Single-cell RNA sequencing (scRNA-Seq) is an emerging strategy for characterizing immune cell populations. Compared to flow or mass cytometry, scRNA-Seq could potentially identify cell types and activation states that lack precise cell surface markers. However, scRNA-Seq is currently limited due to the need to manually classify each immune cell from its transcriptional profile. While recently developed algorithms accurately annotate coarse cell types (e.g. T cells versus macrophages), making fine distinctions (e.g. CD8+ effector memory T cells) remains a difficult challenge. To address this, we developed a machine learning classifier called ImmClassifier that leverages a hierarchical ontology of cell type. We demonstrate that its predictions are highly concordant with flow-based markers from CITE-seq and outperforms other tools (+15% recall, +14% precision) in distinguishing fine-grained cell types with comparable performance on coarse ones. Thus, ImmClassifier can be used to explore more deeply the heterogeneity of the immune system in scRNA-Seq experiments.

Motivation: Bioinformatic analyses are becoming formidably more complex due to the increasing number of steps required to process the data, as well as the proliferation of methods that can be used in each step. To alleviate this difficulty, pipelines are commonly employed. However, pipelines are typically implemented to automate a specific analysis, and thus are difficult to use for exploratory analyses requiring systematic changes to the software or parameters used. Results: To automate the development of pipelines, we have investigated expert systems. We created the Bioinformatics ExperT SYstem (BETSY) that includes a knowledge base where the capabilities of bioinformatics software is explicitly and formally encoded. BETSY is a backwards-chaining rule-based expert system comprised of a data model that can capture the richness of biological data, and an inference engine that reasons on the knowledge base to produce workflows. Currently, the knowledge base is populated with rules to analyze microarray and next generation sequencing data. We evaluated BETSY and found that it could generate workflows that reproduce and go beyond previously published bioinformatics results. Finally, a meta-investigation of the workflows generated from the knowledge base produced a quantitative measure of the technical burden imposed by each step of bioinformatics analyses, revealing the large number of steps devoted to the pre-processing of data. In sum, an expert system approach can facilitate exploratory bioinformatic analysis by automating the development of workflows, a task that requires significant domain expertise. Availability and Implementation: https://github.com/jefftc/changlab. Contact: [email protected].

MOTIVATION: A system-wide approach to revealing the underlying molecular state of a cell is a long-standing biological challenge. Developed over the last decade, gene expression profiles possess the characteristics of such an assay. They have the capacity to reveal both underlying molecular events as well as broader phenotypes such as clinical outcomes. To interpret these profiles, many gene sets have been developed that characterize biological processes. However, the full potential of these gene sets has not yet been achieved. Since the advent of gene expression databases, many have posited that they can reveal properties of activities that are not evident from individual datasets, analogous to how the expression of a single gene generally cannot reveal the activation of a biological process. RESULTS: To address this issue, we have developed a high-throughput method to mine gene expression databases for the regulation of gene sets. Given a set of genes, we scored it against each gene expression dataset by looking for enrichment of co-regulated genes relative to an empirical null distribution. After validating the method, we applied it to address two biological problems. First, we deciphered the E2F transcriptional network. We confirmed that true transcriptional targets exhibit a distinct regulatory profile across a database. Second, we leveraged the patterns of regulation across a database of gene sets to produce an automatically generated catalog of biological processes. These demonstrations revealed the power of a global analysis of the data contained within gene expression databases, and the potential for using them to address biological questions.

BACKGROUND: The biological phenotype of a cell, such as a characteristic visual image or behavior, reflects activities derived from the expression of collections of genes. As such, an ability to measure the expression of these genes provides an opportunity to develop more precise and varied sets of phenotypes. However, to use this approach requires computational methods that are difficult to implement and apply, and thus there is a critical need for intelligent software tools that can reduce the technical burden of the analysis. Tools for gene expression analyses are unusually difficult to implement in a user-friendly way because their application requires a combination of biological data curation, statistical computational methods, and database expertise. RESULTS: We have developed SIGNATURE, a web-based resource that simplifies gene expression signature analysis by providing software, data, and protocols to perform the analysis successfully. This resource uses bayesian methods for processing gene expression data coupled with a curated database of gene expression signatures, all carried out within a GenePattern web interface for easy use and access. CONCLUSIONS: SIGNATURE is available for public use at http://genepattern.genome.duke.edu/signature/.

