Leadeth me unto Truth and delivereth me from those who have already found it

A theory has only the alternative of being true or false.

A model has a third possibility: it may be true, but irrelevant.

With apologies to Manfred Eigen (1927 - 2019)

******************

[This post was updated on 25-Jun-2024]

I've just returned to Cheshire from the Caribbean and, to kick off blogging from 2024 I'll share a photo of the orchids at Berwick-on-Sea on the north coast of Trinidad.

Encountering words like “truth” and “beauty” (here's a good example) in the titles of scientific articles always sets off warning bells for me and I’ll kick off blogging for 2024 with a look at FM2024 (Structure is beauty, but not always truth) that was recently published in Cell (and has already been reviewed by Derek). The authors have highlighted  important issues: we typically use single conformations of targets in design and the experimentally-determined structures used for design may differ substantially from the structures of targets as they exist in vivo. These points do need be stressed given the expanding range of modalities being exploited by drug designers and the increasing use of AI/ML in drug design. That said, it’s my view that the authors have allowed themselves to become prisoners of their article’s title. Specifically, I see “beauty” as a complete red herring and suggest that it would have been much better to have discussed structure in terms of accuracy and relevance rather than truth. Here’s the abstract for FM2024:

Structural biology, as powerful as it is, can be misleading. We highlight four fundamental challenges: interpreting raw experimental data; accounting for motion; addressing the misleading nature of in vitro structures; and unraveling interactions between drugs and “anti-targets.” Overcoming these challenges will amplify the impact of structural biology on drug discovery.

I'll start by taking a look at the introduction and my view is that the authors do need to be much clearer about what they mean by “this hydrogen bond is better than that one” when using terms like “ground truth”. For example, we can infer that the geometry of one target-ligand hydrogen bond is closer to optimal than the geometry of another target-ligand hydrogen bond. However, the energetic cost of breaking a target-ligand hydrogen bond is not something that can generally be measured and, as noted in NoLE, the contribution of an intermolecular contact to affinity is not actually an experimental observable. Ligands associate with their targets (and anti-targets) in aqueous media and this means that intermolecular contacts, for example between polar and non-polar atoms, can destabilize the target-ligand complex without being inherently repulsive. What I’m getting at here is that structures of ligand-target complexes are relatively simple and well-defined entities within the broader context of drug discovery and yet it doesn’t appear useful to discuss them in terms of truth.

The remainder of the post follows the FM2024 section headings.    

A structure is a model, not experimental reality

The term “structure” can have a number of different meanings in structure-based drug design. First, drug targets (and anti-targets) have structures that exist regardless of whether they have been experimentally determined. Second, models are built for drug targets by fitting nuclear coordinates to experimental data such as electron density (these are often referred to as experimental structures although they should strictly be called models because they are abstractions of the experimental data). Third, the structure could have been predicted using computational tools such as AlphaFold2 (here's an article, cited by FM2024, on why we still need experimentally-determined structures). 

In the abstract the authors identify “interpreting raw experimental data” as one of “four fundamental challenges”. However, the actual focus of this section appears to be evaluation of predicted structures rather than interpretation of raw experimental data.  While I’m sure that we can find better ways to interpret raw experimental data, and indeed to evaluate predicted structures, I don’t see either as representing a fundamental challenge. 

Representing wiggling and jiggling is hard

My view is that it’s actually the ensemble of conformations rather than the wiggling and jiggling that we actually need to represent. Simulation of the wiggling and jiggling is one way to generate an ensemble of conformations but it’s not the only way (nor is it necessarily the best way).  That said, it's a lot easier to sell protein motion to venture capitalists than it is to sell ensembles of conformations.

The authors state:

Analogous to how structure-based drug design is great for optimizing “surface complementarity” and electrostatics, future protein modeling approaches will unlock ensemble-based drug design with an ability to predictably tune new and important aspects of design, including entropic contributions [7] and residence times [8] of bound ligands.

The term “entropic contributions” does come across as arm-waving (especially in a drug design context) and my view is that entropy should be seen as an effect rather than a cause. Thermodynamic signatures for binding are certainly of scientific interest but I would argue that they are essentially irrelevant to drug design (it can be instructive to consider how patients might sense the benefits of enthalpically-driven drug binding). The case for increasing residence time might not be quite as solid as many believe it to be (see the F2018 study and this blog post).

