Large language models generate functional protein sequences across diverse families.

Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein sequences with a predictable function across large protein families, akin to generating grammatically and semantically correct natural language sentences on diverse topics. The model was trained on 280 million protein sequences from >19,000 families and is augmented with control tags specifying protein properties. ProGen can be further fine-tuned to curated sequences and tags to improve controllable generation performance of proteins from families with sufficient homologous samples. Artificial proteins fine-tuned to five distinct lysozyme families showed similar catalytic efficiencies as natural lysozymes, with sequence identity to natural proteins as low as 31.4%. ProGen is readily adapted to diverse protein families, as we demonstrate with chorismate mutase and malate dehydrogenase.

Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials.

Prostate cancer is the most frequent cancer in men and a leading cause of cancer death. Determining a patient's optimal therapy is a challenge, where oncologists must select a therapy with the highest likelihood of success and the lowest likelihood of toxicity. International standards for prognostication rely on non-specific and semi-quantitative tools, commonly leading to over- and under-treatment. Tissue-based molecular biomarkers have attempted to address this, but most have limited validation in prospective randomized trials and expensive processing costs, posing substantial barriers to widespread adoption. There remains a significant need for accurate and scalable tools to support therapy personalization. Here we demonstrate prostate cancer therapy personalization by predicting long-term, clinically relevant outcomes using a multimodal deep learning architecture and train models using clinical data and digital histopathology from prostate biopsies. We train and validate models using five phase III randomized trials conducted across hundreds of clinical centers. Histopathological data was available for 5654 of 7764 randomized patients (71%) with a median follow-up of 11.4 years. Compared to the most common risk-stratification tool-risk groups developed by the National Cancer Center Network (NCCN)-our models have superior discriminatory performance across all endpoints, ranging from 9.2% to 14.6% relative improvement in a held-out validation set. This artificial intelligence-based tool improves prognostication over standard tools and allows oncologists to computationally predict the likeliest outcomes of specific patients to determine optimal treatment. Outfitted with digital scanners and internet access, any clinic could offer such capabilities, enabling global access to therapy personalization.

The AI Economist: Taxation policy design via two-level deep multiagent reinforcement learning.

Artificial intelligence (AI) and reinforcement learning (RL) have improved many areas but are not yet widely adopted in economic policy design, mechanism design, or economics at large. The AI Economist is a two-level, deep RL framework for policy design in which agents and a social planner coadapt. In particular, the AI Economist uses structured curriculum learning to stabilize the challenging two-level, coadaptive learning problem. We validate this framework in the domain of taxation. In one-step economies, the AI Economist recovers the optimal tax policy of economic theory. In spatiotemporal economies, the AI Economist substantially improves both utilitarian social welfare and the trade-off between equality and productivity over baselines. It does so despite emergent tax-gaming strategies while accounting for emergent labor specialization, agent interactions, and behavioral change. These results demonstrate that two-level, deep RL complements economic theory and unlocks an AI-based approach to designing and understanding economic policy.

Biological data annotation via a human-augmenting AI-based labeling system.

Biology has become a prime area for the deployment of deep learning and artificial intelligence (AI), enabled largely by the massive data sets that the field can generate. Key to most AI tasks is the availability of a sufficiently large, labeled data set with which to train AI models. In the context of microscopy, it is easy to generate image data sets containing millions of cells and structures. However, it is challenging to obtain large-scale high-quality annotations for AI models. Here, we present HALS (Human-Augmenting Labeling System), a human-in-the-loop data labeling AI, which begins uninitialized and learns annotations from a human, in real-time. Using a multi-part AI composed of three deep learning models, HALS learns from just a few examples and immediately decreases the workload of the annotator, while increasing the quality of their annotations. Using a highly repetitive use-case-annotating cell types-and running experiments with seven pathologists-experts at the microscopic analysis of biological specimens-we demonstrate a manual work reduction of 90.60%, and an average data-quality boost of 4.34%, measured across four use-cases and two tissue stain types.

COVID-19 information retrieval with deep-learning based semantic search, question answering, and abstractive summarization.

