التفاصيل البيبلوغرافية
| العنوان: |
COATI: Multimodal Contrastive Pretraining for Representing and Traversing Chemical Space |
| المؤلفون: |
Benjamin Kaufman, Edward C. Williams, Carl Underkoffler, Ryan Pederson, Narbe Mardirossian, Ian Watson, John Parkhill |
| سنة النشر: |
2024 |
| المجموعة: |
Smithsonian Institution: Figshare |
| مصطلحات موضوعية: |
Biophysics, Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Cancer, Computational Biology, Biological Sciences not elsewhere classified, Chemical Sciences not elsewhere classified, Information Systems not elsewhere classified, using contrastive learning, novel metadynamics algorithm, low computation cost, invertible vector representation, effectively infinite space, druglike chemical space, universal molecular embedding, force molecular generation, simultaneously optimize properties, multiparameter optimization task, multimodal contrastive pretraining, accelerated therapeutic inference, realistic accessible molecules, generative optimization using, four integrated features, coati possesses many, quantitative data sets, present contrastive optimization, proprietary data collected |
| الوصف: |
Creating a successful small molecule drug is a challenging multiparameter optimization problem in an effectively infinite space of possible molecules. Generative models have emerged as powerful tools for traversing data manifolds composed of images, sounds, and text and offer an opportunity to dramatically improve the drug discovery and design process. To create generative optimization methods that are more useful than brute-force molecular generation and filtering via virtual screening, we propose that four integrated features are necessary: large, quantitative data sets of molecular structure and activity, an invertible vector representation of realistic accessible molecules, smooth and differentiable regressors that quantify uncertainty, and algorithms to simultaneously optimize properties of interest. Over the course of 12 months, Terray Therapeutics has collected a data set of 2 billion quantitative binding measurements of small molecules to therapeutic targets, which directly motivates multiparameter generative optimization of molecules conditioned on these data. To this end, we present contrastive optimization for accelerated therapeutic inference (COATI), a pretrained, multimodal encoder-decoder model of druglike chemical space. COATI is constructed without any human biasing of features, using contrastive learning from text and 3D representations of molecules to allow for downstream use with structural models. We demonstrate that COATI possesses many of the desired properties of universal molecular embedding: fixed-dimension, invertibility, autoencoding, accurate regression, and low computation cost. Finally, we present a novel metadynamics algorithm for generative optimization using a small subset of our proprietary data collected for a model protein, carbonic anhydrase, designing molecules that satisfy the multiparameter optimization task of potency, solubility, and drug likeness. This work sets the stage for fully integrated generative molecular design and optimization for small molecules. |
| نوع الوثيقة: |
article in journal/newspaper |
| اللغة: |
unknown |
| Relation: |
https://figshare.com/articles/journal_contribution/COATI_Multimodal_Contrastive_Pretraining_for_Representing_and_Traversing_Chemical_Space/25150025 |
| DOI: |
10.1021/acs.jcim.3c01753.s001 |
| الاتاحة: |
https://doi.org/10.1021/acs.jcim.3c01753.s001 |
| Rights: |
CC BY-NC 4.0 |
| رقم الانضمام: |
edsbas.1BAD74A7 |
| قاعدة البيانات: |
BASE |