Simon Anders simon-anders

biostatistician

simon-anders / cigar.py

Created May 10, 2026 15:16

	import numpy as np
	import pysam
	import numba

	@numba.njit
	def _check_cigar_pos(pos, cigar):
	if pos > cigar.shape[0]:
	raise ValueError("Invalid CIGAR string (1)")

	@numba.njit

simon-anders / corgi_test.R

Created January 29, 2026 14:44

	library( tidyverse )

	read_tsv("~/tmp/truth_gene_expression_protein_coding_summed_by_tissue_negative_strand.csv") %>%
	mutate( gene = coalesce( `Gene name`, `Gene stable ID` ) ) %>%
	column_to_rownames("gene") %>% select( -(1:4) ) %>% as.matrix -> true_expr
	read_tsv("~/tmp/predicted_gene_expression_protein_coding_summed_by_tissue_negative_strand.csv") %>%
	mutate( gene = coalesce( `Gene name`, `Gene stable ID` ) ) %>%
	column_to_rownames("gene") %>% select( -(1:4) ) %>% as.matrix -> pred_expr

simon-anders / make_ab_file.rs

Last active January 23, 2026 00:26

	use std::fs::File;
	use std::io::{BufReader,BufRead,self,Write};
	use std::error::Error;
	use std::collections::{HashMap,VecDeque,HashSet};
	use std::env;


	#[derive(Debug)]
	struct Interval {
	chrom: i32,

simon-anders / zf_atlas_vs_ours.R

Created December 18, 2025 15:33

	# Load "anndata" Python package via reticulate
	# so that we can read the h5ad file

	library( reticulate )
	use_virtualenv("~/pyenvs/main/")
	anndata <- import("anndata")

	# Load the h5ad file from ZebraHub
	# https://figshare.com/ndownloader/files/36736206
	ad <- anndata$read_h5ad("zf_atlas_full_v1_release.h5ad")

simon-anders / gist:525d750b09733e2c9276dbbb161e2e45

Created November 18, 2025 10:08

	library( tidyverse )
	library( haven )

	left_join(
	read_xpt("~/Downloads/DEMO_J.xpt"),
	read_xpt("~/Downloads/BMX_J.xpt"),
	by="SEQN", relationship="one-to-one" ) %>%
	select( subjectId=SEQN, gender_code=RIAGENDR,
	age=RIDAGEYR, ethnicity_code=RIDRETH3, height=BMXHT ) -> nhanes0

simon-anders / sc_density_stan.qmd

Last active October 23, 2024 18:04

	---
	format:
	html:
	embed-resources: true
	---

	# Density estimation for single-cell gene expression with MCMC

	Simon Anders, 2024-10-23

simon-anders / stan_nb_dens.R

Last active October 23, 2024 18:05

	library( rstan )
	options(mc.cores=6)

	n <- 1000
	s <- round( 10^rnorm( n, 3, .5 ) )
	fracs <- 10^ifelse( runif(n)<.7, rnorm( n, -3.3, .4 ), rnorm( n, -1.7, .2 ) )
	k <- rpois( n, fracs*s )

	model <- stan_model( model_code="
	data {

simon-anders / smoothing_demo.R

Created May 28, 2024 12:07


	# Make example data
	n <- 15
	x <- runif( n, 0, 10 )
	y <- sin(x) + rnorm( n, sd=.1 )

	# Make grid to plot smooth curves
	xg <- seq( 0, 10, length.out=1000 )

	# Determine knot positions:

simon-anders / check_c.py

Last active January 14, 2024 19:11

	import gzip, random

	# Load FASTQ file for Chromosome 10 from GRCm38
	with gzip.open("data/Mus_musculus.GRCm38.dna.chromosome.10.fa.gz") as f:
	firstline = f.readline()
	assert firstline.startswith(b'>')
	chrom_seq = b"".join(l.rstrip() for l in f)

	# This here is the file from papagei:mnt/raid/scnmt_data/CpG_filtered
	cpg = scipy.sparse.load_npz( "data/CpG_10.npz" ).tocoo()

simon-anders / example_figure_size.Rmd

Created April 14, 2022 09:53

	## Beispiel für Plot-Größe

	Tidyverse laden:

	```{r}
	library( tidyverse )
	```

	Wir benutzen `mtcars`, eine Standard-Beispiel-Tabelle von R mit technischen Daten
	für (recht alte) Autos: