AI to advance science research
Download as PPTX, PDF1 like109 views
This document discusses how AI can help advance various scientific fields such as mathematics, quantum chemistry, biology, and more. It provides examples of how machine learning has helped mathematicians develop new theories by analyzing patterns in examples. It also discusses how AI is helping push the limits of density functional theory in quantum chemistry and how AlphaFold uses transformers and protein multiple sequence alignments to predict structures with near experimental accuracy. The conclusion emphasizes not becoming a slave to models and maintaining inspiration.
AI to advance science research
- 1. AI in Science Research How can modern AI help to push the boundary of science Ding Li 2022.1
- 3. 3 AI Aids Intuition in Mathematical Discovery The cycle of developing mathematical theories by studying examples. • After recognizing a possible pattern in the properties of mathematical objects, such as convex polyhedra (3D shapes with flat faces, straight edges and vertices that all point outwards), mathematicians typically go through a cycle to understand this pattern. • They first compute the properties of some simple examples and analyze the possible relationships between these properties. • The researchers then refine these relationships. For example, they might come up with Euler’s polyhedron formula, which posits that the number of vertices (V) minus the number of edges (E) plus the number of faces (F) of a convex polyhedron is always equal to two: V − E + F = 2. • They then test this suggested relationship on more complicated examples, discard irrelevant properties and attempt to understand why the relationship holds. If it remains unclear, mathematicians then consider different examples, and the cycle continues. • Davies et al.1 show that machine-learning techniques can help researchers with the refinement step, which usually relies strongly on human intuition Stump 2021
- 4. 4 Advancing mathematics by guiding human intuition with AI Davies 2021 As an illustrative example: let z be convex polyhedra, X(z) ∈ Z2 × R2 be the number of vertices and edges of z, as well as the volume and surface area, and Y(z) ∈ ℤ be the number of faces of z. Euler’s formula states that there is an exact relationship between X(z) and Y(z) in this case: X(z) · (−1, 1, 0, 0) + 2 = Y(z). The framework helps guide the intuition of mathematicians in two ways: by verifying the hypothesized existence of structure/patterns in mathematical objects through the use of supervised machine learning; and by helping in the understanding of these patterns through the use of attribution techniques.
- 6. 6 Pushing the Frontiers of Density Functionals by Solving the Fractional Electron Problem Kirkpatrick 2021 • Computing electronic energies underpins theoretical chemistry and materials science, and density functional theory (DFT) promises an exact and efficient approach • But the approach has limitations and is known to give the wrong results for certain types of molecule. • “It’s sort of the ideal problem for machine learning: you know the answer, but not the formula you want to apply.” • The functional was evaluated by integrating local energies computed by a multilayer perceptron (MLP), which took as input both local and nonlocal features of the occupied Kohn-Sham (KS) orbitals and can be described as a local range-separated hybrid. • To train the functional, the sum of two objective functions was used: a regression a gradient regularization term that ensured that the functional derivatives can be used in self-consistent field (SCF) calculations after training Castelvecchi 2021
- 7. 7 BIOLOGY
- 8. 8 Primary Structure Amino acids (20) Peptide bond Secondary Structure Tertiary Structure Quaternary Structure
- 9. 9 (MSA) Multiple Sequence Alignments Nseq x Nres • Evolutionary constrains • MSA clustering • Cluster deletion • Evolutionary correlations Pairwise Feature Nres x Nres • Physical and geometric constrains • Target feat (amino acids), residue index • Structural templates • Template distogram Near experimental accuracy in most cases for CASP14 assessment (May-July 2020) Jumper 2021 GitHub AlphaFold Protein Structure Database (JAK2) Blog Colab UniProt (JAK2)
- 10. 10 A BERT-style transformer was applied to predict randomly masked individual residues within the MSA, which encourages the network to learn to interpret phylogenetic and covariation relationships without hardcoding a particular correlation statistic into the features. Exchange information iteratively to enable direct reasoning about the spatial and evolutionary relationships in the proteins. Combination of the bioinformatics and physical approaches We hope that AlphaFold—and computational approaches that apply its techniques for other biophysical problems—will become essential tools of modern biology.
- 11. 11 “Do not quench your inspiration and your imagination; do not become the slave of your model.” – Vincent van Gogh