In vitro can be deceiving

The authors identify “addressing the misleading nature of in vitro structures” as a fundamental challenge and they state:

While purifying a protein out of its cellular context can be enabling for in vitro drug discovery, it can also provide a false impression. Recombinant expression can lead to missing post-translational modifications (e.g., phosphorylation or glycosylation) that are critical to understanding the function of a protein.

To this I’d add that we often don’t use the full-length proteins in design and recombinant proteins may have been engineered to make them easier to crystallize or more robust for soaking experiments. Furthermore, target engagement may require the drug to interact with two or more proteins (see HC2017) which will probably be more amenable individually to structure determination than the their complex. I fully agree that it is important for drug designers to be aware that the experimentally-determined structures that they're using differ from the structures of the targets as they exist in vivo.  However, I don't believe that it makes any sense to talk about “the misleading nature of in vitro structures” (or indeed about “in vitro drug discovery”) because target structures are never experimentally determined in vivo and are only misleading to the extent that users overinterpret them. As a more general point users of experimental data do need to very careful about describing the experimental data that they’re using as “misleading” or "deceiving".  

When we use structures to represent targets the issue is much less about the truth of the structures that we’re using and much more about their relevance to the targets that we’re trying to represent. This is not just an issue for structural biology and we might, for example, use the catalytic domain of an enzyme as a model for the full-length protein when running biochemical assays. We have to make assumptions in these situations and we also need to check that these assumptions are reasonable. For example, we might examine the structure-activity relationship in a cell-based assay for consistency with the structure-activity relationship that we’ve observed in the enzyme inhibition assay. It's also worth pointing out that what we observe in cells is usually a coarse approximation to what actually happens in vivo and we can't even measure the intracellular concentration of a drug in vivo.  

Drugs mingle with many different receptors

Drugs do indeed mingle with many receptors in vivo but it’s important to be aware that the consequences of this mingling depend on the drug concentration (a spatiotemporal quantity) at the site of action.  Drug discovery scientists use the term exposure when talking about drug concentration at the site of action and one underappreciated challenge in drug design is that intracellular drug concentration cannot generally be measured in vivo (here’s an open access article that I recommend to everybody working drug discovery). I argue in NoLE that controllability of exposure should be seen as a drug design objective although the current impossibility of measuring intracellular concentration means that we can only assess how effectively the objective has been achieved in an indirect manner. Alternatively, drug design can be seen in terms of minimization of the dose at which therapeutically beneficial effects can be observed.  

One assumption often made in drug design is that the drug concentration at the site of action is equal to the unbound concentration in plasma and this assumption is referred to as the free drug hypothesis (FDH) although the term “free drug theory” is also used. The basis for the FDH is the assumption that the drug can move freely between plasma and the target compartment. In reality the drug concentration at the site of action will generally lag behind its unbound plasma concentration and the lag time is inversely related to the ease with which the drug permeates through the barriers which separate the target from the plasma. There are a couple of scenarios under which you can’t assume that the drug concentration in the target compartment will be the same as its unbound plasma concentration. The first of these is when active transport is significant and this is a scenario with which drug designers tackling targets within the central nervous system (CNS) are familiar with. The second scenario is that there is an ionizable functional group (as is the case for amines) in the molecular structure of the drug and the pH at the site of action differs significantly from plasma pH (as is the case for lysosomes).

There are two general types of undesirable outcome that can result when a drug encounters receptors with which it mingles.  First, the receptor is an anti-target and the encounter results in binding of the drug, leading to toxicity (patients are harmed).  Second, the receptor is a metabolic enzyme or a transporter and the encounter leads to the drug either being turned over or pumped from where it needs to function (patients do not benefit from the treatment).

