Search

Summary: Background: It is uncertain which biological features underpin the response of rectal cancer (RC) to radiotherapy. No biomarker is currently in clinical use to select patients for treatment modifications. Methods: We identified two cohorts of patients (total N = 249) with RC treated with neoadjuvant radiotherapy (45Gy/25) plus fluoropyrimidine. This discovery set included 57 cases with pathological complete response (pCR) to chemoradiotherapy (23%). Pre-treatment cancer biopsies were assessed using transcriptome-wide mRNA expression and targeted DNA sequencing for copy number and driver mutations. Biological candidate and machine learning (ML) approaches were used to identify predictors of pCR to radiotherapy independent of tumour stage. Findings were assessed in 107 cases from an independent validation set (GSE87211). Findings: Three gene expression sets showed significant independent associations with pCR: Fibroblast-TGFβ Response Signature (F-TBRS) with radioresistance; and cytotoxic lymphocyte (CL) expression signature and consensus molecular subtype CMS1 with radiosensitivity. These associations were replicated in the validation cohort. In parallel, a gradient boosting machine model comprising the expression of 33 genes generated in the discovery cohort showed high performance in GSE87211 with 90% sensitivity, 86% specificity. Biological and ML signatures indicated similar mechanisms underlying radiation response, and showed better AUC and p-values than published transcriptomic signatures of radiation response in RC. Interpretation: RCs responding completely to chemoradiotherapy (CRT) have biological characteristics of immune response and absence of immune inhibitory TGFβ signalling. These tumours may be identified with a potential biomarker based on a 33 gene expression signature. This could help select patients likely to respond to treatment with a primary radiotherapy approach as for anal cancer. Conversely, those with predicted radioresistance may be candidates for clinical trials evaluating addition of immune-oncology agents and stromal TGFβ signalling inhibition. Funding: The Stratification in Colorectal Cancer Consortium (S:CORT) was funded by the Medical Research Council and Cancer Research UK (MR/M016587/1).

Drug-Induced Liver Injury (DILI), despite its low occurrence rate, can cause severe side effects or even lead to death. Thus, it is one of the leading causes for terminating the development of new, and restricting the use of already-circulating, drugs. Moreover, its multifactorial nature, combined with a clinical presentation that often mimics other liver diseases, complicate the identification of DILI-related (or “positive”) literature, which remains the main medium for sourcing results from the clinical practice and experimental studies. This work–contributing to the “Literature AI for DILI Challenge” of the Critical Assessment of Massive Data Analysis (CAMDA) 2021– presents an automated pipeline for distinguishing between DILI-positive and negative publications. We used Natural Language Processing (NLP) to filter out the uninformative parts of a text, and identify and extract mentions of chemicals and diseases. We combined that information with small-molecule and disease embeddings, which are capable of capturing chemical and disease similarities, to improve classification performance. The former were directly sourced from the Chemical Checker (CC). For the latter, we collected data that encode different aspects of disease similarity from the National Library of Medicine’s (NLM) Medical Subject Headings (MeSH) thesaurus and the Comparative Toxicogenomics Database (CTD). Following a similar procedure as the one used in the CC, vector representations for diseases were learnt and evaluated. Two Neural Network (NN) classifiers were developed: a baseline model that accepts texts as input and an augmented, extended, model that also utilises chemical and disease embeddings. We trained, validated, and tested the classifiers through a Nested Cross-Validation (NCV) scheme with 10 outer and 5 inner folds. During this, the baseline and extended models performed virtually identically, with F1-scores of 95.04 ± 0.61% and 94.80 ± 0.41%, respectively. Upon validation on an external, withheld, dataset that is meant to assess classifier generalisability, the extended model achieved an F1-score of 91.14 ± 1.62%, outperforming its baseline counterpart which received a lower score of 88.30 ± 2.44%. We make further comparisons between the classifiers and discuss future improvements and directions, including utilising chemical and disease embeddings for visualisation and exploratory analysis of the DILI-positive literature.

