Grand Challenges for Predictive Modeling in Small Molecule Drug Discovery

In this blog post I’ll be taking a look at C2026 (Grand Challenges for Predictive Modeling in Small Molecule Drug Discovery) which has been published as a ChemXriv preprint. A well-organized collection of grand challenges can indeed help focus scientific research effort on the most important challenges and I consider C2026 to be welcome relief from the view that we can solve all problems with AI/ML. The authors put it well with their statement:

While there is substantial enthusiasm (particularly around AI) for revolutionizing drug discovery, this moment demands sharper problem definition.

In my view, however, C2026 could have been be better organized (for example, I would question why covalent binding is in DOMAIN: CHEMISTRY while pKa is in DOMAIN: PHARMACOLOGY). Nevertheless, the article is still at the preprint stage and my feedback will hopefully be helpful for the authors.  

I’ll direct readers to a recent blog post (The objectives of drug design) in which I suggest that it can be helpful to see design of drugs in terms of on-target bioactivity (good things that drugs do to the human body), off-target bioactivity (bad things that drugs do the human body) and exposure (things that the human body does to drugs). Uncertainty pervades drug discovery and even if we knew the exact extent to which a targets were engaged in vivo we still wouldn’t know what effects drugs will have on patients in the absence of other information (this is the uncertainty that results from the complexity of biology). One significant source of uncertainty is that we generally can’t currently measure the concentration of a drug at its site(s) of action and I recommend that everybody working in Drug Discovery (and Chemical Biology) take a look at SR2019 (Smith & Rowland, Intracellular and Intraorgan Concentrations of Small Molecule Drugs: Theory, Uncertainties in Infectious Diseases and Oncology, and Promise DMD 2019 47:667-672). 

Some years ago I suggested that drug design could be classified as prediction-driven or hypothesis-driven and I’ll direct readers to an the P2012 article on hypothesis-driven drug design by former colleagues. Back in 2009 I stated that “in many situations, properties of compounds simply cannot be predicted with the accuracy required for meaningful design, especially when optimization is performed against multiple end points” and, despite some impressive advances in predictive chemistry since then, this is still my view. Put another way drug discovery needs to be considered in a Design of Experiments framework and I consider it an error to perceive it as simply an exercise in prediction.

The value of a prediction made using chemical structure as the only input drops sharply once a sample of the compound has been prepared and decisions as to whether further work on an existing compound is justified will invariably be based on measured data. For example, the PK/PD modelling used to set the dose will typically be based on measured bioactivity (often cell-based) and pharmacokinetics. Aside from speed the great advantage of calculating ‘relative’ (see CAS2017), as opposed to ‘absolute’ free energy is that it enables project team scientists to use existing affinity and potency measurements for design. That said, the purpose of grand challenges like these is to articulate what we need to be able to predict rather than get distracted by feasibility issues.

With the preamble out of the way I’ll focus on the grand challenges and for the remainder of the post my comments will follow the order of the manuscript. As noted in my review of A2025, 'molecule' should not be used as a synonym for either 'compound' or 'chemical structure'. 

DOMAIN: CHEMISTRY

I suggest covering Covalent Binding in DOMAIN: STRUCTURE and DOMAIN: ENERGY and would include reactivity in Challenge: Chemical Stability and Degradation Products (a quinone might be perfectly stable but it’s not something that you would want to have in a enzyme inhibition assay). My view is that physicochemical properties such as pKa, aqueous solubility, aggregation and passive permeability would be more appropriately covered in DOMAIN: CHEMISTRY than in DOMAIN: PHARMACOLOGY and I would also include alkane/water partition coefficient (this is more appropriate than its octanol/water equivalent as for studying aqueous solvation and is also a better model for the core of a lipid bilayer). It might also be worth including UV-Vis absorption and fluorescence here given that both phenomena are widely exploited to assay bioactivity of compounds.

DOMAIN: STRUCTURE

Given significant interest in ‘new modalities’ I suggest referring to ‘targets’ rather than ‘proteins’ and it might be worth considering ternary structures (important in targeted protein degradation). Structures for target-ligand complexes are not directly relevant to design when association is irreversible although they are still useful starting points for building transition state models.

DOMAIN: ENERGY

Many of the quantities that form the basis of drug design fit naturally into DOMAIN: ENERGY given that they are effectively equilibrium constants or rate constants. Given significant interest in ‘new modalities’ I suggest referring to ‘targets’ rather than ‘proteins’. For irreversibly-bound ligands it's also necessary to calculate the transition state energy because target engagement occurs under kinetic control. My view is that  oral absorption and drug distribution as well as modelling of enzymatic reactions (for example, oxidative metabolism by CYPs) and active transport would be easily accommodated within DOMAIN: ENERGY.  One challenge that should be explicitly stated is prediction of plasma drug concentration profiles in humans because it is needed for meaningful PK/PD modelling.

