Goto

Collaborating Authors

Chemicals


How explainable artificial intelligence can help humans innovate

AIHub

The field of artificial intelligence (AI) has created computers that can drive cars, synthesize chemical compounds, fold proteins and detect high-energy particles at a superhuman level. However, these AI algorithms cannot explain the thought processes behind their decisions. A computer that masters protein folding and also tells researchers more about the rules of biology is much more useful than a computer that folds proteins without explanation. Therefore, AI researchers like me are now turning our efforts toward developing AI algorithms that can explain themselves in a manner that humans can understand. If we can do this, I believe that AI will be able to uncover and teach people new facts about the world that have not yet been discovered, leading to new innovations.


New Products

Science

![Figure][1] Porvair Sciences announces Ultravap Mistral—an automation-ready sample evaporator that offers throughput advantages to laboratories looking to optimize and accelerate sample preparation. The Mistral directly and consistently delivers heated gas up to 80°C in each microplate well or tube, facilitating speedy, convenient evaporation of most common chromatography solvents, including dichloromethane, methanol, acetonitrile, hexane, and water. The option for straight or spiral needles allows users to choose between faster drydown (spiral) and better final drying in V-well plates (straight). Highly intuitive software and up to 15 easy-to-use, stored multistep evaporation programs enable even occasional users to gain the full benefits of this unit. For regular users, the Mistral offers the versatility of fully flexible programming, for example, providing for the ideal rate of evaporation for each solvent type. Nova Biomedical announces the addition of a Sample Retain Collector (SRC) for the BioProfile FLEX2 cell-culture analyzer. The FLEX2 automated analyzer offers comprehensive analysis of up to 16 key parameters, including pH, gases, metabolites, osmolality, cell density, and cell viability. A single FLEX2 with the SRC and the previously introduced Online Autosampler (OLS) module provides automated sampling and analysis of these fundamental cell-culture chemistries from as many as 10 bioreactors—and storage by the SRC in as fast as 1 h. This automation package saves hours of time spent on manual sampling, analysis, sample storage, and after-hours cell culture monitoring. The SRC automatically collects cell-culture samples from the FLEX2 OLS and stores them in a refrigerated environment to fulfill regulatory requirements for long-term sample retains, also enabling further offline testing. The SRC allows user-selectable retained sample volumes from 200 μL to 50 mL at a storage temperature of 4°C. BioChromato reports that pharmaceutical companies undertaking absorption, distribution, metabolism, and excretion (ADME) studies are benefiting from integrating RAPID Easy Piercing Seals (EPS) into their screening protocols. ADME scientists commonly use 96- or 384-well microplates to store large numbers of samples for screening. Sample-contamination issues can often arise in ADME studies, as common HPLC solvents such as acetonitrile, water, and dimethyl sulfoxide can extract siloxane out of the silicon-based adhesives used in the microplate seal. RAPID EPS seals use a synthetic-rubber adhesive to create a high-integrity, airtight microplate seal, preventing contamination of ADME samples analyzed by HPLC. In addition, the seals leave no particulate material when pierced by an HPLC autosampler, further safeguarding samples from contamination and eliminating damage to or clogging of your autosampler. They are proven to offer dependable microplate sealing over a working temperature range of −80°C to 80°C. The OpenStand modular platform allows for easy customization. This fully configurable, motorized optical stand, when combined with a range of readily available optics, light sources, and accessories, creates a complete, customizable optical microscope. It is ideal for optogenetics, physiology, electrophysiology, neuroscience, industrial, and general imaging applications. Its modular approach allows maximum interchangeability and flexibility, enabling users to image a wide range of samples for virtually any life science and industrial application, and offering the largest imaging space available. It features a cost-effective, custom development platform that can be set up quickly as a fast-track to a prototype instrument. OpenStand lets you select only the components you need for your specific application, resulting in significant savings while giving you the flexibility to expand and add additional components if requirements change. CS Medical is pleased to announce its distribution agreement with AirClean Systems to offer the AirClean UV Light Box. The growing demand to decontaminate N95 respirators has made shortwave UV light—used for years to decontaminate surfaces—an alternative to other chemical-based methods. Designed to protect the user from exposure to potentially harmful shortwave light energy, the AirClean UV Light Box is available in two widths and performs decontamination of N95 respirators in a total cycle time of 60 min, 30 min per side. Decontamination will make the masks reusable up to five times, helping alleviate the PPE shortage that is common in so many health care facilities and other industries across the nation right now. FUJIFILM Irvine Scientific announces cellnest, a recombinant peptide attachment substrate that provides optimal adhesion and proliferation of stem cells in chemically defined, animal component–free conditions. Attachment substrates mimic the extracellular matrix, a complex, dynamic environment in which cells reside in vivo, and allow for adhesion, expansion, and potential differentiation of stem cells. Unlike animal-derived components, which can introduce unpredictability in results, cellnest delivers consistent results and can smooth the regulatory path to commercialization. It is compatible with any adherent cell type that binds to the Arg-Gly-Asp (RGD) domain, an amino-acid sequence within the extracellular matrix protein fibronectin that mediates cell attachment. cellnest is an ideal companion product to our PRIME-XV portfolio of xeno-free, chemically defined media for stem-cell culture and is well suited for the attachment and growth of mesenchymal stem cells. [1]: pending:yes