I've inserted some comments (italicised in red) into the following quoted text: 

The sad reality that all drug discoverers must face is that however well designed we may believe our compounds to be, they will find ways to interact with many other proteins or nucleic acids in the body and interfere with the normal functions of those biomolecules. While occasionally, the ability of a medicine to bind to multiple biomolecules will increase a drug’s efficacy, such polypharmacology is far more likely to produce undesirable effects. These undesirable outcomes take two forms. Obviously, the direct binding to an anti-target can lead to a bewildering range of toxicities, many of which render the drug too hazardous for any use. [While there are well-known anti-targets such as hERG that must be avoided, my understanding is that those responsible for drug safety generally prefer not to see any off-target activity given the difficulties in prediction of toxicity. Here are a couple of relevant articles (B2012 | J2020) and a link to some information about in vitro safety pharmacology profiling panels from Eurofins. Update 25-Jun-2024: recent review on secondary pharmacology.] More subtly, the binding to anti-targets reduces the ability of the drug to reach the desired target. A drug that largely avoids binding to anti-targets will partition more effectively through the body, enabling it to accumulate at high enough concentrations in the disease-relevant tissue to effectively modulate the function of the target. [I consider it unlikely that binding to an anti-target could account for a significant proportion of the dose. In any case, I’d expect binding of a drug to anti-targets to cause unacceptable toxicity long before it results in sequestration of a significant proportion of the dose.] 

A particular challenge results from the interaction of drugs with the enzymes, transporters, channels, and receptors that are largely responsible for controlling the metabolism and pharmacokinetic properties (DMPK) of those drugs—their absorption, distribution, metabolism, and elimination. Drugs often bind to plasma proteins, preventing them from reaching the intended tissues; [A degree of binding to plasma proteins is not a problem and, in the case of warfarin, is probably essential for the safe use of the drug.] they can block or be substrates for all manner of pumps and transporters, changing their distribution through the body; [Transporters can indeed prevent drugs from getting to their sites of action at therapeutically effective concentrations and limited brain exposure resulting from active efflux is a common issue for CNS drug discovery programs (see H2012 and R2015). I am not aware of any transporters that are definitely considered to be anti-targets from the safety perspective (I'm happy to be corrected on this point) and inhibition of efflux pumps is a recognized tactic (see T2021 and H2020) in drug discovery. Update 25-Jun-2024: I thank Mohamed Diwan M. AbdulHameed (google scholar profile) for making me aware that inhibition of  bile salt export pump (BESP) is considered a risk factor for drug-induced liver injury (DILI). Here's a relevant article.] xenobiotic sensors such as PXR that turn on transcriptional programs recognizing foreign substances; and they often block enzymes like cytochrome P450s, thereby changing their own metabolism and that of other medicines. [Inhibition of CYPs is generally considered undesirable from the safety perspective because of the potential for drug-drug interactions (see H2020). That said, the CYP3A inhibitor ritonavir (see CG2003) is used in the COVID-19 treatment Paxlovid to slow metabolism of SARS-CoV-2 main protease nirmatrelvir.]  They are themselves substrates for P450s and other metabolizing enzymes and, once altered, can no longer carry out their assigned, life-saving function. [Medicinal chemists are well aware of the challenges presented by drug-metabolizing enzymes although it must be stressed that any drug that was cleared too slowly would be considered to be an unacceptable safety risk.] 

Taken together, we refer to these DMPK-related proteins, somewhat tongue-in-cheek, as the “avoidome” (Figure 2). [It is unclear why the authors have chosen to only include DMPK-related proteins in the avoidome (hERG is not a DMPK-related protein but is an anti-target that every drug discovery scientist would wish to avoid blocking). For reasons outlined in the previous paragraph I would actually argue against the inclusion of DMPK-related proteins in the avoidome.]  Unfortunately, the structures of the vast majority of avoidome targets have not yet been determined. Further, many of these proteins are complex machines that contain multiple domains and exhibit considerable structural dynamism. Their binding pockets can be quite large and promiscuous, favoring distinct binding modes for even closely related compounds. [It is not clear whether this assertion is based on experimental observations.] As a consequence, multiple structures spanning a range of bound ligands and protein conformational states will be required to fully understand how best to prevent drugs from engaging these problematic anti-targets.  

