Artificial intelligence is becoming more commonplace with tools like ChatGPT, Gemini and Copilot. But there is a field of science called bioinformatics that takes AI and machine learning to an entirely new level.
Bioinformatics, also known as computational biology, links biological data with information storage, distribution and analysis to support many scientific research areas.
In the latest Short Talks from the Hill podcast, Aranyak Goswami, assistant professor of bioinformatics and computational biology with the University of Arkansas System Division of Agriculture and the University of Arkansas Department of Animal Science, discusses how he is using machine computers to answer complex biological questions.
John Lovett from the University of Arkansas Department of Agricultural Science asked Goswami how he would define bioinformatics.
Aranyak Goswami: Bioinformatics is, in very layman terms, using computer science to solve biological problems. And these biological problems can be therapeutic, things like giving rise to better therapeutic strategies with the help of computational targets that you give.
If you know about the Human Genome Project, which appeared in the early 2000s, that was actually the birth of modern bioinformatics, because we have these sequences of genes. And to put it in very layman terms, we have hundreds and thousands of genes from humans. Actually, 40,000 are the coding genes, to be precise. And that sequence was done with the help of computational approaches. And that gave rise to this modern field of bioinformatics.
Now, with the genetic tools in our hand nowadays, we can extrapolate this not only to humans, but to any kind of model system we want to do. And we can also say that there are a lot of agricultural, plant sciences, animal sciences, animal models. You can extrapolate this.
And if I put it in a very non-sciencey way, then it will be using computer science knowledge to solve biological problems, and also with the advent of AI doing a lot of predictive analysis.
When we talked about it before, I kind of connected it to putting together a puzzle with millions of pieces.
John Lovett: Yeah. Do you put together puzzles in your free time?
Goswami: I like to put puzzles or Lego kind of things when I was a kid. What I really like to keep me sharp is I play chess a lot, chess puzzles I solve.
Bioinformatics is a lot about pattern discovery, pattern finding, pattern matching. And solving chess puzzles in a limited time gives you that mental agility so that you can identify patterns, go for these sequences. So I was always an avid chess player. I just do one or two rounds every day to keep me mentally agile.
And that is very close to puzzle solving, like finding patterns and the best possible move within the shortest possible time. And then I sometimes take the help of computers to analyze whether my move was the best or something.
Lovett: When people hear about gene sequencing, is that people like you or a combination of different disciplines?
Goswami: Yes. So when we talk about gene sequencing, there are two aspects of it. So the one aspect is first of all the experimental aspect.
If I explain it in very simple terms, everybody knows about DNA, which is the basic genetic material of the cell. So experimental biologists basically extract the DNA from an individual. And this DNA, if you see, actually is the bearer of all the genes that we have in our hand.
So there are different experimental techniques that people use to make this genetic profiling. Now our work as a bioinformatician comes next. So when you have these different portions of genes present in different regions of the chromosome, our job is piecing these things together in a computational way so that you can get the complete information.
That was the early days of bioinformatics. Now we have moved a lot forward. The initial goal was to map the genes. But now what we can do is piece together the information and also find out relationships between the genes.
Something we used to call dark matter when we were students is actually the non-coding elements of the gene. And recent research has shown that these non-coding elements are more interesting than the coding elements.
Now, with the help of these computational tools, we can analyze and find relations between the gene regions and the interaction with the non-coding regions. That gives us a lot of perspective about how regulation of a gene happens.
Which means that whatever phenotypes that we see, a particular behavior is not only genetic, but there are also what is called phenotypic data, which is not just transmitted from one individual to the next in the usual hereditary manner, but based upon lifestyle.
For example, the chromosome can get methylation patterns, which are specific to certain individuals, which gives rise to the whole field of epigenetics. This is something from the genomics aspect, which I am an expert of.
Now with the advent of machine learning, there is a lot of predictive things you can do. If you have a list of certain parameters, it can be genes, it can be any kind of information. You can put it in a computer, in very layman terms.
Based upon that, you can identify some signatures of the data which are predictive markers. And when you get new kinds of similar data, you can say whether this data will be following that predictive behavior or not.
