Computational Assessment of Chemical Saturation of Analogue Series under Varying Conditions

Abstract

Assessing the degree to which analogue series are chemically saturated is of major relevance in compound optimization. Decisions to continue or discontinue series are typically made on the basis of subjective judgment. Currently, only very few methods are available to aid in decision making. We further investigate and extend a computational concept to quantitatively assess the progression and chemical saturation of a series. To these ends, existing analogues and virtual candidates are compared in chemical space and compound neighborhoods are systematically analyzed. A large number of analogue series from different sources are studied, and alternative chemical space representations and virtual analogues of different designs are explored. Furthermore, evolving analogue series are distinguished computationally according to different saturation levels. Taken together, our findings provide a basis for practical applications of computational saturation analysis in compound optimization.

DeepCOMO: from structure-activity relationship diagnostics to generative molecular design using the compound optimization monitor methodology

“…As designed, these scores are robust and practically insensitive to the number of VAs that are used, provided VAs outnumber EAs by at least two to three times [ 2 – 4 ]. Furthermore, the choice of chemical reference spaces for compound distance calculations is variable and can be modified according to the characteristic features and requirements of specific optimization efforts.…”

“…This is the scientific context in which the Compound Optimization MOnitor (COMO) methodology evolved. One of the roots of COMO was the development of a scoring scheme to evaluate chemical saturation of compound series on the basis of biological screening data [ 1 , 2 ]. Modifying and extending this scoring scheme and combining it with the assessment of SAR progression then gave rise to the introduction of the COMO approach [ 3 – 5 ], which was originally designed as a diagnostic.…”

Finding Constellations in Chemical Space Through Core Analysis

“…Chemical space analysis of individual analog series has been carried out to measure progression in lead optimization and saturation of analog series (Kunimoto et al, 2018; Vogt et al, 2018; Yonchev et al, 2018). Nevertheless, the fact that assumption (iii) makes analog series inconsistent in as much as the scaffold definition is dependent on the dataset used (Bajorath, 2018) is a limitation for the exploration of chemical space of multiple analog series at once.…”

From SAR Diagnostics to Compound Design: Development Chronology of the Compound Optimization Monitor (COMO) Method

“…In light of this situation, the method development efforts discussed herein chart new territory. [6][7][8][9][10] They ultimately led to the compound optimization monitor (COMO) approach [9,10] that integrates chemical saturation and SAR diagnostics with the prediction of candidate compounds. The following discussion of the theory and scoring schemes is primarily tailored towards a computational audience.…”

“…A systematic investigation of analysis and scoring parameters revealed that saturation scores were essentially stable for feature spaces of different composition and VA populations covering a wide range. [7] Chemical saturation scoring was further refined and combined with another numerical scoring scheme accounting for SAR progression. [8] The basic principles underlying chemical saturation scoring discussed above were further extended as follows.…”