Research

Diseases are caused by a complex interplay between different factors, such as genetics and the environment. A deeper understanding of the genetic risk factors of complex diseases can enable the development of more personalized treatments and prevention strategies.

Our research is focused on developing novel machine-learning methods to advance key computational aspects of precision medicine. We have a particular focus on the integration of genetic studies with relevant molecular patterns extracted from multi-omics data. For this, we aim to develop the next generation of methodologies that will consolidate large and heterogeneous sources of biomedical information to extract biological insight to ultimately improve human health.

Strongly committed to open source and open science, we use GitHub for the development of reproducible workflows and Manubot for the transparent authoring of modern and collaborative scholarly manuscripts.

Integration of genetic studies with gene co-expression patterns

Projecting genetic associations through gene expression patterns highlights disease etiology and drug mechanisms

Milton Pividori, Sumei Lu, Binglan Li, Chun Su, Matthew E. Johnson, …, Benjamin F. Voight, Carsten Skarke, Marylyn D. Ritchie, Struan F. A. Grant, Casey S. Greene

Nature Communications  ·  09 Sep 2023  ·  doi:10.1038/s41467-023-41057-4

Here we introduce the PhenoPLIER framework, an omnigenic approach that integrates genetic studies (GWAS/TWAS) with gene modules learned from expression data. PhenoPLIER provides 1) a regression framework that computes an association between gene modules and diseases, 2) a clustering approach that finds groups of diseases with shared transcriptomic properties, and 3) a gene module-based drug-repurposing method.

Manubot

Manuscript source

Extracting complex transcriptional signatures using not-only-linear correlation coefficients

An efficient, not-only-linear correlation coefficient based on clustering

Milton Pividori, Marylyn D. Ritchie, Diego H. Milone, Casey S. Greene

Cell Systems  ·  01 Sep 2024  ·  doi:10.1016/j.cels.2024.08.005

This article introduces the Clustermatch Correlation Coefficient (CCC), an efficient, easy-to-use and not-only-linear coefficient based on machine learning models. CCC can detect biologically meaningful linear and nonlinear patterns missed by standard, linear-only correlation coefficients.

Manubot

Manuscript source

Automatic revision of scholarly text using AI and large language models

A publishing infrastructure for Artificial Intelligence (AI)-assisted academic authoring

Milton Pividori, Casey S Greene

Journal of the American Medical Informatics Association  ·  14 Jun 2024  ·  doi:10.1093/jamia/ocae139

We developed the Manubot AI Editor, a plugin to the Manubot publishing infrastructure that uses manuscript section-specific prompts and OpenAI’s models to automatically revise and improve the text.

Manubot

Manuscript source

All

2024

An efficient, not-only-linear correlation coefficient based on clustering

Milton Pividori, Marylyn D. Ritchie, Diego H. Milone, Casey S. Greene

Cell Systems  ·  01 Sep 2024  ·  doi:10.1016/j.cels.2024.08.005

This article introduces the Clustermatch Correlation Coefficient (CCC), an efficient, easy-to-use and not-only-linear coefficient based on machine learning models. CCC can detect biologically meaningful linear and nonlinear patterns missed by standard, linear-only correlation coefficients.

Manubot

Manuscript source

Chatbots in science: What can ChatGPT do for you?

Milton Pividori

Nature  ·  14 Aug 2024  ·  doi:10.1038/d41586-024-02630-z

A publishing infrastructure for Artificial Intelligence (AI)-assisted academic authoring

Milton Pividori, Casey S Greene

Journal of the American Medical Informatics Association  ·  14 Jun 2024  ·  doi:10.1093/jamia/ocae139

We developed the Manubot AI Editor, a plugin to the Manubot publishing infrastructure that uses manuscript section-specific prompts and OpenAI’s models to automatically revise and improve the text.

Manubot

Manuscript source

2023

Projecting genetic associations through gene expression patterns highlights disease etiology and drug mechanisms

Milton Pividori, Sumei Lu, Binglan Li, Chun Su, Matthew E. Johnson, …, Benjamin F. Voight, Carsten Skarke, Marylyn D. Ritchie, Struan F. A. Grant, Casey S. Greene

Nature Communications  ·  09 Sep 2023  ·  doi:10.1038/s41467-023-41057-4

Here we introduce the PhenoPLIER framework, an omnigenic approach that integrates genetic studies (GWAS/TWAS) with gene modules learned from expression data. PhenoPLIER provides 1) a regression framework that computes an association between gene modules and diseases, 2) a clustering approach that finds groups of diseases with shared transcriptomic properties, and 3) a gene module-based drug-repurposing method.

