Skip to content

Commit

Permalink
Merge branch 'master' into aggregate-reads
Browse files Browse the repository at this point in the history
  • Loading branch information
@kedhammar
kedhammar committed Jan 17, 2025
2 parents cc7f8ab + cc0c236 commit f8a40fe
Show file tree
Hide file tree
Showing 35 changed files with 215 additions and 238 deletions.
4 changes: 4 additions & 0 deletions VERSIONLOG.md
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,9 @@
# Scilifelab_epps Version Log

## 20250116.1

Ruff 0.9.2 formatting.

## 20250108.1

Replace PR Label checker with a less opaque action.
Expand Down
24 changes: 12 additions & 12 deletions scilifelab_epps/calc_from_args/calculation_methods.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -181,9 +181,9 @@ def summarize_pooling(process: Process, args: Namespace):
cols["input_conc_units"] = str(
fetch_from_arg(art_tuple, args.conc_units_in, process)
)
assert (
cols["input_conc_units"] in ["ng/ul", "nM"]
), f'Unsupported conc. units "{cols["input_conc_units"]}" for art {art_in.name}'
assert cols["input_conc_units"] in ["ng/ul", "nM"], (
f'Unsupported conc. units "{cols["input_conc_units"]}" for art {art_in.name}'
)
else:
# Infer concentration unit
if "ng/ul" in args.conc_in["udf"]:
Expand Down Expand Up @@ -216,9 +216,9 @@ def summarize_pooling(process: Process, args: Namespace):
df_pool = pd.DataFrame(pool_data_rows)
df_pool.index = [art_tuple[0]["uri"].name for art_tuple in pool_tuples]

assert (
df_pool.output_amt_unit.unique().size == 1
), "Inconsistent output amount units."
assert df_pool.output_amt_unit.unique().size == 1, (
"Inconsistent output amount units."
)

# Get a column with consistent concentration units
df_pool["input_conc_nM"] = df_pool.apply(
Expand Down Expand Up @@ -331,9 +331,9 @@ def equimolar_pooling(process: Process, args: Namespace):
cols["input_conc_units"] = str(
fetch_from_arg(art_tuple, args.conc_units_in, process)
)
assert (
cols["input_conc_units"] in ["ng/ul", "nM"]
), f'Unsupported conc. units "{cols["input_conc_units"]}" for art {art_in.name}'
assert cols["input_conc_units"] in ["ng/ul", "nM"], (
f'Unsupported conc. units "{cols["input_conc_units"]}" for art {art_in.name}'
)
else:
# Infer concentration unit
if "ng/ul" in args.conc_in["udf"]:
Expand Down Expand Up @@ -366,9 +366,9 @@ def equimolar_pooling(process: Process, args: Namespace):
df_pool = pd.DataFrame(pool_data_rows)
df_pool.index = [art_tuple[0]["uri"].name for art_tuple in pool_tuples]

assert (
df_pool.output_amt_unit.unique().size == 1
), "Inconsistent output amount units."
assert df_pool.output_amt_unit.unique().size == 1, (
"Inconsistent output amount units."
)

# Get a column with consistent concentration units
df_pool["input_conc_nM"] = df_pool.apply(
Expand Down
6 changes: 3 additions & 3 deletions scilifelab_epps/epp.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ def __enter__(self):
)
except DistributionNotFound as e:
logging.error(e)
logging.error(f"Make sure you have the {self.PACKAGE} " "package installed")
logging.error(f"Make sure you have the {self.PACKAGE} package installed")
sys.exit(-1)
return self

Expand Down Expand Up @@ -185,7 +185,7 @@ def prepend_old_log(self, external_log_file=None):
f.write("=" * 80 + "\n")
except HTTPError: # Probably no artifact found, skip prepending
print(
("No log file artifact found " f"for id: {log_file_name}"),
(f"No log file artifact found for id: {log_file_name}"),
file=sys.stderr,
)
except OSError as e: # Probably some path was wrong in copy
Expand Down Expand Up @@ -417,7 +417,7 @@ def _log_after_change(self):
}

logging.info(
"Updated {d_elt_type} udf: {d_udf}, from {su} to " "{nv}.".format(**d)
"Updated {d_elt_type} udf: {d_udf}, from {su} to {nv}.".format(**d)
)

def copy_udf(self, changelog_f=None):
Expand Down
6 changes: 3 additions & 3 deletions scilifelab_epps/utils/udf_tools.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -236,9 +236,9 @@ def fetch_last(
):
matching_tuples.append(pp_tuple)

assert (
len(matching_tuples) == 1
), "Target artifact matches multiple inputs/outputs in previous step."
assert len(matching_tuples) == 1, (
"Target artifact matches multiple inputs/outputs in previous step."
)

