Machine Learning and Deep Learning in Genetics and Genomics

Wu, Di; Karhade, Deepti Shroff; Pillai, Malvika; Jiang, Min-Zhi; Huang, Le; Li, Gang; Cho, Hunyong; Roach, Jeff; Li, Yun; Divaris, Kimon

doi:10.1007/978-3-030-71881-7_13

Cited by 5 publications

(3 citation statements)

References 142 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Approaches allowing for pleiotropy have the potential to increase the power, sensitivity, and meaning of GWAS, similarly as the HSC-PA approach allowed us to obtain more phenotypic information by accounting for correlations in spectral data. As the field of genetics continues to evolve, it is conceivable that advanced techniques, such as machine learning and deep learning (Libbrecht and Noble, 2015; Wu, Karhade, Pillai, Jiang, Huang, Li, Cho, Roach, Li and Divaris, 2021), could offer more meaningful insights into genetic associations. Previous studies have used random forest models to allow for more complex and interactive effects of individual genetic variants on binary and even multivariate phenotypes, although the interpretation of “significance” in associations is not as straightforward with these models (Brieuc, Waters, Drinan and Naish, 2018; Wang, Goh, Wong, Montana and the Alzheimer’s Disease Neuroimaging Initiative, 2013).…”

Section: Discussionmentioning

confidence: 99%

Association of leaf spectral variation with functional genetic variants

Li,

Czyż,

Ray

et al. 2023

Preprint

View full text Add to dashboard Cite

The application of in-field and aerial spectroscopy to assess functional and phylogenetic variation in plants has led to novel ecological insights and promises to support global assessments of plant biodiversity. Understanding the influence of plant genetic variation on reflectance spectra will help to harness this potential for biodiversity monitoring and improve our understanding of why plants differ in their functional responses to environmental change. Here, we use an unusually well-resolved genetic mapping population in a wild plant, the coyote tobaccoNicotiana attenuata, to associate genetic differences with differences in leaf spectra for plants in a field experiment in their natural environment. We analyzed the leaf reflectance spectra using FieldSpec 4 spectroradiometers on plants from 325 fully genotyped recombinant inbred lines (RILs) ofN. attenuatagrown in a blocked and randomized common garden experiment. We then tested three approaches to conducting Genome-Wide Association Studies (GWAS) on spectral variants. We introduce a new Hierarchical Spectral Clustering with Parallel Analysis (HSC-PA) method which efficiently captured the variation in our high-dimensional dataset and allowed us to discover a novel association, between a locus on Chromosome 1 and the 445-499 nm spectral range, which corresponds to the blue light absorption region of chlorophyll, indicating a genetic basis for variation in photosynthetic efficiency. These associations lie in close proximity to candidate genes known to be expressed in leaves and having annotated functions as methyltransferases, indicating possible underlying mechanisms governing these spectral differences. In contrast, an approach using well-established spectral indices related to photosynthesis, reducing complex spectra to a few dimensionless numbers, was not able to identify any robust associations, while an approach treating single wavelengths as phenotypes identified the same associations as HSC-PA but without the statistical power to pinpoint significant associations. The HSC-PA approach we describe here can support a comprehensive understanding of the genetic determinants of leaf spectral variation which is datadriven but human-interpretable, and lays a robust foundation for future research in plant genetics and remote sensing applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Association of leaf spectral variation with functional genetic variants

Li,

Czyż,

Ray

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning from both genetics and images. In addition to its successful applications to medical imaging [74], deep learning also found success in applications on genomics [33,60,121,138,139]. There is a growing number of recent works that utilize deep neural networks to jointly learn from both modalities, such as [7,10,21,28,37,42,59,81,117,135].…”

Section: Related Workmentioning

confidence: 99%

ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics

Taleb¹,

Kirchler²,

Monti³

et al. 2021

Preprint

View full text Add to dashboard Cite

High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose ContIG, a self-supervised method that can learn from large datasets of unlabeled medical images and genetic data. Our approach aligns images and several genetic modalities in the feature space using a contrastive loss. We design our method to integrate multiple modalities of each individual person in the same model end-toend, even when the available modalities vary across individuals. Our procedure outperforms state-of-the-art selfsupervised methods on all evaluated downstream benchmark tasks. We also adapt gradient-based explainability algorithms to better understand the learned cross-modal associations between the images and genetic modalities. Finally, we perform genome-wide association studies on the features learned by our models, uncovering interesting relationships between images and genetic data.

show abstract

“…However, single-cell pseudotime analysis comes with significant challenges [24]. First, single-cell measurements are usually sparse and high-dimensional [1, 30]. In practice, only a subset of cells may express any given gene, and the capture rate of the genes also varies, which makes pseudotime inference harder.…”

Section: Introductionmentioning

confidence: 99%

Pseudotime analysis for time-series single-cell sequencing and imaging data

Li,

Kim,

Pendyala

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Many single-cell RNA-sequencing studies have collected time-series data to investigate transcriptional changes with respect to various notions of biological time, such as cell differentiation, embryonic development, and response to stimulus. Accordingly, several unsupervised and supervised computational methods have been developed to construct single-cell pseudotime embeddings for extracting the temporal order of transcriptional cell states from these time-series scRNA-seq datasets. However, existing methods, such as psupertime, suffer from low predictive accuracy, and this problem becomes even worse when we try to generalize to other data types such as scATAC-seq or microscopy images. To address this problem, we propose Sceptic, a support vector machine model for supervised pseudotime analysis. Whereas psupertime employs a single joint regression model, Sceptic simultaneously trains multiple classifiers with separate score functions for each time point and also allows for non-linear kernel functions. Sceptic first generates a probability vector for each cell and then aims to predict chronological age via conditional expectation. We demonstrate that Sceptic achieves significantly improved prediction power (accuracy improved by 1.4 − 38.9%) for six publicly available scRNA-seq data sets over state-of-the-art methods, and we show that Sceptic also works well for single-nucleus image data. Moreover, we observe that the pseudotimes assigned by Sceptic show stronger correlations with nuclear morphology features than the observed time labels, suggesting that these pseudotimes accurately capture the heterogeneity of nuclei derived from a single time point and thus provide more informative time labels than the observed times. Finally, we show that Sceptic accurately captures sex-specific differentiation timing from both scATAC-seq and scRNA-seq data.

show abstract

Machine Learning and Deep Learning in Genetics and Genomics

Cited by 5 publications

References 142 publications

Association of leaf spectral variation with functional genetic variants

Association of leaf spectral variation with functional genetic variants

ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics

Pseudotime analysis for time-series single-cell sequencing and imaging data

Contact Info

Product

Resources

About