{"id":851,"date":"2022-11-03T01:19:40","date_gmt":"2022-11-03T01:19:40","guid":{"rendered":"http:\/\/ai4ad.org\/?page_id=851"},"modified":"2024-10-13T23:48:13","modified_gmt":"2024-10-13T23:48:13","slug":"software","status":"publish","type":"page","link":"https:\/\/ai4ad.org\/index.php\/software\/","title":{"rendered":"Software"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"851\" class=\"elementor elementor-851\">\n\t\t\t\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-5131a13e elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"5131a13e\" data-element_type=\"section\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t\t\t<div class=\"elementor-background-overlay\"><\/div>\n\t\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-1053ca7a\" data-id=\"1053ca7a\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-3d99e122 elementor-widget elementor-widget-heading\" data-id=\"3d99e122\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h1 class=\"elementor-heading-title elementor-size-default\">Software &amp;Data<\/h1>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-77a2c43 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"77a2c43\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-e5bf91a\" data-id=\"e5bf91a\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-da0081b elementor-widget elementor-widget-spacer\" data-id=\"da0081b\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-9da0d5f elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"9da0d5f\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-d6b4685\" data-id=\"d6b4685\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-6a4a727 elementor-widget elementor-widget-heading\" data-id=\"6a4a727\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Software<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-9760c45 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"9760c45\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-0164c79\" data-id=\"0164c79\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-586ce76 elementor-widget elementor-widget-text-editor\" data-id=\"586ce76\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<ul><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/vishnubashyam\/DeepBrainNet\"><span style=\"font-weight: 400;\">DeepBrainNet <\/span><\/a><\/span><span style=\"font-weight: 400;\">(PI: Davatzikos)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Brain age prediction on T1 brain scans, Convolutional Neural Network trained on (n=11,729) MRI Input: Skull stripped T1 brain images, registered to a common space, in NITFI Output: Predicted brain age<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Vishnu Bashyam (Vishnu.Bashyam@pennmedicine.upenn.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/zhijian-yang\/SmileGAN\"><span style=\"font-weight: 400;\">Smile-GAN<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Davatzikos)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Deep semi-supervised clustering method designed to identify disease-related neuroanatomical heterogeneity. Inputs: CSV\/TSV files containing image ROI as features, as well as covariates to be adjusted. Output: categorical clustering membership and continuous probability scores<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Zhijian Yang (Zhijian.Yang@Pennmedicine.upenn.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/zhijian-yang\/SurrealGAN\"><span style=\"font-weight: 400;\">Surreal-GAN<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Davatzikos)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Deep semi-supervised representation learning method designed to dissect disease-related neuroanatomical heterogeneity. Inputs: CSV\/TSV files containing image ROI as features, as well as covariates to be adjusted. Output: continuous dimensional scores<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Zhijian Yang (Zhijian.Yang@Pennmedicine.upenn.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/anbai106\/SOPNMF\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">SOPNMF<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Davatzikos)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Using unsupervised factorization method to parcellate the brain into patterns of strucutral covariance (PSC) and correlated these PSCs to common genetic variant to depict the genetic architecture of the human brain. Input: CSV\/TSV containing the path to each MRI. Output: the parcellated PSCs and the loading coefficient, the ROI values.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Junhao Wen (junhao.wen@pennmedicine.upenn.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/cind\/Longitudinal-Disease-Progression-Modeling\"><span style=\"font-weight: 400;\">Longitudinal Disease Progression Modeling<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Toosun)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">The trajectory of a given AD biomarker may take decades, however we are usually limited to much shorter follow up data in ADNI and other AD focused studies. This can impose a challenge when estimating the full course of AD disease progression. Extending the methodology described in Budgeon et. al, we can estimate a full-term disease pathology curve from short term follow up data for multivariate imaging marker data.