Добавил:
Sekretar
kiopkiopkiop18@yandex.ru
t.me/Prokururor I Вовсе не секретарь, но почту проверяю
Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз:
Предмет:
Файл:Ординатура / Хирургия / Библиотека им академика М.И. Перельмана / Книга_117_библиотеки_им_акад_М_И_Перельмана
.pdf
116
https://t.me/med1917
expensive studies are carried out. By allowing for informed action while also taking
into account model logic, medicinal chemistry expertise, and knowledge of the limitations of the system. The goal of XAI-assisted medication development is to aid in
resolving some of these issues [43].
Data analysts, chemoinformaticians, and medicinal chemistry researchers will
be able to collaborate together more effectively, thanks to XAI [44, 45]. Actuality,
XAI already makes it possible to mechanistically evaluate how drugs work [46, 47]
and it helps to improve medication safety and plan organic synthesis [48]. If longterm success is achieved, XAI will offer crucial assistance in the interpretation and
analysis of ever-more complicated chemical data as well as in the development of
fresh pharmaceutical ideas, all while avoiding human bias. Intense challenges with
drug discovery, such as the coronavirus pandemic, may accelerate the development
of application-tailored XAI algorithms to swiftly address particular scientic problems pertaining to human biology and pathophysiology [49, 50].
Although XAI is still in its early stages, it continues to grow quickly, and I anticipate that its importance will rise over the next years. I aim to present an in-depth
overview of the current XAI research in this book chapter, emphasising its advantages, drawbacks, and potential for future drug development. After giving a brief
overview of the most pertinent XAI approaches organised into conceptual categories, the next section presents some current and future applications to drug development. I conclude by summarising the limitations of present XAI and suggesting
potential advances in methodology that might help make these techniques more
usefully useful in pharmaceutical research.
A. V. Geevarghese
2 Applications ofArticial Intelligence inDrug Discovery
2.1 Relation ofQSAR/QSPR withStructure-Based Modelling
withArticial Intelligence
Throughout more than 50years since its inception, QSAR/QSPR modelling has
progressed tremendously [51]. The efcacy of these type of computational models
for predicting biological activities and pharmacokinetic properties, which include
absorption, distribution, metabolism, excretion, and toxicity (ADMET) [52–55], is
unambiguous evidence of their impact on the development of drugs. Those so-called
molecular descriptors are frequently employed to transform the structural characteristics of molecules (such as pharmacophore distribution, physicochemical properties, and functional groups) into machine-readable values for ligand-based QSAR/
QSPR modelling [56]. There are many different types of manually created molecular descriptors, each of which aims to communicate a different feature of the underlying molecular structure. Support vector machines (SVM) and gradient boosting
methods (GBM) are two widely used machine learning techniques that have typically replaced fundamental models like regression models like linear and k-nearest

Explainable Articial Intelligence inDrug Discovery
https://t.me/med1917
117
relatives in QSAR/QSPR approaches, often at the expense of interpretability, to
address more complex and likely non-linear connections between the structure of a
compound and its physicochemical/biological properties [57]. Deep neural network
applications are not new [58]. The 1990s saw the introduction of the bulk of the
most recent advancements in chemoinformatics, including deep and adaptive network topologies, autonomous maps, recurrent systems for sequencing and timeseries analysis, and autoencoders [59–61]. Deep networks, however, went the next
step after winning the Merck Molecular Activity Competition in 2012 [61]. While
there is much debate about whether this specic class of models outperforms competing tactics (such as gradient boosting machines) [62].
Methods for deep learning have multiple advantages when employing the same
set of variables [63]. The potential of deep neural networks to autonomously gather
features throughout training seems possibly the most important. Particularly recurring neural networks [64] and neural networks with graphs (which are additionally
referred to as message-passing techniques) have the ability of producing intrinsic
context-specic representation for chemical structures. This may be done in the
specic case of graph neural networks by learning latent atom and bond representations during the training stage. As a result, modelling activities for which traditional
descriptors were not initially designed is possible using deep learning methodologies. Examples include macrocycles [65], proteolysis-targeting chimaeras
(PROTACs), and modelling of peptides [65, 66].