DOMAIN: PHARMACOLOGY

A number of the challenges in DOMAIN: PHARMACOLOGY are not actually related to pharmacology and challenges such as Toxicity and PK/PD modelling could be accommodated within DOMAIN: ENERGY.

The objectives of drug design

I'll open the post on drug design objectives with photos from a most enjoyable and informative visit to the Australian Synchrotron early in 2010 when I was helping with fragment library design at CSIRO.

I’ve been meaning for ages to do a post like this and was finally goaded into action when I recently looked at two short videos from interviews with Sir Demis Hassabis, founder of Google DeepMind and Isomorphic Labs, and one of the 2024 Nobel Chemistry Prize laureates. Predicting the 3D structure of a protein from its amino acid sequence is a capability that has been eagerly sought for a long time and, as we celebrate the award, we need to also recognize the remarkable foresight of those who launched the Protein Data Bank in 1971 with just seven X-ray crystal structures. We also need to recognize that protein structures are inherently flexible and subject to post translational modification such as glycosylation and phosphorylation. Furthermore, the crystal structure that has actually been determined might correspond to a relatively small portion (for example, a tyrosine kinase domain) of a much larger structure such as a dimeric growth factor receptor.

Let’s take a look at the two videos. In the first video, Sir Demis suggests that the end of disease is “within reach maybe in the next decade or so” and it’s worth pointing out that most of the cost of bringing a drug to market comes from clinical development rather than the actual discovery of the drug (nobody spends “ten years and billions of dollars to design just one drug” and it would be more accurate to say that we do so to see if what we've designed really is a drug). Furthermore, work in the late stage of drug discovery when project teams are assessing their best compounds should not really be regarded as drug design. In the second video, Sir Demis acknowledges that “knowing the structure of a protein is only one step in the drug discovery process” although it’s not clear exactly how “many adjacent AlphaFolds” are going to meaningfully address the issues of side effects.

Drug design is frequently asserted to be a multi-objective exercise and, in this post, I’ll be trying to discuss this in a way that I hope will be helpful to drug discovery scientists using artificial intelligence (AI) and machine learning (ML) in design. The ultimate aim of drug design is to identify compounds (and biological entities such as therapeutic antibodies) that can be used to treat diseases without harming patients and I suggest that this can be stated as three design objectives. My view is that the term 'multi-objective' is more appropriate than 'multi-parameter' in the context of drug design because even against a single objective design can involve optimization of multiple parameters. One characteristic of drug design is that the design process is over long before we get to find out how successfully the outputs of design perform their function (in design of materials it's possible to evaluate design outputs more directly). I recall a Head of Research and Development at Zeneca describing the process as "like steering an oil tanker".

I prefer to use the more general term ‘bioactivity’ to describe the effects of drugs on targets (and anti-targets) because in some cases these effects cannot be meaningfully described by a single parameter such as an IC₅₀ value. As an aside this is a good point at which to celebrate the recent FDA approval of the PROTAC Vepdegestrant for treatment of ESR1m, ER+/HER2- advanced breast cancer and I'll direct readers to this most excellent and timely review on targeted protein degradation. The concentration of a drug in contact with a target (or anti-target), which varies with time, is determined by dose, and by the drug’s absorption, distribution, metabolism, and excretion (commonly referred to as ADME).  While the therapeutic and adverse effects of drugs are what the drug does to the body ADME is what the body does to the drug. Put another way, minimization of toxicity and optimizing ADME are entirely different objectives and I generally recommend that the acronym ADMET not be used.

Uncertainty is omnipresent in drug discovery and, despite what many appear to believe, AI/ML is not going to make this uncertainty vanish as if by magic. Derek was emphasizing the challenges presented by the complexity of biology long before AI came to be seen by some as a panacea for the ills of Pharma/Biotech (here’s a post from almost two decades ago and I also recommend reading his 2025 post on the “End of Disease” interview which also links relevant previous posts). The complexity of biology means that even if we knew the extent of target engagement in vivo (which varies with both dose and time) we wouldn’t generally be able to predict the in vivo effects of the drug with any confidence in the absence of other information. There is also uncertainty in exposure to consider and the concentration of a drug at its site(s) of action generally cannot be measured in vivo unless the target(s) are in direct contact with plasma. Uncertainty in exposure for intracellular targets is also a clinical development issue because failure in a Phase II trial may simply reflect inadequate exposure (we noted in KM2013 that “one can argue that a typical Phase I trial provides an incomplete description of distribution”). I recommend that everybody working in drug discovery and chemical biology read Smith & Rowland (2019) Intracellular and Intraorgan Concentrations of Small Molecule Drugs: Theory, Uncertainties in Infectious Diseases and Oncology, and Promise DMD 47:667-672 DOI. I argue in NoLE that achieving controllability of exposure should be seen as an objective of drug design.

