# Feature Requests **URL:** https://discuss.hail.is/c/features/7.md?page=1 [Latest](https://discuss.hail.is/latest.md) · [Categories](https://discuss.hail.is/categories.md) **Page:** 2 --- ## [Ordinal Regression](https://discuss.hail.is/t/ordinal-regression/1387)
**Author:** [@danking](https://discuss.hail.is/u/danking)\ **Replies:** 21\ **Last updated:** [July 27, 2021, 1:18pm UTC](https://discuss.hail.is/t/ordinal-regression/1387 "2021-07-27T13:18:16Z")
Hail should support ordinal regression. Ordinal regression deals with a dependent variable whose values are finite, discrete and ordered. This differs from a categorical variable where each value can be represented by a … --- ## [Easy Integration Of Parquet Files](https://discuss.hail.is/t/easy-integration-of-parquet-files/1919)
**Author:** [@Haseeb1](https://discuss.hail.is/u/Haseeb1)\ **Replies:** 1\ **Last updated:** [February 19, 2021, 1:24pm UTC](https://discuss.hail.is/t/easy-integration-of-parquet-files/1919 "2021-02-19T13:24:34Z")
Kindly add function to import parquet files into MT and export MT to parquet files. --- ## [Selection analysis in Hail 0.2](https://discuss.hail.is/t/selection-analysis-in-hail-0-2/1907)
**Author:** [@Rost](https://discuss.hail.is/u/Rost)\ **Replies:** 0\ **Last updated:** [February 7, 2021, 1:16pm UTC](https://discuss.hail.is/t/selection-analysis-in-hail-0-2/1907 "2021-02-07T13:16:43Z")
Hi, Hail! I guess many can expect a variety of metrics of selection estimation such as MKT, EHH, iHS, XP-EHH. Is there Hail’s integrated toolkit for this now? Are there any plans to add this soon? --- ## [Clumping variants to calculate polygenic risk scores](https://discuss.hail.is/t/clumping-variants-to-calculate-polygenic-risk-scores/395)
**Author:** [@armartin](https://discuss.hail.is/u/armartin)\ **Replies:** 1\ **Last updated:** [January 20, 2021, 9:58pm UTC](https://discuss.hail.is/t/clumping-variants-to-calculate-polygenic-risk-scores/395 "2021-01-20T21:58:32Z")
It would be helpful to calculate polygenic risk scores if a clump variants function existed. This is a greedy algorithm described in plink here: https://www.cog-genomics.org/plink/1.9/postproc#clump Basically: 1) comput… --- ## [Survival GWAS model (coxph) with interaction term enabled](https://discuss.hail.is/t/survival-gwas-model-coxph-with-interaction-term-enabled/1891)
**Author:** [@Maryam\_Zekavat](https://discuss.hail.is/u/Maryam_Zekavat)\ **Replies:** 0\ **Last updated:** [January 14, 2021, 8:41pm UTC](https://discuss.hail.is/t/survival-gwas-model-coxph-with-interaction-term-enabled/1891 "2021-01-14T20:41:02Z")
Hello! I wanted to see if it’d be possible to add a coxPH model with interaction term as a GWAS model. I’ve been coding it myself using the coxPH function in R’s survival library (https://www.rdocumentation.org/packages… --- ## [Hashlib Functionality in Hail](https://discuss.hail.is/t/hashlib-functionality-in-hail/1771)
**Author:** [@IqviaGarrettBromley](https://discuss.hail.is/u/IqviaGarrettBromley)\ **Replies:** 0\ **Last updated:** [November 4, 2020, 4:57pm UTC](https://discuss.hail.is/t/hashlib-functionality-in-hail/1771 "2020-11-04T16:57:51Z")
It would be beneficial for our use case to support hashlib functionality in hail. Currently the only way to hash a column of strings is to export to pandas, then do the hashing and bring it back into hail after which isn… --- ## [Dataproc connect should support --project command line option](https://discuss.hail.is/t/dataproc-connect-should-support-project-command-line-option/1598)
**Author:** [@kferriter](https://discuss.hail.is/u/kferriter)\ **Replies:** 1\ **Last updated:** [August 28, 2020, 6:57pm UTC](https://discuss.hail.is/t/dataproc-connect-should-support-project-command-line-option/1598 "2020-08-28T18:57:13Z")
A cluster created with hailctl dataproc create that includes a --project option value can’t be referred to with the hailctl dataproc connect command when the project used in the create step is not the same as the one set… --- ## [Compute imputation quality R2](https://discuss.hail.is/t/compute-imputation-quality-r2/1584)
