Additional file 2 of EpiGePT: a pretrained transformer-based language model for context-specific human epigenomics

Additional file 2: Table S1: Comparison of the performance between fine-tuned EpiGePT and baseline methods in predicting HiChIP loops on the K562 cell line (positive-to-negative sample ratio of 1:1). Table S2: Comparison of the performance between fine-tuned EpiGePT and baseline methods in predicting HiChIP loops on the GM12878 cell line (positive-to-negative sample ratio of 1:1). Table S3: Comparison of the performance between fine-tuned EpiGePT and baseline methods in predicting HiChIP loops on the K562 cell line (positive-to-negative sample ratio of 1:2). Table S4: Comparison of the performance between fine-tuned EpiGePT and baseline methods in predicting HiChIP loops on the GM12878 cell line (positive-to-negative sample ratio of 1:2). Table S5: Description and comparison of EpiGePT with different settings. Table S6: The information of DNase-seq bam file across 129 biosamples from the ENCODE project. Table S7: The information of RNA-seq tab-separated values (tsv) file across 129 biosamples from the ENCODE project. Table S8: The preprocessed expression data of 711 human transcription factors from the ENCODE project across 129 biosamples. Table S9: The information of DNase-seq, CTCF and other six Histone markers bam file across 28 cell lines or tissues from the ENCODE project (hg19). Table S10: The information of RNA-seq tab-separated values (tsv) file across 28 cell lines or tissues from the ENCODE project (hg19). Table S11: The preprocessed expression data of 711 human transcription factors from the ENCODE project across 28 cell lines or tissues (hg19). Table S12: The information of RNA-seq tab-separated values (tsv) file across 104 cell lines or tissues from the ENCODE project (hg38). Table S13: The information of DNase-seq, CTCF and other six Histone markers bam file across 104 cell lines or tissues from the ENCODE project (hg38). Table S14: The preprocessed expression data of 711 human transcription factors from the ENCODE project across 104 cell lines or tissues (hg38). Table S15: The order and names of epigenomes of the expression matrices across 56 epigenomes from the ROADMAP project. Table S16: The preprocessed expression data of 642 human transcription factors across 56 epigenomes from the ROADMAP project. Table S17: The computational resource usage, including peak GPU memory and peak RAM consumption (NVIDIA GeForce RTX 3090). Table S18: The computational resource usage, including peak GPU memory and peak RAM consumption (NVIDIA GeForce RTX 4090). Table S19: The computational resource usage, including peak GPU memory and peak RAM consumption (NVIDIA RTX A6000).