This has great applications not only in the biology field. If you see when you are typing your prompt on Apple, this comes from predictive text, and now it has become AI-based.
All of ChatGPT and what you see nowadays is based upon prompts. That is because you are doing a certain kind of prediction. This is word-based prediction. You have one word and you have to predict what the next word would be in a probabilistic manner.
And that is all what ChatGPT is doing, to put it in a very, very layman term.
Lovett: In your presentation at the AI and Ag Symposium, you talked about three projects that benefit Arkansas agriculture. Can you summarize those briefly?
Goswami: The first project I am doing with the Department of Entomology and Plant Pathology and with the Department of Computer Science. Dr. Fiona Goggin from entomology and plant pathology and Dr. Cole Loo from computer science, very competent scientists.
That particular project we are looking into a plant called Arabidopsis thaliana. Agricultural people will know that. We are trying to correlate genomic data and phenomic data.
Genomic data is all the genetic data that we have information about. But for plants, we also collect other kinds of data. We take several measurements. We take photographs of leaf size, crop infestation, pesticides, changes in leaf diameter.
We have genetic data before. We have phenomic data. But there is no integration of this genomic and phenomic data together. And for the first time, we are trying to integrate this data so we can get a complete perspective and not only have good biological context, but also make a better set of precision plants in the future.
The second project is working with swine genetics, because I am part of the animal science department. We have a lot of swine population.
We want to look at the microbiome of swine. For people who do not know microbiome, it is the beneficial microbes present in an animal or a human.
We are looking at how the microbiome grows within the swine population over a certain time period. We are looking at intestinal profiling. Although we have similar ages of swine, microbial health and microbial maturity may vary depending on the microbial pool.
We are trying to analyze this microbial pool and also develop machine learning models. If these are good sets of bacteria, then based upon this test set, what are the good amounts of bacteria that can be beneficial for that particular swine population?
Another project directly under my lab is in the poultry industry. Recently, we saw a great surge in egg prices because poultry went through an epidemic that caused billions of dollars of loss.
We are trying to study a pathogen called Enterococcus cecorum, which infects poultry. We are using computational methods to find out which genes make chickens sick.
This work is with Cobb-Vantress, one of the biggest poultry companies. They are our stakeholders. We are trying to give them candidates they can use as targets for non-vaccine-based antibiotics.
Lovett: You recently published an article about ChatGPT-5 and how the new AI era is changing science. You mentioned philosophical and scientific questions that come with it. Can you talk about that?
Goswami: We can make major scientific advances over the next hundred years. We can go to Mars, have cars that can fly, and solve major diseases.
But the basic proponents of humans, like envying each other and wanting bad things for each other, are tendencies that have persisted for generations. So there is always an ethical perspective that we should take.
The whole field of deep learning and machine learning was brought about by Geoffrey Hinton. He is skeptical about how it is progressing, that it might control us if AI becomes artificial general intelligence.
AI systems might communicate with each other and no longer be under humans. With respect to my article published in a leading journal in India, what I would say is that AI is nothing more than a predictive model.
You give one word and it finds the next possible word. AI is not new. It was known as machine learning, machine intelligence, statistical learning. It has progressed for decades.
Now, with very powerful computing machines, we are getting meaningful interpretations. AI is not thinking the way we think.
But the caution is that brain-inspired designs can perform tasks that overpower us. There should be caution. AI brings a lot of good things, but human values should not be gone.
Lovett: Well, thank you, Dr. Goswami, for coming in today. We really appreciate your insights on AI and your work at the University of Arkansas.
Aranyak Goswami is an assistant professor of bioinformatics and computational biology with the University of Arkansas System Division of Agriculture and the University of Arkansas Department of Animal Science.
He discussed his work with John Lovett from the University of Arkansas Department of Agricultural Science on this month’s episode of Short Talks from the Hill.
If you would like to learn more, you can visit kuaf.com/shorttalks.
Ozarks at Large transcripts are created on a rush deadline. Copy editors utilize AI tools to review work. KUAF does not publish content created by AI. Please reach out to kuafinfo@uark.edu to report an issue. The audio version is the authoritative record of KUAF programming.
