Data Professor
Data & Analytics, Coding Tools, and Research Tools with a focus on bioinformatics and app building.
Nutrition Label
Data Professor delivers accessible, high-integrity tutorials on bioinformatics and data science application building. Content ranges from step-by-step coding walkthroughs to career insights, grounded in the creator's extensive academic background rather than hype.
Strengths
- +
- +
- +
Notes
- !Coding tutorials frequently use pre-made vendor notebooks rather than showing novel problem-solving from scratch.
- !Theoretical explanations are grounded in the creator's academic history, offering more context than standard tech guides.
Rating Breakdown
Breakdown across the key dimensions we rate. Methodology →
Recent Videos
Dentist vibe codes a dental app
Paradigm shift of the developer mindset in the age of GenAI
Build an LLM-Powered Voice Agent in Python
Bioinformatics Project from Scratch PART 2 - Preparing the Data Set
Building a Call Center Analytics Pipeline in Python
Data Science for Bioinformatics
How to Quickly Leverage Computer Vision in Python
From DNA to UI: Connecting the Dots between Theory and Application in Bioinformatics
Code Your Own Multilingual AI in Python that speaks 32 languages
Bioinformatics Project from Scratch PART 1 - Collecting the Data Set
Using Google Colab for Data Science and AI
Building a YouTube AI assistant for content creators with Python
Data Science Podcast with Sebastian Flores
How to level up in Gen AI
Code your own YouTube AI assistant in Python
Why this rating
Evidence receipts showing why each dimension is rated the way it is.
“And that is when I joined Streamlit as a developer advocate... essentially I'm doing the same thing I'm doing on YouTube but then for the company.”[12:08] →
The speaker explicitly discloses his employment with the company whose software he is discussing, integrating it naturally into his career narrative.
“The problem with this is that it is static. It is a PDF file. So if a biologist or a chemist wants to use the prediction model, they cannot use it. They have to know Python.”[07:38] →
Identifies a specific, real-world friction point in academic publishing (static PDFs vs. executable tools) that drives the need for the solution presented.
“We use a concept called QSAR... quantitative structure activity relationship. So essentially we convert the chemical structure into a set of numerical descriptors... fingerprints.”[04:55] →
Demonstrates deep domain knowledge by accurately explaining the underlying bioinformatics methodology (QSAR) before discussing the software implementation.
“The notebook that we're going to use today is available on the LandingAI GitHub.”[00:55] →
The content is a walkthrough of a vendor-provided example notebook rather than a novel implementation or unique problem-solving exercise.
“So essentially we're taking the bounding box coordinates... and then we're going to crop it.”[05:12] →
Explains the logic of the pipeline (detection -> crop -> OCR) clearly, though the technical complexity is abstracted away by the library being showcased.