One way that pharmacokinetic/pharmacodynamic (PK/PD) modellers address the issue of intracellular exposure is to assume that the concentration of drug in contact with its target(s) (and anti-targets) equals its unbound concentration in plasma (which can be measured in real time) and this assumption is referred to as the ‘free drug hypothesis’ (‘principle’ and ‘theory’ are also used in this context although I personally prefer ‘hypothesis’ because it’s an assumption we’re making). There are two scenarios under which the approximation of the concentration of drug at its site(s) of action by its unbound concentration in plasma is known to be unreliable. The first scenario is that there is significant active transport at one or more points on the path between plasma and the drug’s site(s) of action (active efflux is a common problem, especially in CNS drug discovery, although active influx will still cause the assumption to break down). The second scenario is that the pH at the drug’s site(s) of action differs from plasma pH (as would be the case for a lysosomal target) and that there is an ionizable group such as a basic nitrogen in the chemical structure of the drug.

While drug design does indeed have multiple objectives it really shouldn’t need to be said that if the required level of bioactivity cannot be achieved then it becomes irrelevant whether the other objectives are achieved and I’ll direct readers to M2026 (The Affinity Advantage). I see M2026 as providing a much-needed cold shower for a 2024 JMC Editorial (Property-Based Drug Design Merits a Nobel Prize; see blog post) in which it is asserted that “a discovery compound is more likely to become a drug when Fsp3 > 0.40” and that “a compound is more likely to have good developability when PFI < 7”. Nevertheless, I don’t consider M2026 to be especially useful from the perspective of defining drug design objectives because bioactivity is typically quantified by potency rather than affinity in drug discovery projects (an assay for kinase inhibition might have been run at high ATP concentration to mimic the intracellular environment) and some bioactivity objectives are defined in terms of measurements made in cell-based assays. Furthermore, bioactivity for ‘new modalities’ such as irreversible covalent inhibition and targeted protein degradation cannot be adequately described by a single parameter such as an IC₅₀ value.

I criticized the term ‘avoid-ome’ in a previous post and, with apologies for the dreadful pun, I would recommend that its use be avoided (at the risk of repetition ADME and toxicity are entirely separate issues that must be addressed separately). Furthermore, I would question whether drug designers actually need yet another ‘ome’ word and I consider the notion that embracing the avoid-ome will transform drug discovery to be fanciful. While inhibition of cytochrome P450 (CYP) enzymes is generally undesirable from a toxicity perspective a compound that was not cleared by these metabolic enzymes would greatly worry those responsible for drug safety (bear in mind why we worry about inhibition of CYPs in the first place). Furthermore, I would challenge the inclusion by M2026 of serum albumin in a list of anti-targets such as hERG (I’m not aware of anybody suffering cardiac arrest on account of their medication binding to serum albumin) and the excellent B2025 study notes that "most drugs are >95% plasma protein bound (58%), with a large fraction >99% bound (29%)". Binding to plasma proteins should actually be considered within the framework of distribution (it can be instructive to pose the question as to whether you could tell where a drug was simply from knowing the total quantity of it in the body and its unbound plasma concentration). It’s also worth mentioning that binding to plasma proteins will protect an orally-dosed drug from the metabolizing enzymes during its first pass through the liver (before it gets a chance to distribute into the tissues). Variation of the plasma concentration during the dosing interval for an orally-dosed drug is a necessary evil resulting from oral dosing and in many situations the ‘ideal’ pharmacokinetic profile would actually be that resulting from intravenous infusion (plasma concentration of the drug is maintained at a level required for therapeutically useful effects).

At this point I’ll attempt to articulate three general objectives of drug design (the only thing that I’m entirely confident about is here that I won’t get these exactly right). One of the great challenges that drug designers face is that it is usually difficult to identify compounds that simultaneously achieve all the design objectives. Specifying criteria for objectives too permissively increases the risk of choking in clinical development.  However, overly stringent specification of criteria for objectives decreases the likelihood of achieving all of the objectives and will slow the discovery process. I state these objectives in terms of ‘bioactivity’ rather than ‘potency’ to accommodate ‘new’ modalities such as irreversible covalent inhibition and targeted protein degradation although, in many cases, it will be possible to quantify the bioactivity for a compound by a single IC₅₀ or EC₅₀ value. I use ‘maximize’ and ‘minimize’ (as opposed to ‘optimize’) to frame the objectives because there is generally no penalty for identifying better compounds than you think you need. Assessing how well objectives have been achieved involves running a diverse range of assays and, as noted in this blog post on the A2025 study, it is important to be fully aware of the quantitation limits for each and every assay that you use.

