LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset

Chemistry plays a crucial role in many domains, such as drug discovery and material science. While large language models (LLMs) such as GPT-4 exhibit remarkable capabilities on natural language processing tasks, existing work shows their performance on chemistry tasks is discouragingly low. In this paper, however, we demonstrate that our developed LLMs can achieve very strong results on a comprehensive set of chemistry tasks, outperforming the most advanced GPT-4 across all the tasks by a substantial margin and approaching the SoTA task-specific models. The key to our success is a large-scale, comprehensive, high-quality dataset for instruction tuning named SMolInstruct. It contains 14 meticulously selected chemistry tasks and over three million high-quality samples, laying a solid foundation for training and evaluating LLMs for chemistry. Based on SMolInstruct, we fine-tune a set of open-source LLMs, among which, we find that Mistral serves as the best base model for chemistry tasks. We further conduct analysis on the impact of trainable parameters, providing insights for future research.

Modeling Sequences as Star Graphs to Address Over-smoothing in Self-attentive Sequential Recommendation

Self-attention (SA) mechanisms have been widely used in developing sequential recommendation (SR) methods, and demonstrated state-of-the-art performance. However, in this paper, we show that self-attentive SR methods substantially suffer from the over-smoothing issue that item embeddings within a sequence become increasingly similar across attention blocks. As widely demonstrated in the literature, this issue could lead to a loss of information in individual items, and significantly degrade models' scalability and performance. To address the over-smoothing issue, in this paper, we view items within a sequence constituting a star graph and develop a method, denoted as MSSG, for SR. Different from existing self-attentive methods, MSSG introduces an additional internal node to specifically capture the global information within the sequence, and does not require information propagation among items. This design fundamentally addresses the over-smoothing issue and enables MSSG a linear time complexity with respect to the sequence length. We compare MSSG with ten state-of-the-art baseline methods on six public benchmark datasets. Our experimental results demonstrate that MSSG significantly outperforms the baseline methods, with an improvement of as much as 10.10%. Our analysis shows the superior scalability of MSSG over the state-of-the-art self-attentive methods. Our complexity analysis and run-time performance comparison together show that MSSG is both theoretically and practically more efficient than self-attentive methods. Our analysis of the attention weights learned in SA-based methods indicates that on sparse recommendation data, modeling dependencies in all item pairs using the SA mechanism yields limited information gain, and thus, might not benefit the recommendation performance

Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation

In recent years, with large language models (LLMs) achieving state-of-the-art performance in context understanding, increasing efforts have been dedicated to developing LLM-enhanced sequential recommendation (SR) methods. Considering that most existing LLMs are not specifically optimized for recommendation tasks, adapting them for SR becomes a critical step in LLM-enhanced SR methods. Though numerous adaptation methods have been developed, it still remains a significant challenge to adapt LLMs for SR both efficiently and effectively. To address this challenge, in this paper, we introduce a novel side sequential network adaptation method, denoted as SSNA, for LLM enhanced SR. SSNA features three key designs to allow both efficient and effective LLM adaptation. First, SSNA learns adapters separate from LLMs, while fixing all the pre-trained parameters within LLMs to allow efficient adaptation. In addition, SSNA adapts the top-a layers of LLMs jointly, and integrates adapters sequentially for enhanced effectiveness (i.e., recommendation performance). We compare SSNA against five state-of-the-art baseline methods on five benchmark datasets using three LLMs. The experimental results demonstrate that SSNA significantly outperforms all the baseline methods in terms of recommendation performance, and achieves substantial improvement over the best-performing baseline methods at both run-time and memory efficiency during training. Our analysis shows the effectiveness of integrating adapters in a sequential manner. Our parameter study demonstrates the effectiveness of jointly adapting the top-a layers of LLMs.

Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Models

Ligand-based drug design aims to identify novel drug candidates of similar shapes with known active molecules. In this paper, we formulated an in silico shape-conditioned molecule generation problem to generate 3D molecule structures conditioned on the shape of a given molecule. To address this problem, we developed a translation- and rotation-equivariant shape-guided generative model ShapeMol. ShapeMol consists of an equivariant shape encoder that maps molecular surface shapes into latent embeddings, and an equivariant diffusion model that generates 3D molecules based on these embeddings. Experimental results show that ShapeMol can generate novel, diverse, drug-like molecules that retain 3D molecular shapes similar to the given shape condition. These results demonstrate the potential of ShapeMol in designing drug candidates of desired 3D shapes binding to protein target pockets.

