Biology subjects

Williams, M. L.

Publications and source records attributed to Williams, M. L..

3 recordsLinked to original sources

bioRxiv2026

Multigenerational machine learning-based genomic prediction for dermo resistance in eastern oyster Crassostrea virginica

Dermo disease caused by the protist Perkinsus marinus poses a major threat to Eastern oyster aquaculture. We previously conducted genomic selection for dermo resistance and found increased effectiveness over phenotypic selection. Here, we report improved genomic predictions using combined data from three successive generations. We evaluated nine different genomic selection models, including three supervised machine learning architectures: gradient boosting, logistic regression, and random forest. Combining data across multiple generations did not, by itself, substantially improve the accuracy of most models, but the increased sample size provided genotyping confidence of loci with rare alleles. Correlation accuracy of all models significantly increased with the inclusion of low-frequency variants and strong-effect markers identified through a genome-wide association study. Gradient boosting machine learning models outperformed other genomic selection models across all training scenarios, suggesting enhanced capacity to learn generalizable genomic signals associated with dermo resistance. The best gradient boosting model achieved a peak correlation accuracy of 0.410, a substantial improvement over the previous peak accuracy of 0.274 from traditional models. Together, our results highlight the potential of machine learning for genomic selection and the significance of rare variants in determining dermo resistance.

genomics↗

bioRxiv2019

A post-processing algorithm for building longitudinal medication dose data from extracted medication information using natural language processing from electronic health records

ObjectiveWe developed a post-processing algorithm to convert raw natural language processing (NLP) output from electronic health records (EHRs) into a usable format for analysis. This algorithm was specifically developed for creating datasets for use in medication-based studies. Materials and MethodsThe algorithm was developed using output from two NLP systems, MedXN and medExtractR. We extracted medication information from deidentified clinical notes from Vanderbilts EHR system for two medications, tacrolimus and lamotrigine. The algorithm consists of two parts. Part I parses the raw NLP output and connects entities together. Part II removes redundancies and calculates dose intake and daily dose. We evaluated each part by comparing to human-determined gold standards that were generated using approximately 300 records from 10 subjects for each medication and each NLP system. ResultsThe algorithm performed well. For MedXN, the F-measures were at or above 0.99 for Part I and at or above 0.97 for Part II. For medExtractR, the F-measures for Part I were 1.00 and for Part II they were at or above 0.98. DiscussionOur post-processing algorithm was developed separately from an NLP system, making it easier to modify and generalize to other systems. It performed well to convert NLP output to analyzable data, but it cannot perform well in certain cases, such as when incorrect information is extracted by the NLP system. ConclusionOur post-processing algorithm provides a way to convert raw NLP output to a form that is useful for medication-based studies, leading to more opportunities to use EHR data for diverse studies.

bioinformatics↗

bioRxiv2019

A mesoderm-independent role for Nodal signaling in convergence & extension gastrulation movements

During embryogenesis, the distinct morphogenetic cell behavior programs that shape tissues are influenced both by the fate of cells and their position with respect to the embryonic axes, making embryonic patterning a prerequisite for morphogenesis. These two essential processes must therefore be coordinated in space and time to ensure proper development, but mechanisms by which patterning information is translated to the cellular machinery that drives morphogenesis remain poorly understood. Here, we address the role of Nodal morphogen signaling at the intersection of cell fate specification, patterning, and anteroposterior (AP) axis extension in zebrafish gastrulae and embryonic explants. AP axis extension is impaired in Nodal-deficient embryos, but it is unclear whether this defect is strictly secondary to their severe mesendoderm deficiencies or also results from loss of Nodal signaling per se. We find that convergence & extension (C&E) gastrulation movements and underlying mediolateral (ML) cell polarization are reduced in the neuroectoderm of Nodal-deficient mutants and exacerbated by simultaneous disruption of Planar Cell Polarity (PCP) signaling, demonstrating at least partially parallel functions of Nodal and PCP. ML polarity of mutant neuroectoderm cells is not fully restored upon transplantation into wild-type gastrulae, demonstrating a cell autonomous, mesoderm-independent role for Nodal in neural cell polarization. This is further demonstrated by the ability of Nodal ligands to promote neuroectoderm-driven C&E of naive blastoderm explants in a tissue-autonomous fashion. Finally, temporal manipulation of signaling reveals that Nodal contributes to neural C&E in explants after mesoderm is specified and promotes C&E even in the absence of mesoderm. Together these results reveal a mesoderm-independent, cell-autonomous role for Nodal signaling in neural C&E that may cooperate with previously-described mesoderm-dependent mechanisms to drive AP embryonic axis extension.

developmental biology↗