Bioeconomy 2 min

Deep learning: from Sudoku to protein design

Scientists from the Applied Mathematics and Informatics research unit (MIAT) and Toulouse Biotechnology Institute (TBI) at the INRAE Occitanie-Toulouse center have developed a hybrid artificial intelligence (AI) learning method for solving difficult puzzles and designing new proteins.

Published on 17 July 2023

illustration Deep learning: from Sudoku to protein design

Artificial intelligence (AI) language models impress with their ability to respond in a coherent, structured way. But when it comes to reasoning and logic, they are still limited. For example, when ChatGPT is asked to solve a grid of the famous Sudoku puzzle, the solutions it comes up with do not respect the rules, and sometimes even modify the original numbers in the grid.

This difficulty with logical reasoning is not specific to language models. In fact, it is common to most neural networks. They are very good at extracting patterns from data, but much weaker at reasoning from data. But combined with automatic reasoning methods, a general AI should be capable of both learning and reasoning, just like humans do.

Learning to play Sudoku

For automated reasoning, solving hard Sudoku grids is a trivial task when the rules are given. But when it comes to learning them, it is a two-stage process. First, the AI must deduce the rules by observing examples of completed puzzles, then it must use these rules to complete new puzzles. Scientists from the Applied Mathematics and Informatics research unit (MIAT) and Toulouse Biotechnology Institute (TBI) have therefore combined two types of AI to learn how to play Sudoku: a neural network to learn the rules from examples, and a prover to apply these rules to solving new puzzles.

Their hybrid method learns fast (in 15 minutes!) and is minimalist: it requires just 200 examples of complete grids, a fraction of what other approaches require. Plus, it is transparent: the decision made by the discrete prover can be understood by analyzing which rules have been learned. This ’window’ into the process allows for better control and understanding.

From Sudoku to protein design

Proteins are macro-molecules essential to any kind of life as they fulfill many biological and biochemical functions in all living organisms. Designing new proteins has applications in health and green chemistry, among others.

From the proof-of-principle obtained on Sudoku grid solving, scientists have exploited its analogy with protein design. Seen as a "puzzle" in which the aim is to place atoms in space, learning protein models leads to learning its "rules of the game", which can then be used by automatic reasoning tools to design new proteins.

This research combines intuitive recognition of deep learning with meticulous logic of automated reasoning. In addition to its speed and transparency, the real strength of the method developed is its ability to model a variety of problems, from solving Sudoku to real-life issues such as designing new proteins.


AIhub article Bridging the gap between learning and reasoning

M. Defresne, S. Barbe and T. Schiex. Scalable Coupling of Deep Learning with Logical Reasoning. Proceedings of the Thirty-second International International Joint Conference on Artificial Intelligence, IJCAI’2023.

Learn more


New protein created via artificial intelligence

The goal of artificial intelligence (AI) is to help computers (better) solve problems normally dealt with by humans. In Toulouse, bioinformatics researchers have used AI and automated reasoning algorithms to design a hyperstable self-assembling protein. This work is the fruit of a collaboration between INRAE scientists in the Research Unit for Applied Mathematics and Informatics (at the centre of Occitanie-Toulouse) and scientists in Belgium and Japan.

19 February 2020


Thomas Schiex becomes an AAAI Fellow for his outstanding research in artificial intelligence

Thomas Schiex is a researcher director at the INRAE centre of Occitanie-Toulouse, where he carries out work in artificial intelligence (AI) and bioinformatics. His goals are to improve AI's ability to solve difficult automated reasoning problems and to make his results freely available to the international scientific community. Schiex was recently made an Association for the Advancement of Artificial Intelligence (AAAI) Fellow in honour of his overall research achievements. Find out more about Schiex and his work in his portrait, which was written in 2016 after he became a EurAI Fellow.

19 February 2020


Understand how bacteria adapt to their environment

To adapt to environmental changes, bacteria control the degradation of the messenger RNAs (mRNAs), the intermediate molecules between gene expression and protein synthesis. A research team from the Toulouse Biotechnology Institute (INRAE-CNRS-INSA) in collaboration with Inria of Grenoble, has deciphered the underlying regulatory mechanisms. This work was published in two articles in 2020 in the scientific journals mSphere and Journal of Theoretical Biology.

12 February 2021