It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Design

Constrained synthesizability is an unaddressed challenge in generative molecular design. In particular, designing molecules satisfying multi-parameter optimization objectives, while simultaneously being synthesizable and enforcing the presence of specific commercial building blocks in the synthesis. This is practically important for molecule re-purposing, sustainability, and efficiency. In this work, we propose a novel reward function called TANimoto Group Overlap (TANGO), which uses chemistry principles to transform a sparse reward function into a dense and learnable reward function -- crucial for reinforcement learning. TANGO can augment general-purpose molecular generative models to directly optimize for constrained synthesizability while simultaneously optimizing for other properties relevant to drug discovery using reinforcement learning. Our framework is general and addresses starting-material, intermediate, and divergent synthesis constraints. Contrary to most existing works in the field, we show that incentivizing a general-purpose (without any inductive biases) model is a productive approach to navigating challenging optimization scenarios. We demonstrate this by showing that the trained models explicitly learn a desirable distribution. Our framework is the first generative approach to tackle constrained synthesizability.

Best Practices for Multi-Fidelity Bayesian Optimization in Materials and Molecular Research

Multi-fidelity Bayesian Optimization (MFBO) is a promising framework to speed up materials and molecular discovery as sources of information of different accuracies are at hand at increasing cost. Despite its potential use in chemical tasks, there is a lack of systematic evaluation of the many parameters playing a role in MFBO. In this work, we provide guidelines and recommendations to decide when to use MFBO in experimental settings. We investigate MFBO methods applied to molecules and materials problems. First, we test two different families of acquisition functions in two synthetic problems and study the effect of the informativeness and cost of the approximate function. We use our implementation and guidelines to benchmark three real discovery problems and compare them against their single-fidelity counterparts. Our results may help guide future efforts to implement MFBO as a routine tool in the chemical sciences.

Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants

AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they also pose significant challenges for assessment and learning outcomes. We conceptualize these challenges through the lens of vulnerability, the potential for university assessments and learning outcomes to be impacted by student use of generative AI. We investigate the potential scale of this vulnerability by measuring the degree to which AI assistants can complete assessment questions in standard university-level STEM courses. Specifically, we compile a novel dataset of textual assessment questions from 50 courses at EPFL and evaluate whether two AI assistants, GPT-3.5 and GPT-4 can adequately answer these questions. We use eight prompting strategies to produce responses and find that GPT-4 answers an average of 65.8% of questions correctly, and can even produce the correct answer across at least one prompting strategy for 85.1% of questions. When grouping courses in our dataset by degree program, these systems already pass non-project assessments of large numbers of core courses in various degree programs, posing risks to higher education accreditation that will be amplified as these models improve. Our results call for revising program-level assessment design in higher education in light of advances in generative AI.

Gradient Guided Hypotheses: A unified solution to enable machine learning models on scarce and noisy data regimes

Ensuring high-quality data is paramount for maximizing the performance of machine learning models and business intelligence systems. However, challenges in data quality, including noise in data capture, missing records, limited data production, and confounding variables, significantly constrain the potential performance of these systems. In this study, we propose an architecture-agnostic algorithm, Gradient Guided Hypotheses (GGH), designed to address these challenges. GGH analyses gradients from hypotheses as a proxy of distinct and possibly contradictory patterns in the data. This framework entails an additional step in machine learning training, where gradients can be included or excluded from backpropagation. In this manner, missing and noisy data are addressed through a unified solution that perceives both challenges as facets of the same overarching issue: the propagation of erroneous information. Experimental validation of GGH is conducted using real-world open-source datasets, where records with missing rates of up to 98.5% are simulated. Comparative analysis with state-of-the-art imputation methods demonstrates a substantial improvement in model performance achieved by GGH. Specifically in very high scarcity regimes, GGH was found to be the only viable solution. Additionally, GGH's noise detection capabilities are showcased by introducing simulated noise into the datasets and observing enhanced model performance after filtering out the noisy data. This study presents GGH as a promising solution for improving data quality and model performance in various applications.

Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation

Generative molecular design for drug discovery has very recently achieved a wave of experimental validation, with language-based backbones being the most common architectures employed. The most important factor for downstream success is whether an in silico oracle is well correlated with the desired end-point. To this end, current methods use cheaper proxy oracles with higher throughput before evaluating the most promising subset with high-fidelity oracles. The ability to directly optimize high-fidelity oracles would greatly enhance generative design and be expected to improve hit rates. However, current models are not efficient enough to consider such a prospect, exemplifying the sample efficiency problem. In this work, we introduce Saturn, which leverages the Augmented Memory algorithm and demonstrates the first application of the Mamba architecture for generative molecular design. We elucidate how experience replay with data augmentation improves sample efficiency and how Mamba synergistically exploits this mechanism. Saturn outperforms 22 models on multi-parameter optimization tasks relevant to drug discovery and may possess sufficient sample efficiency to consider the prospect of directly optimizing high-fidelity oracles.

Are large language models superhuman chemists?

