biopipen 0.32.1__py3-none-any.whl → 0.33.0__py3-none-any.whl

biopipen/scripts/scrna/SeuratPreparing.R

@@ -1,12 +1,9 @@
-{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
-{{ biopipen_dir | joinpaths: "utils", "caching.R" | source_r }}
-
 library(Seurat)
 library(future)
 library(bracer)
-library(ggplot2)
 library(dplyr)
-# library(tidyseurat)
+library(glue)
+library(biopipen.utils)
 
 metafile <- {{in.metafile | quote}}
 rdsfile <- {{out.rdsfile | quote}}
@@ -14,10 +11,9 @@ joboutdir <- {{job.outdir | quote}}
 envs <- {{envs | r: todot = "-", skip = 1}}
 
 if (isTRUE(envs$cache)) { envs$cache <- joboutdir }
-if (length(envs$cache) > 1) {
-    log_warn("Multiple cache directories (envs.cache) detected, using the first one.")
-    envs$cache <- envs$cache[1]
-}
+
+log <- get_logger()
+reporter <- get_reporter()
 
 set.seed(8525)
 # 8TB
@@ -26,15 +22,15 @@ options(future.rng.onMisuse="ignore")
 options(Seurat.object.assay.version = "v5")
 plan(strategy = "multicore", workers = envs$ncores)
 
-{{ biopipen_dir | joinpaths: "scripts", "scrna", "SeuratPreparing-common.R" | source_r }}
-
-add_report(
+reporter$add(
     list(
         kind = "descr",
         name = "Filters applied",
         content = paste0(
             "<p>Cell filters: ", html_escape(envs$cell_qc), "</p>",
-            "<p>Gene filters: ", html_escape(stringify_list(envs$gene_qc)), "</p>"
+            "<p>Gene filters: </p>",
+            "<p>- Min Cells: ", envs$gene_qc$min_cells, "</p>",
+            "<p>- Excludes: ", html_escape(envs$gene_qc$excludes %||% "Not set"), "</p>"
         )
     ),
     h1 = "Filters and QC"
@@ -48,16 +44,6 @@ metadata <- read.table(
     check.names = FALSE
 )
 
-cache_sig <- capture.output(str(metadata))
-dig_sig <- digest::digest(cache_sig, algo = "md5")
-dig_sig <- substr(dig_sig, 1, 8)
-cache_dir <- NULL
-if (is.character(envs$cache)) {
-    cache_dir <- file.path(envs$cache, paste0(dig_sig, ".seuratpreparing_cache"))
-    dir.create(cache_dir, recursive = TRUE, showWarnings = FALSE)
-    writeLines(cache_sig, file.path(cache_dir, "signature.txt"))
-}
-
 meta_cols = colnames(metadata)
 if (!"Sample" %in% meta_cols) {
     stop("Error: Column `Sample` is not found in metafile.")
@@ -66,77 +52,148 @@ if (!"RNAData" %in% meta_cols) {
     stop("Error: Column `RNAData` is not found in metafile.")
 }
 
-samples = as.character(metadata$Sample)
-
-# used for plotting
-cell_qc_df = NULL
-
-plotsdir = file.path(joboutdir, "plots")
-dir.create(plotsdir, showWarnings = FALSE, recursive = TRUE)
-
-# features for cell QC
-feats = c(
-    "nFeature_RNA", "nCount_RNA",
-    "percent.mt", "percent.ribo", "percent.hb", "percent.plat"
-)
-
-sobj <- run_cell_qc(sobj)
-
-# plot and report the QC
-log_info("Plotting and reporting QC ...")
-dim_df = report_cell_qc(nrow(sobj))
-
-if (is.list(envs$gene_qc)) {
-    sobj <- run_gene_qc(sobj)
-}
-
-dim_df = rbind(
-    dim_df,
-    data.frame(
-        when = "After_Gene_QC",
-        nCells = ncol(sobj),
-        nGenes = nrow(sobj)
-    )
+qcdir = file.path(joboutdir, "qc")
+dir.create(qcdir, showWarnings = FALSE, recursive = TRUE)
+
+sobj <- LoadSeuratAndPerformQC(
+    metadata,
+    per_sample_qc = envs$cell_qc_per_sample,
+    cell_qc = envs$cell_qc,
+    gene_qc = envs$gene_qc,
+    tmpdir = joboutdir,
+    log = log,
+    cache = envs$cache)
+
+log$info("Saving dimension table ...")
+dim_df <- data.frame(
+    when = c("Before QC", "After QC"),
+    nCells = c(nrow(sobj@misc$cell_qc_df), sum(sobj@misc$cell_qc_df$.QC)),
+    nGenes = c(sobj@misc$gene_qc$before, sobj@misc$gene_qc$after)
 )
-
-log_info("Saving dimension table ...")
-write.table(dim_df, file = file.path(plotsdir, "dim.txt"),
+write.table(dim_df, file = file.path(qcdir, "dim.txt"),
             row.names = FALSE, quote = FALSE, sep = "\t")
 
