Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

oncology Oncology

A non-antibiotic-disrupted gut microbiome is associated with clinical responses to CD19-CAR-T cell cancer immunotherapy.

In Nature medicine ; h5-index 170.0

Increasing evidence suggests that the gut microbiome may modulate the efficacy of cancer immunotherapy. In a B cell lymphoma patient cohort from five centers in Germany and the United States (Germany, n = 66; United States, n = 106; total, n = 172), we demonstrate that wide-spectrum antibiotics treatment ('high-risk antibiotics') prior to CD19-targeted chimeric antigen receptor (CAR)-T cell therapy is associated with adverse outcomes, but this effect is likely to be confounded by an increased pretreatment tumor burden and systemic inflammation in patients pretreated with high-risk antibiotics. To resolve this confounding effect and gain insights into antibiotics-masked microbiome signals impacting CAR-T efficacy, we focused on the high-risk antibiotics non-exposed patient population. Indeed, in these patients, significant correlations were noted between pre-CAR-T infusion Bifidobacterium longum and microbiome-encoded peptidoglycan biosynthesis, and CAR-T treatment-associated 6-month survival or lymphoma progression. Furthermore, predictive pre-CAR-T treatment microbiome-based machine learning algorithms trained on the high-risk antibiotics non-exposed German cohort and validated by the respective US cohort robustly segregated long-term responders from non-responders. Bacteroides, Ruminococcus, Eubacterium and Akkermansia were most important in determining CAR-T responsiveness, with Akkermansia also being associated with pre-infusion peripheral T cell levels in these patients. Collectively, we identify conserved microbiome features across clinical and geographical variations, which may enable cross-cohort microbiome-based predictions of outcomes in CAR-T cell immunotherapy.

Stein-Thoeringer Christoph K, Saini Neeraj Y, Zamir Eli, Blumenberg Viktoria, Schubert Maria-Luisa, Mor Uria, Fante Matthias A, Schmidt Sabine, Hayase Eiko, Hayase Tomo, Rohrbach Roman, Chang Chia-Chi, McDaniel Lauren, Flores Ivonne, Gaiser Rogier, Edinger Matthias, Wolff Daniel, Heidenreich Martin, Strati Paolo, Nair Ranjit, Chihara Dai, Fayad Luis E, Ahmed Sairah, Iyer Swaminathan P, Steiner Raphael E, Jain Preetesh, Nastoupil Loretta J, Westin Jason, Arora Reetakshi, Wang Michael L, Turner Joel, Menges Meghan, Hidalgo-Vargas Melanie, Reid Kayla, Dreger Peter, Schmitt Anita, Müller-Tidow Carsten, Locke Frederick L, Davila Marco L, Champlin Richard E, Flowers Christopher R, Shpall Elizabeth J, Poeck Hendrik, Neelapu Sattva S, Schmitt Michael, Subklewe Marion, Jain Michael D, Jenq Robert R, Elinav Eran

2023-Mar-13

oncology Oncology

A generalizable machine learning framework for classifying DNA repair defects using ctDNA exomes.

In NPJ precision oncology

Specific classes of DNA damage repair (DDR) defect can drive sensitivity to emerging therapies for metastatic prostate cancer. However, biomarker approaches based on DDR gene sequencing do not accurately predict DDR deficiency or treatment benefit. Somatic alteration signatures may identify DDR deficiency but historically require whole-genome sequencing of tumour tissue. We assembled whole-exome sequencing data for 155 high ctDNA fraction plasma cell-free DNA and matched leukocyte DNA samples from patients with metastatic prostate or bladder cancer. Labels for DDR gene alterations were established using deep targeted sequencing. Per sample mutation and copy number features were used to train XGBoost ensemble models. Naive somatic features and trinucleotide signatures were associated with specific DDR gene alterations but insufficient to resolve each class. Conversely, XGBoost-derived models showed strong performance including an area under the curve of 0.99, 0.99 and 1.00 for identifying BRCA2, CDK12, and mismatch repair deficiency in metastatic prostate cancer. Our machine learning approach re-classified several samples exhibiting genomic features inconsistent with original labels, identified a metastatic bladder cancer sample with a homozygous BRCA2 copy loss, and outperformed an existing exome-based classifier for BRCA2 deficiency. We present DARC Sign (DnA Repair Classification SIGNatures); a public machine learning tool leveraging clinically-practical liquid biopsy specimens for simultaneously identifying multiple types of metastatic prostate cancer DDR deficiencies. We posit that it will be useful for understanding differential responses to DDR-directed therapies in ongoing clinical trials and may ultimately enable prospective identification of prostate cancers with phenotypic evidence of DDR deficiency.

Ritch Elie J, Herberts Cameron, Warner Evan W, Ng Sarah W S, Kwan Edmond M, Bacon Jack V W, Bernales Cecily Q, Schönlau Elena, Fonseca Nicolette M, Giri Veda N, Maurice-Dror Corinne, Vandekerkhove Gillian, Jones Steven J M, Chi Kim N, Wyatt Alexander W

2023-Mar-13

General General

Evaluating the use of large language model in identifying top research questions in gastroenterology.

In Scientific reports ; h5-index 158.0

The field of gastroenterology (GI) is constantly evolving. It is essential to pinpoint the most pressing and important research questions. To evaluate the potential of chatGPT for identifying research priorities in GI and provide a starting point for further investigation. We queried chatGPT on four key topics in GI: inflammatory bowel disease, microbiome, Artificial Intelligence in GI, and advanced endoscopy in GI. A panel of experienced gastroenterologists separately reviewed and rated the generated research questions on a scale of 1-5, with 5 being the most important and relevant to current research in GI. chatGPT generated relevant and clear research questions. Yet, the questions were not considered original by the panel of gastroenterologists. On average, the questions were rated 3.6 ± 1.4, with inter-rater reliability ranging from 0.80 to 0.98 (p < 0.001). The mean grades for relevance, clarity, specificity, and originality were 4.9 ± 0.1, 4.6 ± 0.4, 3.1 ± 0.2, 1.5 ± 0.4, respectively. Our study suggests that Large Language Models (LLMs) may be a useful tool for identifying research priorities in the field of GI, but more work is needed to improve the novelty of the generated research questions.