I'll conclude the post with what I would argue are the three objectives of drug design:

1. Maximize on-target bioactivity.  This is the least difficult objective to specify because bioactivity characterized in the in vitro assays is likely to translate to target engagement in vivo provided that the compound can be presented to the target(s) at the required concentration. Design outputs are usually evaluated in animal models for the human disease before initiating studies in humans but the design itself is almost invariably done against in vitro end points. 
2. Minimize off-target bioactivity. It is generally more difficult to specify objectives for off-target bioactivity than for on-target bioactivity on account of the numbers and diversity of the assays involved. Design outputs are always evaluated for toxicity in animals before initiating studies in humans (as mandated by regulatory authorities) but the design itself is almost invariably done against in vitro end points.    
3. Maximize controllability of exposure. This objective, which might also be stated as 'Optimize ADME', is the most difficult of the three objectives to specify because, as noted earlier in this post, exposure generally can’t be measured for targets that are not in direct contact with plasma. At absolute minimum it is necessary to demonstrate that a pharmacokinetic profile can be achieved in animals that will maintain the (unbound) concentration of the compound at levels that we believe will result in beneficial therapeutic effects in humans. For targets not in contact with plasma the PK/PD modellers also need to be able to confidently invoke the free drug hypothesis (this is why I prefer to frame the objective in terms of exposure rather than ADME) and this requires that design outputs have good passive permeability and are not subject to active transport. In some cases it will also be necessary to demonstrate access to specific organs such as the CNS.  

 

Return to Flatland

Whoever first referred to Economics as ‘The Dismal Science’ had clearly never read an article on ‘3Dness’ in drug discovery.  My own experience reading articles on this topic is a sensation of having my life force slowly sucked out (I even suggested that reviewing the '3Dness' literature might be considered as an appropriate penance when I recently confessed my sins at St Gallen Cathedral) and the subject of Confession reminds me of a song that the late great Tom Lehrer sang about the Second Vatican Council.

In this post I review the CNM2025 study (Return to Flatland) which examines the heavily-cited LBH2009 study (Escape from Flatland: Increasing Saturation as an Approach to Improving Clinical Success).This also is a good point to mention a Journal of Medicinal Chemistry Editorial (Property-Based Drug Design Merits a Nobel Prize) that I reviewed in a 30-Jul-2024 post. The CNM2025 study, which has already been reviewed by Dan and Ash, opens with: 

The year is 2009, Barack Obama has just been inaugurated and both Lady Gaga and The Black Eyed Peas are at the height of their popularity

This couldn’t help but remind me of the “WORLD WAR 2 BOMBER FOUND ON MOON” headline that appeared on the front page of the Sunday Sport twenty-one years before the publication of LBH2009 (it was was accompanied by a photo of a B-17 in a lunar crater). A few weeks later the headline was “WORLD WAR 2 BOMBER FOUND ON MOON VANISHES” (this time accompanied by a photo of the now empty lunar crater).

I’ll start my review of CNM2025 by quoting from it and, as is usual for posts here at Molecular Design, quoted text is indented with any comments by me italicized in red and enclosed in square brackets. 

The hypothesis was attractive, and the data clearly showed the relationship between Fsp³ and clinical progression with pairwise significance P < 0.001. [This statement is inaccurate and Figure 3 of the LBH2009 study shows statistically significant differences at this level between (a) discovery and phase 2 compounds (b) phase 1 and phase 3 compounds (c) phase 2 compounds & drugs.  The authors of LBH2009 state: “The change in average Fsp³ was statistically significant between adjacent stages in only one case (phase 1 to phase 2)” but they neither show this in Figure 3 of their article nor do they report a P-value for the statistical significance of the mean difference in Fsp³ between phase 1 and phase 2 compounds.] The statistics seemed compelling, though the effect size was modest — an increase in average Fsp³ of 0.09 between sets of phase I and approved drugs equates to a difference of around two additional sp³ carbons per drug molecule only. [The authors of LBH2009 did not actually report this difference to be statistically significant so it is unclear why the authors of CNM2025 have stated that the “statistics seemed compelling”.]

The LBH2009 study is effectively a call to think beyond aromatic rings in drug design and my view is that there are considerable benefits in doing so even though I consider the data analysis in the study to be shaky. Almost three decades ago I included a quinuclidine in the Zeneca fragment library for NMR screening and later at AstraZeneca I would actively search (with minimal success) for amides and heteroaryls derived from bicyclic amines. I see the advantages in looking beyond aromatic rings as stemming primarily from increased molecular diversity and a more controllable coverage of chemical space, and in KM2013 we wrote:

Molecular recognition considerations suggest a focus on achieving axial substitution in saturated rings with minimal steric footprint, for example by exploiting the anomeric effect or by substituting N-acylated cyclic amines at C2.