-add_report(
+reporter$add(
     list(
         kind = "descr",
-        content = paste(
-            "The dimension table for the Seurat object. The table contains the number of cells and genes before and after QC."
-        )
+        content = "The dimension table for the Seurat object. The table contains the number of cells and genes before and after QC. Note that the cell QC is performed before gene QC."
     ),
     list(
         kind = "table",
-        data = list(path = file.path(plotsdir, "dim.txt"))
+        data = list(path = file.path(qcdir, "dim.txt"))
     ),
-    h1 = "Filters and QC"
+    h1 = "Filters and QC",
+    h2 = "Dimension table"
 )
 
-sobj <- run_transformation(sobj)
-sobj <- run_integration(sobj)
+log$info("Visualizing QC metrics ...")
+for (pname in names(envs$qc_plots)) {
+    args <- envs$qc_plots[[pname]]
+    args$kind <- args$kind %||% "cell"
+    args$devpars <- args$devpars %||% list()
+    args$more_formats <- args$more_formats %||% character()
+    args$save_code <- args$save_code %||% FALSE
+    extract_vars(args, "kind", "devpars", "more_formats", "save_code")
+    if (kind == "gene") kind <- "gene_qc"
+    if (kind == "cell") kind <- "cell_qc"
+    args$object <- sobj
+    plot_fn <- if (kind == "cell_qc") {
+        gglogger::register(VizSeuratCellQC)
+    } else {
+        gglogger::register(VizSeuratGeneQC)
+    }
+    p <- do_call(plot_fn, args)
+    prefix <- file.path(qcdir, paste0(slugify(pname), "_", kind))
+    save_plot(p, prefix, devpars, formats = c("png", more_formats))
+    if (save_code) {
+        save_plotcode(p, prefix,
+            setup = c("library(biopipen.utils)", "load('data.RData')", "invisible(list2env('args'))"),
+            "args",
+            auto_data_setup = FALSE)
+    }
+    reporter$add(
+        reporter$image(prefix, more_formats, save_code, kind = "image"),
+        h1 = "Filters and QC",
+        h2 = html_escape(pname)
+    )
+}
+
+sobj <- RunSeuratTransformation(
+    sobj,
+    use_sct = envs$use_sct,
+    SCTransformArgs = envs$SCTransform,
+    NormalizeDataArgs = envs$NormalizeData,
+    FindVariableFeaturesArgs = envs$FindVariableFeatures,
+    ScaleDataArgs = envs$ScaleData,
+    RunPCAArgs = envs$RunPCA,
+    log = log,
+    cache = envs$cache
+)
+sobj <- RunSeuratIntegration(
+    sobj,
+    no_integration = envs$no_integration,
+    IntegrateLayersArgs = envs$IntegrateLayers,
+    log = log,
+    cache = envs$cache
+)
 