Large language models (LLMs) have gained widespread interest due to their ability to process human language and perform tasks on which they have not been explicitly trained. This is relevant for the chemical sciences, which face the problem of small and diverse datasets that are frequently in the form of text. LLMs have shown promise in addressing these issues and are increasingly being harnessed to predict chemical properties, optimize reactions, and even design and conduct experiments autonomously. However, we still have only a very limited systematic understanding of the chemical reasoning capabilities of LLMs, which would be required to improve models and mitigate potential harms. Here, we introduce "ChemBench," an automated framework designed to rigorously evaluate the chemical knowledge and reasoning abilities of state-of-the-art LLMs against the expertise of human chemists. We curated more than 7,000 question-answer pairs for a wide array of subfields of the chemical sciences, evaluated leading open and closed-source LLMs, and found that the best models outperformed the best human chemists in our study on average. The models, however, struggle with some chemical reasoning tasks that are easy for human experts and provide overconfident, misleading predictions, such as about chemicals' safety profiles. These findings underscore the dual reality that, although LLMs demonstrate remarkable proficiency in chemical tasks, further research is critical to enhancing their safety and utility in chemical sciences. Our findings also indicate a need for adaptations to chemistry curricula and highlight the importance of continuing to develop evaluation frameworks to improve safe and useful LLMs.

Molecular Hypergraph Neural Networks

Graph neural networks (GNNs) have demonstrated promising performance across various chemistry-related tasks. However, conventional graphs only model the pairwise connectivity in molecules, failing to adequately represent higher-order connections like multi-center bonds and conjugated structures. To tackle this challenge, we introduce molecular hypergraphs and propose Molecular Hypergraph Neural Networks (MHNN) to predict the optoelectronic properties of organic semiconductors, where hyperedges represent conjugated structures. A general algorithm is designed for irregular high-order connections, which can efficiently operate on molecular hypergraphs with hyperedges of various orders. The results show that MHNN outperforms all baseline models on most tasks of OPV, OCELOTv1 and PCQM4Mv2 datasets. Notably, MHNN achieves this without any 3D geometric information, surpassing the baseline model that utilizes atom positions. Moreover, MHNN achieves better performance than pretrained GNNs under limited training data, underscoring its excellent data efficiency. This work provides a new strategy for more general molecular representations and property prediction tasks related to high-order connections.

FSscore: A Machine Learning-based Synthetic Feasibility Score Leveraging Human Expertise

Determining whether a molecule can be synthesized is crucial for many aspects of chemistry and drug discovery, allowing prioritization of experimental work and ranking molecules in de novo design tasks. Existing scoring approaches to assess synthetic feasibility struggle to extrapolate to out-of-distribution chemical spaces or fail to discriminate based on minor differences such as chirality that might be obvious to trained chemists. This work aims to address these limitations by introducing the Focused Synthesizability score (FSscore), which learns to rank structures based on binary preferences using a graph attention network. First, a baseline trained on an extensive set of reactant-product pairs is established that subsequently is fine-tuned with expert human feedback on a chemical space of interest. Fine-tuning on focused datasets improves performance on these chemical scopes over the pre-trained model exhibiting moderate performance and generalizability. This enables distinguishing hard- from easy-to-synthesize molecules and improving the synthetic accessibility of generative model outputs. On very complex scopes with limited labels achieving satisfactory gains remains challenging. The FSscore showcases how human expert feedback can be utilized to optimize the assessment of synthetic feasibility for a variety of applications.

Holistic chemical evaluation reveals pitfalls in reaction prediction models

The prediction of chemical reactions has gained significant interest within the machine learning community in recent years, owing to its complexity and crucial applications in chemistry. However, model evaluation for this task has been mostly limited to simple metrics like top-k accuracy, which obfuscates fine details of a model's limitations. Inspired by progress in other fields, we propose a new assessment scheme that builds on top of current approaches, steering towards a more holistic evaluation. We introduce the following key components for this goal: CHORISO, a curated dataset along with multiple tailored splits to recreate chemically relevant scenarios, and a collection of metrics that provide a holistic view of a model's advantages and limitations. Application of this method to state-of-the-art models reveals important differences on sensitive fronts, especially stereoselectivity and chemical out-of-distribution generalization. Our work paves the way towards robust prediction models that can ultimately accelerate chemical discovery.

Extracting human interpretable structure-property relationships in chemistry using XAI and large language models

Explainable Artificial Intelligence (XAI) is an emerging field in AI that aims to address the opaque nature of machine learning models. Furthermore, it has been shown that XAI can be used to extract input-output relationships, making them a useful tool in chemistry to understand structure-property relationships. However, one of the main limitations of XAI methods is that they are developed for technically oriented users. We propose the XpertAI framework that integrates XAI methods with large language models (LLMs) accessing scientific literature to generate accessible natural language explanations of raw chemical data automatically. We conducted 5 case studies to evaluate the performance of XpertAI. Our results show that XpertAI combines the strengths of LLMs and XAI tools in generating specific, scientific, and interpretable explanations.