Structure-guided multivalent nanobodies block SARS-CoV-2 infection and suppress mutational escape

Science

Monoclonal antibodies are an important weapon in the battle against COVID-19. However, these large proteins are difficult to produce in the needed quantities and at low cost. Attention has turned to nanobodies, which are aptly named, single-domain antibodies that are easier to produce and have the potential to be administered by inhalation. Koenig et al. describe four nanobodies that bind to the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein and prevent infection of cells (see the Perspective by Saelens and Schepens). Structures show that the nanobodies target two distinct epitopes on the SARS-CoV-2 spike protein. Multivalent nanobodies neutralize virus much more potently than single nanobodies, and multivalent nanobodies that bind two epitopes prevent the emergence of viral escape mutants. Science , this issue p. [eabe6230][1]; see also p. [681][2] ### INTRODUCTION The global scale and rapid spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pose unprecedented challenges to society, health care systems, and science. In addition to effective and safe vaccines, passive immunization by antibody-related molecules offers an opportunity to harness the vertebrate immune system to fight viral infections in high-risk patients. Variable domains of heavy-chain–only antibodies (VHHs), also known as nanobodies, are suitable lead molecules in such efforts, as they are small, extremely stable, easy to engineer, and economic to produce in simple expression systems. ### RATIONALE We engineered improved multivalent nanobodies neutralizing SARS-CoV-2 on the basis of two principles: (i) detailed structural information of their epitopes and binding modes to the viral spike protein and (ii) mechanistic insights into viral fusion with cellular membranes catalyzed by the spike. ### RESULTS Nanobodies specific for the receptor binding domain (RBD) of SARS-CoV-2 spike were identified by phage display using nanobody libraries from an alpaca and a llama immunized with the RBD and inactivated virus. Four of the resulting nanobodies—VHHs E, U, V, and W—potently neutralize SARS-CoV-2 and SARS-CoV-2–pseudotyped vesicular stomatitis virus. X-ray crystallography revealed that the nanobodies bind to two distinct epitopes on the RBD, interfaces “E” and “UVW,” which can be synergistically targeted by combinations of nanobodies to inhibit infection. Cryo–electron microscopy (cryo-EM) of trimeric spike in complex with VHH E and VHH V revealed that VHH E stabilizes a conformation of the spike with all three RBDs in the “up” conformation (3-up), a state that is typically associated with activation by receptor binding. In line with this observation, we found that VHH E triggers the fusion activity of spike in the absence of the cognate receptor ACE2. VHH V, by contrast, stabilizes spike in a 2-up conformation and does not induce fusion. On the basis of the structural information, we designed bi- and trivalent nanobodies with improved neutralizing properties. VHH EEE most potently inhibited infection, did not activate fusion, and likely inactivated virions by outcompeting interaction of the virus with its receptor. Yet evolution experiments revealed emergence of escape mutants in the spike with single–amino acid changes that were completely insensitive to inhibition by VHH EEE. VHH VE also neutralized more efficiently than VHH E or VHH V alone; stabilized the 3-up conformation of spike, as determined by cryo-EM; and more strongly induced the spike fusogenic activity. We conclude that the premature activation of the fusion machinery on virions was an unexpected mechanism of neutralization, as enhanced neutralization could not be attributed simply to better blocking of virus-receptor interactions. Activation of spike in the absence of target membranes likely induces irreversible conformational changes to assume the energetically favorable postfusion conformation without catalyzing fusion per se. Simultaneous targeting of two independent epitopes by VHH VE largely prevented the emergence of resistant escape mutants in evolution experiments. ### CONCLUSION Our results demonstrate the strength of the modular combination of nanobodies for neutralization. Premature activation of spike by nanobodies reveals an unusual mode of neutralization and yields insights into the mechanism of fusion. ![Figure][3] Bivalent nanobodies neutralize by inducing postfusion conformation of the SARS-CoV-2 spike. On virions, SARS-CoV-2 spike trimers are mostly in an inactive configuration with all RBDs in the down conformation (left). Binding of bivalent nanobody VE stabilizes the spike in an active conformation with all RBDs up (middle), triggering premature induction of the postfusion conformation, which irreversibly inactivates the spike protein (right). The pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) continues to spread, with devastating consequences. For passive immunization efforts, nanobodies have size and cost advantages over conventional antibodies. In this study, we generated four neutralizing nanobodies that target the receptor binding domain of the SARS-CoV-2 spike protein. We used x-ray crystallography and cryo–electron microscopy to define two distinct binding epitopes. On the basis of these structures, we engineered multivalent nanobodies with more than 100 times the neutralizing activity of monovalent nanobodies. Biparatopic nanobody fusions suppressed the emergence of escape mutants. Several nanobody constructs neutralized through receptor binding competition, whereas other monovalent and biparatopic nanobodies triggered aberrant activation of the spike fusion machinery. These premature conformational changes in the spike protein forestalled productive fusion and rendered the virions noninfectious. [1]: /lookup/doi/10.1126/science.abe6230 [2]: /lookup/doi/10.1126/science.abg2294 [3]: pending:yes


