Computational approaches streamlining drug discovery

Nature, Год журнала: 2023, Номер 616(7958), С. 673 - 685

Опубликована: Апрель 26, 2023

Computer-aided drug discovery has been around for decades, although the past few years have seen a tectonic shift towards embracing computational technologies in both academia and pharma. This is largely defined by flood of data on ligand properties binding to therapeutic targets their 3D structures, abundant computing capacities advent on-demand virtual libraries drug-like small molecules billions. Taking full advantage these resources requires fast methods effective screening. includes structure-based screening gigascale chemical spaces, further facilitated iterative approaches. Highly synergistic are developments deep learning predictions target activities lieu receptor structure. Here we review recent advances technologies, potential reshaping whole process development, as well challenges they encounter. We also discuss how rapid identification highly diverse, potent, target-selective ligands protein can democratize process, presenting new opportunities cost-effective development safer more small-molecule treatments. Recent approaches application streamlining discussed.

Язык: Английский

---

The rise of self-driving labs in chemical and materials sciences

Nature Synthesis, Год журнала: 2023, Номер 2(6), С. 483 - 492

Опубликована: Янв. 30, 2023

Язык: Английский

---

Autonomous Chemical Experiments: Challenges and Perspectives on Establishing a Self-Driving Lab

Accounts of Chemical Research, Год журнала: 2022, Номер 55(17), С. 2454 - 2466

Опубликована: Авг. 10, 2022

We must accelerate the pace at which we make technological advancements to address climate change and disease risks worldwide. This swifter of discovery requires faster research development cycles enabled by better integration between hypothesis generation, design, experimentation, data analysis. Typical take months years. However, data-driven automated laboratories, or self-driving can significantly molecular materials discovery. Recently, substantial have been made in areas machine learning optimization algorithms that allowed researchers extract valuable knowledge from multidimensional sets. Machine models be trained on large sets literature databases, but their performance often hampered a lack negative results metadata. In contrast, generated laboratories information-rich, containing precise details experimental conditions Consequently, much larger amounts high-quality are gathered laboratories. When placed open repositories, this used community reproduce experiments, for more in-depth analysis, as basis further investigation. Accordingly, will increase accessibility reproducibility science, is sorely needed.In Account, describe our efforts build lab new class materials: organic semiconductor lasers (OSLs). Since they only recently demonstrated, little known about material design rules thin-film, electrically-pumped OSL devices compared other technologies such light-emitting diodes photovoltaics. To realize high-performing materials, developing flexible system synthesis via iterative Suzuki-Miyaura cross-coupling reactions. platform directly coupled analysis purification capabilities. Subsequently, molecules interest transferred an optical characterization setup. currently limited measurements solution. properties ultimately most important solid state (e.g., thin-film device). end different scientific goal, inorganic focused oxygen evolution reaction.While future very promising, numerous challenges still need overcome. These split into cognition motor function. Generally, cognitive related with constraints unexpected outcomes general algorithmic solutions yet developed. A practical challenge could resolved near software control because few instrument manufacturers products mind. Challenges function largely handling heterogeneous systems, dispensing solids performing extractions. As result, it critical understand adapting procedures were designed human experimenters not simple transferring those same actions system, there may efficient ways achieve goal fashion. carefully rethink translation manual protocols.

Язык: Английский

---

Closed-loop optimization of general reaction conditions for heteroaryl Suzuki-Miyaura coupling

Science, Год журнала: 2022, Номер 378(6618), С. 399 - 405

Опубликована: Окт. 27, 2022

General conditions for organic reactions are important but rare, and efforts to identify them usually consider only narrow regions of chemical space. Discovering more general reaction requires considering vast space derived from a large matrix substrates crossed with high-dimensional conditions, rendering exhaustive experimentation impractical. Here, we report simple closed-loop workflow that leverages data-guided down-selection, uncertainty-minimizing machine learning, robotic discover conditions. Application the challenging consequential problem heteroaryl Suzuki-Miyaura cross-coupling identified double average yield relative widely used benchmark was previously developed using traditional approaches. This study provides practical road map solving multidimensional optimization problems search spaces.

