The Mouse Phenome Database (MPD) provides access to primary experimental trait data, genotypic variation, protocols and analysis tools for mouse genetic studies. Data are contributed by investigators worldwide and represent a broad scope of phenotyping endpoints and disease-related traits in naïve mice and those exposed to drugs, environmental agents or other treatments. MPD ensures rigorous curation of phenotype data and supporting documentation using relevant ontologies and controlled vocabularies. As a repository of curated and integrated data, MPD provides a means to access/re-use baseline data, as well as allows users to identify sensitized backgrounds for making new mouse models with genome editing technologies, analyze trait co-inheritance, benchmark assays in their own laboratories, and many other research applications. MPD’s primary source of funding is NIDA. For this reason, a majority of MPD data is neuro- and behavior-related.
This lesson introduces some practical exercises which accompany the Synapses and Networks portion of this Neuroscience for Machine Learners course.
This lesson gives an introduction to the central concepts of machine learning, and how they can be applied in Python using the scikit-learn package.
This lesson provides an overview of self-supervision as it relates to neural data tasks and the Mine Your Own vieW (MYOW) approach.
As a part of NeuroHackademy 2020, Elizabeth DuPre gives a lecture on "Nilearn", a python package that provides flexible statistical and machine-learning tools for brain volumes by leveraging the scikit-learn Python toolbox for multivariate statistics. This includes predictive modelling, classification, decoding, and connectivity analysis.
This video is courtesy of the University of Washington eScience Institute.
This lesson from freeCodeCamp introduces Scikit-learn, the most widely used machine learning Python library.
This lecture goes into detailed description of how to process workflows in the virtual research environment (VRE), including approaches for standardization, metadata, containerization, and constructing and maintaining scientific pipelines.
This lesson provides an overview of how to conceptualize, design, implement, and maintain neuroscientific pipelines in via the cloud-based computational reproducibility platform Code Ocean.
In this workshop talk, you will receive a tour of the Code Ocean ScienceOps Platform, a centralized cloud workspace for all teams.
This lecture covers a wide range of aspects regarding neuroinformatics and data governance, describing both their historical developments and current trajectories. Particular tools, platforms, and standards to make your research more FAIR are also discussed.
This lecture introduces you to the basics of the Amazon Web Services public cloud. It covers the fundamentals of cloud computing and goes through both the motivations and processes involved in moving your research computing to the cloud.
This lesson provides an overview of how to construct computational pipelines for neurophysiological data using DataJoint.
This talk describes approaches to maintaining integrated workflows and data management schema, taking advantage of the many open source, collaborative platforms already existing.
This hands-on tutorial walks you through DataJoint platform, highlighting features and schema which can be used to build robost neuroscientific pipelines.
In this third and final hands-on tutorial from the Research Workflows for Collaborative Neuroscience workshop, you will learn about workflow orchestration using open source tools like DataJoint and Flyte.
This lecture provides a detailed description of how to incorporate HED annotation into your neuroimaging data pipeline.
This lecture describes how to build research workflows, including a demonstrate using DataJoint Elements to build data pipelines.
This lecture covers how to make modeling workflows FAIR by working through a practical example, dissecting the steps within the workflow, and detailing the tools and resources used at each step.
This is a tutorial on designing a Bayesian inference model to map belief trajectories, with emphasis on gaining familiarity with Hierarchical Gaussian Filters (HGFs).
This lesson corresponds to slides 65-90 of the PDF below.
This tutorial introduces pipelines and methods to compute brain connectomes from fMRI data. With corresponding code and repositories, participants can follow along and learn how to programmatically preprocess, curate, and analyze functional and structural brain data to produce connectivity matrices.