# Back-tracking successful, re-assign variables to represent previous step
currentStep = pp
Expand Down
98 changes: 50 additions & 48 deletions scilifelab_epps/zika/methods.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ def pool_fixed_vol(
# Write log header
log = []
for e in [
f"LIMS process {currentStep.id}\n" "\n=== Volume constraints ===",
f"LIMS process {currentStep.id}\n\n=== Volume constraints ===",
f"Minimum pipetting volume: {zika_min_vol} ul",
f"Maximum allowed dst well volume: {well_max_vol} ul",
]:
Expand All @@ -35,9 +35,9 @@ def pool_fixed_vol(
fixed_vol_step_udf = "Transfer Volume for Pooling (uL)"
fixed_vol = currentStep.udf[fixed_vol_step_udf]
assert type(fixed_vol) in [int, float], f"'{fixed_vol_step_udf}' must be a number."
assert (
zika_min_vol <= fixed_vol <= well_max_vol
), f"'{fixed_vol_step_udf}' must be between {zika_min_vol} and {well_max_vol} ul."
assert zika_min_vol <= fixed_vol <= well_max_vol, (
f"'{fixed_vol_step_udf}' must be between {zika_min_vol} and {well_max_vol} ul."
)
log.append(f"Fixed transfer volume: {fixed_vol} ul")

# Get pools
Expand Down Expand Up @@ -156,7 +156,7 @@ def pool(
# Write log header
log = []
for e in [
f"LIMS process {currentStep.id}\n" "\n=== Volume constraints ===",
f"LIMS process {currentStep.id}\n\n=== Volume constraints ===",
f"Minimum pipetting volume: {zika_min_vol} ul",
f"Applied dead volume: {well_dead_vol} ul",
f"Maximum allowed dst well volume: {well_max_vol} ul",
Expand Down Expand Up @@ -190,13 +190,13 @@ def pool(
df_all = zika.utils.fetch_sample_data(currentStep, to_fetch)

# All samples should have accessible volume
assert all(
df_all.vol > well_dead_vol
), f"The minimum required source volume is {well_dead_vol} ul"
assert all(df_all.vol > well_dead_vol), (
f"The minimum required source volume is {well_dead_vol} ul"
)

assert all(
df_all.target_vol <= well_max_vol
), f"All target volumes must be at or below {well_max_vol} uL"
assert all(df_all.target_vol <= well_max_vol), (
f"All target volumes must be at or below {well_max_vol} uL"
)

# Adjust for dead volume
df_all["full_vol"] = df_all.vol.copy()
Expand Down Expand Up @@ -237,9 +237,9 @@ def pool(
conc_unit = "ng/ul"
else:
raise AssertionError("Could not make sense of input UDFs")
assert all(
df_all.conc_units == conc_unit
), "Samples and pools have different conc units"
assert all(df_all.conc_units == conc_unit), (
"Samples and pools have different conc units"
)

# Append target parameters to log
log.append(f"\n\nPooling {len(df_pool)} samples into {pool.name}...")
Expand Down Expand Up @@ -314,10 +314,10 @@ def pool(
f"\nERROR: Overflow in {pool.name}. Decrease number of samples or dilute highly concentrated outliers"
)
log.append(
f"Highest concentrated sample: {highest_conc_sample.sample_name} at {round(highest_conc_sample.conc,2)} {conc_unit}"
f"Highest concentrated sample: {highest_conc_sample.sample_name} at {round(highest_conc_sample.conc, 2)} {conc_unit}"
)
log.append(
f"Pooling cannot be normalized to less than {round(pool_min_sample_vol,1)} ul"
f"Pooling cannot be normalized to less than {round(pool_min_sample_vol, 1)} ul"
)

errors = True
Expand All @@ -327,13 +327,13 @@ def pool(
"\nAn even pool can be created within the following parameter ranges:"
)
log.append(
f" - Amount per sample {round(lowest_common_amount,2)} - {round(pool_max_sample_amt / len(df_pool),2)} {amt_unit}"
f" - Amount per sample {round(lowest_common_amount, 2)} - {round(pool_max_sample_amt / len(df_pool), 2)} {amt_unit}"
)
log.append(
f" - Pool volume {round(pool_min_sample_vol,1)} - {round(well_max_vol,1)} ul"
f" - Pool volume {round(pool_min_sample_vol, 1)} - {round(well_max_vol, 1)} ul"
)
log.append(
f" - Pool concentration {round(pool_min_conc,2)} - {round(pool_max_conc,2)} {conc_unit}"
f" - Pool concentration {round(pool_min_conc, 2)} - {round(pool_max_conc, 2)} {conc_unit}"
)