We believe the structural biology community should “embrace the avoidome” with the same enthusiasm that structure-based design has been applied to intended targets. [My view is that the authors need to clearly articulate their reasons for only including DMPK-related proteins in the avoidome before seeking to direct the activities of structural biology community. I presume that the Target 2035 initiative, which aims to “to create by year 2035 chemogenomic libraries, chemical probes, and/or biological probes for the entire human proteome”, will also cover anti-targets. Having chemical and/or biological probes available for anti-targets should lead to better understanding of toxicity in humans.] The structures of these proteins will shed considerable light on human biology and represent exciting opportunities to demonstrate the power of cutting-edge structural techniques. [Experimental structures of target-ligand complexes do indeed provide valuable direct evidence that a ligand is binding to a protein but the structures themselves are not particularly informative from the perspective of understanding human biology. It is actually high-quality chemical probes that are needed to shed light on human biology and here’s a link to the Chemical Probes Portal. Structures at atomic resolution for protein-ligand complexes are certainly useful for chemical probe design but are not strictly necessary for effective use of chemical probes.]  Crucially, a detailed understanding of the ways that drugs engage with avoidome targets would significantly expedite drug discovery.  [Experimentally-determined structures of anti-targets complexed with ligands are certainly informative when elucidating structure-activity relationships for binding to anti-targets. However, structural information of this nature is much less directly useful for addressing problems such as metabolic lability and active efflux.] This information holds the potential to achieve a profound impact on the discovery of new and enhanced medicines.

Conclusion

The authors assert: 

In drug discovery, truth is a molecule that transforms the practice of medicine. [I disagree with this assertion. In drug discovery truth may also be a compound that, despite an excellent pharmacokinetic profile, chokes comprehensively in phase 2.]

It's been been a long post and this is a good place to leave things. While the authors have raised some valid points I found the 'Drugs mingle with many different receptors' section to be rather confused and I don't think that the drug discovery and structural biology communities are in desperate need of yet another 'ome' word. I hope that my review of FM2024 will be useful for readers of the article while providing helpful feedback for the authors and for the Editors of Cell. 

Five days in Vermont

A couple of months ago I enjoyed a visit to the US (my first for eight years) on which I caught up with old friends before and after a few days in Vermont (where a trip to the golf course can rapidly become a National Geographic Moment). One highlight of the trip was randomly meeting my friend and fellow blogger Ash Jogalekar for the first time in real life (we’ve actually known each other for about fifteen years) on the Boston T Red Line.  Following a couple of nights in green and leafy Belmont, I headed for the Flatlands with an old friend from my days in Minnesota for a Larry Miller group reunion outside Chicago before delivering a short harangue on polarity at Ripon College in Wisconsin. After the harangues, we enjoyed a number of most excellent Spotted Cattle (Only in Wisconsin) in Ripon. I discovered later that one of my Instagram friends is originally from nearby Green Lake and had taken classes at Ripon College while in high school. It is indeed a small world.

The five days spent discussing computer-aided drug design (CADD) in Vermont are what I’ll be covering in this post and I think it’s worth saying something about what drugs need to do in order to function safely.  First, drugs need to have significant effects on therapeutic targets without having significant effects on anti-targets such as hERG or CYPs and, given the interest in new modalities, I’ll be say “effects” rather than “affinity”, although Paul Ehrlich would have reminded us that drugs need to bind in order to exert effects. Second, drugs need to get to their targets at sufficiently high concentrations for their effects to be therapeutically significant (drug discovery scientists use the term ‘exposure’ when discussing drug concentration). Although it is sometimes believed that successful drugs simply reduce the numbers of patients suffering from symptoms it has been known from the days of Paracelsus that it is actually the dose that differentiates a drug from a poison.

Drug design is often said to be multi-objective in nature although the objectives are perhaps not as numerous as many believe (this point is discussed in the introduction section of NoLE, an article that I'd recommend to insomniacs everywhere). The first objective of drug design can be stated in terms of minimization of the concentration at which a therapeutically useful effect on the target is observed (this is typically the easiest objective to define since drug design is typically directed at specific targets). The second objective of drug design can be stated in analogous terms as maximization of the concentration at which toxic effects on the anti-targets are observed (this is a more difficult objective to define because we generally know less about the anti-targets than about the targets). The third objective of drug design is to achieve controllability of exposure (this is typically the most difficult objective to define because drug concentration is a dose-dependent, spaciotemporal quantity and intracellular concentration cannot generally be measured for drugs in vivo). Drug discovery scientists, especially those with backgrounds in computational chemistry and cheminformatics, don’t always appreciate the importance of controlling exposure and the uncertainty in intracellular concentration always makes for a good stock question for speakers and panels of experts.