 # This is the last step, doesn't need to be cached
-if (!is.null(envs$doublet_detector) && envs$doublet_detector != "none") {
-    {{* biopipen_dir | joinpaths: "scripts", "scrna", "SeuratPreparing-doublet_detection.R" | source_r }}
-
-    detector <- tolower(envs$doublet_detector)
-    if (detector == "doubletfinder") detector <- "DoubletFinder"
-    if (detector == "scdblfinder") detector <- "scDblFinder"
-    dd <- run_dd(detector)
-    save_dd(dd, detector)
-    sobj <- add_dd_to_seurat(sobj, dd)
-    plot_dd(sobj, dd, detector)
-    sobj <- filter_dd(sobj, dd, detector)
-    report_dd(detector)
-}
+if (!identical(envs$doublet_detector, "none")) {
+    dbldir <- file.path(joboutdir, "doublets")
+    dir.create(dbldir, showWarnings = FALSE, recursive = TRUE)
+
+    sobj <- RunSeuratDoubletDetection(
+        sobj,
+        tool = envs$doublet_detector,
+        DoubletFinderArgs = envs$DoubletFinder,
+        scDblFinderArgs = envs$scDblFinder,
+        filter = FALSE,
+        log = log,
+        cache = envs$cache
+    )
 
+    log$info("Visualizing doublet detection results ...")
+    if (identical(tolower(envs$doublet_detector), "doubletfinder")) {
+        p <- VizSeuratDoublets(sobj, plot_type = "pK", x_text_angle = 90)
+        save_plot(
+            p, file.path(dbldir, "doubletfinder_pk"),
+            devpars = list(res = 100, width = 800, height = 600),
+            formats = "png")
+        reporter$add(
+            list(
+                kind = "descr",
+                content = paste(
+                    "The pK plot from DoubletFinder to select the optimal pK value.",
+                    "See more at https://github.com/chris-mcginnis-ucsf/DoubletFinder"
+                )
+            ),
+            list(
+                kind = "image",
+                src = file.path(dbldir, "doubletfinder_pk.png")
+            ),
+            h1 = glue("Doublet detection using {envs$doublet_detector}"),
+            h2 = "BC metric vs pK"
+        )
+    }
+
+    for (pt in c("dim", "pie")) {
+        p <- VizSeuratDoublets(sobj, plot_type = pt)
+        save_plot(p, file.path(dbldir, paste0("doublets_", pt)), formats = "png")
+
+        reporter$add(
+            list(
+                src = file.path(dbldir, paste0("doublets_", pt, ".png")),
+                descr = ifelse(pt == "dim", "Dimention Reduction Plot", "Pie Chart")
+            ),
+            h1 = glue("Doublet detection using {envs$doublet_detector}"),
+            h2 = "Doublets distribution",
+            ui = "table_of_images"
+        )
+    }
 
-log_info("Saving QC'ed seurat object ...")
-saveRDS(sobj, rdsfile)
+    sobj <- subset(sobj, subset = !!sym(paste0(sobj@misc$doublets$tool, "_DropletType")) != "doublet")
+}
 
-save_report(joboutdir)
+log$info("Saving QC'ed seurat object ...")
+reporter$save(joboutdir)
+saveRDS(sobj, rdsfile)

