LLLin Li

Lin Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lin Li has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Higher-order equivariant neural networks for charge density prediction in materials

    by Teddy Koker, Keegan Quigley, Eric Taw, Kevin Tibbetts, Lin Li

    The calculation of electron density distribution using density functional theory (DFT) in materials and molecules is central to the study of their quantum and macro-scale properties, yet accurate and efficient calculation remains a long-standing challenge. We introduce ChargE3Net, an E(3)-equivariant graph neural network for predicting electron density in atomic systems. ChargE3Net enables the learning of higher-order equivariant features to achieve high predictive accuracy and model expressivity. We show that ChargE3Net exceeds the performance of prior work on diverse sets of molecules and materials. When trained on the massive dataset of over 100K materials in the Materials Project database, our model is able to capture the complexity and variability in the data, leading to a significant 26.7% reduction in self-consistent iterations when used to initialize DFT calculations on unseen materials. Furthermore, we show that non-self-consistent DFT calculations using our predicted charge densities yield near-DFT performance on electronic and thermodynamic property prediction at a fraction of the computational cost. Further analysis attributes the greater predictive accuracy to improved modeling of systems with high angular variations. These results illuminate a pathway towards a machine learning-accelerated ab initio calculations for materials discovery.


  • Machine-learning-accelerated simulations to enable automatic surface reconstruction

    by Xiaochen Du, James K. Damewood, Jaclyn R. Lunger, Reisel Millan, Bilge Yildiz, Lin Li, Rafael Gómez-Bombarelli

    Understanding material surfaces and interfaces is vital in applications such as catalysis or electronics. By combining energies from electronic structure with statistical mechanics, ab initio simulations can, in principle, predict the structure of material surfaces as a function of thermodynamic variables. However, accurate energy simulations are prohibitive when coupled to the vast phase space that must be statistically sampled. Here we present a bi-faceted computational loop to predict surface phase diagrams of multicomponent materials that accelerates both the energy scoring and statistical sampling methods. Fast, scalable and data-efficient machine learning interatomic potentials are trained on high-throughput density-functional-theory calculations through closed-loop active learning. Markov chain Monte Carlo sampling in the semigrand canonical ensemble is enabled by using virtual surface sites. The predicted surfaces for GaN(0001), Si(111) and SrTiO3(001) are in agreement with past work and indicate that the proposed strategy can model complex material surfaces and discover previously unreported surface terminations.


  • Open Access

    Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries

    by Lin Li, Esther Gupta, John Spaeth, Leslie Shing, Rafael Jaimes, Emily Engelhart, Randolph Lopez, Rajmonda S. Caceres, Tristan Bepler, Matthew E. Walsh

    Therapeutic antibodies are an important and rapidly growing drug modality. However, the design and discovery of early-stage antibody therapeutics remain a time and cost-intensive endeavor. Here we present an end-to-end Bayesian, language model-based method for designing large and diverse libraries of high-affinity single-chain variable fragments (scFvs) that are then empirically measured. In a head-to-head comparison with a directed evolution approach, we show that the best scFv generated from our method represents a 28.7-fold improvement in binding over the best scFv from the directed evolution. Additionally, 99% of designed scFvs in our most successful library are improvements over the initial candidate scFv. By comparing a library’s predicted success to actual measurements, we demonstrate our method’s ability to explore tradeoffs between library success and diversity. Results of our work highlight the significant impact machine learning models can have on scFv development. We expect our method to be broadly applicable and provide value to other protein engineering tasks.


  • Open Access

    Graph Contrastive Learning for Materials

    by Teddy Koker, Keegan Quigley, Will Spaeth, Nathan C. Frey, Lin Li

    Recent work has shown the potential of graph neural networks to efficiently predict material properties, enabling high-throughput screening of materials. Training these models, however, often requires large quantities of labelled data, obtained via costly methods such as ab initio calculations or experimental evaluation. By leveraging a series of material-specific transformations, we introduce CrystalCLR, a framework for constrastive learning of representations with crystal graph neural networks. With the addition of a novel loss function, our framework is able to learn representations competitive with engineered fingerprinting methods. We also demonstrate that via model finetuning, contrastive pretraining can improve the performance of graph neural networks for prediction of material properties and significantly outperform traditional ML models that use engineered fingerprints. Lastly, we observe that CrystalCLR produces material representations that form clusters by compound class.