Язык: Английский

---

A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

Journal of the American Chemical Society, Год журнала: 2022, Номер 144(43), С. 19999 - 20007

Опубликована: Окт. 19, 2022

We report the development of an open-source experimental design via Bayesian optimization platform for multi-objective reaction optimization. Using high-throughput experimentation (HTE) and virtual screening data sets containing high-dimensional continuous discrete variables, we optimized performance by fine-tuning algorithm components such as encodings, surrogate model parameters, initialization techniques. Having established framework, applied optimizer to real-world test scenarios simultaneous yield enantioselectivity in a Ni/photoredox-catalyzed enantioselective cross-electrophile coupling styrene oxide with two different aryl iodide substrates. Starting no previous data, identified conditions that surpassed previously human-driven campaigns within 15 24 experiments, each substrate, among 1728 possible configurations available To make more accessible nonexperts, developed graphical user interface (GUI) can be accessed online through web-based application incorporated features condition modification on fly visualization. This web does not require software installation, removing any programming barrier use platform, which enables chemists integrate routines into their everyday laboratory practices.

Язык: Английский

---

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

Chemical Science, Год журнала: 2022, Номер 14(2), С. 226 - 244

Опубликована: Ноя. 28, 2022

This review outlines several organic chemistry tasks for which predictive machine learning models have been and can be applied.

Язык: Английский

---

On the use of real-world datasets for reaction yield prediction

Chemical Science, Год журнала: 2023, Номер 14(19), С. 4997 - 5005

Опубликована: Янв. 1, 2023

The lack of publicly available, large, and unbiased datasets is a key bottleneck for the application machine learning (ML) methods in synthetic chemistry. Data from electronic laboratory notebooks (ELNs) could provide less biased, large datasets, but no such have been made available. first real-world dataset ELNs pharmaceutical company disclosed its relationship to high-throughput experimentation (HTE) described. For chemical yield predictions, task synthesis, an attributed graph neural network (AGNN) performs as well or better than best previous models on two HTE Suzuki-Miyaura Buchwald-Hartwig reactions. However, training AGNN ELN does not lead predictive model. implications using data ML-based are discussed context predictions.

Язык: Английский

---

Self-Driving Laboratories for Chemistry and Materials Science

Chemical Reviews, Год журнала: 2024, Номер 124(16), С. 9633 - 9732

Опубликована: Авг. 13, 2024

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through automation experimental workflows, along with autonomous planning, SDLs hold potential to greatly accelerate research in chemistry and materials discovery. This review provides in-depth analysis state-of-the-art SDL technology, its applications across various disciplines, implications for industry. additionally overview enabling technologies SDLs, including their hardware, software, integration laboratory infrastructure. Most importantly, this explores diverse range domains where have made significant contributions, from drug discovery science genomics chemistry. We provide a comprehensive existing real-world examples different levels automation, challenges limitations associated each domain.

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

---

Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis

Communications Chemistry, Год журнала: 2024, Номер 7(1)

Опубликована: Янв. 12, 2024

The empirical aspect of descriptor design in catalyst informatics, particularly when confronted with limited data, necessitates adequate prior knowledge for delving into unknown territories, thus presenting a logical contradiction. This study introduces technique automatic feature engineering (AFE) that works on small datasets, without reliance specific assumptions or pre-existing about the target catalysis designing descriptors and building machine-learning models. generates numerous features through mathematical operations general physicochemical catalytic components extracts relevant desired catalysis, essentially screening hypotheses machine. AFE yields reasonable regression results three types heterogeneous catalysis: oxidative coupling methane (OCM), conversion ethanol to butadiene, three-way where only training set is swapped. Moreover, application active learning combines high-throughput experimentation OCM, we successfully visualize machine's process acquiring precise recognition design. Thus, versatile data-driven research key step towards fully automated discoveries.

Язык: Английский

---