A novel statistical method for decontaminating T-cell receptor sequencing data

Abstract

The T-cell receptor (TCR) repertoire is highly diverse among the population and plays an essential role in initiating multiple immune processes. TCR sequencing (TCR-seq) has been developed to profile the T cell repertoire. Similar to other high-throughput experiments, contamination can happen during several steps of TCR-seq, including sample collection, preparation and sequencing. Such contamination creates artifacts in the data, leading to inaccurate or even biased results. Most existing methods assume ‘clean’ TCR-seq data as the starting point with no ability to handle data contamination. Here, we develop a novel statistical model to systematically detect and remove contamination in TCR-seq data. We summarize the observed contamination into two sources, pairwise and cross-cohort. For both sources, we provide visualizations and summary statistics to help users assess the severity of the contamination. Incorporating prior information from 14 existing TCR-seq datasets with minimum contamination, we develop a straightforward Bayesian model to statistically identify contaminated samples. We further provide strategies for removing the impacted sequences to allow for downstream analysis, thus avoiding any need to repeat experiments. Our proposed model shows robustness in contamination detection compared with a few off-the-shelf detection methods in simulation studies. We illustrate the use of our proposed method on two TCR-seq datasets generated locally.

Extension of multi-site analogue series with potent compounds using a bidirectional transformer-based chemical language model

“…26,28,29 BERT has been successfully used in NLP for learning word vectors based on contextual information, in particular, for text classification and next-sentence prediction. [30][31][32][33][34] Unlike other language models that capture context unidirectionally, BERT was designed as a bidirectional model to analyze sentences in forward and backward direction and predict new words conditioned on all other words in sentences. 26,35 Given that next-sentence prediction was conceptually related to the AS extension task, BERT was chosen as a transformer architecture for R-group prediction.…”