# Nudge conc, if necessary
Expand Down Expand Up @@ -380,7 +380,7 @@ def pool(
)
for i, r in df_low.iterrows():
log.append(
f"{r.sample_name} ({round(r.conc,2)} {r.conc_units}, {round(r.vol,2)} uL accessible volume)"
f"{r.sample_name} ({round(r.conc, 2)} {r.conc_units}, {round(r.vol, 2)} uL accessible volume)"
)
log.append(
"The above samples will be depleted and under-represented in the final pool."
Expand All @@ -402,10 +402,10 @@ def pool(
f"\nERROR: Overflow in {pool.name}. Decrease number of samples or dilute highly concentrated outliers"
)
log.append(
f"Highest concentrated sample: {highest_conc_sample.sample_name} at {round(highest_conc_sample.conc,2)} {conc_unit}"
f"Highest concentrated sample: {highest_conc_sample.sample_name} at {round(highest_conc_sample.conc, 2)} {conc_unit}"
)
log.append(
f"Pooling cannot be normalized to less than {round(pool_real_min_sample_vol,1)} ul"
f"Pooling cannot be normalized to less than {round(pool_real_min_sample_vol, 1)} ul"
)

errors = True
Expand All @@ -415,13 +415,13 @@ def pool(
"\nWill try to create a pool that is as even as possible. Accounting for sample depletion, a pool can be created with the following parameter ranges: "
)
log.append(
f" - Target amount per sample {round(target_transfer_amt,2)}"
f" - Target amount per sample {round(target_transfer_amt, 2)}"
)
log.append(
f" - Pool volume {round(pool_real_min_sample_vol,1)}-{round(well_max_vol,1)} ul"
f" - Pool volume {round(pool_real_min_sample_vol, 1)}-{round(well_max_vol, 1)} ul"
)
log.append(
f" - Pool concentration {round(pool_real_min_conc,2)}-{round(pool_real_max_conc,2)} {conc_unit}"
f" - Pool concentration {round(pool_real_min_conc, 2)}-{round(pool_real_max_conc, 2)} {conc_unit}"
)

# Nudge conc, if necessary
Expand Down Expand Up @@ -456,19 +456,19 @@ def pool(
log.append("\nAdjustments:")
if round(target_pool_conc, 2) != round(pool_conc, 2):
log.append(
f" - WARNING: Target pool concentration is adjusted from {round(target_pool_conc,2)} --> {round(pool_conc,2)} {conc_unit}"
f" - WARNING: Target pool concentration is adjusted from {round(target_pool_conc, 2)} --> {round(pool_conc, 2)} {conc_unit}"
)
if round(target_pool_vol, 1) != round(pool_vol, 1):
log.append(
f" - WARNING: Target pool volume is adjusted from {round(target_pool_vol,1)} --> {round(pool_vol,1)} ul"
f" - WARNING: Target pool volume is adjusted from {round(target_pool_vol, 1)} --> {round(pool_vol, 1)} ul"
)
if round(target_pool_conc, 2) == round(pool_conc, 2) and round(
target_pool_vol, 1
) == round(pool_vol, 1):
log.append("Pooling OK")
if round(target_transfer_amt, 2) != round(target_amt_taken, 2):
log.append(
f" - INFO: Amount taken per sample is adjusted from {round(target_amt_taken,2)} --> {round(target_transfer_amt,2)} {amt_unit}"
f" - INFO: Amount taken per sample is adjusted from {round(target_amt_taken, 2)} --> {round(target_transfer_amt, 2)} {amt_unit}"
)

# Calculate and store pool buffer volume
Expand All @@ -480,7 +480,7 @@ def pool(
)
buffer_vols[pool.name] = buffer_vol
log.append(
f"\nThe final pool volume is {round(pool_vol,1)} ul ({round(total_sample_vol,1)} ul sample + {round(buffer_vol,1)} ul buffer)"
f"\nThe final pool volume is {round(pool_vol, 1)} ul ({round(total_sample_vol, 1)} ul sample + {round(buffer_vol, 1)} ul buffer)"
)

# === REPORT DEVIATING SAMPLES ===
Expand All @@ -498,7 +498,7 @@ def pool(
)
log.append("Sample\tFraction")
for name, frac in outlier_samples.values:
log.append(f" - {name}\t{round(frac,2)}")
log.append(f" - {name}\t{round(frac, 2)}")

df_wl = pd.concat([df_wl, df_pool], axis=0)

