Browse
Submit Data
Databases
API
Help

Dataset Information

23 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Evidential Deep Learning for Guided Molecular Property Prediction and Discovery.

ABSTRACT: While neural networks achieve state-of-the-art performance for many molecular modeling and structure-property prediction tasks, these models can struggle with generalization to out-of-domain examples, exhibit poor sample efficiency, and produce uncalibrated predictions. In this paper, we leverage advances in evidential deep learning to demonstrate a new approach to uncertainty quantification for neural network-based molecular structure-property prediction at no additional computational cost. We develop both evidential 2D message passing neural networks and evidential 3D atomistic neural networks and apply these networks across a range of different tasks. We demonstrate that evidential uncertainties enable (1) calibrated predictions where uncertainty correlates with error, (2) sample-efficient training through uncertainty-guided active learning, and (3) improved experimental validation rates in a retrospective virtual screening campaign. Our results suggest that evidential deep learning can provide an efficient means of uncertainty quantification useful for molecular property prediction, discovery, and design tasks in the chemical and physical sciences.

SUBMITTER: Soleimany AP

PROVIDER: S-EPMC8393200 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Evidential meta-model for molecular property prediction.

Project description:MotivationThe usefulness of supervised molecular property prediction (MPP) is well-recognized in many applications. However, the insufficiency and the imbalance of labeled data make the learning problem difficult. Moreover, the reliability of the predictions is also a huddle in the deployment of MPP models in safety-critical fields.ResultsWe propose the Evidential Meta-model for Molecular Property Prediction (EM3P2) method that returns uncertainty estimates along with its predictions. Our EM3P2 trains an evidential graph isomorphism network classifier using multi-task molecular property datasets under the model-agnostic meta-learning (MAML) framework while addressing the problem of data imbalance.Our results showed better prediction performances compared to existing meta-MPP models. Furthermore, we showed that the uncertainty estimates returned by our EM3P2 can be used to reject uncertain predictions for applications that require higher confidence.Availability and implementationSource code available for download at https://github.com/Ajou-DILab/EM3P2.

| S-EPMC10597608 | biostudies-literature

Evidential deep learning for trustworthy prediction of enzyme commission number.

Project description:The rapid growth of uncharacterized enzymes and their functional diversity urge accurate and trustworthy computational functional annotation tools. However, current state-of-the-art models lack trustworthiness on the prediction of the multilabel classification problem with thousands of classes. Here, we demonstrate that a novel evidential deep learning model (named ECPICK) makes trustworthy predictions of enzyme commission (EC) numbers with data-driven domain-relevant evidence, which results in significantly enhanced predictive power and the capability to discover potential new motif sites. ECPICK learns complex sequential patterns of amino acids and their hierarchical structures from 20 million enzyme data. ECPICK identifies significant amino acids that contribute to the prediction without multiple sequence alignment. Our intensive assessment showed not only outstanding enhancement of predictive performance on the largest databases of Uniprot, Protein Data Bank (PDB) and Kyoto Encyclopedia of Genes and Genomes (KEGG), but also a capability to discover new motif sites in microorganisms. ECPICK is a reliable EC number prediction tool to identify protein functions of an increasing number of uncharacterized enzymes.

| S-EPMC10664415 | biostudies-literature

Molecular property prediction by contrastive learning with attention-guided positive sample selection.

Project description:MotivationPredicting molecular properties is one of the fundamental problems in drug design and discovery. In recent years, self-supervised learning (SSL) has shown its promising performance in image recognition, natural language processing, and single-cell data analysis. Contrastive learning (CL) is a typical SSL method used to learn the features of data so that the trained model can more effectively distinguish the data. One important issue of CL is how to select positive samples for each training example, which will significantly impact the performance of CL.ResultsIn this article, we propose a new method for molecular property prediction (MPP) by Contrastive Learning with Attention-guided Positive-sample Selection (CLAPS). First, we generate positive samples for each training example based on an attention-guided selection scheme. Second, we employ a Transformer encoder to extract latent feature vectors and compute the contrastive loss aiming to distinguish positive and negative sample pairs. Finally, we use the trained encoder for predicting molecular properties. Experiments on various benchmark datasets show that our approach outperforms the state-of-the-art (SOTA) methods in most cases.Availability and implementationThe code is publicly available at https://github.com/wangjx22/CLAPS.

| S-EPMC10188298 | biostudies-literature

A Deep Learning based Efficacy Prediction System for Drug Discovery

Project description:This SuperSeries is composed of the SubSeries listed below.