Deep architectures may also benet from multitask learning, which seeks to
identify a common internal representation useful for a collection of connected endpoints. It differs from multi-output learning in that it doesn’t explicitly take use of
relationships between the tasks that need to be learnt [67–69], perform a variety of
activities. Since drug development is a multi-parameter optimisation issue, learning
may be able to better take advantage of data correlation without the necessity for
previous imputation in cases when a chemical library has not been thoroughly evaluated on all relevant outcomes. Prior to the adoption of deep learning approaches,
the concept of multi-output QSAR simulation, which tried to connect a collection of
identied chemical descriptors to measurements, was researched [70–75]. Despite
the potential of multitask learning, it hasn’t yet been demonstrated that it can outperform single-task models [76–79]. Deep learning’s poor performance when there
is little to no data is a well-known issue [80]. By using additional genetic or biological interactome data sources, certain chemogenomic-based techniques could be able
to provide further light on these scenarios [81]. Additionally, there have been recent
developments in “few-shot” learning [82] and meta-learning [83] (a family of
approaches that aims to provide a set of learnable parameters that can quickly adapt
to new, unknown jobs). Therefore, in contrast to approaches that are totally or partially based on physics, the capacity of completely data-driven methodology for
molecular characteristic projections to extrapolate and generate trustworthy predictions for unknown chemical classes is highly constrained. The introduction of extra
active learning approaches (strategies where the model participates in requesting
particular training data for enhanced generalisation) and physics-inspired machine
learning algorithms can overcome these constraints [84, 85]. Given that sufcient

118
https://t.me/med1917
A. V. Geevarghese
sources that would enable good data imputation are usually hard to come by, how
effectively each of these techniques’ individual implementations handle data sparsity will also have a signicant impact on how effective they are [86]. The “blackbox” nature of deep learning models and their often challenging debugging have
also attracted a lot of criticism [87]. To manually include background information
in a way that is easier to grasp, domain-specic features [88, 89] (i.e. descriptors
explicitly constructed with a specic objective) are still an option. By offering
understandable interpretations of the decision-making process used by deep learning systems, explainable AI techniques may be able to provide some partial remedies to these issues [90]. A gap between deep learning and drug discovery knowledge
will be able to close with the ongoing development of feature attribution methodologies [89]. Examples of instance-based explanations include counterfactuals,
model-generated instances that are conditioned on user-dened queries, and attention-based networks [89, 90]. The high expense of deep learning techniques is
another drawback that is frequently mentioned. Deep learning usually requires
lengthier training and evaluation times than many other machine learning techniques because it requires specialised hardware, such as tensor processing units or
consumer-grade graphics processing. Although the aforementioned supposition is
usually accurate, deep learning models can be capable of learning in an Internet
environment by automatically utilising its most well-liked training approach, stochastic gradient-descent optimisation [90].
The benet of this is that it grows exponentially in proportion to the size of the
training dataset, preventing the latter from needing to use the whole system’s memory. Since deep learning models may be stochastically trained on sequential, random batches of data, researchers contend that they may perform better than
competing solutions in big data environments [91]. In a similar vein, predicting
deep learning typically requires far more human expertise in many real-world circumstances compared to other, more well tested approaches. Despite the ease with
which a high-performing random forest model may be trained for hyperparameter
adjustment, our understanding of current deep learning approaches is still insufcient to provide trustworthy defaults [92]. However, recent theory suggests that this
may change soon.
Furthermore, even when the predictions are obviously incorrect, neural networks
show a propensity to give correct responses for deceptive reasons (such as the infamous Clever Hans effect [93]). The dilemma is made signicantly worse by the
possibility that comparable trial circumstances might provide results that are noticeably different when used to forecast characteristics in drug development. The widespread application of uncertainty estimation approaches, whether through deep
learning systems that explicitly include uncertainty into their design, like Bayesian
neural networks [94], or post hoc techniques, such ensemble learning [95], should
minimise this problem in the following years. In contrast to classical QSAR, which
needs a co-crystal or a docking equilibrium to generalise over numerous targets,
incredible progress has also been made in the structure-based modelling of proteinligand activity. To accurately account for the impact from individual descriptors
(such as physical and chemical properties) on a target property, many conventional

Explainable Articial Intelligence inDrug Discovery
https://t.me/med1917
119
methods used partial least squares or multiple linear regression models to model an
explicit, predened mathematical connection of the protein-ligand complex [96–98].
The use of methods that combine various descriptors, such as protein-ligand atom
pair counts [99], property-encoded shape distributions [100], or basic atomic interactions, with sophisticated and exible non-linear models, such as random forests
or support vector machines, increased in the early 2010s.
