Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges

Nguyen, Duc Duy; Cang, Zixuan; Wu, Kedi; Wang, Menglun; Cao, Yin; Wei, Guo-Wei

doi:10.1007/s10822-018-0146-6

Cited by 128 publications

(106 citation statements)

References 66 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…Three submissions from the Evangelidis lab (D3R Receipt IDs: tdcvf, 2v4fk, be0m5) used variations of their DeepScaffOpt method, where an ensemble of deep neural networks was trained on CatS data from ChEMBL. Lastly, six of these submissions are from the Wei lab (D3R Receipt IDs: 0xvrb, 3c8nw, qb2s2, qi5ev, i0rbd, kohoc) and used variations of their topology-based deep learning methods where features were generated by algebraic graphs, differential geometry, and algebraic topology scores [35,[80][81][82][83][84].…”

Section: Analysis By Affinity Prediction Methodsologymentioning

confidence: 99%

D3R grand challenge 4: blind prediction of protein–ligand poses, affinity rankings, and relative binding free energies

parks

Gaieb

Chiu

et al. 2020

J Comput Aided Mol Des

101

View full text Add to dashboard Cite

The Drug Design Data Resource (D3R) aims to identify best practice methods for computer aided drug design through blinded ligand pose prediction and affinity challenges. Herein, we report on the results of Grand Challenge 4 (GC4). GC4 focused on proteins beta secretase 1 and Cathepsin S, and was run in an analogous manner to prior challenges. In Stage 1, participant ability to predict the pose and affinity of BACE1 ligands were assessed. Following the completion of Stage 1, all BACE1 co-crystal structures were released, and Stage 2 tested affinity rankings with co-crystal structures. We provide an analysis of the results and discuss insights into determined best practice methods.

show abstract

Section: Analysis By Affinity Prediction Methodsologymentioning

confidence: 99%

D3R grand challenge 4: blind prediction of protein–ligand poses, affinity rankings, and relative binding free energies

parks

Gaieb

Chiu

et al. 2020

J Comput Aided Mol Des

101

View full text Add to dashboard Cite

show abstract

“…The state-of-art results for drug design, especially protein-ligand binding affinity prediction, can be achieved using the topology-based models. 59,60 Recently, we have applied persistent homology in the analysis of ion aggregations and hydrogen-bonding networks. 87 Our model characterizes very well the two types of ion aggregation models, i.e., local clusters and extended ion networks.…”

mentioning

confidence: 99%

Persistent homology analysis of osmolyte molecular aggregation and their hydrogen-bonding networks

Xia

Anand

Saxena

et al. 2019

Phys. Chem. Chem. Phys.

View full text Add to dashboard Cite

Two types of osmolytes, i.e., trimethylamin N-oxide (TMAO) and urea, demonstrate dramatically different properties in a protein folding process. Even with the great progresses in revealing the potential underlying mechanism of these two osmolyte systems, many problems still remain unsolved. In this paper, we propose to use the persistent homology, a newly-invented topological method, to systematically study the osmolytes molecular aggregation and their hydrogen-bonding network from a global topological perspective. It has been found that, for the first time, TMAO and urea show two extremely different topological behaviors, i.e., extensive network and local cluster. In general, TMAO forms highly consistent large loop or circle structures in high concentrations. In contrast, urea is more tightly aggregated locally. Moreover, the resulting hydrogen-bonding networks also demonstrate distinguishable features. With the concentration increase, TMAO hydrogen-bonding networks vary greatly in their total number of loop structures and large-sized loop structures consistently increase. In contrast, urea hydrogen-bonding networks remain relatively stable with slight reduce of the total loop number. Moreover, the persistent entropy (PE) is, for the first time, used in characterization of the topological information of the aggregation and hydrogen-bonding networks. The average PE systematically increases with the concentration for both TMAO and urea, and decreases in their hydrogen-bonding networks. But their PE variances have totally different behaviors. Finally, topological features of the hydrogen-bonding networks are found to be highly consistent with those from the ion aggregation systems, indicating that our topological invariants can characterize intrinsic features of the "structure making" and "structure breaking" systems.Among the various small molecules that nature employs to cope with the osmotic stress, urea and trimethylamine N-oxide (TMAO) are two osmolytes that attract the most attention. Urea is highly active in a variety of biological processes in the human body as well as those of other mammals and organisms. Urea belongs to a class of compounds known as chaotropic denaturants, which unravel the tertiary structure of proteins by destabilizing internal, non-covalent bonds between atoms. One of the suggested mechanism of urea-induced protein denaturation process is through an indirect effect in which urea perturbs the water-network structure. 74 The local properties of water within solvation shell of urea molecule, have been investigated extensively, using both experimental 65, 71 and molecular dynamics methods. 5, 44 Dramatically different from urea, TMAO helps to not only stablize protein structure, but also fold intrinsically-disorder regions of proteins. 6,7,82 Even though TMAO has been employed to counteract deleterious effect of urea, 81 its stabilization mechanism still remains elusive. It has been proposed that the oxygen atom of TMAO can form strong H-bonds with urea, thus reducing and suppressing H-bon...