**Author:** [@jychung](https://discuss.hail.is/u/jychung)\ **Replies:** 1\ **Last updated:** [August 17, 2020, 8:43pm UTC](https://discuss.hail.is/t/compute-imputation-quality-r2/1584 "2020-08-17T20:43:50Z")
Hello, I am using DS (imputed dosage) in vcf files for GWAS analysis (hl.logistic\_regression\_rows). I could generate gwas output using the function, .export( file\_name ). And these are the header of my output file: loc… --- ## [CollectionExpression join](https://discuss.hail.is/t/collectionexpression-join/1562)
**Author:** [@nlw](https://discuss.hail.is/u/nlw)\ **Replies:** 1\ **Last updated:** [July 31, 2020, 1:41am UTC](https://discuss.hail.is/t/collectionexpression-join/1562 "2020-07-31T01:41:42Z")
Would love if there were a CollectionExpression function to join the collection (array/set) elements with a delimiter and return a string, like the opposite of split(). For example, if a = \['an', 'array', 'of', 'element… --- ## [Hail implementation of RUTH](https://discuss.hail.is/t/hail-implementation-of-ruth/1115)
**Author:** [@jjfarrell](https://discuss.hail.is/u/jjfarrell)\ **Replies:** 3\ **Last updated:** [July 2, 2020, 6:59pm UTC](https://discuss.hail.is/t/hail-implementation-of-ruth/1115 "2020-07-02T18:59:45Z")
There is a robust implementation of HWE Test that takes into account population substructure: RUTH - Robust Unified Hardy-Weinberg Equilibrium Test. It is used for the TopMed pipeline. The GitHub repository is here: … --- ## [Export\_vcf path with .bgz extension creates .bgz directory when using parallel](https://discuss.hail.is/t/export-vcf-path-with-bgz-extension-creates-bgz-directory-when-using-parallel/1333)
**Author:** [@mwilson](https://discuss.hail.is/u/mwilson)\ **Replies:** 2\ **Last updated:** [March 13, 2020, 2:36pm UTC](https://discuss.hail.is/t/export-vcf-path-with-bgz-extension-creates-bgz-directory-when-using-parallel/1333 "2020-03-13T14:36:13Z")
Hello, I’m currently exporting a MT to VCF using parallel=header\_per\_shard and noticed that the .bgz extension is necessary in the provided output path in order to block gzip the shards. This leads to misleading file … --- ## [Friendlier init() response when already initialized](https://discuss.hail.is/t/friendlier-init-response-when-already-initialized/1322)
**Author:** [@Joel\_Thibault](https://discuss.hail.is/u/Joel_Thibault)\ **Replies:** 3\ **Last updated:** [March 3, 2020, 6:07pm UTC](https://discuss.hail.is/t/friendlier-init-response-when-already-initialized/1322 "2020-03-03T18:07:06Z")
\[Context: a Terra/GATK workshop where users run some Hail commands in a Terra Jupyter notebook.\] Hail version 0.2.30-2ae07d872f43 Running the init() command when it’s already initialized results in: FatalError … --- ## [Manhattan Plot for association results](https://discuss.hail.is/t/manhattan-plot-for-association-results/522)
**Author:** [@jjfarrell](https://discuss.hail.is/u/jjfarrell)\ **Replies:** 5\ **Last updated:** [September 16, 2019, 2:24pm UTC](https://discuss.hail.is/t/manhattan-plot-for-association-results/522 "2019-09-16T14:24:11Z")
A Hail Manhattan Plot function would be very useful for summarizing association results. It would be much simpler to implement than the regional plot feature that was requested previously. Here is an R code example: --- ## [Implement SAIGE in Hail](https://discuss.hail.is/t/implement-saige-in-hail/745)
**Author:** [@jjfarrell](https://discuss.hail.is/u/jjfarrell)\ **Replies:** 1\ **Last updated:** [July 23, 2019, 10:25pm UTC](https://discuss.hail.is/t/implement-saige-in-hail/745 "2019-07-23T22:25:34Z")
Porting SAIGE (https://github.com/weizhouUMICH/SAIGE) to Hail would be very useful for analyzing the UK BIobank Data and similar datasets. The R code implements a Generalized mixed model that controls for both imbalanced… --- ## [Download for tutorial notebooks](https://discuss.hail.is/t/download-for-tutorial-notebooks/1005)