Artificial intelligence in new field

#artificialintelligence

Artificial intelligence already is making strides in the development of new drugs, and now the pesticide industry wants in on the action. Switzerland's Syngenta has teamed up with Insilico Medicine to use its deep-learning tools to produce sustainable weedkillers. As well as taking on some of the early-stage work traditionally conducted in a lab, AI could design molecules used in crop-protection tools that are more sustainable and environmentally friendly, the companies said last week. AI is among new methods emerging as environmental and health concerns spur a quest for sustainable alternatives to traditional pesticides used by farmers. Demand also is being supported by regulatory pressures and lawsuits, most notably Bayer's $11 billion settlement deal over claims its long-used glyphosate herbicide causes cancer.


Machine learning made easy for optimizing chemical reactions

Nature

The optimization of reactions used to synthesize target compounds is pivotal to chemical research and discovery, whether in developing a route for manufacturing a life-saving medicine1 or unlocking the potential of a new material2. But reaction optimization requires iterative experiments to balance the often conflicting effects of numerous coupled variables, and frequently involves finding the sweet spot among thousands of possible sets of experimental conditions. Expert synthetic chemists currently navigate this expansive experimental void using simplified model reactions, heuristic approaches and intuition derived from observation of experimental data3. Writing in Nature, Shields et al.4 report machine-learning software that can optimize diverse classes of reaction with fewer iterations, on average, than are needed by humans. Machine learning has emerged as a useful tool for various aspects of chemical synthesis, because it is ideally suited to extrapolating predictive models that are used to solve synthetic problems by recognizing patterns in multidimensional data sets5.


