Unleashing the full potential of deep learning in drug discovery.

Focus areas
→ Foundation Models
→ Inference Engines
→ Orchestration Systems

Multimodal foundation models:

Building accurate representations and simulations of the biological and chemical worlds of drug discovery.

Inference engines and active learners:

Unraveling complex biological and chemical interactions to formulate hypotheses, reveal causal relationships, and learn from results.

Orchestration and reasoning systems:

Execution of optimized experiments for hypothesis testing, laying the foundation for autonomous agents for scientific discovery.

Focus areas
November 1, 2024
QGFN: Controllable Greediness with Action Values
October 29, 2024
ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generation
October 26, 2024
SAFE setup for generative molecular design
October 17, 2024
Benchmarking Transcriptomics Foundation Models for Perturbation Analysis : one PCA still rules them all

Careers @ Valence Labs

Unleash your potential and build the future of scientific discovery at Valence Labs. Explore open opportunities now.

Apply

More Research

October 14, 2024
Graph Classification Gaussian Processes via Hodgelet Spectral Features
October 8, 2024
Batched Bayesian optimization with correlated candidate uncertainties
October 4, 2024
A call for an industry-led initiative to critically assess machine learning for real-world drug discovery
September 11, 2024
On the Scalability of GNNs for Molecular Graphs
September 11, 2024
Automated Discovery of Pairwise Interactions from Unstructured Data
September 10, 2024
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
June 10, 2024
Graph Positional and Structural Encoder
June 2, 2024
Learning to Scale Logits for Temperature-Conditional GFlowNets
May 31, 2024
Amortizing intractable inference in diffusion models for vision, language, and control
May 30, 2024
Targeted Sequential Indirect Experiment Design
May 27, 2024
Discrete Probabilistic Inference as Control in Multi-path Environments
April 2, 2024
Propensity Score Alignment for Unpaired Multimodal Data
November 6, 2023
DGFN: Double Generative Flow Networks
November 2, 2023
Generating QM1B with PySCFipu
October 30, 2023
Role of Structural and Conformational Diversity for Machine Learning Potentials
October 29, 2023
Object-centric architectures enable efficient causal representation learning
October 27, 2023
Latent Space Simulator for Unveiling Molecular Free Energy Landscapes and Predicting Transition Dynamics
October 18, 2023
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
October 16, 2023
Gotta be SAFE: A New Framework for Molecular Design
July 14, 2023
Graph Positional and Structural Encoder
June 7, 2023
Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design
June 5, 2023
Real-World Molecular Out-Of-Distribution: Specification and Investigation
May 26, 2023
UNSAT Solver Synthesis via Monte Carlo Forest Search
May 11, 2023
Towards Understanding and Improving GFlowNet Training
March 6, 2023
MoDTI: Modular Framework For Evaluating Inductive Biases in DTI Modeling
March 6, 2023
Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
February 11, 2023
Sequential Underspecified Instrument Selection for Cause-Effect Estimation
February 9, 2023
Helixer–de novo Prediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model
February 8, 2023
DynGFN: Bayesian Dynamic Causal Discovery Using Generative Flow Networks
February 1, 2023
GFlowNets for AI-driven Scientific Discovery
November 7, 2022
Object-centric Causal Representation Learning
October 23, 2022
Multi-Objective GFlowNets
September 26, 2022
Learning GFlowNets From Partial Episodes for Improved Convergence and Stability
July 9, 2022
Leveraging Structure Between Environments: Phylogenetic Regularization Incentivizes Disentangled Representations
June 16, 2022
Long Range Graph Benchmark
June 2, 2022
Weakly Supervised Representation Learning with Sparse Perturbations
May 25, 2022
Recipe for a General, Powerful, Scalable Graph Transformer
October 29, 2021
Properties From Mechanisms: an Equivariance Perspective on Identifiable Representation Learning
October 8, 2021
3D Infomax improves GNNs for Molecular Property Prediction
October 4, 2021
On the Robustness of Generalization of Drug–Drug Interaction Models
June 7, 2021
Rethinking Graph Transformers with Spectral Attention
December 16, 2020
Helixer: Cross-species Gene Annotation of Large Eukaryotic Genomes Using Deep Learning
December 15, 2020
Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning
October 6, 2020
Directional Graph Networks
May 16, 2020
Geodesics in Fibered Latent Spaces: A Geometric Approach to Learning Correspondences Between Conditions
April 12, 2020
Principal Neighbourhood Aggregation for Graph Nets
May 28, 2019
Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
May 28, 2019
Adaptive Deep Kernel Learning
Our StoryResearchCareers
Privacy Policy
Reach out to us at
info@valencelabs.ca