Learning Grammars of Molecules to Build Them in the Lab : Daily Current Affairs

Relevance: GS-3: Science and Technology- Developments and their Applications and Effects in Everyday Life

Key Phrases: graph grammars; AI, ML, Deeplearning, National Strategy on AI, bottom-up approach

Why in News?

  • Researchers from Massachusetts Institute of Technology (MIT) and International Business Machines (IBM) have together devised a method to generate molecules computationally which combines the power of machine learning with what are called graph grammars

Context

  • Large macromolecules lead us to the basis of life. They form an essential part of our lives and due to their different properties they are used to suit our needs.

Designer Molecules

  • These are molecules of which we formulate a wish list of properties for material (say, desired tensile strength as well as flexibility) and seek to not merely discover, but also “construct,” molecules that exhibit such properties.
  • Technologies used - The generation of these molecules computationally involves the use of Artificial Intelligence (AI) and machine learning (ML) algorithms that require large datasets to train on.
    • Moreover, the molecules thus designed may be hard to synthesise. So, the challenge is to circumvent these shortfalls.
  • This approach requires much smaller datasets (for example, about 100 datasets in the place of 81,000, as the researchers mention) and builds up the molecules in a bottom-up approach.
  • The group has demonstrated this method on naphthalene diisocyanate molecule

Generating Structures

  • Artificial intelligence (AI) techniques, especially the use of ML algorithms, are utilized to find new molecular structures.
    • These methods require tens of thousands of samples to train the neural networks.
    • Knowledge from Chemical Analysis to increase the synthesizability of these molecules.

Challenges of AI and the Datasets

  • Low number of Chemical datasets with required properties.
    • For instance, researchers reported in 2019 that datasets on polyurethane property prediction have as few as 20 samples.
  • Inability to explain the results of ML Algorithms
    • After discovering a molecule, we cannot figure out how we came up with it.
  • The implication is that if we slightly change the desired properties, we may need to search all over again. Explainable AI is considered one of the grand challenges of contemporary AI research.

Grammars of Molecules

  • Utilising the concept of grammar
    • Grammar, in the context of languages, provides rules for how sentences can be constructed from words.
    • We can design chemical grammars that specify rules for constructing molecules from atoms.
      • But, this requires extensive expertise in chemistry, and after the grammar is built, incorporating properties from datasets, or optimisation, is hard.
  • The researchers use mathematical objects called graph grammars for this purpose.
    • What mathematicians call graphs are networks or webs with nodes and edges between them.
    • In this approach, a molecule is represented as a graph where the nodes are strings of atoms and edges are chemical bonds.
  • Getting to the basic structure
    • A grammar for such structures tells us how to replace a string in a node with a whole molecular structure. Thus, parsing a structure means contracting some substructure; we keep doing this repeatedly until we get a single node.
    • The model uses ML techniques to learn graph grammars from datasets.
    • The algorithm takes as input a set of molecular structures and a set of evaluation metrics (for example, synthesizability).
  • Beyond chemistry
    • The grammar is constructed bottom-up, creating rules by contractions; choosing which structures to contract is based on the learning component, a neural network which builds on the chemical information.
    • ● The algorithm simultaneously performs multiple, randomised searches to obtain multiple grammars as candidates.

While the method has been demonstrated for use in building molecules, the applications could be far reaching, beyond chemistry.

Artificial Intelligence

  • Task Force on Artificial Intelligence (AI) for India’s Economic Transformation which recommended an Inter-Ministerial National Artificial Intelligence Mission
  • NITI Aayog has unveiled its discussion paper on national strategy on AI
    • 5 sectors – healthcare, agriculture, education, smart cities and infrastructure, and transportation - has been identified
  • Global Partnership on Artificial Intelligence (GPAI) - India has joined this initiative
    • To guide the responsible development and use of AI in line with human rights, inclusion, diversity, innovation, and economic growth

Source: The Hindu

Mains Question:

Q. What are Graph Grammars? Explain the usage of AI and it’s usage in our daily lives.