Large-Scale Comparison of Alternative Similarity Search Strategies with Varying Chemical Information Contents

Laufkötter, Oliver; Miyao, Tomoyuki; Bajorath, Jürgen

doi:10.1021/acsomega.9b02470

Cited by 9 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In contrast, long FPs cause compute performance and storage issues and may produce overfitted ML models, a problem known as the curse of dimensionality . Several authors explored different MFP and IFP lengths; ,,,,− however, there is no single consensus on length, as results vary with the problem and data sets.…”

Section: Discussionmentioning

confidence: 99%

Prioritizing Virtual Screening with Interpretable Interaction Fingerprints

Fassio

Shub

Ponzoni

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Machine learning-based drug discovery success depends on molecular representation. Yet traditional molecular fingerprints omit both the protein and pointers back to structural information that would enable better model interpretability. Therefore, we propose LUNA, a Python 3 toolkit that calculates and encodes protein–ligand interactions into new hashed fingerprints inspired by Extended Connectivity FingerPrint (ECFP): EIFP (Extended Interaction FingerPrint), FIFP (Functional Interaction FingerPrint), and Hybrid Interaction FingerPrint (HIFP). LUNA also provides visual strategies to make the fingerprints interpretable. We performed three major experiments exploring the fingerprints’ use. First, we trained machine learning models to reproduce DOCK3.7 scores using 1 million docked Dopamine D4 complexes. We found that EIFP-4,096 performed (R 2 = 0.61) superior to related molecular and interaction fingerprints. Second, we used LUNA to support interpretable machine learning models. Finally, we demonstrate that interaction fingerprints can accurately identify similarities across molecular complexes that other fingerprints overlook. Hence, we envision LUNA and its interface fingerprints as promising methods for machine learning-based virtual screening campaigns. LUNA is freely available at .

show abstract

Section: Discussionmentioning

confidence: 99%

Prioritizing Virtual Screening with Interpretable Interaction Fingerprints

Fassio

Shub

Ponzoni

et al. 2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…A 2D similarity-based virtual screening [ 53 , 54 ] was performed on the SwissSimilarity web tool [ 55 ], enabling ligand-based virtual screening of several libraries of small molecules using different approaches. The search was carried out in 31 databases [ 55 ].…”

Section: Aterial and Methodsmentioning

confidence: 99%

SMILES-based 2D-QSAR and similarity search for identification of potential new scaffolds for development of SARS-CoV-2 MPRO inhibitors

2022

View full text Add to dashboard Cite

COVID-19, whose etiological agent is the SARS-CoV-2 virus, has caused over 537.5 million cases and killed over 6.3 million people since its discovery in 2019. Despite the recent development of the first drugs indicated for treating people already infected, the great need to develop new anti-SARS-CoV-2 drugs still exists, mainly due to the possible emergence of new variants of this virus and resistant strains of the current variants. Thus, this work presents the results of QSAR and similarity search studies based only on 2D structures from a set of 32 bicycloproline derivatives, aiming to quickly, reproducibly, and reliably identify potentially useful compounds as scaffolds of new major protease inhibitors (M pro ) of the virus. The obtained QSAR model is based only on topological molecular descriptors. The model has good internal and external statistics, is robust, and does not present a chance correlation. This model was used as one of the tools to support the virtual screening stage carried out in the SwissADME web tool. Five molecules, from an initial set of 2695 molecules, proved to be the most promising, as they were within the model’s applicability domain and linearity range, with low potential to cause carcinogenic, teratogenic, and reproductive toxicity effects and promising pharmacokinetic properties. These five compounds were then selected as the most competent to generate, in future studies, new anti-SARS-CoV-2 agents with drug-likeness properties suitable for use in therapy.

show abstract

“…Usually, researchers may want to search for molecules or materials with similar properties in applications like discovering new drugs or cheaper materials [4][5][6] . Many similarity search methods have been developed for this purpose 7,8 . In general, a similarity search approach consists of three essential components: a molecular representation method, a quantitative metric to measure the similarity of two molecules, and a search algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…[4][5][6] Many similarity search methods have been developed for this purpose. 7,8 In general, a similarity search approach consists of three essential components: a molecular representation method, a quantitative metric to measure the similarity of two molecules, and a search algorithm. The search process usually starts with one or more query molecules (e.g., congurations that have desired properties).…”

Section: Introductionmentioning

confidence: 99%