Initial RNA-seq DESeq2 pipeline manifests

2026-06-21 06:39:53 -04:00
commit 395c18a9e6
9 changed files with 431 additions and 0 deletions
@@ -0,0 +1,69 @@
+# 06-job-deseq2.yaml
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: deseq2-v2
+  namespace: rnaseq
+spec:
+  backoffLimit: 1
+  template:
+    spec:
+      restartPolicy: Never
+
+      containers:
+        - name: deseq2
+          image: quay.io/biocontainers/bioconductor-deseq2:1.46.0--r44he5774e6_1
+          command: ["/bin/sh", "-c"]
+          args:
+            - |
+              set -e
+              cat <<'EOF' > /tmp/deseq2_analysis.R
+              library(DESeq2)
+
+              counts_raw <- read.table("/data/counts/gene_counts.txt",
+                                        header = TRUE, skip = 1, row.names = 1)
+
+              counts <- counts_raw[, 6:11]
+              colnames(counts) <- c("WT_1", "WT_2", "WT_3",
+                                     "SNF2_1", "SNF2_2", "SNF2_3")
+
+              coldata <- data.frame(
+                condition = factor(c("WT", "WT", "WT",
+                                      "SNF2", "SNF2", "SNF2"),
+                                    levels = c("WT", "SNF2"))
+              )
+              rownames(coldata) <- colnames(counts)
+
+              dds <- DESeqDataSetFromMatrix(countData = counts,
+                                             colData = coldata,
+                                             design = ~ condition)
+
+              dds <- DESeq(dds)
+              res <- results(dds)
+              res <- res[order(res$padj), ]
+
+              write.csv(as.data.frame(res), "/data/results/deseq2_results.csv")
+
+              cat("=== Summary ===\n")
+              summary(res)
+
+              cat("\n=== Top 10 genes by adjusted p-value ===\n")
+              print(head(as.data.frame(res), 10))
+              EOF
+
+              Rscript /tmp/deseq2_analysis.R
+          resources:
+            requests:
+              memory: "2Gi"
+              cpu: "2"
+            limits:
+              memory: "4Gi"
+              cpu: "4"
+          volumeMounts:
+            - name: workspace
+              mountPath: /data
+
+      volumes:
+        - name: workspace
+          persistentVolumeClaim:
+            claimName: rnaseq-workspace