Although data analyses (for example, see HY2010) presented in support of the belief that aromatic rings adversely affect aqueous solubility are typically underwhelming I consider the suggestion to be plausible and suggested in K2022 that deleterious effects of aromatic rings are more likely to be due to their potential for making molecular interactions than to their planarity. That said, I should also point out that the analysis of the relationship between aqueous solubility and Fsp³ presented in Figure 5 of LBH2009 is a textbook example of correlation inflation (see Fig. 5 in KM2013) and I suspect that if a team had submitted this analysis at Statistiques Sans Frontières the judges would have either awarded “nul points” or come to the conclusion that the team had played its joker. Given the Lady Gaga reference in CNM2025 I couldn't resist linking this Peter Gabriel song which includes the lyrics "Adolf builds a bonfire, Enrico plays with it" even though I have absolutely no idea what the the lyrics actually mean.

While the analysis of the relationship between aqueous solubility presented in Figure 5 of LBH2009 does endow the study with what I’ll politely call a whiff of the pasture it’s not directly related to the analysis of clinical progression presented in the study. Let’s take a look at Figure 3 in LBH2009 which shows mean Fsp³ values for compounds in discovery, at the three phases of clinical development, and approved drugs. As an aside this analysis would fall foul of current Journal of Medicinal Chemistry author guidelines (see link; accessed 05-Aug-2025) which clearly mandate that “If average values are reported from computational analysis, their variance must be documented”.  As mentioned earlier in this post Figure 3 in LBH2009 shows statistically significant (P value < 0.001) differences between (a) discovery and phase 2 compounds (b) phase 1 and phase 3 compounds (c) phase 2 compounds & drugs. It’s also worth stressing that Figure 3 in LBH2009 does not show statistically significant differences in Fsp³ for any of the clinical development transitions (phase 1 to phase 2; phase 2 to phase 3; phase 3 to approved drug). Figure 3 of in LBH2009 shows 591 phase 2 compounds but only 376 phase 1 compounds, raising questions about the numbers of compounds that have been in clinical development without being recorded in the database.

I think that there are some problems with how the authors of the LBH2009 study have analysed the relationship between Fsp³ and progression through the stages of clinical development.  If charged with analysing this data I would focus on the three clinical development transitions (phase 1 to phase 2; phase 2 to phase 3; phase 3 to approved drug) and wouldn’t waste time on comparisons between discovery compounds and clinical compounds. If analysing the relationship between Fsp³ and the progression from phase 1 to phase 2, I would partition the set of phase 1 compounds into a ‘YES’ subset of compounds that had progressed to phase 2 and a ‘NO’ subset of compounds that had not progressed to phase 2. I would certainly be taking a close  look at distributions of Fsp³ values (some approaches to assessing statistical significance are based on the assumption of Normally-distributed data values) and I’d also be thinking about assessing effect size in addition to statistical significance. However, the problems with the LBH2009 analysis are more fundamental than non-Normal distributions of Fsp³ values.

The authors of LBH2009 assess the progression from phase 1 to phase 2 by comparing the mean Fsp³ value for the phase 1 compounds with the mean Fsp³ value for phase 2 compounds. The problem is that the Fsp³ values for the YES compounds (that have progressed from phase 1 to phase 2) are present in both the data sets for which comparisons are being made. This means that the observed differences in mean Fsp³ values will reflect both the difference between YES and NO compounds (relevant to relationship between Fsp³ and progression from phase 1 to phase 2) and the relative numbers of YES and NO compounds in the phase 1 data (not relevant to relationship between Fsp³ and progression from phase 1 to phase 2). Analysing the data in the way that the authors of LBH2009 have done effectively adds noise to the signal and it’s possible that they would have observed more statistically significant differences in mean Fsp³ values had they analysed the data in a more appropriate manner.

This is an appropriate point at which to discuss correlation in the context of studies such as LBH2009 and CNM2025. It’s actually well known (see L2013) that that Fsp³ values for chemical structures tend to be greater when amine nitrogen atoms are present (this does not invalidate the observed trends in the data but has big implications for how you interpret these trends). There is, however, a much bigger issue which is that correlation does not imply causation. Let’s suppose that you’ve just joined a drug discovery team as they are preparing to select a clinical candidate (I concede that this is most improbable scenario but it does illustrate a point). The team have an excellent understanding of the structure-activity relationship (SAR) and have successfully addressed a number of issues during the lead optimization process (the chemical structures of the compounds have been quite literally shaped by the problems that the team members have solved). Now consider the likely reaction of the team members to a suggestion that probability of success in the clinic would increase if the chemical structure of the best compound were modified so as to increase its Fsp³ value. My view is that the team might think that the person making such a suggestion had just stepped off the shuttle from Planet Tharg (an alien from this planet used to make occasional Sunday Sport  appearances). I see the trends in data observed by the authors of LBH2009 as effects rather than causes (the vanishing B-17 was never there in the first place).

