Li1Oveis Jamialahmadi2Raquel Dias3Junjie Chen4Benyamin Jamialahmadi5Timothy Richard Rebbeck6Vincenzo Carnevale7Sudhir Kumar8Xinghua Shi9Computer & Information Sciences, College of Science and Technology, Temple UniversityComputer & Information Sciences, College of Science and Technology, Temple UniversityDepartment of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, Wallenberg Laboratory, University of GothenburgDepartment of Microbiology and Cell Science, University of FloridaSchool of Computer Science and Technology, Harbin Institute of TechnologyDavid R. Cheriton School of Computer Science, University of WaterlooDivision of Population Sciences, Dana-Farber Cancer InstituteInstitute for Genomics and Evolutionary Medicine, Temple UniversityComputer & Information Sciences, College of Science and Technology, Temple UniversityComputer & Information Sciences, College of Science and Technology, Temple UniversityAbstract Despite advances in sequencing technologies, genome-scale datasets often contain missing bases and genomic segments, hindering downstream analyses. Genotype imputation addresses this issue and has been a cornerstone pre-processing step in genetic and genomic studies. Although various methods have been widely adopted for genotype imputation, it remains challenging to impute certain genomic regions and large structural variants. Here, we present a transformer-based framework, named STICI, for accurate genotype imputation. STICI models automatically learn genome-wide patterns of linkage disequilibrium, evidenced by much higher imputation accuracy in regions with highly linked variants. Our imputation results on the human 1000 Genomes Project and non-human genomes show that STICI can achieve high imputation accuracy comparable to the state-of-the-art genotype imputation methods, with the additional capability to impute multi-allelic variants and various types of genetic variants. STICI can be trained for any collection of genomes automatically using self-supervision. Moreover, STICI shows excellent performance without needing any special presuppositions about the underlying patterns in collections of non-human genomes, pointing to adaptability and applications of STICI to impute missing genotypes in any species.https://doi.org/10.1038/s41467-025-56273-3 |
| spellingShingle | Mohammad Erfan Mowlaei Chong Li Oveis Jamialahmadi Raquel Dias Junjie Chen Benyamin Jamialahmadi Timothy Richard Rebbeck Vincenzo Carnevale Sudhir Kumar Xinghua Shi STICI: Split-Transformer with integrated convolutions for genotype imputation Nature Communications |
| title | STICI: Split-Transformer with integrated convolutions for genotype imputation |
| title_full | STICI: Split-Transformer with integrated convolutions for genotype imputation |
| title_fullStr | STICI: Split-Transformer with integrated convolutions for genotype imputation |
| title_full_unstemmed | STICI: Split-Transformer with integrated convolutions for genotype imputation |
| title_short | STICI: Split-Transformer with integrated convolutions for genotype imputation |
| title_sort | stici split transformer with integrated convolutions for genotype imputation |
| url | https://doi.org/10.1038/s41467-025-56273-3 |
| work_keys_str_mv | AT mohammaderfanmowlaei sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT chongli sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT oveisjamialahmadi sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT raqueldias sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT junjiechen sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT benyaminjamialahmadi sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT timothyrichardrebbeck sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT vincenzocarnevale sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT sudhirkumar sticisplittransformerwithintegratedconvolutionsforgenotypeimputation AT xinghuashi sticisplittransformerwithintegratedconvolutionsforgenotypeimputation |