We are DataTecnica
With our partners and clients, we are innovating and tackling a broad range of problems in global healthcare, from mental health, aging, diabetes, and neurological disorders to hospital administration and diagnostic tools.
Featured Product
DataTecnica.AI
DataTecnica.AI is our flagship large language model powered assistant for biomedical research and data discovery. We have put guardrails and heavily engineered prompts in place to help keep resource use efficient and interactions accurate. We will be rolling out a couple test builds for the NIH and more by Q1 2024. Please reach out if you have any additional questions.
DataTecnica.AI is our flagship large language model powered assistant for biomedical research and data discovery. We have put guardrails and heavily engineered prompts in place to help keep resource use efficient and interactions accurate. We will be rolling out a couple test builds for the NIH and more by Q1 2024. Please reach out if you have any additional questions.
DataTecnica.AI is our flagship large language model powered assistant for biomedical research and data discovery. We have put guardrails and heavily engineered prompts in place to help keep resource use efficient and interactions accurate. We will be rolling out a couple test builds for the NIH and more by Q1 2024. Please reach out if you have any additional questions.
“We are staunch advocates of open science, striving to make data and code easily accessible to the scientific community.”
Collaborative software developement and deploys.
DataTecnica.AI
DataTecnica.AI is our flagship large language model powered assistant for biomedical research and data discovery. We have put guardrails and heavily engineered prompts in place to help keep resource use efficient and interactions accurate. We will be rolling out a couple test builds for the NIH and more by Q1 2024. Please reach out if you have any additional questions.
Open source toolkit to automate and democratize many common genomics and machine learning workflows. The incoming update will also include further optimization for federated learning to enable analyses across data silos. Please see the documentation here and the federated learning proof of concept here.
GenoML
Our fourth genotyping array collaboration with Illumina Inc., designed to maximize discovery across ancestry groups and increase inclusivity in the study of brain diseases. For more information, please refer to this publication detailing its use in the Global Parkinson's Genetics Program.
NeuroBooster
OmicSynth
OmicSynth is an application of our foundational framework for target discovery and due diligence rooted in large-scale genetics and genomics integration plus cell type specific context. A rapidly growing and extensible resource. Check out the build for NIH's Center for Alzheimer's and Related Dementias here, as well as its accompanying preprint here.
D.I.V.E.R.
D: Data file
I: Inventory (and)
V: Verification
E: Environment (for)
R: Research
DIVER is our common data element (CDE) focused tool for data discovery and harmonization. Check out the video walk through here. Rapid development underway.
CRISPRbrain is a foundational #openscience data commons for multi-modal data in edited cells built in collaboration with the Kampmann Lab at UCSF, which can be found here as well as in its most recent publication here. It has been expanded to include many more datasets than the original as well as scaled for lipidomics as well (with proteomic and viral RNA screens incoming shortly).