Drug-induced liver injury (DILI) is a class of adverse drug reactions (ADR) that causes problems in both clinical and research settings. It is the most frequent cause of acute liver failure in the majority of Western countries and is a major cause of attrition of novel drug candidates. Manual trawling of the literature is the main route of deriving information on DILI from research studies. This makes it an inefficient process prone to human error. Therefore, an automatized AI model capable of retrieving DILI-related articles from the huge ocean of literature could be invaluable for the drug discovery community. In this study, we built an artificial intelligence (AI) model combining the power of natural language processing (NLP) and machine learning (ML) to address this problem. This model uses NLP to filter out meaningless text (e.g., stop words) and uses customized functions to extract relevant keywords such as singleton, pair, and triplet. These keywords are processed by an apriori pattern mining algorithm to extract relevant patterns which are used to estimate initial weightings for a ML classifier. Along with pattern importance and frequency, an FDA-approved drug list mentioning DILI adds extra confidence in classification. The combined power of these methods builds a DILI classifier (DILIC), with 94.91% cross-validation and 94.14% external validation accuracy. To make DILIC as accessible as possible, including to researchers without coding experience, an R Shiny app capable of classifying single or multiple entries for DILI is developed to enhance ease of user experience and made available at https://researchmind.co.uk/diliclassifier/. Additionally, a GitHub link (https://github.com/sanjaysinghrathi/DILI-Classifier) for app source code and ISMB extended video talk (https://www.youtube.com/watch?v=j305yIVi_f8) are available as supplementary materials.

Abstract Next-Generation Sequencing technologies are generating a huge amount of genetic data that need to be mapped and analyzed. Single machine sequence alignment tools are becoming incapable or inefficient in keeping track of the same. Therefore, distributed computing platforms based on MapReduce paradigm, which uses thousands of commodity machines to process and analyze huge datasets, are emerging as the best solution for growing genomics data. A lot of MapReduce-based sequence alignment tools like CloudBurst, CloudAligner, Halvade, and SparkBWA are proposed by various researchers in recent few years. These sequence aligners are very fast and efficient. These sequence aligners are capable of aligning billions of reads (stored as fasta or fastq files) on reference genome in few minutes. In the current era of fastly growing technology, analyzing huge genome data fast is not enough. We need to analyze data in real time to automate alignment process. Therefore, we propose a MapReduce-based sequence alignment tool StreamAligner which is implemented on Spark streaming engine. StreamAligner can align stream of reads on reference genome in real time. Therefore, it can be used to automate sequencing and alignment process. It uses suffix array index for read alignment which is generated using distributed index generation algorithm. Due to distributed index generation algorithm, index generation time is very less. It needs to upload index only once when StreamAligner is launched. After that index stays in Spark memory and can be used for an unlimited times without reloading. Whereas, current state-of-the-art sequence aligner either generate (hash index based) or load (sorted index based) index for every task. Hence, StreamAligner reduces time to generate or load index for every task. A working and tested implementation of streamAligner is available on GitHub for download and use. We tested the effectiveness, efficiency, and scalability of our aligner for various standard and real-life datasets.

Abstract Extraction of valuable data from extensive datasets is a standout amongst the most vital exploration issues. Association rule mining is one of the highly used methods for this purpose. Finding possible associations between items in large transaction based datasets (finding frequent itemsets) is most crucial part of the association rule mining task. Many single-machine based association rule mining algorithms exist but the massive amount of data available these days is above the capacity of a single machine based algorithm. Therefore, to meet the demands of this ever-growing enormous data, there is a need for distributed association rule mining algorithm which can run on multiple machines. For these types of parallel/distributed applications, MapReduce is one of the best fault-tolerant frameworks. Hadoop is one of the most popular open-source software frameworks with MapReduce based approach for distributed storage and processing of large datasets using standalone clusters built from commodity hardware. But heavy disk I/O operation at each iteration of a highly iterative algorithm like Apriori makes Hadoop inefficient. A number of MapReduce based platforms are being developed for parallel computing in recent years. Among them, a platform, namely, Spark have attracted a lot of attention because of its inbuilt support to distributed computations. Therefore, we implemented a distributed association rule mining algorithm on Spark named as Adaptive-Miner which uses adaptive approach for finding frequent patterns with higher accuracy and efficiency. Adaptive-Miner uses an adaptive strategy based on the partial processing of datasets. Adaptive-Miner makes execution plans before every iteration and goes with the best suitable plan to minimize time and space complexity. Adpative-Miner is a dynamic association rule mining algorithm which change its approach based on the nature of dataset. Therefore, it is different and better than state-of-the-art static association rule mining algorithms. We conduct in-depth experiments to gain insight into the effectiveness, efficiency, and scalability of the Adaptive-Miner algorithm on Spark. Available: https://github.com/sanjaysinghrathi/Adaptive-Miner