**Author:** [@rbutleriii](https://discuss.hail.is/u/rbutleriii)\ **Replies:** 1\ **Last updated:** [June 30, 2019, 12:41pm UTC](https://discuss.hail.is/t/download-for-tutorial-notebooks/1005 "2019-06-30T12:41:29Z")
Installing and testing hail, I noticed the recommendation to use jupyter notebooks for the tutorials, but the notebooks in the docs are not available using the conda local install. Or rather, find miniconda3/ -name '\*.ip… --- ## [PCA to output allele frequencies alongside loadings?](https://discuss.hail.is/t/pca-to-output-allele-frequencies-alongside-loadings/439)
**Author:** [@konradjk](https://discuss.hail.is/u/konradjk)\ **Replies:** 7\ **Last updated:** [April 24, 2019, 2:22pm UTC](https://discuss.hail.is/t/pca-to-output-allele-frequencies-alongside-loadings/439 "2019-04-24T14:22:08Z")
Title says most of it. I feel like hwe\_normalized\_pca could output the frequency it uses to center alongside the loadings. I’m doing this for downstream projection, which presumably is most of the use cases for outputtin… --- ## [Change distance metric in PCA](https://discuss.hail.is/t/change-distance-metric-in-pca/940)
**Author:** [@lindsayvm](https://discuss.hail.is/u/lindsayvm)\ **Replies:** 5\ **Last updated:** [April 23, 2019, 8:38pm UTC](https://discuss.hail.is/t/change-distance-metric-in-pca/940 "2019-04-23T20:38:28Z")
Hi, I need to do a PCA using the Jaccard distance metric instead of euclidean distance. Is it possible to change the distance metric of pca() or hwe\_normalized\_pca() in any way? Thanks! --- ## [Sandwich corrected standard errors?](https://discuss.hail.is/t/sandwich-corrected-standard-errors/247)
**Author:** [@Michel\_Nivard](https://discuss.hail.is/u/Michel_Nivard)\ **Replies:** 2\ **Last updated:** [April 10, 2019, 9:19pm UTC](https://discuss.hail.is/t/sandwich-corrected-standard-errors/247 "2019-04-10T21:19:55Z")
What are the chances that HAIL at some point will include sandwich corrected SE's for robust inference in dataset which contain family members? Best, Michel --- ## [I want to remove a snp from the regression equation](https://discuss.hail.is/t/i-want-to-remove-a-snp-from-the-regression-equation/882)
**Author:** [@aleriedy](https://discuss.hail.is/u/aleriedy)\ **Replies:** 8\ **Last updated:** [March 1, 2019, 3:26pm UTC](https://discuss.hail.is/t/i-want-to-remove-a-snp-from-the-regression-equation/882 "2019-03-01T15:26:59Z")
Hi I want to remove a specific snp or snps from the regression equation and add it as a covarite Thank you --- ## [Snp x covarite interaction in Hail 0.2](https://discuss.hail.is/t/snp-x-covarite-interaction-in-hail-0-2/879)
**Author:** [@aleriedy](https://discuss.hail.is/u/aleriedy)\ **Replies:** 1\ **Last updated:** [February 26, 2019, 10:57pm UTC](https://discuss.hail.is/t/snp-x-covarite-interaction-in-hail-0-2/879 "2019-02-26T22:57:20Z")
I was wondering if I can include SNP x Covarite interaction term ? Thank you --- ## [Categorical covariates in association analyses](https://discuss.hail.is/t/categorical-covariates-in-association-analyses/399)
**Author:** [@Robert](https://discuss.hail.is/u/Robert)\ **Replies:** 3\ **Last updated:** [February 20, 2019, 3:30pm UTC](https://discuss.hail.is/t/categorical-covariates-in-association-analyses/399 "2019-02-20T15:30:44Z")
At the moment you can only include continuous or boolean covariates. It would be great if categorical variables could also be used as covariates. It’s just a matter of turning each unique value into a boolean dummy varia… --- ## [Ld\_matrix for specific variant/locus and radius](https://discuss.hail.is/t/ld-matrix-for-specific-variant-locus-and-radius/846)
**Author:** [@hhx037](https://discuss.hail.is/u/hhx037)\ **Replies:** 3\ **Last updated:** [February 11, 2019, 5:21pm UTC](https://discuss.hail.is/t/ld-matrix-for-specific-variant-locus-and-radius/846 "2019-02-11T17:21:52Z")
Hi, I was wondering if it would be possible to get a function like ld\_matrix that would return the LD between a single variant/locus and neighbouring variants within a specified radius, that would be very helpful. Chee… --- ## [Web API projects](https://discuss.hail.is/t/web-api-projects/800)