This unique subject has lately observed the emergence of deep learning and used
it, much as its strictly ligand-based cousin. Early methods for predicting bioactivity
were impacted by the advancement of computer vision and picture recognition,
which was primarily driven by convolutional neural networks [101]. To achieve the
same result, further study [102] combined graph-based techniques with feature
enhancements based on distance and angle. In structure-based virtual evaluation
and lead optimisation competitions, several of them were purportedly shown to provide marginal performance advantages over existing methodologies [103, 104].
However, [105–109] it is debatable if certain reputable benchmarks favour ML-based
grading systems over traditional ones. One conceptual limitation of approaches
based on three-dimensional convolutional neural network models is the lack of rotational invariance with reference to the input, a quality crucial for representing
atomic systems. Thanks to recently created neural network architectures like the
Euclidean Neural Networks [110–112] and SchNet [113], which directly incorporate equivariance with respect to the special Euclidean group in three dimensions
(SE(3)) (i.e. rotations and translations) into their design, how to approach this problem has recently become a very active area of study. In the past, these structures
have been used for a number of molecular activities, including the study of molecules’ electrical characteristics [114].
It is predicted that further study will be conducted in this area in the future,
expanding the modelling possibilities. Because deep learning applications in drug
development are expanding quickly and require sizable training sets, thorough data
curation and appropriate benchmarking of newly developed models are crucial.
Chemical substance libraries have grown in size and accessibility over the past several years, with tools like ZINC [115] and ChEMBL [116] acting as standard entry
points for ligand-based programmes. The same pattern was observed for structurebased modelling, for which databases like PDBbind [117] and BindingDB [118]
provide incredibly precise structural information on protein-ligand complexes
together with information on the biological activity associated with such complexes.
The prospect of soon having access to structural data for a large number of potential
therapeutic targets is encouraged by recent developments in protein structure predicting and determination [119].
A lot of money has already been spent on open, standardised assessments of
machine learning techniques in the eld of chemoinformatics. A quick evaluation of
numerous important deep learning methods for drug-related property predictions in
well-curated datasets from disciplines including biophysics, physical chemistry,
and physiology is provided by the MoleculeNet benchmarking suite, in particular.
These improvements to AI based drug developments helps pharmaceutical rms,
publishers, and commercial research bodies continue to produce most structural

120
https://t.me/med1917
activity/property connection data [120–122]. Despite the fact that we have maintained that the amount of public data continues to grow rapidly, who typically see
the information collected as a differentiating advantage that should be kept private.
Recent work suggests that molecular descriptors are routinely used to partly rebuild
molecular structures, which may make it more challenging to communicate data
even at the latent feature level [123]. There have been several attempts to circumvent these limitations, such as the creation of federated and IP-preserving learning
systems [124]. Since then, it has become clear that using sets pulled in a pseudorandom manner from a database to test a model’s performance might result in too
optimistic results. Alternatives like scaffold-based [125] or time-based splits [126],
which aim to approximate the development of a lead optimisation project, may be
more illuminating.
Although there is no “one-size-ts-all” method, it is important to remember that
each evaluation shows how well a model performs in a certain application area.
Potential applications ought to be thought of as the ideal situation for model benchmarking, but we can show that they are not always objective and are not without
bias [127]. Machine learning scoring algorithms [128] have been shown to be reasonably predictive in a number of virtual screening initiatives [129], even if there
isn’t a general benchmarking agreement. The limitations of employing proper performance measures for regression and classication models have also received a lot
of attention.
A. V. Geevarghese
2.2 Articial Intelligence-Based Approaches inDe Novo
Drug Design
De novo design, which entails the creation of novel molecular structures with
desired pharmacological characteristics from scratch, can be regarded as one of the
most challenging automated technology tasks in drug discovery due to the cardinality of the chemical eld of drug-like molecules, which is thought to range in the
order of 1060–10,100 [130, 131]. De novo molecule synthesis is complicated by the
combinatorial issue even if there may be a vast array of potential atomic forms and
molecular structures to examine [132]. Depending on the data used to guide the de
novo design, similar methodologies may be ligand-based, structure-based, or any
mix of the two [133].