I posted previously on  artificial intelligence (AI) in drug design and I think it’s worth highlighting a couple of common misconceptions. The first misconception is that we just need to collect enough data and the drugs will magically condense out of the data cloud that has been generated (this belief appears to have a number of adherents in Silicon Valley).  The second misconception is that drug design is merely an exercise in prediction when it should really be seen in a Design of Experiments framework. It’s also worth noting that genuinely categorical data are rare in drug design and my view is that many (most?) "global" machine learning (ML) models are actually ensembles of local models (this heretical view was expressed in a 2009 article and we were making the point that what appears to be an interpolation may actually be an extrapolation). Increasingly, ML is becoming seen as a panacea and it’s worth asking why quantitative structure activity relationship (QSAR) approaches never really made much of a splash in drug discovery.

I enjoyed catching up with old friends [ D | K | S | R/J | P/M ] as well as making some new ones [ G | B/R | L ]. However, I was disappointed that my beloved Onkel Hugo was not in attendance (I continue to be inspired by Onkel’s laser-like focus on the hydrogen bonding of the ester) and I hope that Onkel has finally forgiven me for asking (in 2008) if Austria was in Bavaria. There were many young people at the gathering in Vermont and their enthusiasm made me greatly optimistic for the future of CADD (I’m getting to the age at which it’s a relief not to be greeted with: "How nice to see you, I thought you were dead!"). Lots of energy at the posters (I learned from one that Voronoi was Ukrainian) although, if we’d been in Moscow, I’d have declined the refreshments and asked for a room on the ground floor (left photo below).  Nevertheless, the bed that folded into the wall (centre and right photos below) provided plenty of potential for hotel room misadventure without the ‘helping hands’ of NKVD personnel.

It'd been four years since CADD had been discussed at this level in Vermont so it was no surprise to see COVID-19 on the agenda. The COVID-19 pandemic led to some very interesting developments including the Covid Moonshot (a very different way of doing drug discovery and one I was happy to contribute to during my 19 month sojourn in Trinidad) and, more tangibly, Nirmatrelvir (an antiviral medicine that has been used to treat COVID-19 infections since early 2022). Looking at the molecular structure of Nirmatrelvir you might have mistaken trifluoroacetyl for a protecting group but it’s actually a important feature (it appears to be beneficial from the permeability perspective). My view is that the alkane/water logP (alkane is a better model than octanol for the hydrocarbon core of a lipid bilayer) for a trifluoroacetamide is likely to be a couple of log units greater than for the corresponding acetamide.

I’ll take you through how the alkane/water logP difference between a trifluoroacetamide and corresponding acetamide can be estimated in some detail because I think this has some relevance to using AI in drug discovery (I tend to approach pKa prediction in an analogous manner). Rather than trying to build an ML model for making the prediction, I’ve simply made connections between measurements for three different physicochemical properties (alkane/water logP, hydrogen bond basicity and hydrogen bond acidity) which is something that could easily be accommodated within an AI framework. I should stress that this approach can only be used because it is a difference in alkane/water logP (as opposed to absolute values) that is being predicted and these physicochemical properties can plausibly be linked to substructures.

Let’s take a look at the triptych below which I admit that is not quite up to the standards of Hieronymus Bosch (although I hope that you find it to be a little less disturbing). The first panel shows values of polarity (q) for some hydrogen bond acceptors and donors (you can find these in Tables 2 and 3 in K2022) that have been derived from alkane/water logP measurements. You could, for example, use these polarity values to predict that reducing the polarity of an amide carbonyl oxygen to the extent that it looks like a ketone will lead to a 2.2 log unit increase in alkane/water logP.  The second panel shows measured hydrogen bond basicity values for three hydrogen bond acceptors (you can find these in this freely available dataset) and the values indicate that a trifluoroacetamide is an even weaker hydrogen bond acceptor than a ketone. Assuming a linear relationship between polarity and hydrogen bond basicity, we can estimate that the trifluoroacetamide carbonyl oxygen is 2.4 log units less polar than the corresponding acetamide. The final panel shows measured hydrogen bond acidity values (you can find these in Table 1 of K2022) that suggest that an imide NH (q = 1.3; 0.5 log units more polar than typical amide NH) will be slightly more polar than the trifluoroacetamide NH of Nirmatrelvir. So to estimate he difference in alkane/water logP values you just need to subtract the additional polarity of trifluoroacetamide NH (0.5 log units) from the lower polarity of the trifluoroacetamide carbonyl oxygen (2.4) to get 1.9 log units.

