The determination of molecular features that mediate clinically aggressive phenotypes in prostate cancer remains a major biological and clinical challenge
. Recent advances in interpretability of ...machine learning models as applied to biomedical problems may enable discovery and prediction in clinical cancer genomics
. Here we developed P-NET-a biologically informed deep learning model-to stratify patients with prostate cancer by treatment-resistance state and evaluate molecular drivers of treatment resistance for therapeutic targeting through complete model interpretability. We demonstrate that P-NET can predict cancer state using molecular data with a performance that is superior to other modelling approaches. Moreover, the biological interpretability within P-NET revealed established and novel molecularly altered candidates, such as MDM4 and FGFR1, which were implicated in predicting advanced disease and validated in vitro. Broadly, biologically informed fully interpretable neural networks enable preclinical discovery and clinical prediction in prostate cancer and may have general applicability across cancer types.
Alterations in DNA damage response (DDR) genes are common in advanced prostate tumors and are associated with unique genomic and clinical features. ATM is a DDR kinase that has a central role in ...coordinating DNA repair and cell-cycle response following DNA damage, and
alterations are present in approximately 5% of advanced prostate tumors. Recently, inhibitors of PARP have demonstrated activity in advanced prostate tumors harboring DDR gene alterations, particularly in tumors with
alterations. However, the role of alterations in DDR genes beyond
in mediating PARP inhibitor sensitivity is poorly understood. To define the role of
loss in prostate tumor DDR function and sensitivity to DDR-directed agents, we created a series of
-deficient preclinical prostate cancer models and tested the impact of
loss on DNA repair function and therapeutic sensitivities.
loss altered DDR signaling, but did not directly impact homologous recombination function. Furthermore,
loss did not significantly impact sensitivity to PARP inhibition but robustly sensitized to inhibitors of the related DDR kinase ATR. These results have important implications for planned and ongoing prostate cancer clinical trials and suggest that patients with tumor
alterations may be more likely to benefit from ATR inhibitor than PARP inhibitor therapy. SIGNIFICANCE: ATM loss occurs in a subset of prostate tumors. This study shows that deleting ATM in prostate cancer models does not significantly increase sensitivity to PARP inhibition but does sensitize to ATR inhibition.
Immune-checkpoint blockade (ICB) has demonstrated efficacy in many tumor types, but predictors of responsiveness to anti-PD1 ICB are incompletely characterized. In this study, we analyzed a ...clinically annotated cohort of patients with melanoma (n = 144) treated with anti-PD1 ICB, with whole-exome and whole-transcriptome sequencing of pre-treatment tumors. We found that tumor mutational burden as a predictor of response was confounded by melanoma subtype, whereas multiple novel genomic and transcriptomic features predicted selective response, including features associated with MHC-I and MHC-II antigen presentation. Furthermore, previous anti-CTLA4 ICB exposure was associated with different predictors of response compared to tumors that were naive to ICB, suggesting selective immune effects of previous exposure to anti-CTLA4 ICB. Finally, we developed parsimonious models integrating clinical, genomic and transcriptomic features to predict intrinsic resistance to anti-PD1 ICB in individual tumors, with validation in smaller independent cohorts limited by the availability of comprehensive data. Broadly, we present a framework to discover predictive features and build models of ICB therapeutic response.
To accelerate cancer research that correlates biomarkers with clinical endpoints, methods are needed to ascertain outcomes from electronic health records at scale. Here, we train deep natural ...language processing (NLP) models to extract outcomes for participants with any of 7 solid tumors in a precision oncology study. Outcomes are extracted from 305,151 imaging reports for 13,130 patients and 233,517 oncologist notes for 13,511 patients, including patients with 6 additional cancer types. NLP models recapitulate outcome annotation from these documents, including the presence of cancer, progression/worsening, response/improvement, and metastases, with excellent discrimination (AUROC > 0.90). Models generalize to cancers excluded from training and yield outcomes correlated with survival. Among patients receiving checkpoint inhibitors, we confirm that high tumor mutation burden is associated with superior progression-free survival ascertained using NLP. Here, we show that deep NLP can accelerate annotation of molecular cancer datasets with clinically meaningful endpoints to facilitate discovery.
