6 May 2019 in Nature Biotechnology
Integration of single-cell RNA sequencing (scRNA-seq) data from multiple experiments, laboratories and technologies can uncover biological insights, but current methods for scRNA-seq data integration are limited by a requirement for datasets to derive from functionally similar cells. We present Scanorama, an algorithm that identifies and merges the shared cell types among all pairs of datasets and accurately integrates heterogeneous collections of scRNA-seq data. We applied Scanorama to integrate and remove batch effects across 105,476 cells from 26 diverse scRNA-seq experiments representing 9 different technologies. Scanorama is sensitive to subtle temporal changes within the same cell lineage, successfully integrating functionally similar cells across time series data of CD14+ monocytes at different stages of differentiation into macrophages. Finally, we show that Scanorama is orders of magnitude faster than existing techniques and can integrate a collection of 1,095,538 cells in just ~9 h.
15 January 2021 in Science
Natural language predicts viral escape: Viral mutations that evade neutralizing antibodies, an occurrence known as viral escape, can occur and may impede the development of vaccines. To predict which mutations may lead to viral escape, Hie et al. used a machine learning technique for natural language processing with two components: grammar (or syntax) and meaning (or semantics) (see the Perspective by Kim and Przytycka). Three different unsupervised language models were constructed for influenza A hemagglutinin, HIV-1 envelope glycoprotein, and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike glycoprotein. Semantic landscapes for these viruses predicted viral escape mutations that produce sequences that are syntactically and/or grammatically correct but effectively different in semantics and thus able to evade the immune system. Science , this issue p. 284 ; see also p. 233
27 April 2022 in Immunity
Mycobacterium tuberculosis lung infection results in a complex multicellular structure: the granuloma. In some granulomas, immune activity promotes bacterial clearance, but in others, bacteria persist and grow. We identified correlates of bacterial control in cynomolgus macaque lung granulomas by co-registering longitudinal positron emission tomography and computed tomography imaging, single-cell RNA sequencing, and measures of bacterial clearance. Bacterial persistence occurred in granulomas enriched for mast, endothelial, fibroblast, and plasma cells, signaling amongst themselves via type 2 immunity and wound-healing pathways. Granulomas that drove bacterial control were characterized by cellular ecosystems enriched for type 1-type 17, stem-like, and cytotoxic T cells engaged in pro-inflammatory signaling networks involving diverse cell populations. Granulomas that arose later in infection displayed functional characteristics of restrictive granulomas and were more capable of killing Mtb. Our results define the complex multicellular ecosystems underlying (lack of) granuloma resolution and highlight host immune targets that can be leveraged to develop new vaccine and therapeutic strategies for TB.
8 June 2023 in Proceedings of the National Academy of Sciences
Sequence-based prediction of drug–target interactions has the potential to accelerate drug discovery by complementing experimental screens. Such computational prediction needs to be generalizable and scalable while remaining sensitive to subtle variations in the inputs. However, current computational techniques fail to simultaneously meet these goals, often sacrificing performance of one to achieve the others. We develop a deep learning model, ConPLex, successfully leveraging the advances in pretrained protein language models (“PLex”) and employing a protein-anchored contrastive coembedding (“Con”) to outperform state-of-the-art approaches. ConPLex achieves high accuracy, broad adaptivity to unseen data, and specificity against decoy compounds. It makes predictions of binding based on the distance between learned representations, enabling predictions at the scale of massive compound libraries and the human proteome. Experimental testing of 19 kinase-drug interaction predictions validated 12 interactions, including four with subnanomolar affinity, plus a strongly binding EPHB1 inhibitor ( K
D
= 1.3 nM). Furthermore, ConPLex embeddings are interpretable, which enables us to visualize the drug–target embedding space and use embeddings to characterize the function of human cell-surface proteins. We anticipate that ConPLex will facilitate efficient drug discovery by making highly sensitive in silico drug screening feasible at the genome scale. ConPLex is available open source at https://ConPLex.csail.mit.edu .
1 November 2020 in Cell Systems
Machine learning that generates biological hypotheses has transformative potential, but most learning algorithms are susceptible to pathological failure when exploring regimes beyond the training data distribution. A solution to address this issue is to quantify prediction uncertainty so that algorithms can gracefully handle novel phenomena that confound standard methods. Here, we demonstrate the broad utility of robust uncertainty prediction in biological discovery. By leveraging Gaussian process-based uncertainty prediction on modern pre-trained features, we train a model on just 72 compounds to make predictions over a 10,833-compound library, identifying and experimentally validating compounds with nanomolar affinity for diverse kinases and whole-cell growth inhibition of Mycobacterium tuberculosis. Uncertainty facilitates a tight iterative loop between computation and experimentation and generalizes across biological domains as diverse as protein engineering and single-cell transcriptomics. More broadly, our work demonstrates that uncertainty should play a key role in the increasing adoption of machine learning algorithms into the experimental lifecycle.
23 February 2022 in Science Translational Medicine
SARS-CoV-2 evolution threatens vaccine- and natural infection–derived immunity and the efficacy of therapeutic antibodies. To improve public health preparedness, we sought to predict which existing amino acid mutations in SARS-CoV-2 might contribute to future variants of concern. We tested the predictive value of features comprising epidemiology, evolution, immunology, and neural network–based protein sequence modeling and identified primary biological drivers of SARS-CoV-2 intrapandemic evolution. We found evidence that ACE2-mediated transmissibility and resistance to population-level host immunity has waxed and waned as a primary driver of SARS-CoV-2 evolution over time. We retroactively identified with high accuracy (area under the receiver operator characteristic curve = 0.92 to 0.97) mutations that will spread, at up to 4 months in advance, across different phases of the pandemic. The behavior of the model was consistent with a plausible causal structure where epidemiological covariates combine the effects of diverse and shifting drivers of viral fitness. We applied our model to forecast mutations that will spread in the future and characterize how these mutations affect the binding of therapeutic antibodies. These findings demonstrate that it is possible to forecast the driver mutations that could appear in emerging SARS-CoV-2 variants of concern. We validated this result against Omicron, showing elevated predictive scores for its component mutations before emergence and rapid score increase across daily forecasts during emergence. This modeling approach may be applied to any rapidly evolving pathogens with sufficiently dense genomic surveillance data, such as influenza, and unknown future pandemic viruses.