Another approaches which lead to drug discovery in de novo-based approaches
is ligand-based methodologies. Ligand-based methods are important area of
research drug discovery and optimisation process, this approach doesn’t need the
isotopic labelling of targeted proteins. Ligand-based methodologies in de novo drug
design approaches can be broadly categorised into two main categories: (i) rulebased methods, which use a set of constructing rules for molecules to be built from
a variety of “building blocks” (such as the reagents or molecular fragments), and (ii)
rule-free methods, which do not use clear construction regulations. One of the

Explainable Articial Intelligence inDrug Discovery
https://t.me/med1917
121
forerunners of contemporary rule-driven de novo design is the Topliss technique
[134], for the serial production of analogues of a strong lead molecules with the
maximum potency. Modern methods entail employing a specied set of chemical
transformations for optimisation, such as matching up molecules in correlation
[135] or using molecular structure and functional group change rules-of-thumb
[136]. Building block assembling and ligands creation are specically included in
synthesis rules in synthesis-oriented techniques. These techniques can be applied,
for illustration, to the development of electronically accessible libraries, like BI
CLAIM [112] and CHIPMUNK [135]. During the late 1990s, hybrid techniques
have been to guide the creation of novel compounds by jointly maximising their
similarity to recognised bioactive ligands and the chemical synthesisability of the
designs, such as TOPAS [136], DOGS [137], and DINGOS [138]. They were developed to regulate the synthesis of novel molecules by optimising both of the design’s
resemblance to already- known active interactions and their potential for chemical
synthesis.
Overcoming molecular developing standards, rule-free strategies aim to generate
compounds with specied characteristics. Contemporary techniques frequently
depend on generating models based on deep learning [139], which take samples
new atoms from a hidden chemical description that has been learnt. The concept of
choosing a molecule from a numerical model for de novo synthesis is related to the
“inverse QSAR” problem discussed in Skvortsova and Zerov’s landmark work in
the early 1990s [140–142]. The use of these approaches is looks increasing in recent
years. Reverse QSAR employs an earlier QSAR model to pinpoint the description
values that t a desired attribute while making molecules.
With the reason of producing molecules, inverse QSAR utilises a current QSAR
modelling to determine descriptor variables that correspond to an ideal trait. The
latter approaches offer an array of disadvantages, notably the challenge in reversedecoding the descriptors of molecules into suitable structures and the existence of
multiple options for each specic characteristic. Creative machine learning handles
some of these problems by simulating the underlying structure of a certain group of
chemicals and then creating new molecules by choosing the obtained distribution
[143]. Most frequently used generative models combine Simplied Molecular Input
Line Entry Systems (SMILES) with natural language processing techniques [144].
The models in question undergo training to acquire the SMILES “syntax” (which
describes about the capacity to generate a scientically acceptable string) on
selected “semantics” (i.e. its similar appealing structural characteristics or bioactivity). Recurring articial neural networks [145, 146] and transfers or learning by
reinforcement [147–149] were the primary underpinnings of these systems. Several
well-known deep learning-derived generated models for learning, such as variational autoencoders [150], generative networks of adversarial networks [151, 152],
as well as others that utilise graph the convolutions, have additionally been widely
published [153]. Recently, instances of conditioned productive approaches are
being offered. These methods employ more data to direct the design process, including molecular descriptor values [154], expression patterns [155], drug-likeness synthesisability, shape in three dimensions, and similarity to drugs. In this context, the

122
https://t.me/med1917
development of harmonious objectives that permit complex and constrained multiparameter optimisations, such as those employed in Pareto [156] or in desirabilitybased techniques [157], which are often required in the discovery of pharmaceuticals,
will provide a considerable challenge in the future.
Most of studies on deep learning-driven de novo synthesis thus far have concentrated on ligand-based approaches. With the reason of concentrating on orphaned
receptor and formerly unexplored macromolecules. These structure-based design
using generative algorithms offers an exciting additional study area [158]. For the
greatest extent of our knowledge, machine learning is still not substantially integrated into these methods, which typically utilise knowledge about the site where
the ligand binds (e.g. via fragment linkage or growing). The makeup and features of
the binding site were nevertheless taken into consideration in the early stages of
ligand design [159–161].
A. V. Geevarghese
3 Articial Intelligence-Based Design forAutomated
Drug Synthesising
The bulk of all known chemicals can be synthesised using a select few reliable techniques [162]. Chemistry still stands in the way of reliable, fully automatic synthesis
planning [163]. One of the reasons is the extensive chemical understanding required
for efcient forward and retrosynthetic planning [156]. Synthesis planning using AI
has a lengthy history in the eld of computer-aided retrosynthetic prediction, dating
back to the 1970s. The use of articial intelligence (AI) for organic synthesis has
experienced a comeback as a consequence of enhanced processing power, the emergence of big data, and the creation of novel deep neural networks and optimisation
techniques. Retrosynthesis, where the main objective is to repeatedly create efcient synthetic pathways for the target molecule, unquestionably benets from rulebased techniques. They attempt to identify retrosynthetic paths by storing
mechanisms for reaction and building skeletal structure. Their dependence on direct
chemical modications or reaction constitutes one of their key disadvantages.
