Deep learning model classifies drug effects based on structure and cell responses.
problem Limited ability to classify chemicals based on their modes of action.
method Integrative deep learning architecture combining molecular structures and cell responses.
result Improved classification performance, reducing error by 4.6%.
CoDrug uses KDE to create valid prediction sets for drug molecules under covariate shift.
problem Creating reliable uncertainty estimates for drug properties from computational models.
method CoDrug employs an energy-based model and KDE to assess and rectify distribution shift.
result CoDrug reduces the coverage gap by over 35% compared to non-adjusted conformal prediction sets.
This paper explores conformal prediction in the learning under privileged information (LUPI) paradigm. We use the SVM+ realization of LUPI in an inductive conformal predictor, and apply it to the MNIST benchmark dataset and three datasets in drug discovery. The results show that using privileged information produces va…
Designing a new drug is a lengthy and expensive process. As the space of potential molecules is very large (10^23-10^60), a common technique during drug discovery is to start from a molecule which already has some of the desired properties. An interdisciplinary team of scientists generates hypothesis about the required…
New method predicts drug side effects from combined use.
problem Predicting side effects from drug combinations.
method Multi-relational knowledge graph completion.
result State-of-the-art results on polypharmacy side effect prediction.
A neural network predicts drug interactions using attention mechanisms.
problem Predicting drug-drug interactions from massive combinations of drugs.
method Siamese self-attention multi-modal neural network integrating drug characteristics.
result The model achieves AUPR scores ranging from 0.77 to 0.92 on various benchmark datasets.
MoFlow generates chemically valid molecular graphs from latent representations.
problem Generating chemically valid molecular graphs from latent representations is challenging.
method MoFlow uses a flow-based approach with Glow for bond generation and a novel graph conditional flow for atom generation, ensuring chemical validity and efficiency.
result MoFlow achieves state-of-the-art performance in molecular graph generation and optimization.
Network medicine predicts repurposable drugs for COVID-19.
problem Identifying effective drugs for SARS-CoV-2 infections quickly.
method Artificial intelligence, network diffusion, and network proximity algorithms.
result A multimodal approach combining predictions from multiple algorithms outperforms individual methods.
Generative model designs drug combinations for improved efficacy and reduced side effects.
problem Designing effective drug combinations to overcome resistance and reduce side effects.
method Developed a deep generative model using HVGAE and a novel reward system.
result Network-principled drug combinations show reduced toxicity and potential for new strategies.
Researchers propose improved multivariate prediction models for HIV drug resistance.
problem Predicting drug resistances of HIV from mutation information.
method Revised stacking algorithms to borrow information among multiple prediction tasks.
result Proposed methods outperform other multivariate prediction methods.
Study repurposes open data to find potential COVID-19 drugs.
problem Developing effective treatments for COVID-19.
method Deep learning network-based approach using large scientific corpus.
result Identified 41 repurposable drugs for COVID-19.
Framework designs antiviral drugs using deep learning and RL.
problem Designing effective antiviral drugs for SARS-CoV-2.
method Deep learning framework with conditional molecular generator and RL.
result Framework generates more antiviral ligands than a VAE baseline.
HLTF generates chemically valid 3D molecules with improved topology control.
problem Generating chemically valid 3D molecules is challenging due to bond topology errors.
method HLTF uses a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures.
result HLTF achieves high validity and uniqueness on QM9 and GEOM-DRUGS datasets.
A key goal of computational personalized medicine is to systematically utilize genomic and other molecular features of samples to predict drug responses for a previously unseen sample. Such predictions are valuable for developing hypotheses for selecting therapies tailored for individual patients. This is especially va…
Benchmark proposes to assess molecule docking efficiency.
problem Lack of realistic benchmarks for measuring progress in drug design.
method Proposes a docking-based benchmark using SMINA software.
result Graph-based generative models fail to generate high-scoring molecules.
A new RL framework optimizes drug-like molecules synthetically.
problem Optimizing drug-like molecules for specific criteria.
method Deep Reinforcement Learning framework for chemical space optimization.
result Outperforms existing methods in pharmacological optimization.
