Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

6.3%12.5%18.8%25.0% · Apr 199419922001200920182026
48 results for de novo drug design

ReLeaSE uses deep reinforcement learning to design novel molecules.

problem Designing molecules with specific properties.
method ReLeaSE integrates generative and predictive deep neural networks trained separately but jointly to generate novel chemical structures.
result ReLeaSE can generate chemical libraries with desired properties.

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.

DOCKSTRING simplifies docking simulations for better drug design benchmarks.

problem Lack of meaningful benchmarks for ligand design.
method Open-source Python package for docking scores, extensive dataset, and pharmaceutically-relevant tasks.
result Docking scores are more appropriate benchmarks than simple physicochemical properties.

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.

New method designs antimicrobial peptides with high potency and low toxicity.

problem Designing potent antimicrobial drugs with low toxicity.
method CLaSS method using deep generative autoencoder and atomistic simulations.
result Design and synthesis of two novel AMPs with high potency and low toxicity.

Advanced GNNs improve molecular generation models.

problem Generating complete graphs with multiple nodes and edges based on labels.
method Replaced standard GNNs with more expressive GNNs in autoregressive and one-shot generation models.
result Advanced GNNs can improve performance of graph generative models, but expressiveness is not a necessity.

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.

A new metric assesses generative models for molecules in drug design.

problem Difficulty in evaluating generative models for molecules.
method Fréchet ChemNet Distance (FCD) using a deep neural network trained to predict drug activities.
result FCD detects diversity and similarity of generated molecules to real ones.

This work improves molecular design by efficiently selecting diverse candidate molecules.

problem Designing molecules that satisfy multiple conflicting objectives.
method A modular 'generate-then-optimize' framework using generative models and a novel acquisition function.
result Significant improvements in sample efficiency across synthetic and application-driven tasks.

DeepNovoV2 improves de novo peptide sequencing from mass spectrometry data.

problem De novo peptide sequencing from mass spectrometry data for personalized cancer vaccines.
method DeepNovoV2 combines T-Net and recurrent neural networks for end-to-end training and prediction.
result DeepNovoV2 achieves 13.01-23.95\% higher accuracy than previous methods.

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.

Heteroencoders improve chemical latent space diversity and molecular generation.

problem Improving chemical latent space properties and diversity in autoencoders.
method Employing SMILES enumeration for encoder or decoder, training RNNs with LSTM, and using QSAR models.
result Heteroencoders yield more diverse latent spaces and better molecular generation.

Few-step protein backbone generators reduce sampling time by over 20x.

problem Computational bottleneck in diffusion-based protein generation models.
method Score distillation adapted for protein backbone generation, combined with inference time noise modulation.
result Significant reduction in sampling time (20+ fold) while maintaining comparable performance.

ALMGIG uses adversarial learning to generate and infer novel molecules efficiently.

problem Efficiently generating and inferring novel molecules using graph representations.
method Adversarial learning framework that avoids explicit graph isomorphism, using cycle-consistency loss and multi-graph Graph Isomorphism Network.
result ALMGIG more accurately learns the distribution over the space of molecules and efficiently searches the molecular space.

SDF-Bayes finds safe drug combinations safely, balancing optimism and caution.

problem Finding safe drug combinations in clinical trials with multiple drugs and patient heterogeneity.
method SDF-Bayes uses Bayesian statistics to choose the most likely MTD while ensuring safety constraints.
result SDF-Bayes outperforms existing methods in both accuracy and safety for drug combination trials.

New models suggest molecules that are often unfeasible to synthesize.

problem Models suggest molecules that are difficult to synthesize.
method Used a computer-aided synthesis planning program to analyze synthesizability of molecules generated by state-of-the-art models.
result State-of-the-art models generate molecules that are often unfeasible to synthesize.