biopipen/scripts/scrna/SlingShot.R

@@ -0,0 +1,71 @@
+{{ biopipen_dir | joinpaths: "utils", "misc.R" | source_r }}
+
+library(rlang)
+library(Seurat)
+library(slingshot)
+
+sobjfile <- {{in.sobjfile | r}}
+outfile <- {{out.outfile | r}}
+group_by <- {{envs.group_by | r}}
+reduction <- {{envs.reduction | r}}
+dims <- {{envs.dims | r}}
+start <- {{envs.start | r}}
+end <- {{envs.end | r}}
+prefix <- {{envs.prefix | r}}
+reverse <- {{envs.reverse | r}}
+align_start <- {{envs.align_start | r}}
+seed <- {{envs.seed | r}}
+
+set.seed(seed)
+if (is.null(group_by)) {
+    stop("envs.group_by is required")
+}
+
+log_info("Reading Seurat object ...")
+srt <- readRDS(sobjfile)
+
+if (!group_by %in% colnames(srt@meta.data)) {
+    stop(paste("Grouping column", group_by, "not found in the Seurat object"))
+}
+
+reduction <- reduction %||% DefaultDimReduc(srt)
+dims <- expand_dims(dims)
+
+if (is.null(prefix)) {
+    prefix <- ""
+} else {
+    prefix <- paste0(prefix, "_")
+}
+
+log_info("Filtering cells in NA group_by ...")
+srt_sub <- srt[, !is.na(srt[[group_by, drop = TRUE]])]
+
+log_info("Running Slingshot ...")
+sl <- slingshot(
+    data = as.data.frame(srt_sub[[reduction]]@cell.embeddings[, dims]),
+    clusterLabels = as.character(srt_sub[[group_by, drop = TRUE]]),
+    start.clus = start, end.clus = end
+)
+
+command <- pbmc_small@commands[[1]]
+attr(command, "name") <- "SlingShot"
+attr(command, "call.string") <- "slingshot(...)"
+attr(command, "params") <- list()
+srt@commands <- srt@commands %||% list()
+srt@commands$Slingshot <- command
+
+df <- as.data.frame(slingPseudotime(sl))
+colnames(df) <- paste0(prefix, colnames(df))
+if (isTRUE(reverse)) {
+    if (isTRUE(align_start)) {
+        df <- apply(df, 2, function(x) max(x, na.rm = TRUE) - x)
+    } else {
+        df <- max(df, na.rm = TRUE) - df
+    }
+}
+
+srt <- AddMetaData(srt, metadata = df)
+srt <- AddMetaData(srt, metadata = slingBranchID(sl), col.name = paste0(prefix, "BranchID"))
+
+log_info("Saving Seurat object ...")
+saveRDS(srt, outfile)

biopipen/scripts/scrna/TopExpressingGenes.R

@@ -161,14 +161,16 @@ do_enrich <- function(expr, odir) {
             next
         }
 
-        png(
-            file.path(odir, paste0("Enrichr-", db, ".png")),
-            res = 100, height = 1000, width = 1000
-        )
-        print(
-            plotEnrich(enriched[[db]], showTerms = 20, title = db) +
+        enrich_p <- plotEnrich(enriched[[db]], showTerms = 20, title = db) +
             theme_prism()
-        )
+        enrich_plot <- file.path(odir, paste0("Enrichr-", db, ".png"))
+        png(enrich_plot, res = 100, height = 1000, width = 1000)
+        print(enrich_p)
+        dev.off()
+
+        enrich_plot_pdf <- file.path(odir, paste0("Enrichr-", db, ".pdf"))
+        pdf(enrich_plot_pdf, height = 10, width = 10)
+        print(enrich_p)
         dev.off()
     }
 }

biopipen/scripts/scrna/celltypist-wrapper.py

@@ -7,14 +7,13 @@ parser.add_argument(
 parser.add_argument("-o", "--output", required=True, help="Output file")
 parser.add_argument("-m", "--model", required=True, help="Model file")
 parser.add_argument(
-    "-v", "--majority_voting",
-    action="store_true",
-    help="Majority voting"
+    "-v", "--majority_voting", action="store_true", help="Majority voting"
 )
 parser.add_argument(
-    "-c", "--over_clustering",
+    "-c",
+    "--over_clustering",
     default="seurat_clusters",
-    help="Over clustering. Ignored if the column does not exist."
+    help="Over clustering. Ignored if the column does not exist.",
 )
 
 
@@ -44,7 +43,9 @@ if __name__ == "__main__":
 
     if args.output.endswith(".h5ad"):
         try:
-            out_adata._raw._var.rename(columns={"_index": "features"}, inplace=True)
+            out_adata._raw._var.rename(  # type: ignore
+                columns={"_index": "features"}, inplace=True
+            )
             del out_adata.raw
         except (KeyError, AttributeError):
             pass

biopipen/scripts/snp/Plink2GTMat.py

@@ -3,15 +3,16 @@ from os import path
 from glob import glob
 from biopipen.utils.misc import run_command, logger
 