The study compares Euclidean and cosine distances in medical drug prescription prediction.
problem Comparing Euclidean and cosine distances in medical drug prescription prediction.
method Established geometric properties and compared distances in real-world medical data.
result Different distances lead to different optimizing nonlinear kernel embedding frameworks.
GraphAF generates chemically valid molecules efficiently and accurately.
problem Generating chemically valid molecular structures while optimizing chemical properties.
method Flow-based autoregressive model combining autoregressive and flow-based approaches.
result GraphAF generates 68% chemically valid molecules without chemical knowledge rules and 100% with rules, achieving state-of-the-art performance.
GeneDisco benchmarks experimental design for drug discovery.
problem Vast experimental design space in drug discovery.
method Machine learning for optimal experimental design.
result Standardised benchmark suite for active learning.
In silico drug-target interaction (DTI) prediction is an important and challenging problem in biomedical research with a huge potential benefit to the pharmaceutical industry and patients. Most existing methods for DTI prediction including deep learning models generally have binary endpoints, which could be an oversimp…
Simpson's paradox can invalidate the results of medical trials if an unobserved variable is considered.
problem The validity of medical trial results can be invalidated by an unobserved confounding variable.
method Simulated controlled trials to demonstrate the paradox.
result The results of a trial can be reversed by including an unobserved confounding variable.
New methods predict drug interactions using drug co-medication patterns and graph matching.
problem Predicting adverse drug reactions from drug combinations.
method Developed novel kernels over drug combinations using support vector machines and graph matching to measure similarities.
result Achieved an AUC of 0.912 on a real-world dataset.
A new drug embedding method using hierarchical drug relations and chemical structures.
problem Learning accurate drug representations from chemical structures and hierarchies.
method Semi-supervised drug embedding using VAE in hyperbolic space.
result The method accurately places drugs in a hierarchy and predicts side-effects.
Study improves drug prediction accuracy for pharmacokinetic parameters.
problem Limited accuracy in predicting pharmacokinetic parameters.
method Integrated transfer learning and multitask learning approach.
result Improved model generalization and predictive ability.
VecMol generates 3D molecules as continuous vector fields, overcoming modality and geometry constraints.
problem Challenges in generating 3D molecules, especially in drug discovery and materials science.
method VecMol reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, parameterized by a neural field and generated using a latent diffusion model.
result Vector-field-based representations show promise for 3D molecular generation, validated on benchmarks.
New method predicts drug interactions from drug images.
problem Predicting drug interactions from molecular structures.
method Siamese neural network using drug structure images.
result First work predicting DDIs from drug images.
Graph-augmented CNN predicts drug interactions with high accuracy.
problem Predicting drug-drug interactions (DDIs) with high accuracy.
method Combining graph CNN with an attentive pooling network to extract structural relations between drug pairs.
result Desirable performance with ROC 0.988, F1-score 0.956, and AUPR 0.986.
Selecting the right drugs for the right patients is a primary goal of precision medicine. In this manuscript, we consider the problem of cancer drug selection in a learning-to-rank framework. We have formulated the cancer drug selection problem as to accurately predicting 1). the ranking positions of sensitive drugs an…
Currently, approximately 30% of epileptic patients treated with antiepileptic drugs (AEDs) remain resistant to treatment (known as refractory patients). This project seeks to understand the underlying similarities in refractory patients vs. other epileptic patients, identify features contributing to drug resistance acr…
Models predict drug interactions with high accuracy.
problem Detecting drug-drug interactions to prevent medical injuries.
method Artificial neural networks and graph similarity measures.
result Models achieve high accuracy in predicting drug interactions.
Deep Rule Forests identifies drug-drug and drug-disease interactions causing AKI.
problem Identifying drug-drug and drug-disease interactions leading to AKI.
method Deep Rule Forests (DRF) algorithm discovering rules from multilayer tree models.
result DRF model outperforms other algorithms in prediction accuracy and interpretability.
New molecular design model outperforms existing methods.
problem Designing valid, unique, and novel molecules.
method Adversarially Regularized Autoencoder (ARAE) combining latent variables from VAE and adversarial training from GAN.
result ARAE outperforms conventional models in validity, uniqueness, and novelty.
