High-throughput synthesis and machine learning assisted design of photodegradable hydrogels

Abstract

Due to the large chemical space, the design of functional and responsive soft materials poses many challenges but also offers a wide range of opportunities in terms of the scope of possible properties. Herein we report an experimental workflow for miniaturized combinatorial high-throughput screening of functional hydrogel libraries. The data created from the analysis of the photodegradation process of more than 900 different types of hydrogel pads is used to train a machine learning (ML) model for automated decision making. Through iterative model optimization based on Bayesian Optimization we achieve a substantial improvement in response properties and thus expanded the scope of material properties obtainable within the chemical space of hydrogels in our study. We therefore demonstrate the potential of combining miniaturized high-throughput experiments with smart optimization algorithms for cost and time efficient optimization of materials properties.

ΔDFT Predicts Inverted Singlet–Triplet Gaps with Chemical Accuracy at a Fraction of the Cost of Wave Function-Based Approaches

“…In contrast to the D–A architecture, MR emitters achieve a small electron–hole overlap by distributing the HOMO and the LUMO on alternating positions of an aromatic π-system . Although this does not reduce electron–hole overlap as much as in D–A emitters and, in turn, leads to larger singlet–triplet gaps, other photophysical properties of MR-TADF emitter are more favorable: The emission spectrum of MR emitters is sharp and thus color pure and the transitions exhibit high oscillator strength and thus short lifetimes. , Because of these and further desirable properties, DABNA and its derivatives are used as fluorescent blue emitters in mass-produced OLED displays …”

What is missing in autonomous discovery: open challenges for the community

“…This has been approached using combinatorial synthesis in small areas (<1 mm 2 ), 114 multinary thin lm synthesis, 115,116 and microdroplet array synthesis. [117][118][119] Recent work with scanning probes has shown that sub-femtoliter solutions can be patterned and combined on surfaces, providing further opportunities to miniaturize experiments. 120,121 Such samples can also serve as miniaturized reactors, 122 having the broad effects of reducing material consumption and increasing experimental throughput.…”