Tumor progression and the efficacy of immunotherapy are strongly influenced by the composition and abundance of immune cells in the tumor microenvironment. Due to the limitations of direct measurement methods, computational algorithms are often used to infer immune cell composition from bulk tumor transcriptome profiles. These estimated tumor immune infiltrate populations have been associated with genomic and transcriptomic changes in the tumors, providing insight into tumor–immune interactions. However, such investigations on large-scale public data remain challenging. To lower the barriers for the analysis of complex tumor–immune interactions, we significantly improved our previous web platform TIMER. Instead of just using one algorithm, TIMER2.0 (http://timer.cistrome.org/) provides more robust estimation of immune infiltration levels for The Cancer Genome Atlas (TCGA) or user-provided tumor profiles using six state-of-the-art algorithms. TIMER2.0 provides four modules for investigating the associations between immune infiltrates and genetic or clinical features, and four modules for exploring cancer-related associations in the TCGA cohorts. Each module can generate a functional heatmap table, enabling the user to easily identify significant associations in multiple cancer types simultaneously. Overall, the TIMER2.0 web server provides comprehensive analysis and visualization functions of tumor infiltrating immune cells.

The goal of pharmacovigilance is to detect, monitor, characterize and prevent adverse drug events (ADEs) with pharmaceutical products. This article is a comprehensive structured review of recent advances in applying natural language processing (NLP) to electronic health record (EHR) narratives for pharmacovigilance. We review methods of varying complexity and problem focus, summarize the current state-of-the-art in methodology advancement, discuss limitations and point out several promising future directions. The ability to accurately capture both semantic and syntactic structures in clinical narratives becomes increasingly critical to enable efficient and accurate ADE detection. Significant progress has been made in algorithm development and resource construction since 2000. Since 2012, statistical analysis and machine learning methods have gained traction in automation of ADE mining from EHR narratives. Current state-of-the-art methods for NLP-based ADE detection from EHRs show promise regarding their integration into production pharmacovigilance systems. In addition, integrating multifaceted, heterogeneous data sources has shown promise in improving ADE detection and has become increasingly adopted. On the other hand, challenges and opportunities remain across the frontier of NLP application to EHR-based pharmacovigilance, including proper characterization of ADE context, differentiation between off- and on-label drug-use ADEs, recognition of the importance of polypharmacy-induced ADEs, better integration of heterogeneous data sources, creation of shared corpora, and organization of shared-task challenges to advance the state-of-the-art.

Immune checkpoint blockade (ICB) therapy revolutionized cancer treatment, but many patients with impaired MHC-I expression remain refractory. Here, we combined FACS-based genome-wide CRISPR screens with a data-mining approach to identify drugs that can upregulate MHC-I without inducing PD-L1. CRISPR screening identified TRAF3, a suppressor of the NFκB pathway, as a negative regulator of MHC-I but not PD-L1. The Traf3-knockout gene expression signature is associated with better survival in ICB-naïve patients with cancer and better ICB response. We then screened for drugs with similar transcriptional effects as this signature and identified Second Mitochondria-derived Activator of Caspase (SMAC) mimetics. We experimentally validated that the SMAC mimetic birinapant upregulates MHC-I, sensitizes cancer cells to T cell–dependent killing, and adds to ICB efficacy. Our findings provide preclinical rationale for treating tumors expressing low MHC-I expression with SMAC mimetics to enhance sensitivity to immunotherapy. The approach used in this study can be generalized to identify other drugs that enhance immunotherapy efficacy. Significance: MHC-I loss or downregulation in cancer cells is a major mechanism of resistance to T cell–based immunotherapies. Our study reveals that birinapant may be used for patients with low baseline MHC-I to enhance ICB response. This represents promising immunotherapy opportunities given the biosafety profile of birinapant from multiple clinical trials. This article is highlighted in the In This Issue feature, p. 1307

This article reviews recent advances in applying natural language processing (NLP) to Electronic Health Records (EHRs) for computational phenotyping. NLP-based computational phenotyping has numerous applications including diagnosis categorization, novel phenotype discovery, clinical trial screening, pharmacogenomics, drug-drug interaction (DDI) and adverse drug event (ADE) detection, as well as genome-wide and phenome-wide association studies. Significant progress has been made in algorithm development and resource construction for computational phenotyping. Among the surveyed methods, well-designed keyword search and rule-based systems often achieve good performance. However, the construction of keyword and rule lists requires significant manual effort, which is difficult to scale. Supervised machine learning models have been favored because they are capable of acquiring both classification patterns and structures from data. Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes. Integrating heterogeneous data sources have become increasingly important and have shown promise in improving model performance. Often better performance is achieved by combining multiple modalities of information. Despite these many advances, challenges and opportunities remain for NLP-based computational phenotyping, including better model interpretability and generalizability, and proper characterization of feature relations in clinical narratives.

The recent advancement in spatial transcriptomics technology has enabled multiplexed profiling of cellular transcriptomes and spatial locations. As the capacity and efficiency of the experimental technologies continue to improve, there is an emerging need for the development of analytical approaches. Furthermore, with the continuous evolution of sequencing protocols, the underlying assumptions of current analytical methods need to be re-evaluated and adjusted to harness the increasing data complexity. To motivate and aid future model development, we herein review the recent development of statistical and machine learning methods in spatial transcriptomics, summarize useful resources, and highlight the challenges and opportunities ahead.