Abstract Summary: The Biopython project is a mature open source international collaboration of volunteer developers, providing Python libraries for a wide range of bioinformatics problems. Biopython includes modules for reading and writing different sequence file formats and multiple sequence alignments, dealing with 3D macro molecular structures, interacting with common tools such as BLAST, ClustalW and EMBOSS, accessing key online databases, as well as providing numerical methods for statistical learning. Availability: Biopython is freely available, with documentation and source code at www.biopython.org under the Biopython license. Contact: All queries should be directed to the Biopython mailing lists, see www.biopython.org/wiki/[email protected].

MOTIVATION: Understanding the full meaning of the biology captured in molecular profiles, within the context of the entire biological system, cannot be achieved with a simple examination of the individual genes in the signature. To facilitate such an understanding, we have developed GATHER, a tool that integrates various forms of available data to elucidate biological context within molecular signatures produced from high-throughput post-genomic assays. RESULTS: Analyzing the Rb/E2F tumor suppressor pathway, we show that GATHER identifies critical features of the pathway. We further show that GATHER identifies common biology in a series of otherwise unrelated gene expression signatures that each predict breast cancer outcome. We quantify the performance of GATHER and find that it successfully predicts 90% of the functions over a broad range of gene groups. We believe that GATHER provides an essential tool for extracting the full value from molecular signatures generated from genome-scale analyses. AVAILABILITY: GATHER is available at http://gather.genome.duke.edu/

Summary: We describe a database and information discovery system named DIG (Duke Integrated Genomics) designed to facilitate the process of gene annotation and the discovery of functional context. The DIG system collects and organizes gene annotation and functional information, and includes tools that support an understanding of genes in a functional context by providing a framework for integrating and visualizing gene expression, protein interaction and literature-based interaction networks. Availability: The DIG system is freely accessible at http://dig.cagp.duke.edu/ Contact: [email protected] Supplementary information: http://data.cgt.duke.edu.dig

MOTIVATION: New high-throughput technologies have accelerated the accumulation of knowledge about genes and proteins. However, much knowledge is still stored as written natural language text. Therefore, we have developed a new method, GAPSCORE, to identify gene and protein names in text. GAPSCORE scores words based on a statistical model of gene names that quantifies their appearance, morphology and context. RESULTS: We evaluated GAPSCORE against the Yapex data set and achieved an F-score of 82.5% (83.3% recall, 81.5% precision) for partial matches and 57.6% (58.5% recall, 56.7% precision) for exact matches. Since the method is statistical, users can choose score cutoffs that adjust the performance according to their needs. AVAILABILITY: GAPSCORE is available at http://bionlp.stanford.edu/gapscore/

OBJECTIVE: The growth of the biomedical literature presents special challenges for both human readers and automatic algorithms. One such challenge derives from the common and uncontrolled use of abbreviations in the literature. Each additional abbreviation increases the effective size of the vocabulary for a field. Therefore, to create an automatically generated and maintained lexicon of abbreviations, we have developed an algorithm to match abbreviations in text with their expansions. DESIGN: Our method uses a statistical learning algorithm, logistic regression, to score abbreviation expansions based on their resemblance to a training set of human-annotated abbreviations. We applied it to Medstract, a corpus of MEDLINE abstracts in which abbreviations and their expansions have been manually annotated. We then ran the algorithm on all abstracts in MEDLINE, creating a dictionary of biomedical abbreviations. To test the coverage of the database, we used an independently created list of abbreviations from the China Medical Tribune. MEASUREMENTS: We measured the recall and precision of the algorithm in identifying abbreviations from the Medstract corpus. We also measured the recall when searching for abbreviations from the China Medical Tribune against the database. RESULTS: On the Medstract corpus, our algorithm achieves up to 83% recall at 80% precision. Applying the algorithm to all of MEDLINE yielded a database of 781,632 high-scoring abbreviations. Of all the abbreviations in the list from the China Medical Tribune, 88% were in the database. CONCLUSION: We have developed an algorithm to identify abbreviations from text. We are making this available as a public abbreviation server at \url[http://abbreviation.stanford.edu/].