From listmaster animalgenome.org Wed Jan 8 21:28:38 2020
Return-Path: <listmasteranimalgenome.org>
From: Malachy Campbell <campbell.malachygmail.com>
Postmaster: submission approved by list moderator
To: Members of AnGenMap <angenmapanimalgenome.org>
Subject: Postdoctoral Associate - Machine Learning Genetics
of Oat Composition (Cornell University)
Date: Wed, 08 Jan 2020 21:28:38 -0600
The position is in the Plant Breeding and Genetics Section at Cornell
University, and is part of a USDA Agriculture and Food Research Initiative
grant to breed more nutritious oat. Oat is uniquely valued among grain
crops for the health-promoting composition of its seeds. This position
seeks to apply novel machine learning methods to extensive genomic,
transcriptomic, and metabolomic datasets. Results should generate effective
methods to improve the composition of oat seed.
The Plant Breeding & Genetics Section, within the School of Integrative
Plant Science, trains interdisciplinary scientists in the elaboration of
new breeding methods, the discovery of genetic mechanisms important for
economically important traits, and the creation of genetic stocks,
germplasm, and varieties. We promote a collaborative and interactive
workspace to improve learning, cross connectivity, and mutual support
between basic and applied researchers. Cornell University plant breeders
are world leaders in innovative plant breeding research, teaching, and
extension, and we collaborate globally.
The Jannink lab works with several crop species (wheat, oat, barley,
cassava, and the brown algae sugar kelp) to develop genomic prediction
methods and integrate them optimally into breeding schemes. We work
together to discover, build on, and share new ideas and tools from across
computational disciplines that lead to successful applied breeding
outcomes. With the Jannink lab, Dr. Michael Gore and Dr. Mark Sorrells
provide leadership on the multiomic oat selection project.
In research for this project, the postdoc will collaborate with oat
breeders at Universities in Minnesota, Wisconsin and South Dakota, as well
as a postdoctoral associate currently working on the project. We have
characterized an oat diversity panel of 384 genotypes with high-density DNA
marker data, RNA-seq gene expression data, and non-targeted LC-MS, GC-MS,
and targeted fatty acid methyl ester data of mature oat seed. We will
analyze these data to identify important genomic drivers of the mature oat
seed metabolome. We will test whether results from this analysis can
improve prediction accuracy in a series of 18 biparental crosses. We will
also sequence a population of 1,500 oat TILLING (Targeted Induced Local
Lesions In Genomes) lines at putative causal loci to determine if their
metabolomes are indeed affected.
We seek a candidate with machine learning expertise, specifically deep
learning neural network methods, and interest in applications relating to
genetic variation and complex biological systems. The datasets described
have rich structure and are amenable to machine learning analyses to
identify patterns eluding linear models. Aided by other project personnel,
the postdoc will identify patterns in the metabolomic and transcriptomic
assays and their associations with genetic variation. The postdoc will
construct learning models to identify multifactorial causes of seed
composition variation, enabling the prediction of the impact of genetic
perturbation on seed composition and suggesting effective breeding
strategies to leverage this ability.
Anticipated Division of Time: Field work, sample prep, data collection
(25%); Machine learning analysis and interpretation (30%); Writing (30%);
Training of lab members and collaborators in machine learning (15%)
Position Requirements: Ph.D. in engineering, statistics, or computer
science focused on machine learning, with experience or interest in genetic
or complex biology applications, or Ph.D. in genetics with emphasis on
machine learning analysis of genetic data. Proven scientific writing
ability and communication skills.
Preferred Specific Skills: Knowledge of genetics and genetic data types and
analysis. Knowledge of biochemistry, metabolomics or systems biology
methods. Basic bioinformatics skills (sequence alignment, use of gene
annotations). Basic notions of plant or animal breeding.
How to Apply: Candidates should send a statement of interest, curriculum
vitae, contact information for three references and a statement of
diversity, equity and inclusion (
https://cals.cornell.edu/...-inclusion).
Submit all application materials to Academic Jobs Online (
https://academicjobsonline.org/ajo/jobs/15773). Questions about the
position can be addressed to Dr. Michael Gore at: mag87cornell.edu .
Review of applications will begin immediately and continue until the
position is filled.
Diversity and Inclusion are a part of Cornell University’s heritage. We are
a recognized employer and educator valuing AA/EEO, Protected Veterans, and
Individuals with Disabilities.
--
Postdoctoral Research Associate
Plant Breeding and Genetics Section
Cornell University
https://malachycampbell.github.io/
|