BioScript

Communications of the ACM

This paper introduces BioScript, a domain-specific language (DSL) for programmable biochemistry that executes on emerging microfluidic platforms. The goal of this research is to provide a simple, intuitive, and type-safe DSL that is accessible to life science practitioners. The novel feature of the language is its syntax, which aims to optimize human readability; the technical contribution of the paper is the BioScript type system. The type system ensures that certain types of errors, specific to biochemistry, do not occur, such as the interaction of chemicals that may be unsafe. Results are obtained using a custom-built compiler that implements the BioScript language and type system. The last two decades have witnessed the emergence of software-programmable laboratory-on-a-chip (pLoC) technology, enabled by technological advances in microfabrication and coupled with scientific understanding of microfluidics, the fundamental science of fluid behavior at the micro- to nanoliter scale. The net result of these collective advancements is that many experimental laboratory procedures have been miniaturized, accelerated, and automated, similar in principle to how the world's earliest computers automated tedious mathematical calculations that were previously performed by hand. Although the vast majority of microfluidic devices are effectively application-specific integrated circuits (ASICs), a variety of programmable LoCs have been demonstrated.16, With a handful of exceptions, research on programming languages and compiler design for programmable LoCs has lagged behind their silicon counterparts. To address this need, this paper presents a domain-specific programming language (DSL) and type system for a specific class of pLoC that manipulate discrete droplets of liquid on a two-dimensional grid. The basic principles of the language and type system readily generalize to programmable LoCs, realized across a wide variety of microfluidic technologies.


How explainable artificial intelligence can help humans innovate

#artificialintelligence

The field of artificial intelligence (AI) has created computers that can drive cars, synthesize chemical compounds, fold proteins and detect high-energy particles at a superhuman level. However, these AI algorithms cannot explain the thought processes behind their decisions. A computer that masters protein folding and also tells researchers more about the rules of biology is much more useful than a computer that folds proteins without explanation. Therefore, AI researchers like me are now turning our efforts toward developing AI algorithms that can explain themselves in a manner that humans can understand. If we can do this, I believe that AI will be able to uncover and teach people new facts about the world that have not yet been discovered, leading to new innovations.


New Products

Science

![Figure][1] The McPherson 234/302 compact vacuum-ultraviolet spectrometer has a digital grating drive for precise wavelength selection and positioning from 30 nm to 1,100 nm. Micrometer adjustable slits vary from 0.01 mm ~3 mm in width and 2 mm ~20 mm in height. Software is available along with LabVIEW drivers. This instrument's normal incidence design has optional multiple input or output ports. It can also be easily used as a spectrograph with a microchannel plate intensifier or charge-coupled device detector, or as a scanning monochromator—one instrument can do both functions while remaining under vacuum. There are many options for customization: We can provide ultrahigh vacuum nonmagnetic versions or customized adapters for the customer's vacuum pumps, detectors, or light sources. Double monochromators for exceptionally low stray light and high spectral purity are also available. Special or standard, every instrument ships with certified spectral calibration. Compatible with all 2D-barcoded tube racks in SBS format and with a footprint of only slightly more than one plate/rack position, the Ziath DataPaq Express offers a space-saving way to integrate a fast full-rack scanner onto a liquid-handling robot. Designed with a separate power and processing box that can be positioned under your liquid-handling robot and under your deck, this compact scanner frees up vital deck space. Its uniquely low form factor allows liquid-handling robots easy gripper access to simply pick up and dispense from racks on top of the scanner. Offering rapid image scanning and decoding in just 2 s, the camera-based DataPaq Express will also help improve your robotic workflow. Baseplates and drivers are available to enable easy integration with most commercial liquid-handling robots. The Smart Evaporator C1 from BioChromato is an easy-to-use, affordable system optimized to concentrate or dry single samples directly from any tube or vial (up to 32-mm neck diameter) in even high-boiling solvents such as DMSO, DMF, or water. Drawing on BioChromato's patented spiral plug evaporation technology, the compact, benchtop system offers fast, effective evaporation in tubes or vials without solvent bumping, eliminating the risk of sample loss and cross-contamination and saving valuable time. The Smart Evaporator C1 can handle solvent volumes up to 40 mL, which can be extremely useful for concentrating compounds after organic synthesis or for drying analytical samples at relatively high speeds. The versatile C1 can also manage small tubes and vials (e.g., 1.5 mL) where solvent volumes can be as little as 0.1 mL or less. Porvair Sciences provides a complete design and manufacture service to help customers develop new and innovative custom microplates for specialist applications. We are widely recognized as a leader in the field of molding ultrapure plastic materials such as polystyrene, polypropylene, and polycarbonate. Decades of experience in ultrasonic welding, surface treatment techniques, co-sintering of polymers/silicas, and specialist assembly, combined with a strong understanding of analytical applications, make us an ideal OEM partner for development and production of optimized custom microplate solutions. From single-well to 1,536-well microplates, Porvair Sciences has the knowledge, expertise, and flexibility to design and manufacture to customer specifications. Our team of engineers and creative thinkers allows us to develop high-quality products for filtration, storage, and separation and to push the boundaries of microplate design for the life science and analytical markets. With its unique safety-locking mechanism and robust, adjustable support frame/lifting platform option, the Multicell PLUS high-pressure reactor from Asynt sets a new benchmark for operator safety, all-round accessibility, and ease-of-use. Manufactured from 316 stainless steel, the unit operates at pressures up to 50 barg and temperatures up to 200ºC. Asynt offers options for the system to be manufactured from alternative materials that can withstand highly corrosive/caustic chemicals, and for increased operational conditions up to 200 barg and temperatures of over 300ºC. While the Multicell PLUS accommodates 8 × 30 mL cells as standard, options are offered for 4-, 6-, and 10-cell arrangements with individual cell volumes up to 100 mL. Motor-driven, magnetically coupled overhead stirring is also offered as an option for more viscous reaction mixtures. Optional independent isolation of each cell allows the user to charge each vessel with differing chemistry and pressures without cross-contamination between cells. Milo is the world's first automated single-cell Western (scWestern) platform. The instrument measures protein expression in thousands of cells in a single run, allowing you to profile heterogeneity in your samples through single-cell analysis. Just load your cell suspension, and the scWest chip captures ~1,000 single cells. Milo then performs a fast, 1-min SDS-PAGE (sodium dodecyl sulphate–polyacrylamide gel electrophoresis) separation on each single-cell lysate on-chip. Then just probe with your favorite conventional Western blot antibodies to measure ~12 proteins per cell using a variety of multiplexing strategies. Milo's Single-Cell Western technology unlocks the single-cell proteome to measure more of the proteome than is possible with any other single-cell protein analysis technique. [1]: pending:yes


