Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

Meli, Rocco; Morris, Garrett M.; Biggin, Philip C.

doi:10.3389/fbinf.2022.885983

Cited by 68 publications

(71 citation statements)

References 383 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scoring of minimum-energy poses indicated that 3 had the best scoring pose with binding affinity measured using the Vina approach 32 of −8.433 kcal/mol, which was better than the parent compound (1, −7.5 kcal/mol) (Table 2). This was further supported by the improved Vinardo scoring function, 33,34 which held true even after local minimization of the top poses.…”

Section: Molecular Docking Of Ivacaftor Derivativesmentioning

confidence: 75%

Synthesis and Evaluation of Ivacaftor Derivatives with Reduced Lipophilicity

Iazzi,

Junor,

Doshi

et al. 2023

ACS Omega

View full text Add to dashboard Cite

Section: Molecular Docking Of Ivacaftor Derivativesmentioning

confidence: 75%

Synthesis and Evaluation of Ivacaftor Derivatives with Reduced Lipophilicity

Iazzi,

Junor,

Doshi

et al. 2023

ACS Omega

View full text Add to dashboard Cite

“…26 However, docking does not allow estimation of affinity. 48,49 The observation that cGMP inhibits ATPase activity of purified NKA only at supraphysiological concentrations makes it unlikely that the effects of cGMP on Na + reabsorption result from direct ATPase inhibition. However, dopamine and other hormones reduce Na + flux in RPTCs indirectly by NKA internalization.…”

Section: Discussionmentioning

confidence: 99%

Evidence That Binding of Cyclic GMP to the Extracellular Domain of NKA (Sodium-Potassium ATPase) Mediates Natriuresis

Kemp

Howell

Gildea

et al. 2023

Circulation Research

View full text Add to dashboard Cite

BACKGROUND: Extracellular renal interstitial cGMP inhibits renal proximal tubule (RPT) sodium (Na + ) reabsorption via Src (Src family kinase) activation. Through which target extracellular cGMP acts to induce natriuresis is unknown. We hypothesized that cGMP binds to the extracellular α1-subunit of NKA (sodium-potassium ATPase) on RPT basolateral membranes to inhibit Na + transport similar to ouabain—a cardiotonic steroid. METHODS AND RESULTS: Urine Na + excretion was measured in uninephrectomized 12-week-old female Sprague-Dawley rats that received renal interstitial infusions of vehicle (5% dextrose in water), cGMP (18, 36, and 72 μg/kg per minute; 30 minutes each), or cGMP+rostafuroxin (12 ng/kg per minute) or were subjected to pressure-natriuresis±rostafuroxin infusion. Rostafuroxin is a digitoxigenin derivative that displaces ouabain from NKA. Renal interstitial cGMP and raised renal perfusion pressure induced natriuresis and increased phosphorylated Src Tyr416 and Erk 1/2 (extracellular signal-regulated protein kinase 1/2) Thr202/Tyr204 ; these responses were abolished with rostafuroxin coinfusion. To assess cGMP binding to NKA, we performed competitive binding studies with isolated rat RPTs using bodipy-ouabain (2 μM)+cGMP (10 µM) or rostafuroxin (10 µM) and 8-biotin-11-cGMP (2 μM)+ouabain (10 μM) or rostafuroxin (10 µM). cGMP or rostafuroxin reduced bodipy-ouabain fluorescence intensity, and ouabain or rostafuroxin reduced 8-biotin-11-cGMP staining. We cross-linked isolated rat RPTs with 4-N 3 -PET-8-biotin-11-cGMP (2 μM); 8-N 3 -6-biotin-10-cAMP served as negative control. Precipitation with streptavidin beads followed by immunoblot analysis showed that RPTs after cross-linking with 4-N 3 -PET-8-biotin-11-cGMP exhibited a significantly stronger signal for NKA than non–cross-linked samples and cross-linked or non–cross-linked 8-N 3 -6-biotin-10-cAMP RPTs. Ouabain (10 μM) reduced NKA in cross-linked 4-N 3 -PET-8-biotin-11-cGMP RPTs confirming fluorescence staining. 4-N 3 -PET-8-biotin-11-cGMP cross-linked samples were separated by SDS gel electrophoresis and slices corresponding to NKA molecular weight excised and processed for mass spectrometry. NKA was the second most abundant protein with 50 unique NKA peptides covering 47% of amino acids in NKA. Molecular modeling demonstrated a potential cGMP docking site in the ouabain-binding pocket of NKA. CONCLUSIONS: cGMP can bind to NKA and thereby mediate natriuresis.

show abstract

“…31,32 Applications of more recently developed techniques such as gradient boosting, deep neural networks, and transformers to early-phase drug discovery have been very successful, including applications to molecular docking. [33][34][35][36] Here, we combined the CP framework with several state-of-the-art classification algorithms to develop a workflow for accelerated structure-based virtual screening. We demonstrate that our most efficient workflow identifies the topscoring compounds in ultralarge compound libraries and reduces the number of molecules to be explicitly docked by three orders of magnitude.…”

Section: Recent Breakthroughs In Artificial Intelligence Have Revived...mentioning

confidence: 99%

Rapid Traversal of Ultralarge Chemical Space using Machine Learning Guided Docking Screens

Luttens

Sparring

Norinder

et al. 2023

Preprint

View full text Add to dashboard Cite

The accelerating growth of make-on-demand chemical libraries provides novel opportunities to identify starting points for drug discovery with virtual screening. However, the recently released multi-billion-scale libraries are too challenging to screen even for the fastest structure-based docking methods. Here, we introduce a strategy that combines machine learning and molecular docking to enable rapid virtual screening of databases containing billions of compounds. In our workflow, a classification algorithm is first trained to identify top-scoring compounds based on molecular docking of one million compounds to the target protein. The conformal prediction framework is then used to make selections from the multi-billion-scale library, drastically reducing the number of compounds to be scored by the docking algorithm. The performance of the approach was benchmarked on a set of eight different target proteins, and classifiers based on gradient boosting, deep neural network, and transformer architectures were evaluated. The CatBoost classifier exhibited the optimal balance between speed and accuracy and was used to adapt the workflow for screens of ultralarge libraries. The optimized workflow was demonstrated to identify >90% of the very top-scoring molecules in a library with 0.2 billion compounds, which only required docking of 3-5% of this set. Application to a library with >3.5 billion compounds showed that molecules with substantially improved docking scores can be identified by machine learning, enabling efficient virtual screening of the largest commercial chemical libraries available. The accelerated virtual screening workflow has been made publicly available to facilitate exploration of vast chemical libraries for drug discovery.

show abstract

Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

Cited by 68 publications

References 383 publications

Synthesis and Evaluation of Ivacaftor Derivatives with Reduced Lipophilicity

Synthesis and Evaluation of Ivacaftor Derivatives with Reduced Lipophilicity

Evidence That Binding of Cyclic GMP to the Extracellular Domain of NKA (Sodium-Potassium ATPase) Mediates Natriuresis

Rapid Traversal of Ultralarge Chemical Space using Machine Learning Guided Docking Screens

Contact Info

Product

Resources

About