Chemical space is a recurring theme in drug design and its vastness, which defies human comprehension, has inspired much navel-gazing over the years (it’s actually tangible chemical space that’s relevant to drug design). In drug discovery we need to be able to navigate chemical space (ideally without having to ingest huge quantities of Spice) and, given that Ukrainian chemists have revolutionized the world's idea of tangible chemical space (and have also made it a whole lot larger), it is most appropriate to have a Ukrainian guide who is most ably assisted by a trusty Transylvanian sidekick. I see benefits from considering molecular complexity more explicitly when mapping chemical space. 

   

AI (as its evangelists keep telling us) is quite simply awesome at generating novel molecular structures although, as noted in a previous post, there’s a little bit more to drug design than simply generating novel molecular structures. Once you’ve generated a novel molecular structure you need to decide whether or not to synthesize the compound and, in AI-based drug design, molecular structures are often assessed using ML models for biological activity as well as absorption, distribution, metabolism and excretion (ADME) behaviour. It’s well-known that you need a lot of data for training these ML models but you also need to check that the compounds for which you’re making predictions lie within the chemical space occupied by the training set (one way to do this is to ensure that close structural analogs of these compounds exist in the training set) because you can’t be sure that the big data necessarily cover the regions of chemical space of interest to drug designers using the models. A panel discusses the pressing requirement for more data although ML modellers do need to be aware that there’s a huge difference between assembling data sets for benchmarking and covering chemical space at sufficiently high resolution to enable accurate prediction for arbitrary compounds.  

There are other ways to think about chemical space. For example, differences in biological activity and ADME-related properties can also be seen in terms of structural relationships between compounds. These structural relationships can be defined in terms of molecular similarity (Tanimoto coefficient for the molecular fingerprints of X and Y is 0.9) or substructure (X is the 3-chloro analog of Y). Many medicinal chemists think about structure-activity relationships (SARs) and structure-property relationships (SPRs) in terms of matched molecular pairs (MMPs: pairs of molecular structures that are linked by specific substructural relationships) and free energy perturbation (FEP) can also be seen in this framework. Strong nonadditivity and activity cliffs (large differences in activity observed for close structural analogs) are of considerable interest as SAR features in their own right and because prediction is so challenging (and therefore very useful for testing ML and physics-based models for biological activity). One reason that drug designers need to be aware of activity cliffs and nonadditivity in their project data is that these SAR features can potentially be exploited for selectivity.

        

Cheminformatic approaches can also help you to decide how to synthesize the compounds that you (or your AI Overlords) have designed and automated synthetic route planning is a prerequisite for doing drug discovery in ‘self-driving’ laboratories. The key to success in cheminformatics is getting your data properly organized before starting analysis and the Open Reaction Database (ORD), an open-access schema and infrastructure for structuring and sharing organic reaction data, facilitates training of models. One area that I find very exciting is the use of high-throughput experimentation in the search for new synthetic reactions which can led to better coverage of unexplored chemical space. It’s well known in industry that the process chemists typically synthesize compounds by routes that differ from those used by the medicinal chemists and data-driven multi-objective optimization of catalysts can lead to more efficient manufacturing processes (a higher conversion to the desired product also makes for a cleaner crude product). 

It’s now time to wrap up what’s been a long post. Some of what is referred to as AI appears to already be useful in drug discovery (especially in the early stages) although non-AI computational inputs will continue to be significant for the foreseeable future. I see a need for cheminformatic thinking in drug discovery to shift from big data (global ML models) to focused data (generate project specific data efficiently for building local ML models) and also see advantages in using atom-based descriptors that are clearly linked to molecular interactions. One issue for data-driven approaches to prediction of biological activity such as ML and QSAR modelling is that the need for predictive capability is greatest when there's not much relevant data and this is a scenario under which physics-based approaches have an advantage. In my view, validation of ML models is not a solved problem since clustering in chemical space can cause validation procedures to make optimistic assessments of model quality. I continue to have significant concerns about how relationships (which are not necessarily linear) between descriptors are handled in ML modelling and remain generally skeptical of claims for interpretability of ML models (as noted in NoLE, the contribution of a protein–ligand contact to affinity is not, in general, an experimental observable).

Many thanks for staying with me to the end and hope to see many of you at EuroQSAR in Barcelona next year. I'll leave you with a memory from the early days of chemical space navigation.