Novel RL approach for molecular design using quantum mechanics.

problem Existing RL methods for molecular design are limited in scope and reward function.
method Formulation in Cartesian coordinates, direct use of quantum mechanics for reward function, translation and rotation invariant state-action space.
result Agent efficiently learns to solve molecular design tasks from scratch.

CF-GPS learns policies from logged data by considering counterfactual outcomes.

problem Learning policies from limited real experience in complex environments.
method Assumes logged real experience and models counterfactual outcomes. Uses structural causal models for evaluation.
result Improves policy evaluation and search results on a grid-world task.

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.

Bayesian methods improve drug discovery experiment design.

problem Optimizing drug screening experiments in high-dimensional data.
method Bayesian inference and optimisation with upper confidence bound algorithms, Thompson sampling, and sparse tree search.
result Sparse tree search techniques outperform other methods in drug toxicity screening.

DESMILES uses deep learning to improve drug discovery by optimizing molecule properties.

problem Improving the efficiency and accuracy of drug discovery through better molecular design.
method DESMILES is a deep neural network model that optimizes molecular properties for drug discovery.
result DESMILES achieved a 77% lower failure rate in modifying molecules to inhibit the dopamine receptor D2 compared to state-of-the-art models.

Unified model learns from proteins and ligands for drug design.

problem Disjoint data sources and modeling assumptions limit joint use of structure- and ligand-based drug design.
method Contrastive Geometric Learning for Unified Computational Drug Design (ConGLUDe)
result Unified model achieves competitive zero-shot virtual screening performance and state-of-the-art ligand-conditioned pocket selection.

NucleusDiff models atomic nuclei interactions to prevent separation violations in drug design.

problem Maintaining minimum pairwise distance between atoms to avoid separation violations in drug design.
method Enforces distance constraint between atomic nuclei and manifolds in a diffusion model.
result Reduces separation violations by up to 100.00% and enhances binding affinity by up to 22.16%.

Generative model tailors anticancer drugs based on transcriptomic data.

problem Designing effective anticancer drugs considering genetic profiles.
method RL framework using pretrained VAEs to generate compounds conditioned on transcriptomic data.
result Generative model produces molecules with high predicted inhibitory effects.

CASTER predicts drug interactions using chemical substructures.

problem Identifying potential drug-drug interactions during drug design.
method CASTER uses sequential pattern mining, auto-encoding, and dictionary learning to predict DDIs.
result CASTER outperformed state-of-the-art models and provided interpretable predictions.

MolHF generates complex molecules with hierarchical flow-based model.

problem Designing novel molecular structures with desired properties.
method MolHF is a hierarchical normalizing flow model that generates molecular graphs in a coarse-to-fine manner.
result MolHF achieves state-of-the-art performance in random generation and property optimization.

FRnet-DTI predicts drug-target interactions using deep learning.

problem Predicting drug-target interactions for therapeutic drug design.
method Auto encoder and convolutional classifier with feature manipulation and classification.
result Significantly improved on drug-target interaction prediction metrics.

Algorithm generates new drug molecules from prototypes, showing diversity and validity.

problem Designing new drugs from existing prototypes is expensive and time-consuming.
method Conditional Diversity Networks (CDN) for unsupervised generation of drug molecules.
result Generated molecules are valid and significantly different from prototypes, including FDA-approved drugs.

Improved 3D generative models for drug design reduce bias and enhance data efficiency.

problem Data sparsity and bias in 3D molecular design models.
method Multi-level contrastive learning protocol for bias control and data efficiency.
result Hierarchical generative models that are topologically unbiased and explainable.

New loss function optimization improves training speed and accuracy.

problem Optimizing neural network performance through loss functions.
method Genetic Loss-function Optimization (GLO) using genetic programming and CMA-ES.
result GLO loss functions lead to better performance with fewer training steps.

Model predicts VKA dosage for Indian patients, aiding in safe medication.

problem Safe and accurate dosing of VKA drugs for Indian patients.
method Support Vector Machine (SVM) Regression model trained on patient data.
result Predicted dosages closely match actual dosages.