Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back

Science, Год журнала: 2023, Номер 382(6677)

Опубликована: Дек. 21, 2023

A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In first study, experimentally realized 294 unreported across three automatic iterations design-make-test-analyze cycles while exploring structure-function space four rarely reported scaffolds. each iteration, property prediction models that guided exploration learned structure-property diverse scaffold derivatives, which were multistep syntheses a variety reactions. The second study exploited trained explored chemical previously discover nine top-performing within lightly space.

Язык: Английский

---

A critical examination of robustness and generalizability of machine learning prediction of materials properties

npj Computational Materials, Год журнала: 2023, Номер 9(1)

Опубликована: Апрель 7, 2023

Abstract Recent advances in machine learning (ML) have led to substantial performance improvement material database benchmarks, but an excellent benchmark score may not imply good generalization performance. Here we show that ML models trained on Materials Project 2018 can severely degraded new compounds 2021 due the distribution shift. We discuss how foresee issue with a few simple tools. Firstly, uniform manifold approximation and projection (UMAP) be used investigate relation between training test data within feature space. Secondly, disagreement multiple illuminate out-of-distribution samples. demonstrate UMAP-guided query by committee acquisition strategies greatly improve prediction accuracy adding only 1% of data. believe this work provides valuable insights for building databases enable better robustness generalizability.

Язык: Английский

---

Combinatorial synthesis for AI-driven materials discovery

Nature Synthesis, Год журнала: 2023, Номер 2(6), С. 493 - 504

Опубликована: Март 9, 2023

Язык: Английский

---

Revolutionizing drug formulation development: The increasing impact of machine learning

Advanced Drug Delivery Reviews, Год журнала: 2023, Номер 202, С. 115108 - 115108

Опубликована: Сен. 27, 2023

Язык: Английский

---

Advanced supramolecular design for direct ink writing of soft materials

Chemical Society Reviews, Год журнала: 2023, Номер 52(5), С. 1614 - 1649

Опубликована: Янв. 1, 2023

This review draws connections between top-down direct-ink-writing and bottom-up supramolecular designs. Examples of supramolecularly designed viscoelastic inks perspectives using motifs for 3D printing have been discussed.

Язык: Английский

---

Unleashing the Power of Artificial Intelligence in Materials Design

Materials, Год журнала: 2023, Номер 16(17), С. 5927 - 5927

Опубликована: Авг. 30, 2023

The integration of artificial intelligence (AI) algorithms in materials design is revolutionizing the field engineering thanks to their power predict material properties, de novo with enhanced features, and discover new mechanisms beyond intuition. In addition, they can be used infer complex principles identify high-quality candidates more rapidly than trial-and-error experimentation. From this perspective, herein we describe how these tools enable acceleration enrichment each stage discovery cycle novel optimized properties. We begin by outlining state-of-the-art AI models design, including machine learning (ML), deep learning, informatics tools. These methodologies extraction meaningful information from vast amounts data, enabling researchers uncover correlations patterns within structures, compositions. Next, a comprehensive overview AI-driven provided its potential future prospects are highlighted. By leveraging such algorithms, efficiently search analyze databases containing wide range identification promising for specific applications. This capability has profound implications across various industries, drug development energy storage, where performance crucial. Ultimately, AI-based approaches poised revolutionize our understanding materials, ushering era accelerated innovation advancement.

Язык: Английский

---

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Journal of the American Chemical Society, Год журнала: 2023, Номер 145(40), С. 21699 - 21716

Опубликована: Сен. 27, 2023

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable fundamentally interesting, because they often involve new physical phenomena compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) automated experimentation have widely proposed to accelerate target identification synthesis planning. In this Perspective, we argue the data-driven methods commonly used today well-suited for optimization not realization of exceptional molecules. Finding such outliers should be possible using ML, only by shifting away from traditional ML approaches tweak composition, crystal structure, reaction pathway. We highlight case studies high-Tc oxide superconductors superhard demonstrate challenges ML-guided discovery discuss limitations automation task. then provide six recommendations development capable discovery: (i) Avoid tyranny middle focus on extrema; (ii) When data limited, qualitative predictions direction than interpolative accuracy; (iii) Sample what can made how make it defer optimization; (iv) Create room (and look) unexpected while pursuing your goal; (v) Try fill-in-the-blanks input output space; (vi) Do confuse human understanding model interpretability. conclude a description these integrated into workflows, which enable materials.

Язык: Английский

---

Accelerated chemical science with AI

Digital Discovery, Год журнала: 2023, Номер 3(1), С. 23 - 33

Опубликована: Дек. 6, 2023

The ASLLA Symposium focused on accelerating chemical science with AI. Discussions data, new applications, algorithms, and education were summarized. Recommendations for researchers, educators, academic bodies provided.

Язык: Английский

---

Exploiting redundancy in large materials datasets for efficient machine learning with less data

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Ноя. 10, 2023

Extensive efforts to gather materials data have largely overlooked potential redundancy. In this study, we present evidence of a significant degree redundancy across multiple large datasets for various material properties, by revealing that up 95% can be safely removed from machine learning training with little impact on in-distribution prediction performance. The redundant is related over-represented types and does not mitigate the severe performance degradation out-of-distribution samples. addition, show uncertainty-based active algorithms construct much smaller but equally informative datasets. We discuss effectiveness in improving robustness provide insights into efficient acquisition training. This work challenges "bigger better" mentality calls attention information richness rather than narrow emphasis volume.

Язык: Английский

---

Perspective: Machine learning in experimental solid mechanics

Journal of the Mechanics and Physics of Solids, Год журнала: 2023, Номер 173, С. 105231 - 105231

Опубликована: Янв. 31, 2023

Язык: Английский

---