Linguistic measures of chemical diversity and the “keywords” of molecular collections

Woźniak, Michał; Wołos, Agnieszka; Modrzyk, Urszula; Górski, Rafał L.; Winkowski, Jan; Bajczyk, Michał D.; Szymkuć, Sara; Grzybowski, Bartosz A.; Eder, Maciej

doi:10.1038/s41598-018-25440-6

Cited by 25 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We experimented with k ranging between the values of 7-12 and there was no statistically significant difference in the prediction performance, therefore we chose 8 to be the character length similar to our previous work [30]. A recent study by [25] also showed that most of the maximum common substructures (MCS) in drugs had between 8 and 12 characters.…”

Section: Ligand Smiles (Ls)mentioning

confidence: 99%

“…We utilize the PROSITE database [24] to extract motifs and profiles that are associated with a biologically significant function and domain. Then, we benefit from a recent study that showed that maximum common substructures (MCS) of ligands constitute the actual words in the chemical space [25]. Approximately 100K MCS were used to extract a new set of words from the ligands.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DeepDTA: deep drug–target binding affinity prediction

2018

View full text Add to dashboard Cite

MotivationThe identification of novel drug–target (DT) interactions is a substantial part of the drug discovery process. Most of the computational methods that have been proposed to predict DT interactions have focused on binary classification, where the goal is to determine whether a DT pair interacts or not. However, protein–ligand interactions assume a continuum of binding strength values, also called binding affinity and predicting this value still remains a challenge. The increase in the affinity data available in DT knowledge-bases allows the use of advanced learning techniques such as deep learning architectures in the prediction of binding affinities. In this study, we propose a deep-learning based model that uses only sequence information of both targets and drugs to predict DT interaction binding affinities. The few studies that focus on DT binding affinity prediction use either 3D structures of protein–ligand complexes or 2D features of compounds. One novel approach used in this work is the modeling of protein sequences and compound 1D representations with convolutional neural networks (CNNs).ResultsThe results show that the proposed deep learning based model that uses the 1D representations of targets and drugs is an effective approach for drug target binding affinity prediction. The model in which high-level representations of a drug and a target are constructed via CNNs achieved the best Concordance Index (CI) performance in one of our larger benchmark datasets, outperforming the KronRLS algorithm and SimBoost, a state-of-the-art method for DT binding affinity prediction.Availability and implementation https://github.com/hkmztrk/DeepDTA Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Ligand Smiles (Ls)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

DeepDTA: deep drug–target binding affinity prediction

2018

View full text Add to dashboard Cite

show abstract

“…WideDTA [26] is an extension of DeepDTA [25] where drugs and proteins are represented as words, instead of characters as in DeepDTA. In particular, drugs are described via most common substructures, denoted as Ligand Maximum Common Substructures (LMCS) [39]; and proteins are represented through most conserved subse-quences, which are Protein Domain profiles or Motifs (PDM), retrieved from PROSITE database [30].…”

Section: Deep Learning (Deepdta and Widedta)mentioning

confidence: 99%

GraphDTA: Predicting drug–target binding affinity with graph neural networks

Nguyen

Quinn

et al. 2019

Preprint

146

250

View full text Add to dashboard Cite

Background: While the development of new drugs is costly, time consuming, and often accompanied with safety issues, drug repurposing, where old drugs with established safety are used for medical conditions other than originally developed, is an attractive alternative. Then, how the old drugs work on new targets becomes a crucial part of drug repurposing and gains much of interest. Several statistical and machine learning models have been proposed to estimate drug-target binding affinity and deep learning approaches have been shown to be among state-of-the-art methods. However, drugs and targets in these models have been commonly represented in 1D strings, regardless the fact that molecules are by nature formed by the chemical bonding of atoms. Method: In this work, we propose GraphDTA to capture the structural information of drugs, possibly enhancing the predictive power of the affinity. In particular, unlike competing methods, drugs are represented as graphs and graph convolutional networks are used to learn drug-target binding affinity. We trial our method on two benchmark datasets of drug-target binding affinity and compare the performance with state-of-the-art models in the research field. Results: The results show that our proposed method can not only predict the affinity better than non-deep learning models, but also outperform competing deep learning approaches. This demonstrates the practical advantages of graph-based representation for molecules in providing accurate prediction of drug-target binding affinity. The application may also include any recommendation systems where either or both of the user-and product-like sides can be represented in graphs. Availability and implementation: The proposed models are implemented in Python. Related data, pre-trained models, and source code are publicly available at https://github.com/thinng/GraphDTA.

show abstract

“…The same authors extended DeepDTA to WideDTA [ 152 ]. This time, instead of only considering the SMILES label encoding for the ligand, substructure information is also included where a list of the 100,000 most frequent maximum common substructures defined by Woźniak et al [ 159 ] are used. For the protein description, approximately 500 motifs and domains are extracted from the PROSITE database [ 160 ] and label encoded.…”

Section: Recent Developmentsmentioning

confidence: 99%

Deep Learning in Virtual Screening: Recent Applications and Developments

Kimber

Chen

Volkamer

2021

IJMS

136

View full text Add to dashboard Cite

Drug discovery is a cost and time-intensive process that is often assisted by computational methods, such as virtual screening, to speed up and guide the design of new compounds. For many years, machine learning methods have been successfully applied in the context of computer-aided drug discovery. Recently, thanks to the rise of novel technologies as well as the increasing amount of available chemical and bioactivity data, deep learning has gained a tremendous impact in rational active compound discovery. Herein, recent applications and developments of machine learning, with a focus on deep learning, in virtual screening for active compound design are reviewed. This includes introducing different compound and protein encodings, deep learning techniques as well as frequently used bioactivity and benchmark data sets for model training and testing. Finally, the present state-of-the-art, including the current challenges and emerging problems, are examined and discussed.

show abstract

Linguistic measures of chemical diversity and the “keywords” of molecular collections

Cited by 25 publications

References 30 publications

DeepDTA: deep drug–target binding affinity prediction

DeepDTA: deep drug–target binding affinity prediction

GraphDTA: Predicting drug–target binding affinity with graph neural networks

Deep Learning in Virtual Screening: Recent Applications and Developments

Contact Info

Product

Resources

About