RLSynC: Offline-Online Reinforcement Learning for Synthon Completion

Retrosynthesis is the process of determining the set of reactant molecules that can react to form a desired product. Semi-template-based retrosynthesis methods, which imitate the reverse logic of synthesis reactions, first predict the reaction centers in the products, and then complete the resulting synthons back into reactants. These methods enable necessary interpretability and high practical utility to inform synthesis planning. We develop a new offline-online reinforcement learning method RLSynC for synthon completion in semi-template-based methods. RLSynC assigns one agent to each synthon, all of which complete the synthons by conducting actions step by step in a synchronized fashion. RLSynC learns the policy from both offline training episodes and online interactions which allow RLSynC to explore new reaction spaces. RLSynC uses a forward synthesis model to evaluate the likelihood of the predicted reactants in synthesizing a product, and thus guides the action search. We compare RLSynC with the state-of-the-art retrosynthesis methods. Our experimental results demonstrate that RLSynC can outperform these methods with improvement as high as 14.9% on synthon completion, and 14.0% on retrosynthesis, highlighting its potential in synthesis planning.

Nearest-Neighbor Sampling Based Conditional Independence Testing

The conditional randomization test (CRT) was recently proposed to test whether two random variables X and Y are conditionally independent given random variables Z. The CRT assumes that the conditional distribution of X given Z is known under the null hypothesis and then it is compared to the distribution of the observed samples of the original data. The aim of this paper is to develop a novel alternative of CRT by using nearest-neighbor sampling without assuming the exact form of the distribution of X given Z. Specifically, we utilize the computationally efficient 1-nearest-neighbor to approximate the conditional distribution that encodes the null hypothesis. Then, theoretically, we show that the distribution of the generated samples is very close to the true conditional distribution in terms of total variation distance. Furthermore, we take the classifier-based conditional mutual information estimator as our test statistic. The test statistic as an empirical fundamental information theoretic quantity is able to well capture the conditional-dependence feature. We show that our proposed test is computationally very fast, while controlling type I and II errors quite well. Finally, we demonstrate the efficiency of our proposed test in both synthetic and real data analyses.

T-Cell Receptor Optimization with Reinforcement Learning and Mutation Policies for Precesion Immunotherapy

T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune response. Optimizing TCR sequences for TCR recognition represents a fundamental step towards the development of personalized treatments to trigger immune responses killing cancerous or virus-infected cells. In this paper, we formulated the search for these optimized TCRs as a reinforcement learning (RL) problem, and presented a framework TCRPPO with a mutation policy using proximal policy optimization. TCRPPO mutates TCRs into effective ones that can recognize given peptides. TCRPPO leverages a reward function that combines the likelihoods of mutated sequences being valid TCRs measured by a new scoring function based on deep autoencoders, with the probabilities of mutated sequences recognizing peptides from a peptide-TCR interaction predictor. We compared TCRPPO with multiple baseline methods and demonstrated that TCRPPO significantly outperforms all the baseline methods to generate positive binding and valid TCRs. These results demonstrate the potential of TCRPPO for both precision immunotherapy and peptide-recognizing TCR motif discovery.

$\mathsf{G^2Retro}$: Two-Step Graph Generative Models for Retrosynthesis Prediction

Retrosynthesis is a procedure where a molecule is transformed into potential reactants and thus the synthesis routes are identified. We propose a novel generative framework, denoted as $\mathsf{G^2Retro}$, for one-step retrosynthesis prediction. $\mathsf{G^2Retro}$ imitates the reversed logic of synthetic reactions, that is, first predicting the reaction centers to convert the target molecule into fragments named synthons, and then transforming synthons into reactants, following previous semi-template-based methods. In predicting reaction centers, $\mathsf{G^2Retro}$ defines a comprehensive set of reaction center types, and enables diversity in the predicted reactions by considering multiple reaction center candidates. In completing synthons, $\mathsf{G^2Retro}$ deploys a sequence of substructure attachments to transform synthons into reactants, which utilize a holistic view of the most updated structures of the synthons to be completed, as well as all the involved synthon and product structures. Here we show that $\mathsf{G^2Retro}$ is able to better prioritize the most possible reactants in the benchmark dataset than the state-of-the-art methods, and discover novel and highly likely reactions that are not included in the benchmark dataset.