Active Learning Enables Extrapolation in Molecular Generative Models

• URL: http://arxiv.org/abs/2501.02059v1
• Date: Fri, 03 Jan 2025 19:07:06 GMT
• Title: Active Learning Enables Extrapolation in Molecular Generative Models
• Authors: Evan R. Antoniuk, Peggy Li, Nathan Keilbart, Stephen Weitzner, Bhavya Kailkhura, Anna M. Hiszpanski,
• Abstract summary: We create an active-learning, closed-loop molecule generation pipeline for molecular generative models. Compared against other generative model approaches, only our active learning approach generates molecules with properties that extrapolate beyond the training data. The proportion of stable molecules generated is 3.5x higher than the next-best model.
• Score: 11.234291560423943
• License:
• Abstract: Although generative models hold promise for discovering molecules with optimized desired properties, they often fail to suggest synthesizable molecules that improve upon the known molecules seen in training. We find that a key limitation is not in the molecule generation process itself, but in the poor generalization capabilities of molecular property predictors. We tackle this challenge by creating an active-learning, closed-loop molecule generation pipeline, whereby molecular generative models are iteratively refined on feedback from quantum chemical simulations to improve generalization to new chemical space. Compared against other generative model approaches, only our active learning approach generates molecules with properties that extrapolate beyond the training data (reaching up to 0.44 standard deviations beyond the training data range) and out-of-distribution molecule classification accuracy is improved by 79%. By conditioning molecular generation on thermodynamic stability data from the active-learning loop, the proportion of stable molecules generated is 3.5x higher than the next-best model.

Related papers

• MolMiner: Transformer architecture for fragment-based autoregressive generation of molecular stories [7.366789601705544]
  Chemical validity, interpretability of the generation process and flexibility to variable molecular sizes are among some of the remaining challenges for generative models in computational materials design. We propose an autoregressive approach that decomposes molecular generation into a sequence of discrete and interpretable steps. Our results show that the model can effectively bias the generation distribution according to the prompted multi-target objective.
  arXiv  Detail & Related papers  (2024-11-10T22:00:55Z)
• Conditional Synthesis of 3D Molecules with Time Correction Sampler [58.0834973489875]
  Time-Aware Conditional Synthesis (TACS) is a novel approach to conditional generation on diffusion models. It integrates adaptively controlled plug-and-play "online" guidance into a diffusion model, driving samples toward the desired properties.
  arXiv  Detail & Related papers  (2024-11-01T12:59:25Z)
• Pre-training of Molecular GNNs via Conditional Boltzmann Generator [0.0]
  We propose a pre-training method for molecular GNNs using an existing dataset of molecular conformations. We show that our model has a better prediction performance for molecular properties than existing pre-training methods.
  arXiv  Detail & Related papers  (2023-12-20T15:30:15Z)
• STRIDE: Structure-guided Generation for Inverse Design of Molecules [0.24578723416255752]
  $textbfSTRIDE$ is a generative molecule workflow that generates novel molecules with an unconditional generative model guided by known molecules without any retraining. Our generated molecules have on average 21.7% lower synthetic accessibility scores and also reduce ionization potential by 5.9% of generated molecules via guiding.
  arXiv  Detail & Related papers  (2023-11-06T08:22:35Z)
• Molecule Design by Latent Space Energy-Based Modeling and Gradual Distribution Shifting [53.44684898432997]
  Generation of molecules with desired chemical and biological properties is critical for drug discovery. We propose a probabilistic generative model to capture the joint distribution of molecules and their properties. Our method achieves very strong performances on various molecule design tasks.
  arXiv  Detail & Related papers  (2023-06-09T03:04:21Z)
• Retrieval-based Controllable Molecule Generation [63.44583084888342]
  We propose a new retrieval-based framework for controllable molecule generation. We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria. Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
  arXiv  Detail & Related papers  (2022-08-23T17:01:16Z)
• Exploring Chemical Space with Score-based Out-of-distribution Generation [57.15855198512551]
  We propose a score-based diffusion scheme that incorporates out-of-distribution control in the generative differential equation (SDE) Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones found with existing methods, and even the top 0.01% of the original training pool.
  arXiv  Detail & Related papers  (2022-06-06T06:17:11Z)
• Molecular Attributes Transfer from Non-Parallel Data [57.010952598634944]
  We formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data. Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-11-30T06:10:22Z)
• Generating stable molecules using imitation and reinforcement learning [0.0]
  We propose a reinforcement learning approach for generating molecules in cartesian coordinates. We learn basic chemical rules from imitation learning on the GDB-11 database to create an initial model. We then deploy multiple copies of the model conditioned on a specific stoichiometry in a reinforcement learning setting.
  arXiv  Detail & Related papers  (2021-07-11T10:18:19Z)
• Learning Latent Space Energy-Based Prior Model for Molecule Generation [59.875533935578375]
  We learn latent space energy-based prior model with SMILES representation for molecule modeling. Our method is able to generate molecules with validity and uniqueness competitive with state-of-the-art models.
  arXiv  Detail & Related papers  (2020-10-19T09:34:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.