Radiologic screening of high-risk adults reduces lung-cancer-related mortality; however, a small minority of eligible individuals undergo such screening in the United States. The availability of blood-based tests could increase screening uptake. Here researchers introduce improvements to cancer personalized profiling by deep sequencing (CAPP-Seq), a method for the analysis of circulating tumour DNA (ctDNA), to better facilitate screening applications. They show that, although levels are very low in early-stage lung cancers, ctDNA is present prior to treatment in most patients and its presence is strongly prognostic. They develop and prospectively validate a machine-learning method termed'lung cancer likelihood in plasma' (Lung-CLiP), which can robustly discriminate early-stage lung cancer patients from risk-matched controls.

Some -omics tools can be more accurate, sensitive or efficient than others. Yet benchmarking is no tell-all. Inflammatory bowel disease (IBD) is a complex genetic disease that is instigated and amplified by the confluence of multiple genetic and environmental variables that perturb the immune–microbiome axis. Here the authors describe IBD as a model disease in the context of leveraging human genetics to dissect interactions in cellular and molecular pathways that regulate homeostasis of the mucosal immune system. Machine learning can tell different types of knot apart just by'looking' at them.

Intensive-care clinicians are presented with large quantities of measurements from multiple monitoring systems. Researchers used machine learning to develop an early-warning system that integrates measurements from multiple organ systems using a high-resolution database with 240 patient-years of data. It predicts 90% of circulatory-failure events in the test set, with 82% identified more than 2 h in advance, resulting in an area under the receiver operating characteristic curve of 0.94 and an area under the precision-recall curve of 0.63. ProteoClade is a Python toolkit that performs taxa-specific peptide assignment, protein inference, and quantitation for multi-species proteomics experiments. ProteoClade scales to hundreds of millions of protein sequences, requires minimal computational resources, and is open source, multi-platform, and accessible to non-programmers.

Digitized patient charts were supposed to revolutionize medical practice. Artificial intelligence could help unlock their potential. Identification of functional elements for a protein of interest is important for achieving a mechanistic understanding. Here, researchers report a strategy, PArsing fragmented DNA Sequences from CRISPR Tiling MUtagenesis Screening (PASTMUS), which provides a streamlined workflow and a bioinformatics pipeline to identify critical amino acids of proteins in their native biological contexts. Determining how chromosomes are positioned and folded within the nucleus is critical to understanding the role of chromatin topology in gene regulation.

The single-molecule multiplex chromatin interaction data are generated by emerging 3D genome mapping technologies such as GAM, SPRITE, and ChIA-Drop. These datasets provide insights into high-dimensional chromatin organization, yet introduce new computational challenges. MIA-Sig is an algorithmic solution based on signal processing and information theory. The authors demonstrate its ability to de-noise the multiplex data, assess the statistical significance of chromatin complexes, and identify topological domains and frequent inter-domain contacts. Identifying personalized driver genes that lead to particular cancer initiation and progression of individual patient is one of the biggest challenges in precision medicine.

Researchers have generated a diverse repository of 838,644 histopathologic images and used them to optimize and discretize learned representations into 512-dimensional feature vectors. They show that individual machine-engineered features correlate with salient human-derived morphologic constructs and ontological relationships. Dynamic and reversible RNA modifications such as N6-methyladenosine (m6A) can play important roles in regulating messenger RNA (mRNA) splicing, export, stability and translation. Researchers developed RNAmod (https://bioinformatics.sc.cn/RNAmod), an interactive, one-stop, web-based platform for the automated analysis, annotation, and visualization of mRNA modifications in 21 species. MOLI, a multi-omics late integration method based on deep neural networks, takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction.

Reseachers benchmarked 22 classification methods that automatically assign cell identities including single-cell-specific and general-purpose classifiers. The performance of the methods is evaluated using 27 publicly available single-cell RNA sequencing datasets of different sizes, technologies, species, and levels of complexity. The general-purpose support vector machine classifier has overall the best performance across the different experiments. Researchers present a novel algorithm for predicting genetic ancestry using only variables that are routinely captured in electronic health records (EHRs), such as self-reported race and ethnicity, and condition billing codes. Using patients that have both genetic and clinical information at Columbia University / New York-Presbyterian Irving Medical Center, they developed a pipeline that uses only clinical data to predict the genetic ancestry of all patients of which more than 80% identify as other or unknown.

The conventional model of oncogenic RAS-MAPK pathway signaling in cancer suggests that mutations in the pathway render downstream signaling largely independent of regulation (autonomous). However, the emerging model of a semiautonomous state through which pathological RAS signaling remains under some control suggests a potential therapeutic opportunity to target upstream regulators, such as SHP2, SOS, and GRB2. Mass spectrometry is a predominant experimental technique in metabolomics and related fields, but metabolite structural elucidation remains highly challenging. Researchers report SIRIUS 4 (https://bio.informatik.uni-jena.de/sirius/), Amazon SageMaker is an end-to-end machine learning platform that enables users to prepare training data and build machine learning models quickly using pre-built Jupyter notebook with pre-built algorithms. In this blog post, the authors use Amazon Rekognition to extract text from the images and Amazon Comprehend Medical to help them to identify and detect the Protected Health Information (PHI).

A cancer-fighting virus has shown some promise against a devastating childhood tumour of the eye. Retinoblastomas are tumours of the developing retina that sometimes result in surgical removal of the eye. This cancer is often caused by mutations that alter a tumour-suppressing protein called RB1. Researchers tested the effects of a genetically engineered virus that infects cancer cells that exhibit altered RB1 activity. The team cultured cells from 12 retinoblastoma samples and found that the virus infected and killed cells in 11 of these cultures.

Silicon Valley is in the midst of a health craze, and it is being driven by "Eastern" medicine. It's been a record year for US medical investing, but investors in Beijing and Shanghai are now increasingly leading the largest deals for US life science and biotech companies. In fact, Chinese venture firms have invested more this year into life science and biotech in the US than they have back home, providing financing for over 300 US-based companies, per Pitchbook. Chinese capital's newfound appetite also flows into the mainland. Business is booming for Chinese medical startups, who are also seeing the strongest year of venture investment ever, with over one hundred companies receiving $4 billion in investment.