Single cell RNA sequencing (scRNA-seq) has revolutionized the study of gene expression in individual cell types, but scRNA-seq studies have focused primarily on expression of protein-coding genes. Long noncoding RNAs (lncRNAs) are more diverse than protein-coding genes, yet remain underexplored in part because they are underrepresented in reference annotations applied to scRNA-seq. Merging annotations containing protein-coding and lncRNA genes is not sufficient, because the addition of lncRNA genes that overlap in sense and antisense with protein-coding genes will affect how reads are counted for both protein-coding and lncRNA genes. Here, we introduce Singletrome, a Singularity image that integrates protein-coding and lncRNA gene transfer format (GTF) annotations to generate enhanced annotations that take into account the sense and antisense overlap of annotated genes, maps scRNA-seq data, and produces files for downstream analysis and visualization. With Singletrome, we detected thousands of lncRNAs not included in GENCODE, clustered cell types based solely on lncRNA expression, and demonstrated that machine learning can predict cell type and disease through lncRNAs alone. This comprehensive annotation will allow mapping of lncRNA expression across cell types of the human body, facilitating the development of an atlas of human lncRNAs in health and disease with the ability to integrate new lncRNA annotations as they become available.