MoleculeNet: A Benchmark for Molecular Machine Learning

Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.; Gomes, Joseph; Geniesse, Caleb; Pappu, Aneesh; Leswing, Karl; Pande, Vijay S.

doi:10.48550/arxiv.1703.00564

Cited by 32 publications

(51 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some of these can be achieved by using all the physical, chemical and structural properties [31], which all together are rarely well documented so getting this information is considered cumbersome task. Over time, this has been tackled by using several alternative approaches that work well for specific problems [32,33,34,35,36,37]. However, obtaining robust representations of molecules for diverse machine learning problems is still a challenging task and any gold standard method that works consistently for all kind of problems is yet to be known.…”

Section: Data Generation and Molecular Representationmentioning

confidence: 99%

Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective

Joshi,

Kumar

2021

Preprint

View full text Add to dashboard Cite

Domain-aware machine learning (ML) models have been increasingly adopted for accelerating small molecule therapeutic design in the recent years. These models have been enabled by significant advancement in state-of-the-art artificial intelligence (AI) and computing infrastructures. Several ML architectures are predominantly and independently used either for predicting the properties of small molecules, or for generating lead therapeutic candidates. Synergetically using these individual components along with robust representation and data generation techniques autonomously in closed loops holds enormous promise for accelerated drug design which is a time consuming and expensive task otherwise. In this perspective, we present the most recent breakthrough achieved by each of the components, and how such autonomous AI and ML workflow can be realized to radically accelerate the hit identification and lead optimization. Taken together, this could significantly shorten the timeline for end-to-end antiviral discovery and optimization times to weeks upon the arrival of a novel zoonotic transmission event. Our perspective serves as a guide for researchers to practice autonomous molecular design in therapeutic discovery.

show abstract

Section: Data Generation and Molecular Representationmentioning

confidence: 99%

Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective

Joshi,

Kumar

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Following an identical approach as the original Chemception paper, [9] we obtained the Tox21, HIV, and Free-Solv datasets (Table 1) from the MoleculeNet benchmark database, [30] to evaluate the performance of Chemception for predicting toxicity, activity and solvation free energy respectively. These datasets comprise of a mix of large vs small datasets, physical vs non-physical properties and regression vs classification problems.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…The baseline model for comparison is the multilayer perceptron (MLP) deep neural network model (random data splitting) reported in the Molecu-leNet benchmark. [30]. In addition, we also compare to a novel convolutional graph algorithm (ConvGraph).…”

Section: Augchemception Performance Against Contemporary Modelsmentioning

confidence: 99%

How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?

Goh

Siegel

Vishnu

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

The meteoric rise of deep learning models in computer vision research, having achieved human-level accuracy in image recognition tasks is firm evidence of the impact of representation learning of deep neural networks. In the chemistry domain, recent advances have also led to the development of similar CNN models, such as Chemception, that is trained to predict chemical properties using images of molecular drawings. In this work, we investigate the effects of systematically removing and adding localized domain-specific information to the image channels of the training data. By augmenting images with only 3 additional basic information, and without introducing any architectural changes, we demonstrate that an augmented Chemception (AugChemception) outperforms the original model in the prediction of toxicity, activity, and solvation free energy. Then, by altering the information content in the images, and examining the resulting model's performance, we also identify two distinct learning patterns in predicting toxicity/activity as compared to solvation free energy. These patterns suggest that Chemception is learning about its tasks in the manner that is consistent with established knowledge. Thus, our work demonstrates that advanced chemical knowledge is not a pre-requisite for deep learning models to accurately predict complex chemical properties.

show abstract

“…60,[67][68][69][70][71][72] Since graph theory offers a nature representation of molecular structure, it is a common approach for analyzing chemical datasets 56,[73][74][75][76][77] and biomolecular datasets. 60,[78][79][80][81][82][83] Although there was much effort in constructing various graph representations in the past, graph based quantitative models are often less accurate than other competitive models in the analysis and prediction of biomolecular properties from massive and diverse datasets. Indeed, in the protein stability changes upon mutation analysis, the other models 23,52,84 are more accurate than the graph-based approach.…”

Section: Introductionmentioning

confidence: 99%

MathDL: mathematical deep learning for D3R Grand Challenge 4

Nguyen

Gao

Wang

et al. 2019

J Comput Aided Mol Des

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

MoleculeNet: A Benchmark for Molecular Machine Learning

Cited by 32 publications

References 9 publications

Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective

Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective

How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?

MathDL: mathematical deep learning for D3R Grand Challenge 4

Contact Info

Product

Resources

About