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Tamar Schaap (tamar.schaap@ucsf.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/cind\/Simulated_Clinical_Trials\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">Clinical Trial Simulation<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Tosun)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Clinical Trial Simulation allows a user to estimate the statistical power of a pre-defined treatment effect at a set of sample sizes. This may be useful in informing recruitment of future clinical trials enriched based on different biomarker signature criteria. Using a Linear-Mixed-Effects Model (LME) trained on pilot data, a user can estimate the power of a treatment effect at a sample size via Monte Carlo Simulation.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Tamar Schaap (tamar.schaap@ucsf.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/Alii-Ganjj\/GenoPhenoMutualLearning\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">MultimodalGAN<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Huang)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">GAN model and knowledge distillation based machine learning algorithm to integrate multimodal genotype and phenotype data and especially deal with missing data modality in prediction, also can predict the longitudinal outcomes<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Alireza Ganjdanesh (alireza.ganjdanesh@pitt.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/taehojo\/SWAT-CNN\/\"><span style=\"font-weight: 400;\">SWAT-CNN<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Saykin)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">A novel three-step approach for identification of genetic variants using deep learning to identify phenotype-related SNPs that can be applied to develop accurate disease classification models.<\/span><\/li><li><i><span style=\"font-weight: 400;\">Contact: Taeho Jo (<\/span><\/i><a href=\"mailto:tjo@iu.edu\"><i><span style=\"font-weight: 400;\">tjo@iu.edu<\/span><\/i><\/a><i><span style=\"font-weight: 400;\">)<\/span><\/i><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/vishnubashyam\/DeepBrainNet\">DeepBrainNet<\/a><\/span>\u00a0(PI: Davatzikos)<ul><li>Brain age prediction on T1 brain scans, Convolutional Neural Network trained on (n=11,729) MRI Input: Skull stripped T1 brain images, registered to a common space, in NITFI Output: Predicted brain age<\/li><li><em>Contact: Vishnu Bashyam (Vishnu.Bashyam@pennmedicine.upenn.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/sites.pitt.edu\/~liz119\/contents\/CommPOOL\/CommPool_model.zip\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">CommPool<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Zhan, Huang)<\/span><\/li><li style=\"list-style-type: none;\"><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Using brain network data as the input and hierarchically learn the representation from the entire brain graph. The learned latent space features can be used for clinical classification or predictions.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Haoteng Tang (haoteng.tang@pitt.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/yaz91\/dataIntegration\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">DisentangledVGAE<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Huang, Thompson, Zhan)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">A new multi-view graph auto-encoder method to learn the disentangled representation from different brain data modalities (the inputs can be imaigng featuers, brain networks, genetics features) to help various downstream analysis (outcome or cognitive decline predictions).<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Yanfu Zhang(yaz91@pitt.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/CuriiHQ\/AI4AD\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">GLM Tiled Data Example<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Zaranek)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Example for running a GLM on Tiled Data.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Sarah Zaranek (ai4ad@support.curii.com)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/arvados\/lightning\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">Lightning<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Zaranek)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Lightning is the system that performs tiling. Genomes are split into small segments (tiles), on average roughly 250 bp long. All unique tile variants are collected into a tile library, where a genome can be stored by using position references into the lightning tile library.