Search for: All records

Abstract ObjectiveExtracting social determinants of health (SDoHs) from medical notes depends heavily on labor-intensive annotations, which are typically task-specific, hampering reusability and limiting sharing. Here, we introduce SDoH-GPT, a novel framework leveraging few-shot learning large language models (LLMs) to automate the extraction of SDoH from unstructured text, aiming to improve both efficiency and generalizability. Materials and MethodsSDoH-GPT is a framework including the few-shot learning LLM methods to extract the SDoH from medical notes and the XGBoost classifiers which continue to classify SDoH using the annotations generated by the few-shot learning LLM methods as training datasets. The unique combination of the few-shot learning LLM methods with XGBoost utilizes the strength of LLMs as great few shot learners and the efficiency of XGBoost when the training dataset is sufficient. Therefore, SDoH-GPT can extract SDoH without relying on extensive medical annotations or costly human intervention. ResultsOur approach achieved tenfold and twentyfold reductions in time and cost, respectively, and superior consistency with human annotators measured by Cohen's kappa of up to 0.92. The innovative combination of LLM and XGBoost can ensure high accuracy and computational efficiency while consistently maintaining 0.90+ AUROC scores. DiscussionThis study has verified SDoH-GPT on three datasets and highlights the potential of leveraging LLM and XGBoost to revolutionize medical note classification, demonstrating its capability to achieve highly accurate classifications with significantly reduced time and cost. ConclusionThe key contribution of this study is the integration of LLM with XGBoost, which enables cost-effective and high quality annotations of SDoH. This research sets the stage for SDoH can be more accessible, scalable, and impactful in driving future healthcare solutions. 

Abstract PurposeTo examine the effect of incorporating self‐supervised denoising as a pre‐processing step for training deep learning (DL) based reconstruction methods on data corrupted by Gaussian noise. K‐space data employed for training are typically multi‐coil and inherently noisy. Although DL‐based reconstruction methods trained on fully sampled data can enable high reconstruction quality, obtaining large, noise‐free datasets is impractical. MethodsWe leverage Generalized Stein's Unbiased Risk Estimate (GSURE) for denoising. We evaluate two DL‐based reconstruction methods: Diffusion Probabilistic Models (DPMs) and Model‐Based Deep Learning (MoDL). We evaluate the impact of denoising on the performance of these DL‐based methods in solving accelerated multi‐coil magnetic resonance imaging (MRI) reconstruction. The experiments were carried out on T2‐weighted brain and fat‐suppressed proton‐density knee scans. ResultsWe observed that self‐supervised denoising enhances the quality and efficiency of MRI reconstructions across various scenarios. Specifically, employing denoised images rather than noisy counterparts when training DL networks results in lower normalized root mean squared error (NRMSE), higher structural similarity index measure (SSIM) and peak signal‐to‐noise ratio (PSNR) across different SNR levels, including 32, 22, and 12 dB for T2‐weighted brain data, and 24, 14, and 4 dB for fat‐suppressed knee data. ConclusionWe showed that denoising is an essential pre‐processing technique capable of improving the efficacy of DL‐based MRI reconstruction methods under diverse conditions. By refining the quality of input data, denoising enables training more effective DL networks, potentially bypassing the need for noise‐free reference MRI scans. 

Abstract Highly selective C−H functionalization remains an ongoing challenge in organic synthetic methodologies. Biocatalysts are robust tools for achieving these difficult chemical transformations. Biocatalyst engineering has often required directed evolution or structure‐based rational design campaigns to improve their activities. In recent years, machine learning has been integrated into these workflows to improve the discovery of beneficial enzyme variants. In this work, we combine a structure‐based self‐supervised machine learning framework, MutComputeX, with classical molecular dynamics simulations to down select mutations for rational design of a non‐heme iron‐dependent lysine dioxygenase, LDO. This approach consistently resulted in functional LDO mutants and circumvents the need for extensive study of mutational activity before‐hand. Our rationally designed single mutants purified with up to 2‐fold higher expression yields than WT and displayed higher total turnover numbers (TTN). Combining five such single mutations into a pentamutant variant, LPNYI LDO, leads to a 40 % improvement in the TTN (218±3) as compared to WT LDO (TTN=160±2). Overall, this work offers a low‐barrier approach for those seeking to synergize machine learning algorithms with pre‐existing protein engineering strategies. 

Abstract Large language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology and medicine has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Here we report our proposed few-shot learning approach, which uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. Our experiments, which involved seven rare tissues from different cancer types, demonstrate that the LLM-based prediction model achieves significant accuracy with very few or zero samples. Our proposed model, the CancerGPT (with ~ 124M parameters), is comparable to the larger fine-tuned GPT-3 model (with ~ 175B parameters). Our research contributes to tackling drug pair synergy prediction in rare tissues with limited data, and also advancing the use of LLMs for biological and medical inference tasks. 