-indir = {{in.indir | repr}}  # noqa: E999 # pyright: ignore
-outfile = {{out.outfile | repr}}  # pyright: ignore
-plink = {{envs.plink | repr}}  # pyright: ignore
-ncores = {{envs.ncores | repr}}  # pyright: ignore
-transpose = {{envs.transpose | repr}}  # pyright: ignore
-samid = {{envs.samid | repr}}  # pyright: ignore
-varid = {{envs.varid | repr}}  # pyright: ignore
-trans_chr = {{envs.trans_chr | repr}}  # pyright: ignore
-missing_id = {{envs.missing_id | repr}}  # pyright: ignore
+indir: str = {{in.indir | quote}}  # noqa: E999 # pyright: ignore
+outfile: str = {{out.outfile | quote}}  # pyright: ignore
+plink: str = {{envs.plink | quote}}  # pyright: ignore
+ncores: int = {{envs.ncores | repr}}  # pyright: ignore
+transpose: bool = {{envs.transpose | repr}}  # pyright: ignore
+samid: str = {{envs.samid | repr}}  # pyright: ignore
+varid: str = {{envs.varid | repr}}  # pyright: ignore
+trans_chr: dict = {{envs.trans_chr | repr}}  # pyright: ignore
+missing_id: str = {{envs.missing_id | repr}}  # pyright: ignore
+gtcoding: str = {{envs.gtcoding | repr}}  # pyright: ignore
 trans_chr = trans_chr or {}
 
 bedfile = glob(path.join(indir, '*.bed'))
@@ -37,6 +38,14 @@ cmd = [
 
 run_command(cmd, fg=True, env={"cwd": path.dirname(outfile)})
 
+
+def _vcf_gtcoding(gt):
+    try:
+        return str(2 - int(gt))
+    except (ValueError, TypeError):
+        return "NA"
+
+
 if not transpose:  # rows are variants, columns are samples
     # .traw file is created, tab-separated, with the following columns:
     trawfile = output + ".traw"
@@ -82,7 +91,10 @@ if not transpose:  # rows are variants, columns are samples
                     .replace('{ref}', ref)
                     .replace('{alt}', alt)
                 )
-                record = [variant] + line[6:]
+                if gtcoding == "plink":
+                    record = [variant] + line[6:]
+                else:  # vcf
+                    record = [variant] + [_vcf_gtcoding(x) for x in line[6:]]
                 fout.write('\t'.join(record) + '\n')
 
 else:
@@ -129,5 +141,8 @@ else:
                 fid = line[0]
                 iid = line[1]
                 sam = samid.replace('{fid}', fid).replace('{iid}', iid)
-                record = [sam] + line[6:]
+                if gtcoding == "plink":
+                    record = [sam] + line[6:]
+                else:  # vcf
+                    record = [sam] + [_vcf_gtcoding(x) for x in line[6:]]
                 fout.write('\t'.join(record) + '\n')

biopipen/scripts/snp/PlinkFilter.py

@@ -1,17 +1,17 @@
-"""Script for snp.PlinkFilter"""
+from __future__ import annotations
 
 from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-indir = {{in.indir | repr}}  # pyright: ignore # noqa: #999
-samples_file = {{in.samples_file | repr}}  # pyright: ignore
-variants_file = {{in.variants_file | repr}}  # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
+indir: str = {{in.indir | quote}}  # pyright: ignore # noqa: #999
+samples_file = {{in.samples_file | quote}}  # pyright: ignore
+variants_file = {{in.variants_file | quote}}  # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 
 plink = {{envs.plink | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
-samples = {{envs.samples | repr}}  # pyright: ignore
-variants = {{envs.variants | repr}}  # pyright: ignore
+samples: list[str] | str = {{envs.samples | repr}}  # pyright: ignore
+variants: list[str] | str = {{envs.variants | repr}}  # pyright: ignore
 e_samples_file = {{envs.samples_file | repr}}  # pyright: ignore
 e_variants_file = {{envs.variants_file | repr}}  # pyright: ignore
 keep = {{envs.keep | repr}}  # pyright: ignore

biopipen/scripts/snp/PlinkFromVcf.py

@@ -1,12 +1,14 @@
-from os import path
+from __future__ import annotations
+
+from os import path, PathLike
 from biopipen.core.filters import dict_to_cli_args
 from biopipen.utils.reference import tabix_index
 from biopipen.utils.misc import run_command
 