Lahat Adi, Shachar Eyal, Avidan Benjamin, Shatz Zina, Glicksberg Benjamin S, Klang Eyal

2023-Mar-13

General General

Benchmarking machine learning robustness in Covid-19 genome sequence classification.

In Scientific reports ; h5-index 158.0

The rapid spread of the COVID-19 pandemic has resulted in an unprecedented amount of sequence data of the SARS-CoV-2 genome-millions of sequences and counting. This amount of data, while being orders of magnitude beyond the capacity of traditional approaches to understanding the diversity, dynamics, and evolution of viruses, is nonetheless a rich resource for machine learning (ML) approaches as alternatives for extracting such important information from these data. It is of hence utmost importance to design a framework for testing and benchmarking the robustness of these ML models. This paper makes the first effort (to our knowledge) to benchmark the robustness of ML models by simulating biological sequences with errors. In this paper, we introduce several ways to perturb SARS-CoV-2 genome sequences to mimic the error profiles of common sequencing platforms such as Illumina and PacBio. We show from experiments on a wide array of ML models that some simulation-based approaches with different perturbation budgets are more robust (and accurate) than others for specific embedding methods to certain noise simulations on the input sequences. Our benchmarking framework may assist researchers in properly assessing different ML models and help them understand the behavior of the SARS-CoV-2 virus or avoid possible future pandemics.

Ali Sarwan, Sahoo Bikram, Zelikovsky Alexander, Chen Pin-Yu, Patterson Murray

2023-Mar-13

Public Health Public Health

Metabolomic profiles in night shift workers: A cross-sectional study on hospital female nurses.

In Frontiers in public health

BACKGROUND AND AIM : Shift work, especially including night shifts, has been found associated with several diseases, including obesity, diabetes, cancers, and cardiovascular, mental, gastrointestinal and sleep disorders. Metabolomics (an omics-based methodology) may shed light on early biological alterations underlying these associations. We thus aimed to evaluate the effect of night shift work (NSW) on serum metabolites in a sample of hospital female nurses.

METHODS : We recruited 46 nurses currently working in NSW in Milan (Italy), matched to 51 colleagues not employed in night shifts. Participants filled in a questionnaire on demographics, lifestyle habits, personal and family health history and work, and donated a blood sample. The metabolome was evaluated through a validated targeted approach measuring 188 metabolites. Only metabolites with at least 50% observations above the detection limit were considered, after standardization and log-transformation. Associations between each metabolite and NSW were assessed applying Tobit regression models and Random Forest, a machine-learning algorithm.

RESULTS : When comparing current vs. never night shifters, we observed lower levels of 21 glycerophospholipids and 6 sphingolipids, and higher levels of serotonin (+171.0%, 95%CI: 49.1-392.7), aspartic acid (+155.8%, 95%CI: 40.8-364.7), and taurine (+182.1%, 95%CI: 67.6-374.9). The latter was higher in former vs. never night shifters too (+208.8%, 95%CI: 69.2-463.3). Tobit regression comparing ever (i.e., current + former) and never night shifters returned similar results. Years worked in night shifts did not seem to affect metabolite levels. The Random-Forest algorithm confirmed taurine and aspartic acid among the most important variables in discriminating current vs. never night shifters.

CONCLUSIONS : This study, although based on a small sample size, shows altered levels of some metabolites in night shift workers. If confirmed, our results may shed light on early biological alterations that might be related to adverse health effects of NSW.

Borroni Elisa, Frigerio Gianfranco, Polledri Elisa, Mercadante Rosa, Maggioni Cristina, Fedrizzi Luca, Pesatori Angela Cecilia, Fustinoni Silvia, Carugno Michele

2023

Random Forest, Tobit regression, machine-learning, night shift work, nurses, occupational health, targeted metabolomics

General General

Situation-Aware BDI Reasoning to Detect Early Symptoms of Covid 19 Using Smartwatch.

In IEEE sensors journal

Ambient intelligence plays a crucial role in healthcare situations. It provides a certain way to deal with emergencies to provide the essential resources such as nearest hospitals and emergency stations promptly to avoid deaths. Since the outbreak of Covid-19, several artificial intelligence techniques have been used. However, situation awareness is a key aspect to handling any pandemic situation. The situation-awareness approach gives patients a routine life where they are continuously monitored by caregivers through wearable sensors and alert the practitioners in case of any patient emergency. Therefore, in this paper, we propose a situation-aware mechanism to detect Covid-19 systems early and alert the user to be self-aware regarding the situation to take precautions if the situation seems unlikely to be normal. We provide Belief-Desire-Intention intelligent reasoning mechanism for the system to analyze the situation after acquiring the data from the wearable sensors and alert the user according to their environment. We use the case study for further demonstration of our proposed framework. We model the proposed system by temporal logic and map the system illustration into a simulation tool called NetLogo to determine the results of the proposed system.

Saleem Kiran, Saleem Misbah, Ahmad Rana Zeeshan, Javed Abdul Rehman, Alazab Mamoun, Gadekallu Thippa Reddy, Suleman Ahmad

2023-Jan

Covid-19, NetLogo, Situation-awareness, ambient intelligence, belief-desire-intention (BDI), healthcare