  • Open Access

    Machine Learning Optimization of Candidate Antibodies Yields Highly Diverse Sub-nanomolar Affinity Antibody Libraries

    by Lin Li, Esther Gupta, John Spaeth, Leslie Shing, Rafael Jaimes, Rajmonda Sulo Caceres, Tristan Bepler, Matthew E. Walsh

    Therapeutic antibodies are an important and rapidly growing drug modality. However, the design and discovery of early-stage antibody therapeutics remain a time and cost-intensive endeavor. In this work, we present an end-to-end Bayesian, language model-based method for designing large and diverse libraries of high-affinity single-chain variable fragments (scFvs). We integrate target-specific binding affinities with information from millions of natural protein sequences in a probabilistic machine learning framework to design thousands of scFvs that are then empirically measured. In a head-to-head comparison with a directed evolution approach, we show that the best scFv generated from our method represents a 28.8-fold improvement in binding over the best scFv from the directed evolution. Additionally, 99% of the designed scFvs in our most successful library are improvements over the initial candidate scFv. By comparing a library’s predicted success to actual measurements, we demonstrate our method’s ability to explore tradeoffs between library success and diversity during the design phase and prior to experimental testing. The results of our work highlight the significant impact machine learning models can have on scFv development. We expect our end-to-end method to be broadly applicable and able to provide value to other protein engineering tasks.


  • Open Access

    Graph Model Selection via Random Walks

    by Lin Li, William M. Campbell, Rajmonda S. Caceres

    In this paper, we present a novel approach based on the random walk process for finding meaningful representations of a graph model. Our approach leverages the transient behavior of many short random walks with novel initialization mechanisms to generate model discriminative features. These features are able to capture a more comprehensive structural signature of the underlying graph model. The resulting representation is invariant to both node permutation and the size of the graph, allowing direct comparison between large classes of graphs. We test our approach on two challenging model selection problems: the discrimination in the sparse regime of an Erd\"{o}s-Renyi model from a stochastic block model and the planted clique problem. Our representation approach achieves performance that closely matches known theoretical limits in addition to being computationally simple and scalable to large graphs.

  • Open Access

    Making Sense of Unstructured Text Data

    by Lin Li, William M. Campbell, Cagri Dagli, Joseph P. Campbell

    Many network analysis tasks in social sciences rely on pre-existing data sources that were created with explicit relations or interactions between entities under consideration. Examples include email logs, friends and followers networks on social media, communication networks, etc. In these data, it is relatively easy to identify who is connected to whom and how they are connected. However, most of the data that we encounter on a daily basis are unstructured free-text data, e.g., forums, online marketplaces, etc. It is considerably more difficult to extract network data from unstructured text. In this work, we present an end-to-end system for analyzing unstructured text data and transforming the data into structured graphs that are directly applicable to a downstream application. Specifically, we look at social media data and attempt to predict the most indicative words from users' posts. The resulting keywords can be used to construct a context+content network for downstream processing such as graph-based analysis and learning. With that goal in mind, we apply our methods to the application of cross-domain entity resolution. The performance of the resulting system with automatic keywords shows improvement over the system with user-annotated hashtags.

  • Open Access

    Cross-Domain Entity Resolution in Social Media

    by W. M. Campbell, Lin Li, C. Dagli, J. Acevedo-Aviles, K. Geyer, J. P. Campbell, C. Priebe

    The challenge of associating entities across multiple domains is a key problem in social media understanding. Successful cross-domain entity resolution provides integration of information from multiple sites to create a complete picture of user and community activities, characteristics, and trends. In this work, we examine the problem of entity resolution across Twitter and Instagram using general techniques. Our methods fall into three categories: profile, content, and graph based. For the profile-based methods, we consider techniques based on approximate string matching. For content-based methods, we perform author identification. Finally, for graph-based methods, we apply novel cross-domain community detection methods and generate neighborhood-based features. The three categories of methods are applied to a large graph of users in Twitter and Instagram to understand challenges, determine performance, and understand fusion of multiple methods. Final results demonstrate an equal error rate less than 1%.

  • Open Access

    Matching Community Structure Across Online Social Networks

    by Lin Li, W. M. Campbell

    The discovery of community structure in networks is a problem of considerable interest in recent years. In online social networks, often times, users are simultaneously involved in multiple social media sites, some of which share common social relationships. It is of great interest to uncover a shared community structure across these networks. However, in reality, users typically identify themselves with different usernames across social media sites. This creates a great difficulty in detecting the community structure. In this paper, we explore several approaches for community detection across online social networks with limited knowledge of username alignment across the networks. We refer to the known alignment of usernames as seeds. We investigate strategies for seed selection and its impact on networks with a different fraction of overlapping vertices. The goal is to study the interplay between network topologies and seed selection strategies, and to understand how it affects the detected community structure. We also propose several measures to assess the performance of community detection and use them to measure the quality of the detected communities in both Twitter-Twitter networks and Twitter-Instagram networks.