Let’s return to the CNM2025 study and its authors state:

Using data from the Cortellis Drug Discovery Intelligence database, we repeated an analysis similar to that of Lovering et al. to assess Fsp³ in drugs approved post-2009 and those in active clinical development as of mid-2024 (Fig. 1). [I would challenge the claim that the analysis presented in CNM2025 is similar to that presented in LBH2009. The supplementary material for CNM2025 indicates that the data summarised in Fig. 1b correspond to the period 2012 through 2024 (it is not clear whether the database has been updated to account for compounds that have fallen out of active development during this period. As is the case for Figure 3 in LBH2009, Fig.1b in CNM2025 shows more phase 2 compounds (816) than phase 1 compounds (421), raising similar questions about the numbers of compounds that have been in clinical development without being recorded in the database. I thank fellow blogger  Dan Erlanson for suggesting that I examine the supplemental information for CNM2025.] Although our methods used contemporary data sources different to Lovering et al., we obtained comparable Fsp³ data for approved drugs prior to 2009. More recently however, the picture appears to have changed with approvals shifting to lower Fsp³ drugs (Fig. 1a). Similarly, when looking at drugs currently in clinical development (Fig. 1b), there appeared to be no clear relationship between highest phase reached and Fsp³, suggesting the key conclusion noted by Lovering et al. has not persisted. In all data sets, exemplars with Fsp³ = 0 as well as Fsp³ = 1 are extensively seen. [It is necessary to account for the number of hypotheses have been tested for statistical significance when quoting P-values (see R2016 and VM2018).]

Fig. 1a in CNM2025 shows the time-dependence of Fsp³ distributions for approved drugs according to approval date and I remain unconvinced of the value of analysis like this (on first encountering analysis of time-dependence of drug properties a quarter of a century ago I recall being left with the distinct impression that some senior medicinal chemists where I worked had a bit too much time on their hands). However, it is immaterial whether or not you are as underwhelmed as I am by time-dependence of drug properties because no such analysis is actually reported in LBH2009 and this is one reason that I challenge the claim by made by the authors of CNM2025 that they “repeated an analysis similar to that of Lovering et al. to assess Fsp³ in drugs approved post-2009 and those in active clinical development as of mid-2024”.  

Now let’s take a look at Fig. 1b in CNM2025 and this should be compared with Figure 3 in LBH2009. In some ways the former is an improvement on the latter since the violin plots show the distributions of Fsp³ values for each group of compounds and, as mentioned earlier in the post, I don’t think that it makes any sense to include discovery compounds in analysis like this (as the authors of LBH2009 did). Although these two figures look superficially similar they are actually very different and, given that the authors of CNM2025 only included "compounds in clinical trials as of mid-2024" in their study, I would argue that their study does not properly examine the link between Fsp³ and clinical progression. I agree that the difference between mean Fsp³ values for drugs approved up to 2009 and for drugs approved after 2009 is statistically significant. What is not clear from the analysis summarized in Fig. 1b in CNM2025 is whether the lower Fsp³ values of drugs that were approved after 2009 reflect smaller increases in Fsp³ over the course of clinical development (the B-17 has disappeared from the lunar crater) or lower Fsp³ values for compounds entering clinical development (the B-17 is still in the lunar crater). I think it's possible to address this question but you would need to analyse the data a lot more carefully than the authors of CNM2025 appear to have done. For example, you might examine the time-dependencies of mean Fsp³ values for compounds evaluated in phase 1 and the corresponding mean Fsp³ values for compounds that progressed or failed to progress to phase 2. While I consider more careful analysis of progression to be feasible I see little or no value from the perspective of real world drug discovery in actually performing the analysis more carefully.

This is a good point at which to wrap up and, unless the the trends in the data can shown to reflect causation, the debate can be described as bald men fighting over a comb (as one who is follicly challenged I always find it painful to use this phrase). I see variation in drug properties with time as an effect rather than a cause and Forrest Gump would have been well aware of this fifteen years before the publication of LBH2019 when he famously observed that "shit happens". One point on which the CNM2025 authors and I do appear to agree is that there is not currently a B-17 in a lunar crater. Where we appear to differ is that they seem to be suggesting this was because it has vanished while I never believed that it was ever there in the first place. I’ll let the late great Dave Allen have the last word.