Expand Down Expand Up @@ -535,7 +535,7 @@ def pool(
for pool in pools:
if buffer_vols[pool.name] > 0:
comments.append(
f"Add {round(buffer_vols[pool.name],1)} ul buffer to pool {pool.name} (well {pool.location[1]})"
f"Add {round(buffer_vols[pool.name], 1)} ul buffer to pool {pool.name} (well {pool.location[1]})"
)

# Write the output files
Expand Down Expand Up @@ -606,7 +606,7 @@ def norm(

log = []
for e in [
f"LIMS process {currentStep.id}\n" "\n=== Dilution strategy ===",
f"LIMS process {currentStep.id}\n\n=== Dilution strategy ===",
f"Expand volume to obtain target conc: {volume_expansion}",
f"Base calculations on user measurements: {use_customer_metrics}",
"\n=== Volume constraints ===",
Expand All @@ -623,12 +623,12 @@ def norm(

# Assert required UDFs are populated in step
for output_name, output in outputs.items():
assert is_filled(
output, udfs["target_amt"]
), f"UDF '{udfs['target_amt']}' missing for {output.name}"
assert is_filled(
output, udfs["target_vol"]
), f"UDF '{udfs['target_vol']}' missing for {output.name}"
assert is_filled(output, udfs["target_amt"]), (
f"UDF '{udfs['target_amt']}' missing for {output.name}"
)
assert is_filled(output, udfs["target_vol"]), (
f"UDF '{udfs['target_vol']}' missing for {output.name}"
)

# Fetch sample data

Expand Down Expand Up @@ -662,13 +662,13 @@ def norm(
amt_unit = "ng" if conc_unit == "ng/ul" else "fmol"

# Assertions
assert all(
df.target_vol <= well_max_vol
), f"All target volumes must be at or below {well_max_vol} uL"
assert all(df.target_vol <= well_max_vol), (
f"All target volumes must be at or below {well_max_vol} uL"
)

assert all(
df.vol > well_dead_vol
), f"The minimum required source volume is {well_dead_vol} ul"
assert all(df.vol > well_dead_vol), (
f"The minimum required source volume is {well_dead_vol} ul"
)
df["full_vol"] = df.vol.copy()
df.loc[:, "vol"] = df.vol - well_dead_vol

Expand Down Expand Up @@ -696,7 +696,7 @@ def norm(
}
for i, r in df.iterrows():
log.append(
f"\n{r.sample_name} (conc {round(r.conc,2)} {conc_unit}, vol {round(r.vol,1)} ul)"
f"\n{r.sample_name} (conc {round(r.conc, 2)} {conc_unit}, vol {round(r.vol, 1)} ul)"
)

# Cases
Expand Down Expand Up @@ -733,7 +733,9 @@ def norm(
tot_vol = r.min_transfer_amt / r.target_conc
else:
tot_vol = well_max_vol
log.append(f"INFO: Expanding total volume to {round(tot_vol,1)} ul")
log.append(
f"INFO: Expanding total volume to {round(tot_vol, 1)} ul"
)
sample_vol = zika_min_vol
buffer_vol = tot_vol - sample_vol

Expand All @@ -746,7 +748,7 @@ def norm(
# Adress cases where buffer volume is lower than the minimum transfer amount
if 0 < buffer_vol < zika_min_vol:
log.append(
f"WARNING: Required buffer volume ({round(buffer_vol,1)} ul) is less than minimum transfer volume {zika_min_vol} ul"
f"WARNING: Required buffer volume ({round(buffer_vol, 1)} ul) is less than minimum transfer volume {zika_min_vol} ul"
)
log.append("INFO: Omitting buffer")
tot_vol -= buffer_vol
Expand All @@ -761,7 +763,7 @@ def norm(
elif round(final_conc_frac, 2) < 1:
log.append("WARNING: Final concentration is below target")
log.append(
f"--> Diluting {round(sample_vol,1)} ul ({round(final_amt,2)} {amt_unit}) to {round(tot_vol,1)} ul ({round(final_conc,2)} {conc_unit}, {round(final_conc_frac*100,1)}% of target)"
f"--> Diluting {round(sample_vol, 1)} ul ({round(final_amt, 2)} {amt_unit}) to {round(tot_vol, 1)} ul ({round(final_conc, 2)} {conc_unit}, {round(final_conc_frac * 100, 1)}% of target)"
)

# Append calculation results to dict
Expand Down
4 changes: 1 addition & 3 deletions scripts/calculate_cell_nuclei_conc.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -60,9 +60,7 @@ def main(lims, pid, epp_logger):
parser.add_argument(
"--log",
dest="log",
help=(
"File name for standard log file, " "for runtime information and problems."
),
help=("File name for standard log file, for runtime information and problems."),
)
args = parser.parse_args()

Expand Down
Loading

0 comments on commit f8a40fe

Please sign in to comment.