Local neighborhood behavior in a combinatorial library context

Horvath, Dragos; Koch, Christian J.; Schneider, Gisbert; Marcou, Gilles; Varnek, Alexandre

doi:10.1007/s10822-011-9416-2

Cited by 9 publications

(13 citation statements)

References 38 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept of molecular similarity is at the core of much of cheminformatics, on the simple grounds that structures that are more similar to each other tend to have more similar bioeffects, an elementary idea typically referred to as the "molecular similarity principle" (e.g., [98,[132][133][134]). Its particular importance commonly comes in circumstances where one has a "hit" in a bioassay and wishes to select from a library of Finally, here we show (using for clarity drugs and fluorophores only (Figure 20)) the closeness of chlorpromazine and prazosin in UMAP space when the NT-Xent temperature factor is 0.1.…”

Section: Discussionmentioning

confidence: 99%

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

Shrivastava

Kell

2021

Molecules

View full text Add to dashboard Cite

The question of molecular similarity is core in cheminformatics and is usually assessed via a pairwise comparison based on vectors of properties or molecular fingerprints. We recently exploited variational autoencoders to embed 6M molecules in a chemical space, such that their (Euclidean) distance within the latent space so formed could be assessed within the framework of the entire molecular set. However, the standard objective function used did not seek to manipulate the latent space so as to cluster the molecules based on any perceived similarity. Using a set of some 160,000 molecules of biological relevance, we here bring together three modern elements of deep learning to create a novel and disentangled latent space, viz transformers, contrastive learning, and an embedded autoencoder. The effective dimensionality of the latent space was varied such that clear separation of individual types of molecules could be observed within individual dimensions of the latent space. The capacity of the network was such that many dimensions were not populated at all. As before, we assessed the utility of the representation by comparing clozapine with its near neighbors, and we also did the same for various antibiotics related to flucloxacillin. Transformers, especially when as here coupled with contrastive learning, effectively provide one-shot learning and lead to a successful and disentangled representation of molecular latent spaces that at once uses the entire training set in their construction while allowing “similar” molecules to cluster together in an effective and interpretable way.

show abstract

Section: Discussionmentioning

confidence: 99%

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

Shrivastava

Kell

2021

Molecules

View full text Add to dashboard Cite

show abstract

“…A straightforward method to regroup compounds with nearly identical responsibilities is cell-based clustering in responsibility vector space, i.e., tessellating the responsibility vector space into a grid of cubic “cells” and assuming compound members of a same cell being representatives of a common responsibility pattern (RP). Thus, the RP of the compound can be instantly determined by rounding up its responsibility vector. Compounds that have common responsibility patterns are clustered together in the map and provide a basis to further analyze groups of related compounds.…”

Section: Materials and Methodsmentioning

confidence: 99%

Privileged Structural Motif Detection and Analysis Using Generative Topographic Maps

Kayastha

Horvath

Gilberg

et al. 2017

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Identification of "privileged structural motifs" associated with specific target families is of particular importance for designing novel bioactive compounds. Here, we demonstrate that they can be extracted from a data distribution represented on a two-dimensional map obtained by Generative Topographic Mapping (GTM). In GTM, structurally related molecules are grouped together on the map. Zones of the map preferentially populated by target-specific compounds were delineated, which helped to capture common substructures on the basis of which these compounds were grouped together by GTM. Such privileged structural motifs were identified across three major target superfamilies including proteases, kinases, and G protein coupled receptors. Traditionally, the search for privileged structural motifs focused on scaffolds, whereas motifs were detected here without prior knowledge of compound classification in GTMs. This alternative way of navigating medicinal chemistry space further extends the classical, scaffold-centric approach. Importantly, detected motifs might also comprise fuzzy sets of similar scaffolds, pharmacophore-like patterns, or, by contrast, well-defined scaffolds with specific substituent patterns.

show abstract

“…active). While there are better suited criteria [32,33] to specifically monitor neighborhood behavior compliance, herein the generally applicable ROC AUC criterion is used to score the potential predictive performance of the method, after ranking candidates in decreasing similarity order (Tanimoto scores) to the used query. Also, as an alternative to a simple similarity searching, similarity searching with data fusion is taken.…”

Section: Benchmarked Modelsmentioning

confidence: 99%

Multi-task generative topographic mapping in virtual screening

Lin

Horvath

Marcou

et al. 2019

J Comput Aided Mol Des

Self Cite

View full text Add to dashboard Cite

The previously reported procedure to generate "universal" Generative Topographic Maps (GTMs) of the drug-like chemical space is in practice a multi-task learning process, in which both operational GTM parameters (example: map grid size) and hyperparameters (key example: the molecular descriptor space to be used) are being chosen by an evolutionary process in order to fit/select "universal" GTM manifolds. After selection (a one-time task aimed at optimizing the compromise in terms of neighborhood behavior compliance, over a large pool of various biological targets), for any further use the manifolds are ready to provide "fit-free" predictive models. Using any structure-activity set-irrespectively whether the associated target served at map fitting stage or not-the generation or "coloring" a property landscape enables predicting the property for any external molecule, with zero additional fitable parameters involved. While previous works have signaled the excellent behavior of such models in aggressive threefold cross-validation assessments of their predictive power, the present work wished to explore their behavior in Virtual Screening (VS), here simulated on hand of external DUD ligand and decoy series that are fully disjoint from the ChEMBL-extracted landscape coloring sets. Beyond the rather robust results of the universal GTM manifolds in this challenge, it could be shown that the descriptor spaces selected by the evolutionary multi-task learner were intrinsically able to serve as an excellent support for many other VS procedures, starting from parameter-free similarity searching, to local (target-specific) GTM models, to parameter-rich, nonlinear Random Forest and Neural Network approaches.

show abstract

Local neighborhood behavior in a combinatorial library context

Cited by 9 publications

References 38 publications

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

Privileged Structural Motif Detection and Analysis Using Generative Topographic Maps

Multi-task generative topographic mapping in virtual screening

Contact Info

Product

Resources

About