About

Portrait of Dileep Kishore

I’m a computational biologist in the Environmental Genomics and Systems Biology division at Lawrence Berkeley National Laboratory. I build data infrastructure and AI tooling for biological research, and I work on microbial ecology, mostly on what plant-associated microbes do and how they interact.

Most of my recent work is on agentic systems for science. That means natural language interfaces to scientific databases, multi-agent orchestration with LangChain and LangGraph, Model Context Protocol integrations that let a language model query a data lakehouse directly, and retrieval over domain literature and datasets. Under all of it is the lakehouse, where I work on schema design, data modelling and the ETL pipelines. It holds genomic and phenotypic data for hundreds of poplar genotypes, and feeds a foundation model for photosynthesis.

The microbial work is where I started, and it still runs alongside. I build machine learning pipelines that predict traits like carbon utilization from genomic features, across a thousand-odd bacterial genomes. The FastAPI services and the Nextflow and Snakemake workflows around them exist so the results are usable by people who did not build them. My Ph.D. was in bioinformatics, on inferring microbial interaction networks.

Nearly everything here is collaborative, with experimental biologists and domain scientists at Lawrence Berkeley and Oak Ridge. I contributed to these projects, I don’t run them.

Experience

Where I’ve worked.

  • Aug 2026–Present

  • Mar–Aug 2026

    Computational Biologist

    Oak Ridge National Laboratory

  • Mar 2023–Mar 2026

    Postdoctoral Research Associate

    Oak Ridge National Laboratory

  • Jan–Mar 2023

    Postdoctoral Fellow

    Boston University

Education

  • Jun 2016–Dec 2022

    Ph.D. in Bioinformatics

    Boston University, USA

    GPA 4.00/4.00 · Advisor: Dr. Daniel Segrè

  • Sep 2011–May 2016

    B.Tech (Honors) & M.Tech (Dual Degree) in Biotechnology

    Indian Institute of Technology Madras, India

    GPA 9.23/10.00 · Advisor: Dr. Karthik Raman

Publications & talks

Peer-reviewed

  • Kishore, Dileep; Birzu, Gabriel; Hu, Zhenjun; DeLisi, Charles; Korolev, Kirill S; Segrè, Daniel; . Inferring microbial co-occurrence networks from amplicon data: a systematic evaluation. mSystems. 2023.
  • Pacheco, Alan R; Pauvert, Charlie; Kishore, Dileep; Segrè, Daniel; . Toward FAIR Representations of Microbial Interactions. mSystems. 2022.
  • Federico, Anthony; Karagiannis, Tanya; Karri, Kritika; Kishore, Dileep; Koga, Yusuke; Campbell, Joshua D; Monti, Stefano; . Pipeliner: A Nextflow-Based Framework for the Definition of Sequencing Data Processing Pipelines. Frontiers in Genetics. 2019.

Preprints

  • Hu, Zhenjun; Kishore, Dileep; Wang, Yan; Birzu, Gabriel; DeLisi, Charles; Korolev, Kirill S; Segrè, Daniel; . A resource for the comparison and integration of heterogeneous microbiome networks. BioRxiv. 2022 (2022.08.07.503059).
  • Kishore, Dileep; Chandrasekaran, Srikiran; . Introducing and benchmarking the accuracy of cayenne: A Python package for stochastic simulations. BioRxiv. 2020 (2020.10.10.334623).

In preparation

  • Kishore, D.; Ranjan, P.; Neely, C.; Cashman, M.; Riehl, W.; Joachimiak, M. P.; Edirisinghe, J. N.; Faria, J. P.; Cohen, M. B.; Sakhaff, Z.; Weisenhorn, P.; Pelletier, D. A.; Doktycz, M. J.; Cottingham, R. W.; Henry, C. S.; Arkin, A. P.; Dehal, P. S.. Beyond canonical pathways: Diagnosing confounders and generalizing genotype-to-phenotype models across bacterial growth collections.
  • Freiburger, A. P.*; Kishore, D.*; Pelletier, D.; Doktycz, M.; Henry, C.; Ranjan, P.. Succinct metrics of microbial metabolism to predict community interactions.
  • Meena, M. G.; Kishore, D.; Asthagiri, D.; Doktycz, M. J.. Exploring the use of quantum-based computing for facilitating spatially and temporally resolved models of a whole cell.

* Co-first author

Selected talks & posters

  • An AI-Ready Data Lakehouse for Genomic Photosynthesis: Enabling Foundational Models for Bioenergy Crop Engineering

    Poster · PAG 33 (Plant and Animal Genome), 2025

  • Modeling and Predicting Plant-Associated Microbial Interactions in KBase: From Genomes to Community-Level Phenotypes

    Workshop talk · PAG 33 (Plant and Animal Genome), 2025

  • Beyond canonical pathways: Diagnosing confounders and generalizing genotype-to-phenotype models across bacterial growth collections

    Talk · Oak Ridge Postdoctoral Association Symposium, 2025

  • Improving the Prediction and Interpretability of Microbial Nutrient Utilization Phenotypes

    Poster · DOE BSSD Genomic Science Program, 2025

  • Leveraging Machine Learning for Enhanced Prediction of Microbial Carbon Utilization Phenotypes

    Talk and poster · DOE BSSD Genomic Science Program, 2024

  • From Genotypes to Ecosystems: Unraveling Microbial Interactions through Machine Learning to Engineer Stable Synthetic Communities

    Talk · PAG 31 (Plant and Animal Genome), 2024

  • From Genotypes to Ecosystems: Unraveling Microbial Interactions through Machine Learning to Engineer Stable Synthetic Communities

    Talk · ICME 2023 (International Conference on Microbiome Engineering)