Assessment of AI-generated chemical structures using ML

Previous << || >> Next  

In an earlier post I considered what it might mean to describe drug design as AI-based. In this post I’ll take a general look at using machine learning (ML) to predict biological activity (and other pharmaceutically-relevant properties) for AI-generated chemical structures. Whether or not ML models ultimately prove to be fit for this purpose it is worth pointing out that many visionaries and thought leaders who tout computation as a panacea for humanity’s ills fail to recognize the complexity of biology (take a look at In The Pipeline posts from 2007 | 2015 | 2024). One point worth emphasizing in connection with the complexity of biology is that it is not currently possible to measure the concentration of a drug at its site of action for intracellular targets in live humans (here's an article on intracellular and intraorgan drug concentration that I recommend to everybody working in drug discovery and chemical biology). While I won't actually be saying anything about AI (here's a recent post from In The Pipeline that takes a look at how things are going for early movers in the field of AI drug discovery) in the current post I'll reiterate the point with which I concluded the earlier post:

One error commonly made by people with an AI/ML focus is to consider drug design purely as an exercise in prediction while, in reality, drug design should be seen more in a Design of Experiments framework.  

In that earlier post I noted that there’s a bit more to drug design than simply generating novel molecular structures and suggesting how the compounds should be synthesized. While I'm certainly not denying the challenges presented by the complexity of biology the current post will focus on some of the challenges associated with assessing chemical structures churned out by generative AI. One way of doing this is to build models for predicting biological activity and other pharmaceutically relevant properties such as aqueous solubility, permeability and metabolic stability. This is something that people have been trying to do for many years and the term ‘Quantitative Structure-Activity Relationship’ (QSAR) has been in use for over half a century (the inaugural EuroQSAR conference was held in Prague in 1973 a mere five years after Czechoslovakia had been invaded by the Soviet Union, the Polish People's Republic, the People's Republic of Bulgaria, and the Hungarian People's Republic). My view is that many of the ML models that get built with drug design in mind could accurately be described as QSAR models and I would not describe QSAR models as AI.

In the current post, I'll be discussing ML models for predicting quantities such as potency, aqueous solubility and permeability that are continuous variables which I refer to as 'regression-based ML models' (while some readers will not be happy with this label I do need to make it absolutely clear that the post is about one type of ML model and the label 'QSAR-like' could also have been used). I’ll leave classification models for another post although it’s worth mentioning that genuinely categorical data are actually rare in drug discovery (you should always be wary of gratuitous categorization of continuous data since this is a popular way to disguise the weakness of trends and KM2013 will give you some tips on what to look out for). It also needs to be stressed that the ML is a very broad label and that utility in one area (prediction of protein-folding for example) doesn't mean that that ML models will necessarily prove useful in other area.      

To build a regression-based ML model you first need to assemble a training set of compounds for which the appropriate measurements have been made and pIC₅₀ values are commonly used to quantify biological activity (I recommend reading the LR2024 study on combining results from different assays although, as discussed in this post, I don’t consider it meaningful to combine data from multiple pairs of assays when calculating correlation-based metrics for assay compatibility). Next, you calculate values of descriptors for the chemical structures of the compounds in your training set (descriptors are typically derived from the connectivity in the chemical structure although atom counts and predicted values of physicochemical properties are also used). Finally, you use the ML modelling tools to find a function of the descriptors that best predicts the biological activity (or a pharmaceutically-relevant property) for the compounds in the training set. Generally you should also validate your models and this is especially important for models with large numbers of adjustable parameters.

There appears to be a general consensus that you need plenty of data for building ML models and some will even say “quantity has a quality all of its own” (this is sometimes stated as Stalin’s view of the T-34 tank although I consider this unlikely and the T-34 was actually an excellent tank which also happened to get produced in large numbers). Most people building regression-based ML models are also aware that you need a sufficiently wide spread in the measured data used for training the model (the variance in the measured data should be large in comparison with the precision of the measurement). Lead optimization is typically done within structural series and building a regression-based ML model that is predictively useful is likely to require data that have been measured for compounds in the structural series of interest.  These data requirements are quite stringent and I see this as one reason that QSAR approaches do not appear to have had much impact on the discovery of drugs despite the drug discovery literature being awash with QSAR articles. Back in 2009 (see K2009) I compared prediction-driven drug design with hypothesis-driven drug design, noting that the former is often not viable and that the latter is more commonly used in pharmaceutical and agrochemical discovery (former colleagues discussed hypothesis-driven molecular design in the context of the design-make-test-analyse cycle in the P2012 article).

With freshly painted T-34 at Brest Fortress, Belarus (June 2017)

There are some other points that you need to pay attention to when building regression-based ML models.  First, replicate measurements for the response variable (the quantity that you’re trying to predict) should be normally distributed and this is one reason why we model pIC₅₀ rather than IC₅₀. Second, the data values for the training set should be uniformly distributed in the descriptor space (my view, expressed in B2009, is that many 'global' predictive models are actually ensembles of local models). Third, the descriptors should not be strongly correlated or the method used to build the regression-based ML model must be able to account for relationships between descriptors (while it’s relatively straightforward to handle linear relationships between descriptors in simple regression analysis it’s not clear how effectively this can be achieved with more sophisticated algorithms used for building regression-based ML models).

