Autonomous retrosynthesis of gold nanoparticles <i>via</i> spectral shape matching

Vaddi, Kiran; Chiang, Huat Thart; Pozzo, Lilo D.

doi:10.1039/d2dd00025c

Cited by 29 publications

(30 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While significant work has gone into developing synthesis platforms and methods that mostly focus on small-molecule − and colloidal − synthesis, comparatively less focus has been given to polymer synthesis . In the last several years, several groups have taken advantage of the versatility of reversible addition–fragmentation chain transfer (RAFT) polymerization and constructed automated copolymer synthesis platforms. ,− These studies seek to find the polymer sequence or reaction conditions that achieves an optimal material property such as 19 F magnetic resonance signal (MRI) signal for contrast agents, retained enzyme efficiency for protein stabilizers, or simply the conversion and dispersity of the synthesis itself …”

Section: New Progressmentioning

confidence: 99%

Emerging Trends in Machine Learning: A Polymer Perspective

Martin

Audus

2023

ACS Polym. Au

View full text Add to dashboard Cite

In the last five years, there has been tremendous growth in machine learning and artificial intelligence as applied to polymer science. Here, we highlight the unique challenges presented by polymers and how the field is addressing them. We focus on emerging trends with an emphasis on topics that have received less attention in the review literature. Finally, we provide an outlook for the field, outline important growth areas in machine learning and artificial intelligence for polymer science and discuss important advances from the greater material science community.

show abstract

Section: New Progressmentioning

confidence: 99%

Emerging Trends in Machine Learning: A Polymer Perspective

Martin

Audus

2023

ACS Polym. Au

View full text Add to dashboard Cite

show abstract

“…This process will repeat until a predetermined experimental budget is exhausted. Indeed, AL strategies such as Bayesian optimization [24][25][26] and variance-based sampling 23 have recently been applied in the context of closed-loop design of nanomaterials, including inorganic nanoparticles, 27,28 polymeric nanoparticles encapsulating nucleic acids, 29 and polymer-protein hybrids. 30 Few-shot learning for accurate prediction of nanomedicines for novel active agents.…”

Section: B Machine Learning Strategies To Enhance Efficient Formulati...mentioning

confidence: 99%

Self-Driving Laboratories: A Paradigm Shift in Nanomedicine Development

Hickman

Bannigan

Bao

et al. 2022

Preprint

View full text Add to dashboard Cite

Nanomedicines have transformed promising therapeutic agents into clinically approved medicines with optimal safety and efficacy profiles. This is exemplified by the mRNA vaccines against COVID-19, which were made possible by lipid nanoparticle technology. Despite the success of nanomedicines to date, their design remains far from trivial in part due to the complexity associated with their preclinical development. Herein we propose a nanomedicine materials acceleration platform (NanoMAP) to streamline the preclinical development of these formulations. NanoMAP combines high-throughput experimentation with state-of-the-art advances in artificial intelligence (including active learning and few-shot learning) as well as a web-based application for data sharing. The deployment of NanoMAP requires interdisciplinary collaboration between leading figures in drug delivery and artificial intelligence to enable this data-driven design approach. The proposed approach will not only expedite the development of next generation nanomedicines, but also encourage participation of the pharmaceutical science community in a large data curation initiative.

show abstract

“…The starting point of our analysis is the consideration of measurement profiles as points in an infinite-dimensional function space. Some of our recent work has used this approach to analyze UV-Vis spectroscopic curves of nanostructures in problems related to explorative study for design rules [22] and material retrosynthesis [17]. A function space is a vector space analog for functions as points equipped with an appropriate inner product that can be used to measure lengths and angles.…”

Section: Metric Geometry Of Function Spacesmentioning

confidence: 99%

“…all the shapes that can be obtained by warping. The distance in Equation ( 4) is referred to as the "amplitude" distance in [17] as it measures the variation corresponding to y-scale or the amplitude. Defining the shape distance requires us to solve an optimization problem of finding the infimum of the distance d F that is defined using functions and the warping function.…”

Section: Metric Geometry Of Function Spacesmentioning

confidence: 99%

“…In this work, we extend the statistical shape theory ideas to experimentally measured one-dimensional profiles by considering them as points in an infinite-dimensional function space. In particular, we use the Amplitude-Phase distance defined in [17] to construct a 'shape' distance between profiles by only considering the aligned amplitude distance that effectively quotients the distance contribution from shape independent features. The amplitude distance defined can be used as an alternative to the Euclidean distance to learn shape-based representations and thus identify a shape-invariant metric structure of the data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Metric geometry tools for automatic structure phase map generation

Vaddi

Pozzo

2022

Preprint

View full text Add to dashboard Cite

Extracting a phase map that provides a hierarchical summary of high-throughput experiments is a long-standing bottleneck for the modern goal of achieving automation and acceleration in material discovery. A phase map that underpins the inherent properties of materials is typically denoted using a composition-structure map but can be extended to other relevant parameters such as synthesis. This paper describes a computational statistical tool to efficiently obtain a phase map from multi-scale experimental measurement profiles on-the-fly during high-throughput measurements. We motivate the construction of a phase map as the problem of learning the underlying metric geometry defined by a set of templates in infinite-dimensional function spaces. We provide a statistical analysis tool to obtain a phase map as an asymptotic of the diffusion of resulting distance functions on the composition. Using examples from small-angle X-ray scattering experiments of polymer blend systems, we show that learned metric geometry can efficiently differentiate ordered phase regions with shifted, missing, and broad Bragg peaks along with features related to non-Bragg behavior in scattering data characteristic of soft-matter systems. The metric geometry allows us to define a shape distance between scattering profiles invariant to phase-independent transformations thus valuable for obtaining a phase map. We also apply the methodology to benchmark experimental diffraction data to showcase the qualitative improvement over existing methods and broad applicability.

show abstract

Autonomous retrosynthesis of gold nanoparticles via spectral shape matching

Abstract: A Riemannian metric for spectral data is introduced to efficiently compute shape matching distances for material retrosynthesis in high-throughput autonomous laboratories.

Cited by 29 publications

References 21 publications

Emerging Trends in Machine Learning: A Polymer Perspective

Emerging Trends in Machine Learning: A Polymer Perspective

Self-Driving Laboratories: A Paradigm Shift in Nanomedicine Development

Metric geometry tools for automatic structure phase map generation

Contact Info

Product

Resources

About