2023-03-31 | GSE165175 | GEO

A Deep Learning based Efficacy Prediction System for Drug Discovery [Trametinib]

Project description:Target protein-based drug and research compound discovery has been undeniably successful strategy in life science research, yet many diseases and biological processes lack obvious targets to enable these approaches. Here, to overcome this major challenge we have developed a deep-learning based efficacy prediction system (DLEPS) to identify potent agents to treat diverse diseases; DLEPS was trained using L1000 project chemical induced “changes of transcriptional profiles” (CTP) data as input. Strikingly, we found that the CTPs for previously unexamined molecules were precisely predicted (0.74 Pearson correlation coefficient). We used DLEPS to examine 4 disorders, and experimentally validated that perillen, chikusetsusaponin IV, trametinib, and liquiritin confer disease-relevant impacts against obesity, hyperuricemia, NASH, and COVID-19, respectively. Importantly, DLEPS also uncovered the biological insight that the MEK-ERK signaling pathway should be understood as a target for developing anti-NASH agents. Beyond illustrating that DLEPS is an effective tool for drug repurposing and development with diverse diseases (including those lacking targets), our study shows how diverse transcriptomics datasets can be harnessed to identify inhibitors and activator chemicals that can expand the scope of biological investigations well beyond mutant-bases analyses.

2023-03-31 | GSE165174 | GEO

A Deep Learning based Efficacy Prediction System for Drug Discovery [Perillen]

2023-03-31 | GSE165173 | GEO

Deep learning-guided discovery of a narrow-spectrum antibiotic against Acinetobacter baumannii

Project description:Acinetobacter baumannii is a nosocomial Gram-negative pathogen that often displays multidrug-resistance due to its robust outer membrane and its ability to acquire and retain extracellular DNA. Moreover, it can survive for prolonged durations on surfaces and is resistant to desiccation. Discovering new antibiotics against A. baumannii has proven challenging through conventional screening approaches. Fortunately, machine learning methods allow for the rapid exploration of chemical space, increasing the probability of discovering new chemical matter with antibacterial activity against this burdensome pathogen. Here, we screened ~7,500 molecules for those that inhibited the growth of A. baumannii in vitro. We trained a deep neural network with this growth inhibition dataset and performed predictions on the Drug Repurposing Hub for structurally novel molecules with activity against A. baumannii. Through this approach, we discovered abaucin, an antibacterial compound with narrow-spectrum activity against A. baumannii, which could overcome intrinsic and acquired resistance mechanisms in clinical isolates. Further investigations revealed that abaucin perturbs lipoprotein trafficking through a mechanism involving LolE, a functionally conserved protein that contributes to shuttling lipoproteins from the inner membrane to the outer membrane. Moreover, abaucin was able to control an A. baumannii infection in a murine wound model. Together, this work highlights the utility of machine learning in discovering new antibiotics and describes a promising lead with narrow-spectrum activity against a challenging Gram-negative pathogen.

2023-02-01 | GSE214305 | GEO

Molecular property prediction by semantic-invariant contrastive learning.

Project description:MotivationContrastive learning has been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, existing methods that generate molecular views by noise-adding operations for contrastive learning may face the semantic inconsistency problem, which leads to false positive pairs and consequently poor prediction performance.ResultsTo address this problem, in this article, we first propose a semantic-invariant view generation method by properly breaking molecular graphs into fragment pairs. Then, we develop a Fragment-based Semantic-Invariant Contrastive Learning (FraSICL) model based on this view generation method for molecular property prediction. The FraSICL model consists of two branches to generate representations of views for contrastive learning, meanwhile a multi-view fusion and an auxiliary similarity loss are introduced to make better use of the information contained in different fragment-pair views. Extensive experiments on various benchmark datasets show that with the least number of pre-training samples, FraSICL can achieve state-of-the-art performance, compared with major existing counterpart models.Availability and implementationThe code is publicly available at https://github.com/ZiqiaoZhang/FraSICL.

| S-EPMC10397537 | biostudies-literature

Attribute-guided prototype network for few-shot molecular property prediction.

Project description:The molecular property prediction (MPP) plays a crucial role in the drug discovery process, providing valuable insights for molecule evaluation and screening. Although deep learning has achieved numerous advances in this area, its success often depends on the availability of substantial labeled data. The few-shot MPP is a more challenging scenario, which aims to identify unseen property with only few available molecules. In this paper, we propose an attribute-guided prototype network (APN) to address the challenge. APN first introduces an molecular attribute extractor, which can not only extract three different types of fingerprint attributes (single fingerprint attributes, dual fingerprint attributes, triplet fingerprint attributes) by considering seven circular-based, five path-based, and two substructure-based fingerprints, but also automatically extract deep attributes from self-supervised learning methods. Furthermore, APN designs the Attribute-Guided Dual-channel Attention module to learn the relationship between the molecular graphs and attributes and refine the local and global representation of the molecules. Compared with existing works, APN leverages high-level human-defined attributes and helps the model to explicitly generalize knowledge in molecular graphs. Experiments on benchmark datasets show that APN can achieve state-of-the-art performance in most cases and demonstrate that the attributes are effective for improving few-shot MPP performance. In addition, the strong generalization ability of APN is verified by conducting experiments on data from different domains.

| S-EPMC11318080 | biostudies-literature

A Deep Learning based Efficacy Prediction System for Drug Discovery [Chikusetsusaponin IV]

2023-03-31 | GSE165171 | GEO