Hello everyone, Last year I wrote several posts on the large language models (LLM) of DNA sequences (evo/evo2 papers), and some readers emailed me asking about the plans to continue the series. Here is an exciting update for you. Guhan Thiagarajan, a high-school student, worked with me and built a “toy model” to help you explore these concepts.
In earlier blog posts, we explored how AI models are being used for protein folding and DNA language modeling. Machine learning is driving rapid progress in another important area of biology: antibiotic discovery. Rushil Mohan, a smart high-school student, worked with me and wrote a fantastic review post to introduce you to this fascinating area of research.
On Saturday, I ran Alphafold for the first time. Google built a website (Alphafold Server) through which you can run the program directly. The results are really positive, or cross that, extremely positive (wink). Here I provide a brief tutorial and a description of what I found.
Note: Please check our full plan for the series here
Alright class ! If you are still here, you already completed part (i) covering Scikit-learn for machine learning and became familiar with the Pytorch library for AI in part (ii). As part of the first lesson, you also watched the StatQuest videos explaining four machine learning concepts.
Note: Please check our full plan for the series here
In part (i) of this guide, you learned to use Python library Scikit-learn for machine learning. Today you will get familiar with Pytorch for AI.
Note: Please check our full plan for the series here
These days, many biologists are trying to learn machine learning and artificial intelligence. That is not surprising. Recent research papers in genomics, molecular biology, drug discovery, ecology, or bioinformatics are increasingly using terms and concepts from those fields. Here is a short roadmap on how to start, and moreover, how to proceed rapidly through the maze.
In a classic scene from Idiocracy, we see the citizens of a fictional United States from year 2500 repeatedly insisting that Brawndo is the “thirst mutilator” because it contains electrolytes, while water belongs only in the toilet. The slogan is repeated so many times by the Brawndo company that it has become deeply embedded in their thinking.
The Internet revolution never truly arrived in scientific publishing. Instead, an old system that was functional in its time was scaled up in a largely cargo-cult manner, producing today’s grotesque, dysfunctional, and extraordinarily expensive publishing ecosystem.
Most scientists tolerate this absurdity because they are insulated from its costs. First, they learn to accept the dysfunction as the inevitable “cost of doing business.” Second, universities pay the subscription bills, so individual researchers working there rarely feel the price and paywalled gatekeeping directly.
Clearly the current publishing model is utterly dysfunctional. The best way to see that is to ask the following question. If the current system is thrown away, and the scientists gather to create a brand new system for publishing, will they build a replica of the current model? Will they beg the journal companies to lock up their papers in exchange for free work of writing, editing, reviewing and most importantly doing the entire research?
The publication system in biology is mindblowingly ridiculous as often pointed out by Mike Eisen. I was planning to buy a biology book published in the 1990s and wanted to check an old review on it before spending my money. The price of the thick book came down to below $20, but the one page review article still costs $32.99.
These days, corporate entities are increasingly dominating research in basic science. This essay looks into how this will change the most cherised convention of science.
I came across an interesting blog post titled Biology is Messy. The main argument is that biology is not built on top of reductionist theories, and the current push to collect large amount of data and use “AI” to “solve” biology is not likely to lead to finding reductionist theories either. Instead we will get a bunch of overfitted models hyped up as “solutions” by corporate entities.
Right now everyone is either enamored of or is completely turned off by AI. Speaking of being fed up, please check the students at University of Florida booing at this commencement event. Much of their reactions comes from intense hype generated by the tech-bros of Silly Con valley to increase stock prices of their companies.
On the subject of reconstructing gene regulatory networks (GRNs) from RNAseq and scRNAseq data, I am working through a number of review papers and the techniques described therein.
As I learn from them, I will post my notes here for the benefit of others. Also, in this context, I will discuss how we can use AI (chatGPT) to speed up learning of bioinformatics tools.