Manubot

Manuscript source

The high-dimensional space of human diseases built from diagnosis records and mapped to genetic loci

Gengjie Jia, Yu Li, Xue Zhong, Kanix Wang, Milton Pividori, …, Michiaki Kubo, Nancy J. Cox, James Evans, Xin Gao, Andrey Rzhetsky

Nature Computational Science  ·  22 May 2023  ·  doi:10.1038/s43588-023-00453-y

2022

Discerning asthma endotypes through comorbidity mapping

Gengjie Jia, Xue Zhong, Hae Kyung Im, Nathan Schoettler, Milton Pividori, …, Michiaki Kubo, Nancy J. Cox, Carole Ober, Andrey Rzhetsky, Julian Solway

Nature Communications  ·  07 Nov 2022  ·  doi:10.1038/s41467-022-33628-8

2021

Exploiting the GTEx resources to decipher the mechanisms at GWAS loci

Alvaro N. Barbeira, Rodrigo Bonazzola, Eric R. Gamazon, Yanyu Liang, YoSon Park, …, Ayellet V. Segrè, Christopher D. Brown, Tuuli Lappalainen, Xiaoquan Wen, Hae Kyung Im

Genome Biology  ·  26 Jan 2021  ·  doi:10.1186/s13059-020-02252-4

Probabilistic colocalization of genetic variants from complex and molecular traits: promise and limitations

Abhay Hukku, Milton Pividori, Francesca Luca, Roger Pique-Regi, Hae Kyung Im, Xiaoquan Wen

The American Journal of Human Genetics  ·  01 Jan 2021  ·  doi:10.1016/j.ajhg.2020.11.012

2020

Polygenic transcriptome risk scores improve portability of polygenic risk scores across ancestries

Yanyu Liang, Milton Pividori, Ani Manichaikul, Abraham A. Palmer, Nancy J. Cox, Heather Wheeler, Hae Kyung Im

Cold Spring Harbor Laboratory  ·  13 Nov 2020  ·  doi:10.1101/2020.11.12.373647

PhenomeXcan: Mapping the genome to the phenome through the transcriptome

Milton Pividori, Padma S. Rajagopal, Alvaro Barbeira, Yanyu Liang, Owen Melia, Lisa Bastarache, YoSon Park, GTEx Consortium, Xiaoquan Wen, Hae K. Im

Science Advances  ·  11 Sep 2020  ·  doi:10.1126/sciadv.aba2083

DL4papers: a deep learning approach for the automatic interpretation of scientific articles

L A Bugnon, C Yones, J Raad, M Gerard, M Rubiolo, G Merino, M Pividori, L Di Persia, D H Milone, G Stegmayer

Bioinformatics  ·  24 Feb 2020  ·  doi:10.1093/bioinformatics/btaa111

2019

Predicting novel microRNA: a comprehensive comparison of machine learning approaches.

Georgina Stegmayer, Leandro E Di Persia, Mariano Rubiolo, Matias Gerard, Milton Pividori, Cristian Yones, Leandro A Bugnon, Tadeo Rodriguez, Jonathan Raad, Diego H Milone

Briefings in bioinformatics  ·  27 Sep 2019  ·  pmid:29800232

Shared and distinct genetic risk factors for childhood-onset and adult-onset asthma: genome-wide and transcriptome-wide studies

Milton Pividori, Nathan Schoettler, Dan L Nicolae, Carole Ober, Hae Kyung Im

The Lancet Respiratory Medicine  ·  01 Jun 2019  ·  doi:10.1016/S2213-2600(19)30055-4

Integrating predicted transcriptome from multiple tissues improves association detection

Alvaro N. Barbeira, Milton Pividori, Jiamao Zheng, Heather E. Wheeler, Dan L. Nicolae, Hae Kyung Im

PLOS Genetics  ·  22 Jan 2019  ·  doi:10.1371/journal.pgen.1007889

2018

ukbREST: efficient and streamlined data access for reproducible research in large biobanks

Milton Pividori, Hae Kyung Im

Bioinformatics  ·  05 Nov 2018  ·  doi:10.1093/bioinformatics/bty925

Clustermatch: discovering hidden relations in highly diverse kinds of qualitative and quantitative data without standardization

Milton Pividori, Andres Cernadas, Luis A de Haro, Fernando Carrari, Georgina Stegmayer, Diego H Milone

Bioinformatics  ·  24 Oct 2018  ·  doi:10.1093/bioinformatics/bty899

2016

Diversity control for improving the analysis of consensus clustering

Milton Pividori, Georgina Stegmayer, Diego H. Milone

Information Sciences  ·  01 Sep 2016  ·  doi:10.1016/j.ins.2016.04.027

2015

A very simple and fast way to access and validate algorithms in reproducible research

Georgina Stegmayer, Milton Pividori, Diego H. Milone

Briefings in Bioinformatics  ·  28 Jul 2015  ·  doi:10.1093/bib/bbv054

2010

How to Develop Intelligent Agents in an Easy Way with FAIA

Jorge Roa, Milton Pividori, Ma. De los Milagros Gutiérrez, Georgina Stegmayer

Quality and Communicability for Interactive Hypermedia Systems  ·  01 Jan 2010  ·  doi:10.4018/978-1-61520-763-3.ch006

FAIA: Un framework para el desarrollo de agentes inteligentes

EdUTecNe  ·  01 Jan 2010  ·  isbn:978-987-25855-9-4