Abstract Engineering stabilized proteins is a fundamental challenge in the development of industrial and pharmaceutical biotechnologies. We present Stability Oracle: a structure-based graph-transformer framework that achieves SOTA performance on accurately identifying thermodynamically stabilizing mutations. Our framework introduces several innovations to overcome well-known challenges in data scarcity and bias, generalization, and computation time, such as: Thermodynamic Permutations for data augmentation, structural amino acid embeddings to model a mutation with a single structure, a protein structure-specific attention-bias mechanism that makes transformers a viable alternative to graph neural networks. We provide training/test splits that mitigate data leakage and ensure proper model evaluation. Furthermore, to examine our data engineering contributions, we fine-tune ESM2 representations (Prostata-IFML) and achieve SOTA for sequence-based models. Notably, Stability Oracle outperforms Prostata-IFML even though it was pretrained on 2000X less proteins and has 548X less parameters. Our framework establishes a path for fine-tuning structure-based transformers to virtually any phenotype, a necessary task for accelerating the development of protein-based biotechnologies. 

Abstract Protein language models, like the popular ESM2, are widely used tools for extracting evolution-based protein representations and have achieved significant success on downstream biological tasks. Representations based on sequence and structure models, however, show significant performance differences depending on the downstream task. A major open problem is to obtain representations that best capture both the evolutionary and structural properties of proteins in general. Here we introduceImplicitStructureModel(ISM), a sequence-only input model with structurally-enriched representations that outperforms state-of-the-art sequence models on several well-studied benchmarks including mutation stability assessment and structure prediction. Our key innovations are a microenvironment-based autoencoder for generating structure tokens and a self-supervised training objective that distills these tokens into ESM2’s pre-trained model. We have madeISM’s structure-enriched weights easily available: integrating ISM into any application using ESM2 requires changing only a single line of code. Our code is available athttps://github.com/jozhang97/ISM. 

Abstract Robotics researchers have been focusing on developing autonomous and human-like intelligent robots that are able to plan, navigate, manipulate objects, and interact with humans in both static and dynamic environments. These capabilities, however, are usually developed for direct interactions with people in controlled environments, and evaluated primarily in terms of human safety. Consequently, human-robot interaction (HRI) in scenarios with no intervention of technical personnel is under-explored. However, in the future, robots will be deployed in unstructured and unsupervised environments where they will be expected to work unsupervised on tasks which require direct interaction with humans and may not necessarily be collaborative. Developing such robots requires comparing the effectiveness and efficiency of similar design approaches and techniques. Yet, issues regarding the reproducibility of results, comparing different approaches between research groups, and creating challenging milestones to measure performance and development over time make this difficult. Here we discuss the international robotics competition called RoboCup as a benchmark for the progress and open challenges in AI and robotics development. The long term goal of RoboCup is developing a robot soccer team that can win against the world’s best human soccer team by 2050. We selected RoboCup because it requires robots to be able to play with and against humans in unstructured environments, such as uneven fields and natural lighting conditions, and it challenges the known accepted dynamics in HRI. Considering the current state of robotics technology, RoboCup’s goal opens up several open research questions to be addressed by roboticists. In this paper, we (a) summarise the current challenges in robotics by using RoboCup development as an evaluation metric, (b) discuss the state-of-the-art approaches to these challenges and how they currently apply to RoboCup, and (c) present a path for future development in the given areas to meet RoboCup’s goal of having robots play soccer against and with humans by 2050. 

We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the Label DP setting where only the label is sensitive. We give improved upper and lower bounds on the excess risk for DP-ERM. In particular, we show that the error only scales polylogarithmically in terms of the sensitive domain size, improving upon previous results that scale polynomially in the sensitive domain size ( 

An ideal traffic simulator replicates the realistic long-term point-to-point trip that a self-driving system experiences during deployment. Prior models and benchmarks focus on closed-loop motion simulation for initial agents in a scene. This is problematic for long-term simulation. Agents enter and exit the scene as the ego vehicle enters new regions. We propose InfGen, a unified next-token prediction model that performs interleaved closed-loop motion simulation and scene generation. InfGen automatically switches between closed-loop motion simulation and scene generation mode. It enables stable long-term rollout simulation. InfGen performs at the state-of-the-art in short-term (9s) traffic simulation, and significantly outperforms all other methods in long-term (30s) simulation. 

People use videos to learn new recipes, exercises, and crafts. Such videos remain difficult for blind and low vision (BLV) people to follow as they rely on visual comparison. Our observations of visual rehabilitation therapists (VRTs) guiding BLV people to follow how-to videos revealed that VRTs provide both proactive and responsive support including detailed descriptions, non-visual workarounds, and progress feedback. We propose Vid2Coach, a system that transforms how-to videos into wearable camera-based assistants that provide accessible instructions and mixed-initiative feedback. From the video, Vid2Coach generates accessible instructions by augmenting narrated instructions with demonstration details and completion criteria for each step. It then uses retrieval-augmented-generation to extract relevant non-visual workarounds from BLV-specific resources. Vid2Coach then monitors user progress with a camera embedded in commercial smart glasses to provide context-aware instructions, proactive feedback, and answers to user questions. BLV participants (N=8) using Vid2Coach completed cooking tasks with 58.5\% fewer errors than when using their typical workflow and wanted to use Vid2Coach in their daily lives. Vid2Coach demonstrates an opportunity for AI visual assistance that strengthens rather than replaces non-visual expertise.