The COVID-19 global pandemic has resulted in international efforts to understand, track, and mitigate the disease, yielding a significant corpus of COVID-19 and SARS-CoV-2-related publications across scientific disciplines. Throughout 2020, over 400,000 coronavirus-related publications have been collected through the COVID-19 Open Research Dataset. Here, we present CO-Search, a semantic, multi-stage, search engine designed to handle complex queries over the COVID-19 literature, potentially aiding overburdened health workers in finding scientific answers and avoiding misinformation during a time of crisis. CO-Search is built from two sequential parts: a hybrid semantic-keyword retriever, which takes an input query and returns a sorted list of the 1000 most relevant documents, and a re-ranker, which further orders them by relevance. The retriever is composed of a deep learning model (Siamese-BERT) that encodes query-level meaning, along with two keyword-based models (BM25, TF-IDF) that emphasize the most important words of a query. The re-ranker assigns a relevance score to each document, computed from the outputs of (1) a question-answering module which gauges how much each document answers the query, and (2) an abstractive summarization module which determines how well a query matches a generated summary of the document. To account for the relatively limited dataset, we develop a text augmentation technique which splits the documents into pairs of paragraphs and the citations contained in them, creating millions of (citation title, paragraph) tuples for training the retriever. We evaluate our system ( http://einstein.ai/covid ) on the data of the TREC-COVID information retrieval challenge, obtaining strong performance across multiple key information retrieval metrics.

Deep learning-enabled medical computer vision.

A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields-including medicine-to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques-powered by deep learning-for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit-including cardiology, pathology, dermatology, ophthalmology-and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies.

Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains.

For newly diagnosed breast cancer, estrogen receptor status (ERS) is a key molecular marker used for prognosis and treatment decisions. During clinical management, ERS is determined by pathologists from immunohistochemistry (IHC) staining of biopsied tissue for the targeted receptor, which highlights the presence of cellular surface antigens. This is an expensive, time-consuming process which introduces discordance in results due to variability in IHC preparation and pathologist subjectivity. In contrast, hematoxylin and eosin (H&E) staining-which highlights cellular morphology-is quick, less expensive, and less variable in preparation. Here we show that machine learning can determine molecular marker status, as assessed by hormone receptors, directly from cellular morphology. We develop a multiple instance learning-based deep neural network that determines ERS from H&E-stained whole slide images (WSI). Our algorithm-trained strictly with WSI-level annotations-is accurate on a varied, multi-country dataset of 3,474 patients, achieving an area under the curve (AUC) of 0.92 for sensitivity and specificity. Our approach has the potential to augment clinicians' capabilities in cancer prognosis and theragnosis by harnessing biological signals imperceptible to the human eye.

Dye-sensitized solar cells under ambient light powering machine learning: towards autonomous smart sensors for the internet of things.

The field of photovoltaics gives the opportunity to make our buildings ''smart'' and our portable devices "independent", provided effective energy sources can be developed for use in ambient indoor conditions. To address this important issue, ambient light photovoltaic cells were developed to power autonomous Internet of Things (IoT) devices, capable of machine learning, allowing the on-device implementation of artificial intelligence. Through a novel co-sensitization strategy, we tailored dye-sensitized photovoltaic cells based on a copper(ii/i) electrolyte for the generation of power under ambient lighting with an unprecedented conversion efficiency (34%, 103 µW cm-2 at 1000 lux; 32.7%, 50 µW cm-2 at 500 lux and 31.4%, 19 µW cm-2 at 200 lux from a fluorescent lamp). A small array of DSCs with a joint active area of 16 cm2 was then used to power machine learning on wireless nodes. The collection of 0.947 mJ or 2.72 × 1015 photons is needed to compute one inference of a pre-trained artificial neural network for MNIST image classification in the employed set up. The inference accuracy of the network exceeded 90% for standard test images and 80% using camera-acquired printed MNIST-digits. Quantization of the neural network significantly reduced memory requirements with a less than 0.1% loss in accuracy compared to a full-precision network, making machine learning inferences on low-power microcontrollers possible. 152 J or 4.41 × 1020 photons required for training and verification of an artificial neural network were harvested with 64 cm2 photovoltaic area in less than 24 hours under 1000 lux illumination. Ambient light harvesters provide a new generation of self-powered and "smart" IoT devices powered through an energy source that is largely untapped.