MolecularRNN generates realistic molecules with desired properties.
problem Designing new molecules with specific properties.
method Graph recurrent generative model with likelihood pretraining and policy gradient tuning.
result Significant distribution shift to desired ranges for lipophilicity, drug-likeness, and melting point.
Novel model predicts anticancer compound sensitivity with high accuracy and interpretability.
problem Predicting anticancer compound sensitivity with high accuracy and interpretability.
method Multimodal attention-based convolutional encoder using SMILES, gene expression profiles, and protein-protein interaction networks.
result The model significantly outperforms baseline models and demonstrates high interpretability.
The paper addresses selection bias in conformal prediction for focal units.
problem Selection bias in marginally valid conformal prediction intervals for focal units.
method A general framework for constructing selection-conditional coverage prediction sets.
result Efficient methods for various selection rules with exact finite-sample coverage.
CardiGraphormer uses SSL and GNNs to improve drug discovery.
problem Challenges in drug discovery due to combinatorial chemical space and limited approved drugs.
method Combines self-supervised learning, Graph Neural Networks, and Cardinality Preserving Attention.
result Enhanced predictive performance and interpretability in drug discovery.
Method learns drug-disease representations for repositioning opportunities.
problem Identifying new uses for existing drugs.
method Multi-relation unsupervised graph embedding model.
result Superior prediction performance in repositioning opportunities.
Text classification on drug SMILES strings yields competitive drug type classification results.
problem Classifying drug types using conventional text classification methods.
method Treated drug SMILES as sentences and applied basic NLP methods for classification.
result Competitive drug type classification results achieved.
We present the Network-based Biased Tree Ensembles (NetBiTE) method for drug sensitivity prediction and drug sensitivity biomarker identification in cancer using a combination of prior knowledge and gene expression data. Our devised method consists of a biased tree ensemble that is built according to a probabilistic bi…
Bi-GNN models drug interactions using a bi-level graph approach.
problem Predicting drug-drug interactions using machine learning.
method Bi-level graph neural networks that consider both interaction graph and representation graphs of drugs.
result Bi-GNN model improves DDI prediction accuracy compared to existing methods.
MuLFA predicts drug interactions more accurately than existing methods.
problem Improving drug safety by predicting drug interactions.
method Proposes MuLFA, a factorization autoencoder that models nonlinear interactions between drug pairs.
result MuLFA outperforms state-of-the-art methods in predicting drug interactions.
Computational Drug Repositioning (CDR) is the task of discovering potential new indications for existing drugs by mining large-scale heterogeneous drug-related data sources. Leveraging the patient-level temporal ordering information between numeric physiological measurements and various drug prescriptions provided in E…
Predict drug-drug side effects using co-attention neural network.
problem Early detection of polypharmacy side effects in drug combinations.
method Co-attention neural network architecture for DDI prediction.
result State-of-the-art results on predicting side effects from drug types and structures.
Optimizes latent space of VAEs using decoder uncertainty to generate valid objects.
problem Lack of robustness in optimizing VAE latent space for black-box properties.
method Importance sampling-based estimator of decoder epistemic uncertainty to guide optimization.
result Improves trade-off between black-box objective and validity of generated samples.
A new framework optimizes molecules using deep reinforcement learning.
problem Optimizing molecules while maintaining chemical validity and drug-likeness.
method Combining deep reinforcement learning with domain knowledge of chemistry, MolDQN directly modifies molecules.
result MolDQN achieves optimization of molecules without bias from pre-training datasets.
GENN predicts drug interactions by modeling correlations between link labels.
problem Predicting drug-drug interactions with consideration of link type correlations.
method GENN uses graph energy neural networks to model link type correlations in DDI prediction.
result GENN outperforms baseline models by 13.77% and 5.01% in PR-AUC on two real-world datasets.
Deep learning predicts synergistic drug combinations from multi-omics data.
problem Predicting effective drug combinations to overcome cancer drug resistance.
method AuDNNsynergy model integrating gene expression, copy number, genetic mutation data and drug properties.
result AuDNNsynergy model outperforms state-of-the-art approaches.
Dr.S recommends cancer drugs based on genomic data.
problem Personalizing cancer treatments using genomic information.
method Machine learning to identify optimal drug-gene associations.
result Developed a Drug Recommendation System (Dr.S) for cancer cell lines.