Table of Contents

• Coverage
• Dataset Description
  • Methods & Sampling
  • Data Processing Description
  • BCO-DMO Processing Description
  • Problem Description
• Related Datasets
• Parameters
• Project Information
• Funding

Acronyms:

SNP = Single-nucleotide Polymorphism
MLA = Machine Learning Algorithm
LD = Linkage Disequilibrium
NCBI = National Center for Biotechnology Information
DNA = Deoxyribonucleic acid
MVP = Model Validation Program
ABC = Aquaculture Genetics and Breeding Technology Center
VIMS = Virginia Institute of Marine Science 
GO = Gene Ontology

Source populations for monoculture treatments included six wild populations and two proprietary broodstock lines (DEBY and LOLA) from the Aquaculture Genetics and Breeding Technology Center (ABC), Virginia Institute of Marine Science (VIMS). Wild populations spanned the species’ native range, which is structured into distinct genetic clusters separated by the Florida peninsula (Reeb & Avise, 1990, Puritz et al., 2022). Populations included oysters from: a variable salinity site in Texas (W1-TX), a low salinity site in Louisiana (W2-LA), a high salinity site on the east coast of Florida (W3-FL), a moderate salinity site in the James River, Virginia (W4-VA), a variable salinity site in New Hampshire (W5-NH), and a high salinity site in Maine (W6-ME). W4-VA was considered local to both common garden sites due to its geographic proximity and intermediate salinity. 

Gill tissue was collected from each parent (n = 160) after spawning and stored in 95% ethanol at -80°C. DNA was extracted using the Qiagen DNeasy Blood and Tissue Kit and shipped to Neogen Genomics (Lincoln, NE) for genotyping on a 200K ThermoFisher Affymetrix Axiom SNP array derived from a 600K array (Gómez-Chiarri et al., 2015; Guo et al., 2023; Modak et al., 2021; Puritz et al., 2024) aligned to the haplotig-masked Crassostrea virginica reference genome (C_virginica-3.0, GCA_002022765.4).

Raw genotypes were processed and filtered in R v4.4.2 (R Core Team 2025). Missing SNPs were imputed using LEA v3.6.0 (Frichot & François, 2015) with K = 2 ancestral groups to produce a full SNP set. We thinned SNPs for linkage disequilibrium (LD) for population structure analysis and neutral parameterization of genome scans (Lotterhos, 2019) using bigsnpr v1.11.3 (Privé et al., 2018). The archived genotype matrix contains the processed, imputed genotype calls per individual encoded in 0/1/2 integer format (homozygous reference, heterozygous, and homozygous alternate, respectively). The accompanying SNP metadata file provides per-locus descriptions including genomic position, gene identifiers, functional descriptions, Gene Ontology terms, and population genetic statistics derived from OutFLANK (FST, expected heterozygosity, p-values, q-values, and outlier flags), as well as a flag indicating inclusion in the LD-thinned dataset, enabling straightforward filtering for only LD-thinned SNPs.

Raw genotypes were processed and filtered in R v4.4.2 (R Core Team 2025; Supp. Methods: genotype filtering). Missing SNPs were imputed using LEA v3.6.0 (Frichot & François, 2015) with K = 2 ancestral groups to produce a full SNP set. We thinned SNPs for linkage disequilibrium (LD) for population structure analysis and neutral parameterization of genome scans (Lotterhos, 2019) using bigsnpr v1.11.3 (Privé et al., 2018).

https://github.com/DrK-Lo/MVP-H2F-HatcheryField

- Loaded data from "Exp_parents_SNP_metadata.csv" into table "998738_v1_oyster-genotype-annotations" using CSV format with row 1 as header; treated empty strings and "nd" as missing values
- Renamed column "AX-ID" to "AX_ID"
- Set data types for all 29 columns: AX_ID, Affx_ID, Group, SNPType, Sequence, cust_id, gene_description, gene_id, go_ids, go_terms, mutID, on_oystercv, organism, scaffold, OutlierFlag, thinned_dataset as string; Chromosome, Position, Rank, Replicates, Tile_Std, Tile_max, Tile_v3 as integer; FST, He, chrom_position, pvalues, pvaluesRightTail, qvalues as number
- Output final table as "998738_v1_oyster-genotype-annotations.csv"

- Provided matrix file Exp_parents_full_SNP_matrix.rds attached as a data file directly. [not imported as a table]

NSF Award Abstract:
Environmental change can be rapid and involve multiple aspects of the environment changing at the same time, such as warming and increased disease pressure. Rapid environmental change threatens the productivity of aquaculture and crops on which humans depend. Predicting organisms' vulnerabilities to rapid and multifactor environmental change, however, is a major scientific challenge. A hurdle to addressing this challenge arises from the complex and non-intuitive ways that organisms adapt, through changes at the level of the DNA sequence, to many environmental stresses at the same time. Thus, there is a need for new approaches to understand and predict adaptation in multivariate environments. To address this need, this project integrates research and education with a Model Validation Program (MVP). The research is developing and evaluating Machine Learning Algorithms (MLAs) for understanding and predicting adaptation of organisms to multivariate environments from their DNA sequences. To evaluate MLAs, this research combines both data simulation and an empirical test in the field with the Eastern Oyster, which provide important ecosystem services and support a multi-million dollar industry. For oysters, this research is studying how temperature, disease pressure, and salinity interact with evolutionary history to determine fitness in the field. This research advances efforts toward addressing the major scientific challenge of predicting adaptation in complex environments by integrating concepts across the frontiers of marine, evolutionary, and statistical sciences in a new way. Machine learning and model validation are not traditionally taught in the marine and environmental sciences, but are becoming increasingly relevant to these fields. As part of a broader education program, this research is developing MVP Learning Modules for high school students and undergraduates, which help students build the foundational knowledge they need to critically evaluate and apply models. Modules are being disseminated to hundreds of students in the greater Boston area and are being made available online for widespread use. The MVP mentoring program is training graduate students, undergraduates, and high school students in marine evolutionary ecology, statistical genomics, and machine learning. This research addresses a pressing societal need to more informatively match genotypes to environments for restoration, farming, and assisted gene flow efforts. Results are being disseminated to stakeholders in the oyster industry.

The goal of this research is to evaluate if MLAs, which can model non-linearities, can be used to understand and predict adaptation to multivariate environments under a wide range of scenarios. In Objective 1, the Principal Investigator (PI) is creating simulated datasets with different aspects of realism, and using them to evaluate and refine the MLAs. This novel set of simulations is studying genome evolution under high gene flow in complex, multivariate environments. In Objective 2, the PI is building on their expertise with the Eastern oyster to evaluate the MLAs in a field setting. The PI is first developing a comprehensive seascape genomic dataset and using it to train MLAs to predict an individual's multivariate environment based on a single nucleotide polymorphism genotype. Then, the PI is testing if the MLA prediction can predict the fitness of different genotypes from across the species range when raised in common garden field conditions. In Objective 3, the PI is integrating research and education by using the data obtained from Objs. 1 and 2 to develop a series of original "MVP Learning Modules" with interactive web apps for persons at different levels of understanding, using the relatable example of an oyster restoration project. This research lays the foundation for future studies by producing datasets that could become classical examples for developing and benchmarking innovative modeling approaches.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.