graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

Karlov, Dmitry S.; Sosnin, Sergey; Fedorov, Maxim V.; Popov, Petr

doi:10.1021/acsomega.9b04162

Cited by 71 publications

(66 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Li et al [45] 2020 C: SMILES CSG P: AA seq BLOSUM62 matrix A multi-objective neural network to predict non-covalent interactions and binding affinites. Karlov et al [96] 2020 co-complex structure 3D grid representation map An MPNN framework for learning protein–ligand complex features and predicting binding affinity. C: Compound, P: Protein, CSG: Chemical Structure Graph, SPS: SSPro/ACCPro.…”

Section: Discussionmentioning

confidence: 99%

“…One limitation of GCN is that GCN considers local neighboring nodes only and has difficulty in reflecting the global 3D structure and edge information. To overcome the limitation, Karlov et al [96] used MPNN to embed drug compounds by considering both nodes and edges. In a recent study, ensembles of DL methods were used for CPI prediction Li et al [45] .…”

Section: Ai Methods For Cpi Predictionmentioning

confidence: 99%

See 1 more Smart Citation

A review on compound-protein interaction prediction methods: Data, format, representation and model

Lim

Cho

et al. 2021

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

There has recently been a rapid progress in computational methods for determining protein targets of small molecule drugs, which will be termed as compound protein interaction (CPI). In this review, we comprehensively review topics related to computational prediction of CPI. Data for CPI has been accumulated and curated significantly both in quantity and quality. Computational methods have become powerful ever to analyze such complex the data. Thus, recent successes in the improved quality of CPI prediction are due to use of both sophisticated computational techniques and higher quality information in the databases. The goal of this article is to provide reviews of topics related to CPI, such as data, format, representation, to computational models, so that researchers can take full advantages of these resources to develop novel prediction methods. Chemical compounds and protein data from various resources were discussed in terms of data formats and encoding schemes. For the CPI methods, we grouped prediction methods into five categories from traditional machine learning techniques to state-of-the-art deep learning techniques. In closing, we discussed emerging machine learning topics to help both experimental and computational scientists leverage the current knowledge and strategies to develop more powerful and accurate CPI prediction methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Ai Methods For Cpi Predictionmentioning

confidence: 99%

A review on compound-protein interaction prediction methods: Data, format, representation and model

Lim

Cho

et al. 2021

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

show abstract

“…Furthermore, to identify tool compounds to elucidate pharmacological actions, quantitative predictions will be more helpful than qualitative predictions. To this end, lines of reports have constructed various regression models using chemical representations in conjunction with information on their targets, such as three-dimensional compound-protein complex information 13 , amino acid sequence information [14][15][16] , assay information for target proteins 17,18 , and information on the atoms from the amino acid in the vicinity of the binding site of a compound 19,20 .…”

Section: Prediction Of Pharmacological Activities From Chemical Strucmentioning

confidence: 99%

Prediction of pharmacological activities from chemical structures with graph convolutional neural networks

Sakai

Nagayasu

Shibui

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Many therapeutic drugs are compounds that can be represented by simple chemical structures, which contain important determinants of affinity at the site of action. Recently, graph convolutional neural network (GCN) models have exhibited excellent results in classifying the activity of such compounds. For models that make quantitative predictions of activity, more complex information has been utilized, such as the three-dimensional structures of compounds and the amino acid sequences of their respective target proteins. As another approach, we hypothesized that if sufficient experimental data were available and there were enough nodes in hidden layers, a simple compound representation would quantitatively predict activity with satisfactory accuracy. In this study, we report that GCN models constructed solely from the two-dimensional structural information of compounds demonstrated a high degree of activity predictability against 127 diverse targets from the ChEMBL database. Using the information entropy as a metric, we also show that the structural diversity had less effect on the prediction performance. Finally, we report that virtual screening using the constructed model identified a new serotonin transporter inhibitor with activity comparable to that of a marketed drug in vitro and exhibited antidepressant effects in behavioural studies.

show abstract

“…For instance, other self-supervised and unsupervised learning algorithms such as Principal Component Analysis, t-Distributed Stochastic Neighbor Embedding, and Variational Autoencoders can be used to reveal significant feature-based influences on binding affinity [60][61][62][63]. Analyzing the relationship between features instead of just independent features' influence can also reveal significant chemical phenomena that influence binding affinity [64,65].…”

Section: Limitations and Future Workmentioning

confidence: 99%

Self-Supervised Machine Learning Approach for Identifying Biochemical Influences on Protein-Ligand Binding Affinity

Singh¹

2021

Preprint

View full text Add to dashboard Cite

Drug discovery is incredibly time-consuming and expensive, averaging over 10 years and $985 million per drug. Calculating the binding affinity between a target protein and a ligand is critical for discovering viable drugs. Although supervised machine learning (ML) models can predict binding affinity accurately, they suffer from lack of interpretability and inaccurate feature selection caused by multicollinear data. This study used self-supervised ML to reveal underlying protein-ligand characteristics that strongly influence binding affinity. Protein-ligand 3D models were collected from the PDBBind database and vectorized into 2422 features per complex. LASSO Regression and hierarchical clustering were utilized to minimize multicollinearity between features. Correlation analyses and Autoencoder-based latent space representations were generated to identify features significantly influencing binding affinity. A Generative Adversarial Network was used to simulate ligands with certain counts of a significant feature, and thereby determine the effect of a feature on improving binding affinity with a given target protein. It was found that the CC and CCCN fragment counts in the ligand notably influence binding affinity. Re-pairing proteins with simulated ligands that had higher CC and CCCN fragment counts could increase binding affinity by 34.99-37.62% and 36.83%-36.94%, respectively. This discovery contributes to a more accurate representation of ligand chemistry that can increase the accuracy, explainability, and generalizability of ML models so that they can more reliably identify novel drug candidates. Directions for future work include integrating knowledge on ligand fragments into supervised ML models, examining the effect of CC and CCCN fragments on fragment-based drug design, and employing computational techniques to elucidate the chemical activity of these fragments.

show abstract

graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

Cited by 71 publications

References 59 publications

A review on compound-protein interaction prediction methods: Data, format, representation and model

A review on compound-protein interaction prediction methods: Data, format, representation and model

Prediction of pharmacological activities from chemical structures with graph convolutional neural networks

Self-Supervised Machine Learning Approach for Identifying Biochemical Influences on Protein-Ligand Binding Affinity

Contact Info

Product

Resources

About