show abstract

“…GC3, our submissions achieved the top places in 10 out of 26 official contests. 27 These achievements have confirmed the predictive power and efficiency of our MathDL models in drug design and discovery. However, there were still some shortcomings existing in our previous approaches mostly concerning the pose generation performance and ability to rank affinities of compounds with diverse chemical structures.…”

Section: Introductionmentioning

confidence: 61%

“…Specifically, our prediction of the free energy set in Stage 2 was ranked the best in GC2 in our first participation of D3R competitions. 27 In our second participation, i.e. GC3, our submissions achieved the top places in 10 out of 26 official contests.…”

Section: Introductionmentioning

confidence: 91%

MathDL: mathematical deep learning for D3R Grand Challenge 4

Nguyen

Gao

Wang

et al. 2019

J Comput Aided Mol Des

Self Cite

View full text Add to dashboard Cite

We present the performances of our mathematical deep learning (MathDL) models for D3R Grand Challenge 4 (GC4). This challenge involves pose prediction, affinity ranking, and free energy estimation for beta secretase 1 (BACE) as well as affinity ranking and free energy estimation for Cathepsin S (CatS). We have developed advanced mathematics, namely differential geometry, algebraic graph, and/or algebraic topology, to accurately and efficiently encode high dimensional physical/chemical interactions into scalable low-dimensional rotational and translational invariant representations. These representations are integrated with deep learning models, such as generative adversarial networks (GAN) and convolutional neural networks (CNN) for pose prediction and energy evaluation, respectively. Overall, our MathDL models achieved the top place in pose prediction for BACE ligands in Stage 1a. Moreover, our submissions obtained the highest Spearman correlation coefficient on the affinity ranking of 460 CatS compounds, and the smallest centered root mean square error on the free energy set of 39 CatS molecules. It is worthy to mention that our method for docking pose predictions has significantly improved from our previous ones. * Corresponding to Guo-Wei Wei. The Drug Design Data Resource (D3R) offers blind communitywide challenges of ligand pose and binding affinity ranking predictions. 1-3 Benchmarks in D3R contests contain high quality structures and reliable binding energies supplied by experimental groups before the publication. These challenges provide computer-aided drug design (CADD) community a great opportunity to validate, calibrate, and develop drug virtual screening (VS) models. The latest D3R Grand Challenge 4 (GC4), took place from September 4th 2018 to December 4th, 2018. GC4 presented two different protein targets, Cathepsin S (CatS) and beta secretase 1 (BACE), which were generously supplied by Janssen Pharmaceuticals and Novartis, respectively. There were two stages in GC4. The first one has two subchallenges, namely Stage 1a and Stage 1b. In Stage 1a, participants were asked to predict the pose, rank the affinity, and estimate the free energy of BACE ligands. Following Stage 1a, Stage 1b revealed the receptor structures and participants were asked again to predict the crystallographic poses of 20 BACE ligands. There was no affinity calculation in this stage 1b. The second part of GC4 was called Stage 2 which contained the affinity rankings and free energy challenges for both BACE and CatS compounds. In this last stage, participants were able to take advantage of experimental structures of BACE complexes released right after stage 1b.A successful VS model requires a reliable ligand conformation generation and highly accurate scoring function to predict binding affinities. There are several state-of-the-art software packages to take care of the first component of VS, for example, Autodock Vina, 4 GOLD, 5 GLIDE, 6 ICM, 7 etc. Unfortunately, one may fail dramatically to achieve decent poses if blindly using t...

show abstract

Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges

Cited by 128 publications

References 66 publications

D3R grand challenge 4: blind prediction of protein–ligand poses, affinity rankings, and relative binding free energies

D3R grand challenge 4: blind prediction of protein–ligand poses, affinity rankings, and relative binding free energies

Persistent homology analysis of osmolyte molecular aggregation and their hydrogen-bonding networks

MathDL: mathematical deep learning for D3R Grand Challenge 4

Contact Info

Product

Resources

About