Usually, these require human developing and curation. In recent years, methods
employed in the processing of natural languages, such sequence-to-sequence structures and transformers designs, have acted as motivation for this eld of study [164].
The reality that the order of arrangement of fragment in molecular biology matches
that of phrases in the English language provides an impetus for this area of research
[165]. Rule-free strategies often take into consideration outcomes in written representations (such as SMILES) and analyse them using an architecture consisting of
encoders and decoders in order to foresee the related synthetic precursor at an a step
response distance [166]. An improvement over this architecture is provided by
tiered articial neural networks [167], which divide the retrosynthesis predictions
issue into response type categorisation and response rule selection processes. A
molecular similarity approach that had previously been disclosed [168] and which

Explainable Articial Intelligence inDrug Discovery
https://t.me/med1917
123
has been demonstrated to give improved performance over earlier baselines for
comparison served as the impetus for the creation of this division. The bulk of the
previously discussed solutions concentrate on the linear one-step retrosynthesis
problem, however there is also a combinatorial opponent that is gaining ground.
One of the most signicant developments in the last 10years has been the effective exploration of chemically reactive spaces using advanced search techniques
like Monte Carlo Tree Search [163]. This development was sparked by improvements in reinforcement learning. One-step precursor predictions and the construction of hypergraphs, or directed acyclic graphs with edges that can link several
nodes at simultaneously, were employed in a recent study [165] to represent fake
pathways in an effort to better understand the reactants and reagents. While the
majority of the remedies described previously focus on the linear one-step retrosynthesis issue, an alternative scenario includes a combinatorial opposition that is rapidly expanding.
Despite the fact that such problems may be handled by using reaction data
already available, forward synthesis requires knowledge from reactions that produce no products at all. The databases now in use for chemical reactions are heavily
biased in favour of data on successful reactions [169]. There is a critical need for
further data, such as details on byproducts or experimental conditions (such solvent
and temperature). Some steps have been done to extend known reaction databases
with unfavourable reaction outcomes in an effort to get around some of these restrictions [170]. By doing this, new tailored data compilations for automated synthesis
planning have also been produced [171]. Earlier methods used are data-derived
reaction templates and ranking machine learning proof-of-concept response templates to rate candidate compounds [170, 171], once the information on reactants
and reagent had been given [172]. The objective of newer techniques is to rate compounds immediately by approaching the problem of chemical response predictions
as a graphical conversion job [173]. A different set of techniques opted to employ
rst-principle computations to evaluate the energy obstacles of a specic procedure,
prompted by advances in the eld of quantum mechanics.
For medium-to-large structures, this approach is physically impractical. This discrepancy might soon be bridged by quantum-mechanical articial intelligence’s
accurate estimations of energy and force [171]. The use of natural language processing techniques that utilise the transformers [172] or recurring neural networks architecture [173] are additionally gaining popularity with regard to template-free
forward synthesis predictions. A top-1 reactant precision over 90% was observed
documented for them. Some novel alternative deep learning algorithms [174, 175]
chose to represent reaction predictions as an electron rearrangement exercise in
addition to using message-passing neural networks to learn. The latter method,
however, lters out many pertinent organic processes because they cannot be clearly
identied as electron ows.