I’ve created a graphic (Figure 1) to illustrate some of the modelling difficulties that result from uneven coverage in the descriptor space and it goes without saying that reality will be way more complex. The entities that occupy this chemical space are compounds and the coordinates of a point show the values of the descriptors X₁ and X₂ that have been calculated from the corresponding chemical structures (the terms ‘2D structure’ and ‘molecular graph’ also used). I’ve depicted real compounds for which measured data are available as black circles and virtual compounds (for which predictions are to be made) as five-pointed stars. The clusters (color-coded but also labelled A, B and C in case any readers are colour blind) are much more clearly defined than would be the case in a real chemical space. Proximity in chemical space implies similarity between compounds and the clusters might correspond to three different structural series.

Let’s suppose that we’ve been able to build a useful local model to predict pIC₅₀ for each cluster even though we’ve not been able to build a predictively useful global model. Under this scenario you’d have a relatively high degree of confidence in the pIC₅₀ values predicted for the virtual compounds (depicted as five-pointed stars) that lie within the clusters and a much lower degree of confidence in the virtual compound that is indicated by the arrow. If, however, we were to ignore the structure of the data and take a purely global view then we would conclude that the virtual compound indicated by the arrow occupied a central location in this region of chemical space and that the other three virtual compounds occupied peripheral locations. Put another way, the applicability domain of the model is not a single contiguous region of chemical space and what would appear to be an interpolation by a model is actually an extrapolation. 

It is important to take account of correlations between descriptors when building prediction models. A commonly employed tactic is to perform principal component analysis (PCA) which generates a new set of orthogonal descriptors and also provides an assessment of the dimensionality of the descriptor space. There are also ways to deal with correlations between descriptors in the model building process (PLS is the best known of these and the K1999 review might also be of interest). Correlations between descriptors also complicate interpretation of ML models and my stock response to any claim that an ML model is interpretable would be to ask how relationships between descriptors had been accounted for in the modelling of the data. An excellent illustrative example (see L2012) of a correlation between descriptors is the tendency of the presence of a basic nitrogen in a chemical structure to be associated with higher values of the Fsp³ descriptor (which, as pointed out in this post, should really be referred to as the I_ALI descriptor).

Let’s take another look at Figure 1. The axes of the ellipse representing Cluster A are aligned with the axes of the figure which tells us that X₁ and X₂ are uncorrelated for the compounds in this cluster.  Cluster B is also represented by an ellipse although its axes are not aligned with the axes of the figure which implies a linear correlation between X₁ and X₂ for the compounds in this cluster (you can use PCA to create two new orthogonal descriptors by rotating the plot around an axis that is perpendicular to the X₁-X₂ plane). Cluster C is a bigger problem because the correlation between X₁ and X₂ is non-linear (the cluster is not represented as an ellipse) and it would be rather more difficult to generate two new orthogonal descriptors for the compounds in this cluster. My view is that  PCA is less meaningful when there is a lot of clustering in data sets and I would also question the value of PLS and related methods in these situations. 

Let’s consider another scenario by supposing that we’ve been unable to build a useful local model for prediction of any of the three clusters in Figure 1.  If, however, the average pIC₅₀ values differ for each of the three clusters we can still extract some predictivity from the data by finding a function of X₁ and X₂ that correlates with the average pIC₅₀ values for the clusters. This is one way that clustering of compounds in the descriptor space can trick you into thinking that a global model has a broader applicability domain than is actually the case. Under this scenario it would be very unwise to try to interpret the model or use it to make predictions for compounds that sit outside the clusters. 

This is a good point at which to wrap up my post on regression-based ML (or QSAR-like if you prefer) models for predicting biological activity and other properties relevant to drug design such as aqueous solubility, permeability and metabolic stability. There appears to be a general consensus that building these models requires a lot of data and, in my view, this means that models like these are actually of limited utility in real world drug design. The basic difficulty is that a project team with enough data for building useful regression-based ML models is likely to be at a relatively advanced stage (the medicinal chemists will already understand the structure-activity relationships and be aware of project-specific issues such as poor aqueous solubility or high turnover by metabolic enzymes). Drug discovery scientists tend to be less aware of the problems that arise from clustering of compounds in descriptor space and, in my view, this is a factor that should be considered by those seeking to assemble data sets for benchmarking (see W2024). I'll leave you with a suggestion (it was considered a terrible idea at the time and probably still is by most ML thought leaders) I made over twenty years ago that each predicted value should be accompanied by chemical structures and measured values for the three closest neighbours in the descriptor space of the model.

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.