-invcf = {{in.invcf | repr}}  # noqa: E999 # pyright: ignore
-outprefix = {{in.invcf | stem0 | repr}} # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
-args = {{envs | dict | repr}}  # pyright: ignore
+invcf: str | PathLike = {{in.invcf | quote}}  # noqa: E999 # pyright: ignore
+outprefix: str = {{in.invcf | stem0 | quote}} # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
+args: dict = {{envs | dict}}  # pyright: ignore
 
 plink = args.pop("plink")
 tabix = args.pop("tabix")
@@ -23,6 +25,7 @@ args.setdefault("max_alleles", 2)
 # This makes it possible to keep the allele order in the output
 # no need for plink2
 # args["keep_allele_order"] = True
+args.setdefault("keep_allele_order", True)
 
 # resolve plink 1.x --set-missing-var-ids doesn't distinguish $1, $2,...
 # for ref and alts

biopipen/scripts/snp/PlinkSimulation.py

@@ -4,9 +4,9 @@ from slugify import slugify
 from simpleconf import Config
 from biopipen.utils.misc import logger, run_command, dict_to_cli_args
 
-configfile = {{in.configfile | repr}}  # pyright: ignore # noqa: E999
-outdir = {{out.outdir | repr}}  # pyright: ignore
-gtmatfile = {{out.gtmat | repr}}  # pyright: ignore
+configfile: str = {{in.configfile | quote}}  # pyright: ignore # noqa: E999
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
+gtmatfile: str = {{out.gtmat | quote}}  # pyright: ignore
 config = Config.load(configfile)
 
 default_nsnps = {{envs.nsnps | repr}}  # pyright: ignore
@@ -21,7 +21,7 @@ default_maxfreq = {{envs.maxfreq | repr}}  # pyright: ignore
 default_hetodds = {{envs.hetodds | repr}}  # pyright: ignore
 default_homodds = {{envs.homodds | repr}}  # pyright: ignore
 default_missing = {{envs.missing | repr}}  # pyright: ignore
-default_args = {{envs.args | repr}}  # pyright: ignore
+default_args: dict = {{envs.args | repr}}  # pyright: ignore
 default_transpose_gtmat = {{envs.transpose_gtmat | repr}}  # pyright: ignore
 default_sample_prefix = {{envs.sample_prefix | repr}}  # pyright: ignore
 

biopipen/scripts/snp/PlinkUpdateName.py

@@ -1,9 +1,9 @@
 from pathlib import Path
 from biopipen.utils.misc import run_command, dict_to_cli_args, logger
 
-indir = {{in.indir | repr}}  # pyright: ignore # noqa: #999
-namefile = {{in.namefile | repr}}  # pyright: ignore
-outdir = {{out.outdir | repr}}  # pyright: ignore
+indir: str = {{in.indir | quote}}  # pyright: ignore # noqa: #999
+namefile: str = {{in.namefile | quote}}  # pyright: ignore
+outdir: str = {{out.outdir | quote}}  # pyright: ignore
 plink = {{envs.plink | repr}}  # pyright: ignore
 bcftools = {{envs.bcftools | repr}}  # pyright: ignore
 ncores = {{envs.ncores | repr}}  # pyright: ignore
@@ -111,7 +111,7 @@ if namefile.endswith(".vcf") or namefile.endswith(".vcf.gz"):
             else:
                 info = readline(finfo)
 
-    namefile = namefile_tmp
+    namefile = str(namefile_tmp)
 
 args = {
     "": plink,

biopipen/scripts/stats/ChowTest.R

@@ -12,15 +12,17 @@ transpose_input <- {{envs.transpose_input | r}}
 transpose_group <- {{envs.transpose_group | r}}
 