Accelerating the screening of amorphous polymer electrolytes by learning to reduce random and systematic errors in molecular dynamics simulations

arXiv.org Artificial Intelligence

Machine learning has been widely adopted to accelerate the screening of materials. Most existing studies implicitly assume that the training data are generated through a deterministic, unbiased process, but this assumption might not hold for the simulation of some complex materials. In this work, we aim to screen amorphous polymer electrolytes which are promising candidates for the next generation lithium-ion battery technology but extremely expensive to simulate due to their structural complexity. We demonstrate that a multi-task graph neural network can learn from a large amount of noisy, biased data and a small number of unbiased data and reduce both random and systematic errors in predicting the transport properties of polymer electrolytes. This observation allows us to achieve accurate predictions on the properties of complex materials by learning to reduce errors in the training data, instead of running repetitive, expensive simulations which is conventionally used to reduce simulation errors. With this approach, we screen a space of 6247 polymer electrolytes, orders of magnitude larger than previous computational studies. We also find a good extrapolation performance to the top polymers from a larger space of 53362 polymers and 31 experimentally-realized polymers. The strategy employed in this work may be applicable to a broad class of material discovery problems that involve the simulation of complex, amorphous materials.


Automated Synthesis of Steady-State Continuous Processes using Reinforcement Learning

arXiv.org Artificial Intelligence

Computer-aided process synthesis has been an important field of chemical engineering for decades [2]. There exists a vast amount of methods in computer-aided process synthesis, in which the roles of human and computer are quite different and vary in their proportions. On one end of the spectrum, humans invent flowsheets, provide mechanistic models of apparatus and physicochemical properties, and employ computers solely in simulations to evaluate and check the invented designs. On the other end of the spectrum, there is automated flowsheet synthesis, which we call rather human-aided process synthesis by a computer. Therein, the structure of the process and operating levels are chosen autonomously by the computer based on input by the human (typically a problem statement and the physicochemical property data). Siirola [3] classified automated flowsheet synthesis into three categories: superstructure optimization, evolutionary modification and systematic generation. In superstructure optimization, a large flowsheet structure (the superstructure) is set up in a way, so that a large set of process alternatives can be obtained by removing parts of that structure [4,5]. An objective function or cost function is defined and the optimal configuration for the flowsheet is determined by an optimization algorithm that uses decision variables to remove parts of the superstructure. Evolutionary modification works as follows: A process flowsheet is devised (by any method at hand), analyzed and changed in one or more ways repeatedly to improve it.