Artificial intelligence based chemistry models are a promising method of exploring chemical reaction design spaces. However, training datasets based on experimental synthesis are typically reported only for the optimal synthesis reactions. This leads to an inherited bias in the model predictions. Therefore, robust datasets that span the entirety of the solution space are necessary to remove inherited bias and permit complete training of the space. In this study, an artificial intelligence model based on a Variational AutoEncoder (VAE) has been developed and investigated to synthetically generate continuous datasets. The approach involves sampling the latent space to generate new chemical reactions. This developed technique is demonstrated by generating over 7,000,000 new reactions from a training dataset containing only 7,000 reactions. The generated reactions include molecular species that are larger and more diverse than the training set.
This content will become publicly available on February 27, 2025
Uncertainty-Aware Yield Prediction with Multimodal Molecular Features
Predicting chemical reaction yields is pivotal for efficient chemical synthesis, an area that focuses on the creation of novel compounds for diverse uses. Yield prediction demands accurate representations of reactions for forecasting practical transformation rates. Yet, the uncertainty issues broadcasting in real-world situations prohibit current models to excel in this task owing to the high sensitivity of yield activities and the uncertainty in yield measurements. Existing models often utilize single-modal feature representations, such as molecular
fingerprints, SMILES sequences, or molecular graphs, which is not sufficient to capture the complex interactions
and dynamic behavior of molecules in reactions. In this paper, we present an advanced Uncertainty-Aware Multimodal model (UAM) to tackle these challenges. Our approach seamlessly integrates data sources from multiple modalities by encompassing sequence representations, molecular graphs, and expert-defined chemical reaction features for a comprehensive representation of reactions. Additionally, we address both the model and data-based uncertainty, refining the model’s predictive capability. Extensive experiments on three datasets, including two high throughput experiment (HTE) datasets and one chemist-constructed Amide coupling reaction
dataset, demonstrate that UAM outperforms the stateof-the-art methods. The code and used datasets are available at https://github.com/jychen229/Multimodal-reaction-yieldprediction.
more »
« less
- Award ID(s):
- 2202693
- NSF-PAR ID:
- 10500185
- Publisher / Repository:
- AAAI Press, Washington, DC, USA
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- ISSN:
- 2159-5399
- ISBN:
- 978-1-57735-887-9
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
Abstract—Materials Genomics initiative has the goal of rapidly synthesizing materials with a given set of desired properties using data science techniques. An important step in this direction is the ability to predict the outcomes of complex chemical reactions. Some graph-based feature learning algorithms have been proposed recently. However, the comprehensive relationship between atoms or structures is not learned properly and not explainable, and multiple graphs cannot be handled. In this paper, chemical reaction processes are formulated as translation processes. Both atoms and edges are mapped to vectors represent- ing the structural information. We employ the graph convolution layers to learn meaningful information of atom graphs, and further employ its variations, message passing networks (MPNN) and edge attention graph convolution network (EAGCN) to learn edge representations. Particularly, multi-view EAGCN groups and maps edges to a set of representations for the properties of the chemical bond between atoms from multiple views. Each bond is viewed from its atom type, bond type, distance and neighbor environment. The final node and edge representations are mapped to a sequence defined by the SMILES of the molecule and then fed to a decoder model with attention. To make full usage of multi-view information, we propose multi-view attention model to handle self correlation inside each atom or edge, and mutual correlation between edges and atoms, both of which are important in chemical reaction processes. We have evaluated our method on the standard benchmark datasets (that have been used by all the prior works), and the results show that edge embedding with multi-view attention achieves superior accuracy compared to existing techniques.more » « less
-
The lack of publicly available, large, and unbiased datasets is a key bottleneck for the application of machine learning (ML) methods in synthetic chemistry. Data from electronic laboratory notebooks (ELNs) could provide less biased, large datasets, but no such datasets have been made publicly available. The first real-world dataset from the ELNs of a large pharmaceutical company is disclosed and its relationship to high-throughput experimentation (HTE) datasets is described. For chemical yield predictions, a key task in chemical synthesis, an attributed graph neural network (AGNN) performs as well as or better than the best previous models on two HTE datasets for the Suzuki–Miyaura and Buchwald–Hartwig reactions. However, training the AGNN on an ELN dataset does not lead to a predictive model. The implications of using ELN data for training ML-based models are discussed in the context of yield predictions.more » « less
-
Learning multimodal representations is a fundamentally complex research problem due to the presence of multiple heterogeneous sources of information. Although the presence of multiple modalities provides additional valuable information, there are two key challenges to address when learning from multimodal data: 1) models must learn the complex intra-modal and cross-modal interactions for prediction and 2) models must be robust to unexpected missing or noisy modalities during testing. In this paper, we propose to optimize for a joint generative-discriminative objective across multimodal data and labels. We introduce a model that factorizes representations into two sets of independent factors: multimodal discriminative and modality-specific generative factors. Multimodal discriminative factors are shared across all modalities and contain joint multimodal features required for discriminative tasks such as sentiment prediction. Modality-specific generative factors are unique for each modality and contain the information required for generating data. Experimental results show that our model is able to learn meaningful multimodal representations that achieve state-of-the-art or competitive performance on six multimodal datasets. Our model demonstrates flexible generative capabilities by conditioning on independent factors and can reconstruct missing modalities without significantly impacting performance. Lastly, we interpret our factorized representations to understand the interactions that influence multimodal learning.more » « less
-
Information technologies enable programmers and engineers to design and synthesize systems of startling complexity that nonetheless behave as intended. This mastery of complexity is made possible by a hierarchy of formal abstractions that span from high-level programming languages down to low-level implementation specifications, with rigorous connections between the levels. DNA nanotechnology presents us with a new molecular information technology whose potential has not yet been fully unlocked in this way. Developing an effective hierarchy of abstractions may be critical for increasing the complexity of programmable DNA systems. Here, we build on prior practice to provide a new formalization of ‘domain-level’ representations of DNA strand displacement systems that has a natural connection to nucleic acid biophysics while still being suitable for formal analysis. Enumeration of unimolecular and bimolecular reactions provides a semantics for programmable molecular interactions, with kinetics given by an approximate biophysical model. Reaction condensation provides a tractable simplification of the detailed reactions that respects overall kinetic properties. The applicability and accuracy of the model is evaluated across a wide range of engineered DNA strand displacement systems. Thus, our work can serve as an interface between lower-level DNA models that operate at the nucleotide sequence level, and high-level chemical reaction network models that operate at the level of interactions between abstract species.more » « less