Immune checkpoint blockade (ICB) therapies, which potentiate the body's natural immune response against tumor cells, have shown immense promise in the treatment of various cancers. Currently, tumor ...mutational burden (TMB) and programmed death ligand 1 (PD-L1) expression are the primary biomarkers evaluated for clinical management of cancer patients across histologies. However, the wide range of responses has demonstrated that the specific molecular and genetic characteristics of each patient's tumor and immune system must be considered to maximize treatment efficacy. Here, we review the various biological pathways and emerging biomarkers implicated in response to PD-(L)1 and cytotoxic T lymphocyte-associated antigen 4 (CTLA-4) therapies, including oncogenic signaling pathways, human leukocyte antigen (HLA) variability, mutation and neoantigen burden, microbiome composition, endogenous retroviruses (ERV), and deficiencies in chromatin remodeling and DNA damage repair (DDR) machinery. We also discuss several mechanisms that have been observed to confer resistance to ICB, such as loss of phosphatase and tensin homolog (PTEN), loss of major histocompatibility complex (MHC) I/II expression, and activation of the indoleamine 2,3-dioxygenase 1 (IDO1) and transforming growth factor beta (TGFβ) pathways. Clinical trials testing the combination of PD-(L)1 or CTLA-4 blockade with molecular mediators of these pathways are becoming more common and may hold promise for improving treatment efficacy and response. Ultimately, some of the genes and molecular mechanisms highlighted in this review may serve as novel biological targets or therapeutic vulnerabilities to improve clinical outcomes in patients.
Longitudinal data on key cancer outcomes for clinical research, such as response to treatment and disease progression, are not captured in standard cancer registry reporting. Manual extraction of ...such outcomes from unstructured electronic health records is a slow, resource-intensive process. Natural language processing (NLP) methods can accelerate outcome annotation, but they require substantial labeled data. Transfer learning based on language modeling, particularly using the Transformer architecture, has achieved improvements in NLP performance. However, there has been no systematic evaluation of NLP model training strategies on the extraction of cancer outcomes from unstructured text. We evaluated the performance of nine NLP models at the two tasks of identifying cancer response and cancer progression within imaging reports at a single academic center among patients with non-small cell lung cancer. We trained the classification models under different conditions, including training sample size, classification architecture, and language model pre-training. The training involved a labeled dataset of 14,218 imaging reports for 1112 patients with lung cancer. A subset of models was based on a pre-trained language model, DFCI-ImagingBERT, created by further pre-training a BERT-based model using an unlabeled dataset of 662,579 reports from 27,483 patients with cancer from our center. A classifier based on our DFCI-ImagingBERT, trained on more than 200 patients, achieved the best results in most experiments; however, these results were marginally better than simpler "bag of words" or convolutional neural network models. When developing AI models to extract outcomes from imaging reports for clinical cancer research, if computational resources are plentiful but labeled training data are limited, large language models can be used for zero- or few-shot learning to achieve reasonable performance. When computational resources are more limited but labeled training data are readily available, even simple machine learning architectures can achieve good performance for such tasks.
Gene regulatory networks (GRNs) provide a representation of relationships between regulators and their target genes. Several methods for GRN inference, both unsupervised and supervised, have been ...developed to date. Because regulatory relationships consistently reprogram in diverse tissues or under different conditions, GRNs inferred without specific biological contexts are of limited applicability. In this report, a machine learning approach is presented to predict GRNs specific to developing
embryos. We developed the Beacon GRN inference tool to predict GRNs occurring during seed development in Arabidopsis based on a support vector machine (SVM) model. We developed both global and local inference models and compared their performance, demonstrating that local models are generally superior for our application. Using both the expression levels of the genes expressed in developing embryos and prior known regulatory relationships, GRNs were predicted for specific embryonic developmental stages. The targets that are strongly positively correlated with their regulators are mostly expressed at the beginning of seed development. Potential direct targets were identified based on a match between the promoter regions of these inferred targets and the
elements recognized by specific regulators. Our analysis also provides evidence for previously unknown inhibitory effects of three positive regulators of gene expression. The Beacon GRN inference tool provides a valuable model system for context-specific GRN inference and is freely available at https://github.com/BeaconProjectAtVirginiaTech/beacon_network_inference.git.
Taxonomy of plant pathogenic bacteria is challenging because pathogens of different crops often belong to the same named species but current taxonomy does not provide names for bacteria below the ...subspecies level. The introduction of the host range-based pathovar system in the 1980s provided a temporary solution to this problem but has many limitations. The affordability of genome sequencing now provides the opportunity for developing a new genome-based taxonomic framework. We already proposed to name individual bacterial isolates based on pairwise genome similarity. Here, we expand on this idea and propose to use genome similarity-based codes, which we now call life identification numbers (LINs), to describe and name bacterial taxa. Using 93 genomes of Pseudomonas syringae sensu lato, LINs were compared with a P. syringae genome tree whereby the assigned LINs were found to be informative of a majority of phylogenetic relationships. LINs also reflected host range and outbreak association for strains of P. syringae pathovar actinidiae, a pathovar for which many genome sequences are available. We conclude that LINs could provide the basis for a new taxonomic framework to address the shortcomings of the current pathovar system and to complement the current taxonomic system of bacteria in general.