CASTER: Predicting Drug Interactions with Chemical Substructure Representation

Huang, Kexin; Xiao, Cao; Hoang, Trong Nghia; Glass, Lucas M.; Sun, Jimeng

doi:10.1609/aaai.v34i01.5412

Cited by 105 publications

(73 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature Extractor. The molecular substructure is an important cue for molecular interactions [21,22]. Therefore, the key idea behind Mol-BERT is that we strengthen to obtain a better representation of molecular substructures by pretraining BERT on the vast unlabeled SMILES sequences.…”

Section: Methodsmentioning

confidence: 99%

“…And SMILES-BERT was proposed to pretrain the model through a masked SMILES recovery task by designing attention mechanism-based transformer layer [20]. These pretrained methods pay more attention to the contextual information of molecular sequences, but they hardly consider some molecular substructure (i.e., functional groups) that essentially contributes to the molecular property [21,22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mol‐BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

Jiang

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Molecular property prediction is an essential task in drug discovery. Most computational approaches with deep learning techniques either focus on designing novel molecular representation or combining with some advanced models together. However, researchers pay fewer attention to the potential benefits in massive unlabeled molecular data (e.g., ZINC). This task becomes increasingly challenging owing to the limitation of the scale of labeled data. Motivated by the recent advancements of pretrained models in natural language processing, the drug molecule can be naturally viewed as language to some extent. In this paper, we investigate how to develop the pretrained model BERT to extract useful molecular substructure information for molecular property prediction. We present a novel end-to-end deep learning framework, named Mol-BERT, that combines an effective molecular representation with pretrained BERT model tailored for molecular property prediction. Specifically, a large-scale prediction BERT model is pretrained to generate the embedding of molecular substructures, by using four million unlabeled drug SMILES (i.e., ZINC 15 and ChEMBL 27). Then, the pretrained BERT model can be fine-tuned on various molecular property prediction tasks. To examine the performance of our proposed Mol-BERT, we conduct several experiments on 4 widely used molecular datasets. In comparison to the traditional and state-of-the-art baselines, the results illustrate that our proposed Mol-BERT can outperform the current sequence-based methods and achieve at least 2% improvement on ROC-AUC score on Tox21, SIDER, and ClinTox dataset.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Mol‐BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

Jiang

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Sequence-based methods One research line is to formulate molecular generation as a sequence based problem (Dai et al 2018;Kusner, Paige, and Hernández-Lobato 2017;Zhou et al 2017;Gómez-Bombarelli et al 2018;Hong et al 2019;Huang et al 2020). Most of these methods are based on the simplified molecular-input line-entry system (SMILES), a line notation describing the molecular structure using short ASCII strings (Weininger 1988).…”

Section: Related Workmentioning

confidence: 99%

CORE: Automatic Molecule Optimization Using Copy & Refine Strategy

Xiao

Sun

2020

AAAI

Self Cite

View full text Add to dashboard Cite

Molecule optimization is about generating molecule Y with more desirable properties based on an input molecule X. The state-of-the-art approaches partition the molecules into a large set of substructures S and grow the new molecule structure by iteratively predicting which substructure from S to add. However, since the set of available substructures S is large, such an iterative prediction task is often inaccurate especially for substructures that are infrequent in the training data. To address this challenge, we propose a new generating strategy called “Copy&Refine” (CORE), where at each step the generator first decides whether to copy an existing substructure from input X or to generate a new substructure, then the most promising substructure will be added to the new molecule. Combining together with scaffolding tree generation and adversarial training, CORE can significantly improve several latest molecule optimization methods in various measures including drug likeness (QED), dopamine receptor (DRD2) and penalized LogP. We tested CORE and baselines using the ZINC database and CORE obtained up to 11% and 21% relatively improvement over the baselines on success rate on the complete test set and the subset with infrequent substructures, respectively.

show abstract

“…Last, the related task of predicting interactions of two drugs [121] or synergistic effects of anticancer drug combinations has been addressed with deep networks [122][123][124]. One model is available via a web service [122], and others investigated polypharmacy side effects with GCNs [125].…”

Section: Feature Selectionmentioning

confidence: 99%

Trends in Deep Learning for Property-driven Drug Design

Born

Manica

2021

CMC

View full text Add to dashboard Cite

: It is more pressing than ever to reduce the time and costs for developing lead compounds in the pharmaceutical industry. The co-occurrence of advances in high-throughput screening and the rise of deep learning (DL) have enabled the development of large-scale multimodal predictive models for virtual drug screening. Recently, deep generative models have emerged as a powerful tool for exploring the chemical space and raising hopes to expedite the drug discovery process. Following this progress in chemocentric approaches for generative chemistry, the next challenge is to build multimodal conditional generative models that leverage disparate knowledge sources when biochemical mapping properties to target structures. Here, we call the community to bridge drug discovery more closely with systems biology when designing deep generative models. Complementing the plethora of reviews on the role of DL in chemoinformatics, we herein specifically focus on the interface of predictive and generative modeling for drug discovery. Through a systematic publication keyword search on PubMed and a selection of preprint servers (arXiv, biorXiv, chemRxiv, and medRxiv), we quantify trends in the field and find that molecular graphs and VAEs have become the most widely adopted molecular representations and architectures in generative models, respectively. We discuss progress on DL for toxicity, drug-target affinity, and drug sensitivity prediction and specifically focus on conditional molecular generative models that encompass multimodal prediction models. Moreover, we outline prospects in the field and identify challenges such as the integration of deep learning systems into experimental workflows in a closed-loop manner or the adoption of federated machine learning techniques to overcome data sharing barriers. Other challenges include, but are not limited to interpretability in generative models, more sophisticated metrics for the evaluation of molecular generative models, and, following up on that, community-accepted benchmarks for both multimodal drug property prediction and property-driven molecular design.

show abstract

CASTER: Predicting Drug Interactions with Chemical Substructure Representation

Cited by 105 publications

References 21 publications

Mol‐BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

Mol‐BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

CORE: Automatic Molecule Optimization Using Copy & Refine Strategy

Trends in Deep Learning for Property-driven Drug Design

Contact Info

Product

Resources

About