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Tom Clegg (ai4ad@support.curii.com)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/arvados\/l7g-ml\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">ML with Tiled Data<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Zaranek)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">This shows examples as well as source code for ML with Tiled Data. Also includes imputation workflow for imputing gvcfs before tiling<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Sarah Zaranek (ai4ad@support.curii.com)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/lshen\/adomics\"><span style=\"font-weight: 400;\">adomics<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Shen)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Mendelian randomization (MR) is a versatile tool to identify the possible causal relationship between an omics biomarker and disease outcome using genetic variants as instrumental variables. This work provides a framework for summary data based MR analysis where multiple omics biomarkers can be viewed as multiple exposures, with an emphasis on the combination tests and special handling due to correlated P-values from single-exposure MR tests.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Chong Jin (Chong.Jin@Pennmedicine.upenn.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/github.com\/mansooru\/MTS2CCA\"><span style=\"font-weight: 400;\"><span style=\"text-decoration: underline;\">MTS2CCA<\/span><\/span><\/a><span style=\"font-weight: 400;\"> (PI: Shen)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">MTS2CCA is a novel imaging genomics association algorithm to deliver interpretable results and improve integration of imaging and genomics dataset. This work revealed promising features of single-nucleotide polymorphisms and brain regions related to sleep. The identified features can be used to improve clinical score prediction using promising imaging genetic biomarkers.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Mansu Kim (mansu.kim@catholic.ac.kr)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/JaesikKim\/temporal-GNN\"><span style=\"font-weight: 400;\">temporal-GNN<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Shen)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Temporal-GNN is an interpretable graph neural network (GNN) model for AD prognostic prediction based on longitudinal neuroimaging data while embracing the valuable knowledge of structural brain connectivity<\/span><\/li><li><i><span style=\"font-weight: 400;\">Contact: Mansu Kim (<\/span><\/i><a href=\"mailto:mansu.kim@catholic.ac.kr\"><i><span style=\"font-weight: 400;\">mansu.kim@catholic.ac.kr<\/span><\/i><\/a><i><span style=\"font-weight: 400;\">)<\/span><\/i><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/cumc\/xqtl-pipeline\"><span style=\"font-weight: 400;\">xQTL-protocol<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Wang)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">A reproducible molecular QTL analysis for the NIH\/NIA Alzheimer\u2019s Disease Sequencing Project Functional Genomics Consortium.<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Gao Wang (wang.gao@columbia.edu)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/USC-IGC\/style_transfer_harmonization\"><span style=\"font-weight: 400;\">Style Transfer Harmonization<\/span><\/a><\/span><span style=\"font-weight: 400;\"> (PI: Jahanshad)<\/span><ul><li style=\"font-weight: 400;\" aria-level=\"2\"><span style=\"font-weight: 400;\">Harmonizes T1w images to a reference by attempting to match the \u201cstyle\u201d of the reference without altering anatomical features<\/span><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><i><span style=\"font-weight: 400;\">Contact: Mengting Liu (liumt55@mail.sysu.edu.cn)<\/span><\/i><\/li><\/ul><\/li><li style=\"font-weight: 400;\" aria-level=\"2\"><a href=\"https:\/\/github.com\/zhijian-yang\/SmileGAN\"><span style=\"text-decoration: underline;\">Smile-GAN<\/span><\/a> (PI: Davatzikos)<ul><li>Deep semi-supervised clustering method designed to identify disease-related neuroanatomical heterogeneity. Inputs: CSV\/TSV files containing image ROI as features, as well as covariates to be adjusted. Output: categorical clustering membership and continuous probability scores<\/li><li><em>Contact: Zhijian Yang (Zhijian.Yang@Pennmedicine.upenn.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/zhijian-yang\/SurrealGAN\"><span style=\"text-decoration: underline;\">Surreal-GAN<\/span><\/a> (PI: Davatzikos)<ul><li>Deep semi-supervised representation learning method designed to dissect disease-related neuroanatomical heterogeneity. Inputs: CSV\/TSV files containing image ROI as features, as well as covariates to be adjusted. Output: continuous dimensional scores<\/li><li><em>Contact: Zhijian Yang (Zhijian.Yang@Pennmedicine.upenn.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/anbai106\/SOPNMF\"><span style=\"text-decoration: underline;\">SOPNMF<\/span><\/a> (PI: Davatzikos)<ul><li>Using unsupervised factorization method to parcellate the brain into patterns of strucutral covariance (PSC) and correlated these PSCs to common genetic variant to depict the genetic architecture of the human brain. Input: CSV\/TSV containing the path to each MRI. Output: the parcellated PSCs and the loading coefficient, the ROI values.