124
https://t.me/med1917
A. V. Geevarghese
4 Discussion
Given the variety of explanations and methods that may be used to complete a task
[176], current XAI also faces technological difculties. The majority of approaches
need to be customised for every application instead of being offered as “out-of-thebox” solutions which can be used instantly. In addition, in order to gure out which
model decisions require additional justications, what kinds of responds are important to the consumer and which ones are just simple or expected [177], an in-depth
comprehension of the issue area is essential. Human decision-making justications
produced by explainable articial intelligence must be complex, plausible, and usefully informative for the relevant scientic community. It is going to be essential to
explore further the benets and drawbacks when utilising traditional chemical language for expressing the range of choices of these models. Drawing on comprehensible “low level” chemical representations that are appropriate for algorithmic
learning and have direct meaning for chemists (such as SMILES strings [145, 178],
sequences of amino acids [179, 180], and different three-dimensional voxelised representations is an advance in the correct direction. Several recent studies utilise
established biochemical descriptors, that capture structural characteristics that are
predened a priori, such as hashed binary ngerprints [181, 182], topochemical and
geometric descriptors [183, 184]. Because they may be more readily articulated
using the well-known language of chemistry, molecular representations have a clear
inclination to be used when attempting to implement XAI.The interpretability of
the model is inuenced by both the specied machine learning approach and the
chemical description. In light of this, creating unique, understandable molecular
representations for machine learning will be an important area of research in the
years to come. The next step will also involve the creation of simple methods that
circumvent the problems posed by non-interpretable yet dense data descriptions by
making sufciently accurate forecasts and providing explanations that are comparable to those provided by people. Because there are currently no techniques that
incorporate all of the outlined desirable XAI features (transparency, justication,
informativeness, and uncertainty estimation), consensus (jury) techniques that combine the benets of various (X)AI approaches and boost model dependability will
be crucial in the short- to medium-term. In the long run, juror XAI techniques will
represent a means to offer numerous perspectives on the simulated biochemical
process by depending on various algorithms and chemical representations. The bulk
of machine learning drug discovery techniques now in use [185, 186] ignore applicability domain limits, or the region of the chemical space where statistical learning
assumptions are met. According to the author, these constraints ought to be considered an essential part of XAI as an accurate assessment of modelling accuracy has
been shown to be of greater signicance in making choices compared to the modelling method itself [187]. Knowing whether to employ a particular algorithm would
undoubtedly assist address the issue of deep learning models’ high condence in
incorrect predictions and prevent needless extrapolations simultaneously. The bulk
of machine learning drug discovery techniques now in use [185, 186] ignore

Explainable Articial Intelligence inDrug Discovery
https://t.me/med1917
applicability domain limits, or the region of the chemical space where statistical
learning assumptions are met. Knowing whether to employ a particular algorithm
would undoubtedly assist address the issue of deep learning models’ high condence in incorrect predictions and prevent needless extrapolations simultaneously.
In light of this, machine learning practitioners who work in time- and moneysensitive scenarios, such as drug discovery, have a responsibility to carefully examine and analyse the predictions resulting from their modelling decisions. There is
presently no open-community platform for XAI in the creation of pharmaceuticals,
with the aim of sharing and enhancing software, modelling interpretations, and
related training data through cooperative efforts of academics with varied scientic
backgrounds. The initial step in the right direction is being implemented by initiatives such MELLODDY (Machine Learning Ledger Orchestration for Drug
Discovery), that aims at creating federated, decentralised modelling for secure handling of information among pharmaceutical companies. Such collaborations ought
to promote the creation, verication, and adoption of XAI and the rationales these
tools offer.
125
5 Conclusion
Complete comprehension of models based on deep learning may be difcult in the
environment of therapeutic research, although the provided forecasts might still be
helpful to the researcher. It is going to be needed to meticulously organise an array
control examines to assess the machine-driven ideas and improve their reliability
and neutrality whereas aiming for interpretation that closely match the senses of
humans. Additionally, there is proof suggesting applications of articial intelligence
are starting to be utilised extensively in the eld of drug research and design cycle.
Considering signicant recent advances in the QSAR simulation, de novo molecular design etc., these techniques are now gradually coming to many of the community’s aspirations. Yet, it is yet to be seen how these approaches are going to be
successful in helping scientists develop and synthesise “more effective drugs
quickly.” Within the setting of predicting characteristics associated with ligands that
techniques depending upon relatively “raw” biochemical depictions, like neural networks using graphs and SMILES-based neural networks with recurrent neurons, are
expected to perform a minimum as well as descriptor-based models. These techniques also allow for better use of information, such as via multitask and Internetbased learning, and are readily applicable to a bigger category of chemical substances
and modelling tasks. On the contrary, conformation-aware machine learning is still
in its early stages, particularly when taking into consideration methods that include
three-dimensional symmetry into the design of the system. However, it is realistic to
expect swift progress in the application of them for the discovery of drugs as well as
associated elds like quantum physics or material research, especially as an alternative for rst-principle computations, that are substantially more challenging. Over
the last couple of decades, rules-based and rule-free approaches to de novo drug
Соседние файлы в папке Библиотека им академика М.И. Перельмана