**Author:** [@lasuperclasse](https://discuss.hail.is/u/lasuperclasse)\ **Replies:** 28\ **Last updated:** [December 27, 2018, 10:46am UTC](https://discuss.hail.is/t/web-api-projects/800 "2018-12-27T10:46:31Z")
Hi all, Do you know of any projects developing a web API layer for Hail? Open GitHub projects preferred of course :wink: --- ## [Exporting intermediate components of score test](https://discuss.hail.is/t/exporting-intermediate-components-of-score-test/793)
**Author:** [@pyspark\_user](https://discuss.hail.is/u/pyspark_user)\ **Replies:** 3\ **Last updated:** [December 17, 2018, 2:05am UTC](https://discuss.hail.is/t/exporting-intermediate-components-of-score-test/793 "2018-12-17T02:05:16Z")
Our group would like to perform logistic regression of rare variants across 10 or so moderate sized data sets. In order to perform a score test combining summary statistics over these data sets, we would need the compone… --- ## [Extend Hail to R with Sparklyr](https://discuss.hail.is/t/extend-hail-to-r-with-sparklyr/786)
**Author:** [@jjfarrell](https://discuss.hail.is/u/jjfarrell)\ **Replies:** 1\ **Last updated:** [November 28, 2018, 3:32pm UTC](https://discuss.hail.is/t/extend-hail-to-r-with-sparklyr/786 "2018-11-28T15:32:56Z")
It would be great if R could be used to analyze Hail Matrix tables. That would have a couple benefits: 1. Allow the use of many R and bio conductor packages available on hail tables and matrix tables. 2. Provide R user… --- ## [Logistic-mixed model?](https://discuss.hail.is/t/logistic-mixed-model/780)
**Author:** [@Maryam\_Zekavat](https://discuss.hail.is/u/Maryam_Zekavat)\ **Replies:** 1\ **Last updated:** [November 26, 2018, 11:36pm UTC](https://discuss.hail.is/t/logistic-mixed-model/780 "2018-11-26T23:36:38Z")
Hi Folks! Just curious, is there an ETA for logistic mixed models? Thanks so much! Best, Maryam --- ## [Lambda for qq plot](https://discuss.hail.is/t/lambda-for-qq-plot/749)
**Author:** [@jjfarrell](https://discuss.hail.is/u/jjfarrell)\ **Replies:** 1\ **Last updated:** [November 5, 2018, 6:10pm UTC](https://discuss.hail.is/t/lambda-for-qq-plot/749 "2018-11-05T18:10:56Z")
It would be very useful to include the lambda (also known as the genomic inflation factor) for the Hail qq plot. λ is defined as the median of the resulting chi-squared test statistics divided by the expected median of t… --- ## [Rsid absent from table generated by logistic\_regression\_rows](https://discuss.hail.is/t/rsid-absent-from-table-generated-by-logistic-regression-rows/715)
**Author:** [@hhx037](https://discuss.hail.is/u/hhx037)\ **Replies:** 2\ **Last updated:** [October 24, 2018, 9:45am UTC](https://discuss.hail.is/t/rsid-absent-from-table-generated-by-logistic-regression-rows/715 "2018-10-24T09:45:58Z")
Now that hl.logistic\_regression\_rows generates a table (which is great, no complaint here! :slight\_smile: ), the rsid field is missing. I’m guessing it’s also the case for linreg. Would it be possible to include it in t… --- ## [CNV analysis in Hail](https://discuss.hail.is/t/cnv-analysis-in-hail/671)
**Author:** [@rswenson](https://discuss.hail.is/u/rswenson)\ **Replies:** 1\ **Last updated:** [October 1, 2018, 2:30pm UTC](https://discuss.hail.is/t/cnv-analysis-in-hail/671 "2018-10-01T14:30:14Z")
I know there was an inquiry about this in 2016, but has there been any change to include CNV analysis, or rather that upon import of CNV VCFs that we are able to perform the necessary analysis without having to perhaps d… --- ## [LASSO / elastic net regression on blocks of variants](https://discuss.hail.is/t/lasso-elastic-net-regression-on-blocks-of-variants/492)
**Author:** [@tpoterba](https://discuss.hail.is/u/tpoterba)\ **Replies:** 5\ **Last updated:** [May 12, 2018, 6:52am UTC](https://discuss.hail.is/t/lasso-elastic-net-regression-on-blocks-of-variants/492 "2018-05-12T06:52:24Z")
from @tshmak: By “block”, I was referring to LD blocks, so non-overlapping regions in the genome. Experience told us that running a lasso or a elastic net using the entire dataset is not only slow but also not as good … [Previous page](https://discuss.hail.is/c/features/7.md) [Next page](https://discuss.hail.is/c/features/7.md?page=2)