<\/li><li><em>Contact: Junhao Wen (junhao.wen@pennmedicine.upenn.edu)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/cind\/Longitudinal-Disease-Progression-Modeling\">Longitudinal Disease Progression Modeling<\/a><\/span> (PI: Toosun)<ul><li>The trajectory of a given AD biomarker may take decades, however we are usually limited to much shorter follow up data in ADNI and other AD focused studies. This can impose a challenge when estimating the full course of AD disease progression. Extending the methodology described in Budgeon et. al, we can estimate a full-term disease pathology curve from short term follow up data for multivariate imaging marker data.<\/li><li><em>Contact: Tamar Schaap (tamar.schaap@ucsf.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/cind\/Simulated_Clinical_Trials\"><span style=\"text-decoration: underline;\">Clinical Trial Simulation<\/span><\/a> (PI: Tosun)<ul><li>Clinical Trial Simulation allows a user to estimate the statistical power of a pre-defined treatment effect at a set of sample sizes. This may be useful in informing recruitment of future clinical trials enriched based on different biomarker signature criteria. Using a Linear-Mixed-Effects Model (LME) trained on pilot data, a user can estimate the power of a treatment effect at a sample size via Monte Carlo Simulation.<\/li><li><em>Contact: Tamar Schaap (tamar.schaap@ucsf.edu)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/Alii-Ganjj\/GenoPhenoMutualLearning\">MultimodalGAN<\/a><\/span> (PI: Huang)<ul><li>GAN model and knowledge distillation based machine learning algorithm to integrate multimodal genotype and phenotype data and especially deal with missing data modality in prediction, also can predict the longitudinal outcomes<\/li><li><em>Contact: Alireza Ganjdanesh (alireza.ganjdanesh@pitt.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/taehojo\/SWAT-CNN\/\"><span style=\"text-decoration: underline;\">SWAT-CNN<\/span><\/a> (PI: Saykin)<ul><li>A novel three-step approach for identification of genetic variants using deep learning to identify phenotype-related SNPs that can be applied to develop accurate disease classification models.<\/li><li><em>Contact: Taeho Jo (tjo@iu.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/sites.pitt.edu\/~liz119\/contents\/CommPOOL\/CommPool_model.zip\"><span style=\"text-decoration: underline;\">CommPool<\/span><\/a> (PI: Zhan, Huang)<ul><li>Using brain network data as the input and hierarchically learn the representation from the entire brain graph. The learned latent space features can be used for clinical classification or predictions.<\/li><li><em>Contact: Haoteng Tang (haoteng.tang@pitt.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/yaz91\/dataIntegration\"><span style=\"text-decoration: underline;\">DisentangledVGAE<\/span><\/a> (PI: Huang, Thompson, Zhan)<ul><li>A new multi-view graph auto-encoder method to learn the disentangled representation from different brain data modalities (the inputs can be imaigng featuers, brain networks, genetics features) to help various downstream analysis (outcome or cognitive decline predictions).<\/li><li><em>Contact: Yanfu Zhang(yaz91@pitt.edu)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/CuriiHQ\/AI4AD\"><span style=\"text-decoration: underline;\">GLM Tiled Data Example<\/span><\/a> (PI: Zaranek)<ul><li>Example for running a GLM on Tiled Data.<\/li><li><em>Contact: Sarah Zaranek (ai4ad@support.curii.com)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/arvados\/lightning\"><span style=\"text-decoration: underline;\">Lightning<\/span><\/a> (PI: Zaranek)<ul><li>Lightning is the system that performs tiling. Genomes are split into small segments (tiles), on average roughly 250 bp long. All unique tile variants are collected into a tile library, where a genome can be stored by using position references into the lightning tile library.<\/li><li><em>Contact: Tom Clegg (ai4ad@support.curii.com)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/arvados\/l7g-ml\">ML with Tiled Data<\/a><\/span> (PI: Zaranek)<ul><li>This shows examples as well as source code for ML with Tiled Data. Also includes imputation workflow for imputing gvcfs before tiling<\/li><li><em>Contact: Sarah Zaranek (ai4ad@support.curii.com)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/lshen\/adomics\">adomics<\/a><\/span> (PI: Shen)<ul><li>Mendelian randomization (MR) is a versatile tool to identify the possible causal relationship between an omics biomarker and disease outcome using genetic variants as instrumental variables. This work provides a framework for summary data based MR analysis where multiple omics biomarkers can be viewed as multiple exposures, with an emphasis on the combination tests and special handling due to correlated P-values from single-exposure MR tests.<\/li><li><em>Contact: Chong Jin (Chong.Jin@Pennmedicine.upenn.edu)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/mansooru\/MTS2CCA\">MTS2CCA<\/a><\/span> (PI: Shen)<ul><li>MTS2CCA is a novel imaging genomics association algorithm to deliver interpretable results and improve integration of imaging and genomics dataset. This work revealed promising features of single-nucleotide polymorphisms and brain regions related to sleep. The identified features can be used to improve clinical score prediction using promising imaging genetic biomarkers.