 log_info("Reading input files ...")
-indata <- read.table(infile, header = TRUE, sep = "\t", row.names = 1)
+indata <- read.table(infile, header = TRUE, sep = "\t", row.names = 1, check.names = FALSE)
 if (transpose_input) {
 	indata <- t(indata)
 }
-groupdata <- read.table(groupfile, header = TRUE, sep = "\t", row.names = 1)
+groupdata <- read.table(groupfile, header = TRUE, sep = "\t", row.names = 1, check.names = FALSE)
 if (transpose_group) {
 	groupdata <- t(groupdata)
 }
-fmldata <- read.table(fmlfile, header = TRUE, sep = "\t", row.names = NULL)
+allgroups = na.omit(unique(unlist(groupdata)))
+
+fmldata <- read.table(fmlfile, header = TRUE, sep = "\t", row.names = NULL, check.names = FALSE)
 colnames(fmldata)[1:2] <- c("Group", "Formula")
 
 chow.test <- function(fml, grouping) {
@@ -63,26 +65,43 @@ chow.test <- function(fml, grouping) {
 	)
 }
 
-formatlm <- function(m) {
-	if (class(m) == 'lm') {
-		coeff <- as.list(m$coefficients)
+formatlm <- function(m, g = NULL, type = "coeff") {
+	if (is.null(g)) {
 		vars <- all.vars(m$terms)
-		terms <- unlist(sapply(na.omit(c(vars[2:length(vars)], '(Intercept)', 'N')), function(x) {
-			ce <- coeff[[x]] %||% coeff[[bQuote(x)]]
-			if (x == 'N') {
-				paste0('N=', nrow(m$model))
-			} else if (is.null(ce)) {
-				NULL
-			} else {
-				l <- ifelse(x == '(Intercept)', '_', x)
-				paste0(l, '=', round(ce, 3))
-			}
-		}))
+		if (type == "pval") {
+			df <- as.data.frame(summary(m)$coefficients)
+			terms <- unlist(sapply(na.omit(c(vars[2:length(vars)], '(Intercept)', 'N')), function(x) {
+				pv <- df[x, 4] %||% df[bQuote(x), 4]
+				if (x == 'N') {
+					paste0('N=', nrow(m$model))
+				} else if (is.null(pv)) {
+					NULL
+				} else {
+					l <- ifelse(x == '(Intercept)', '_', x)
+					paste0(l, '=', signif(pv, digits = 4))
+				}
+			}))
+		} else {
+			coeff <- as.list(m$coefficients)
+			terms <- unlist(sapply(na.omit(c(vars[2:length(vars)], '(Intercept)', 'N')), function(x) {
+				ce <- coeff[[x]] %||% coeff[[bQuote(x)]]
+				if (x == 'N') {
+					paste0('N=', nrow(m$model))
+				} else if (is.null(ce)) {
+					NULL
+				} else {
+					l <- ifelse(x == '(Intercept)', '_', x)
+					paste0(l, '=', round(ce, 3))
+				}
+			}))
+		}
 		paste(terms[!is.null(terms)], collapse = ', ')
 	} else {
-		paste(sapply(names(m), function(x) {
-			paste0(x, ': ', formatlm(m[[x]]))
-		}), collapse = ' // ')
+		gm <- m[[as.character(g)]]
+		if (is.null(gm)) {
+			return(NA)
+		}
+		formatlm(gm, type = type)
 	}
 }
 
@@ -98,8 +117,15 @@ results <- do_call(rbind, lapply(
         log_debug("  Running Chow test for formula: {fmlrow$Formula} (grouping = {fmlrow$Group})")
 
         res <- chow.test(fmlrow$Formula, fmlrow$Group)
-		fmlrow$Pooled <- formatlm(res$pooled.lm)
-		fmlrow$Groups <- formatlm(res$group.lms)
+		fmlrow$Pooled_Coef <- formatlm(res$pooled.lm)
+		for (g in allgroups) {
+			fmlrow[[paste0("Group_", g, "_Coef")]] <- formatlm(res$group.lms, g)
+		}
+		# fmlrow$Groups <- formatlm(res$group.lms)
+		fmlrow$Pooled_Pval <- formatlm(res$pooled.lm, type="pval")
+		for (g in allgroups) {
+			fmlrow[[paste0("Group_", g, "_Pval")]] <- formatlm(res$group.lms, g, type="pval")
+		}
 		fmlrow$SSR <- res$group.ssr
 		fmlrow$SumSSR <- res$pooled.ssr
 		fmlrow$Fstat <- res$Fstat