<\/li><li><em>Contact: Mansu Kim (mansu.kim@catholic.ac.kr)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/JaesikKim\/temporal-GNN\">temporal-GNN<\/a><\/span> (PI: Shen)<ul><li>Temporal-GNN is an interpretable graph neural network (GNN) model for AD prognostic prediction based on longitudinal neuroimaging data while embracing the valuable knowledge of structural brain connectivity<\/li><li><em>Contact: Mansu Kim (mansu.kim@catholic.ac.kr)<\/em><\/li><\/ul><\/li><li><a href=\"https:\/\/github.com\/cumc\/xqtl-pipeline\"><span style=\"text-decoration: underline;\">xQTL-protocol<\/span><\/a> (PI: Wang)<ul><li>A reproducible molecular QTL analysis for the NIH\/NIA Alzheimer&#8217;s Disease Sequencing Project Functional Genomics Consortium.<\/li><li><em>Contact: Gao Wang (wang.gao@columbia.edu)<\/em><\/li><\/ul><\/li><li><span style=\"text-decoration: underline;\"><a href=\"https:\/\/github.com\/USC-IGC\/style_transfer_harmonization\">Style Transfer Harmonization<\/a><\/span> (PI: Jahanshad)<ul><li>Harmonizes T1w images to a reference by attempting to match the &#8220;style&#8221; of the reference without altering anatomical features<\/li><li><em>Contact: Mengting Liu (liumt55@mail.sysu.edu.cn)<\/em><\/li><\/ul><\/li><\/ul>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-497b850 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"497b850\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-a0fa2af\" data-id=\"a0fa2af\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-58d81d4 elementor-widget elementor-widget-spacer\" data-id=\"58d81d4\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-43c55d0 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"43c55d0\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-353bde5\" data-id=\"353bde5\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-28d130a elementor-widget elementor-widget-heading\" data-id=\"28d130a\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Datasets<\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-1c50193 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"1c50193\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-7b67242\" data-id=\"7b67242\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-854ebc0 elementor-widget elementor-widget-text-editor\" data-id=\"854ebc0\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<ul><li>ADNI, WHICAP (PI: Davatzikos)<ul><li>Types of Processing: MUlti-atlas region Segmentation(MUSE), Deep-learning based intracranial volume (DLICV), harmonization, SPARE scores; visualize segemntation results, scripts to calculate z scores and rank and check extreme cases, plot ROI trend to detect possible outliers<\/li><li>Measures: Harmonized MUSE ROI volumes, Harmonized RAVENS voxel-based maps, DLICV, Canonical SPARE-AD and SPARE-BA, Disentangled SPARE-AD and SPARE-BA, Smile-GAN MCI\/AD patterns<\/li><\/ul><\/li><li>ADNI, ADSP, WHICAP (PI: Zaranek)<ul><li>Types of Processing: Tiled data (filtered by QC&gt;20) , Annotation of Tile variants, GLM on Tiled data<\/li><li>Measures: Filtered tile data, tile data annotations, top features of GLM from tiled data<\/li><\/ul><\/li><\/ul>\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-32dbb65 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"32dbb65\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-237d1f2\" data-id=\"237d1f2\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-53a8f21 elementor-widget elementor-widget-spacer\" data-id=\"53a8f21\" data-element_type=\"widget\" data-widget_type=\"spacer.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<div class=\"elementor-spacer\">\n\t\t\t<div class=\"elementor-spacer-inner\"><\/div>\n\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Software &amp;Data Software DeepBrainNet (PI: Davatzikos) Brain age prediction on T1 brain scans, Convolutional Neural Network trained on (n=11,729) MRI Input: Skull stripped T1 brain images, registered to a common space, in NITFI Output: Predicted brain age Contact: Vishnu Bashyam (Vishnu.Bashyam@pennmedicine.upenn.edu) Smile-GAN (PI: Davatzikos) Deep semi-supervised clustering method designed to identify disease-related neuroanatomical heterogeneity. Inputs: &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"https:\/\/ai4ad.org\/index.php\/software\/\"> <span class=\"screen-reader-text\">Software<\/span> Read More &raquo;<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"om_disable_all_campaigns":false,"_mi_skip_tracking":false,"footnotes":""},"class_list":["post-851","page","type-page","status-publish","hentry"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/pages\/851"}],"collection":[{"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/comments?post=851"}],"version-history":[{"count":14,"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/pages\/851\/revisions"}],"predecessor-version":[{"id":882,"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/pages\/851\/revisions\/882"}],"wp:attachment":[{"href":"https:\/\/ai4ad.org\/index.php\/wp-json\/wp\/v2\/media?parent=851"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}