Gerber Lab’s “MDITRE: Scalable and Interpretable Machine Learning for Predicting Host Status from Temporal Microbiome Dynamics” is mSystems Editor’s Pick

Gerber Lab’s “MDITRE: Scalable and Interpretable Machine Learning for Predicting Host Status from Temporal Microbiome Dynamics” is mSystems Editor’s Pick

Longitudinal microbiome data sets are being generated with increasing regularity, and there is broad recognition that these studies are critical for unlocking the mechanisms through which the microbiome impacts human health and disease. However, there is a dearth of computational tools for analyzing microbiome time-series data. To address this gap, we developed an open-source software package, Microbiome Differentiable Interpretable Temporal Rule Engine (MDITRE), which implements a new highly efficient method leveraging deep-learning technologies to derive human-interpretable rules that predict host status from longitudinal microbiome data. Using semi-synthetic and a large compendium of publicly available 16S rRNA amplicon and metagenomics sequencing data sets, we demonstrate that in almost all cases, MDITRE performs on par with or better than popular uninterpretable machine learning methods, and orders-of-magnitude faster than the prior interpretable technique. MDITRE also provides a graphical user interface, which we show through case studies can be used to derive biologically meaningful interpretations linking patterns of microbiome changes over time with host phenotypes. 

Mahmood Lab’s Pan-cancer integrative histology-genomic analysis is featured on cover of Cancer Cell

Mahmood Lab’s Pan-cancer integrative histology-genomic analysis is featured on cover of Cancer Cell

The rapidly emerging field of computational pathology has demonstrated promise in developing objective prognostic models from histology images. However, most prognostic models are either based on histology or genomics alone and do not address how these data sources can be integrated to develop joint image-omic prognostic models. Additionally, identifying explainable morphological and molecular descriptors from these models that govern such prognosis is of interest. We use multimodal deep learning to jointly examine pathology whole-slide images and molecular profile data from 14 cancer types. Our weakly supervised, multimodal deep-learning algorithm is able to fuse these heterogeneous modalities to predict outcomes and discover prognostic features that correlate with poor and favorable outcomes. We present all analyses for morphological and molecular correlates of patient prognosis across the 14 cancer types at both a disease and a patient level in an interactive open-access database to allow for further exploration, biomarker discovery, and feature assessment.

Chen RJ, Lu MY, Williamson DFK, Chen TY, Lipkova J, Noor Z, Shaban M, Shady M, Williams M, Joo B, Mahmood F. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell. 2022 Aug 8;40(8):865-878.e6. doi: 10.1016/j.ccell.2022.07.004. PMID: 35944502.

Graduate Students, Gerber Lab

I am always excited to work with talented graduate students with interests relevant to my lab, which focuses on developing novel machine learning/computational biology/wet lab approaches to further understanding of the microbiome–the trillions of microbes living on and within us. This fascinating, complex and dynamic ecosystem is crucial for human health, and when disrupted may contribute to a variety of diseases including infections, arthritis, allergies, cancer, heart and bowel disorders.

In general, I can only be a primary advisor (and provide financial support) for students enrolled at Harvard or MIT. However, I am open to co-advising students at other institutions.

If you’re interested, email me at ggerber#bwh.harvard.edu. Please include your CV and a brief description of your research interests.

Students should have a high level of interest in:

  • Developing and applying new technologies to biomedical problems.
  • Advancing knowledge of the microbiome and its role in human health and disease.
  • Having your work make an impact on healthcare outcomes.
  • Working on an interdisciplinary team and collaborating with computational, wet lab and clinical scientists.

About the lab: the Gerber Lab develops novel statistical machine learning models and high-throughput experimental systems to understand the role of the microbiota in human diseases, and applies these findings to develop new diagnostic tests and therapies. A particular focus of the Gerber Lab is understanding dynamic behaviors of host-microbial ecosystems. Our work in this area includes Bayesian statistical machine learning methods for discovering temporal patterns in microbiome data, inferring dynamical systems models from microbiome time-series data, or predicting host status from microbiome time-series data with human interpretable rules. We have applied these methods to a number of clinically relevant questions including understanding dynamic effects of antibiotics, infections and dietary changes on the microbiome, and designing bacteriotherapies for C. difficile infection and food allergy. We also apply our methods to synthetic biology problems, to engineer consortia of bacteria for diagnostic and therapeutic purposes.

Environment:  the Gerber Lab is located in the Division of Computational Pathology, which Dr. Gerber heads, at Brigham and Women’s Hospital (BWH) at Harvard Medical School (HMS), and the Massachusetts Host-Microbiome Center, which Dr. Gerber co-directs. BWH, an HMS affiliated teaching hospital is adjacent to the HMS main quad and is the second largest non-university recipient of NIH research funding. The broad mandate of the BWH Division of Computational Pathology is to develop and apply advanced computational methods for furthering the understanding, diagnosis and treatment of human diseases. The Division is situated within the BWH Department of Pathology, which houses over 40+ established investigators, 50+ postdoctoral research fellows, and 100+ research support staff. In addition, BWH is part of the greater Longwood Medical Area in Boston, a rich, stimulating environment conducive to intellectual development and research collaborations, which includes HMS, Harvard School of Public Health, Boston Children’s Hospital and the Dana Farber Cancer Institute.

Postdoctoral Fellow, Deep Learning for Microbiome, Gerber Lab

Post-doctoral positions available (with flexible start dates) to develop novel deep learning approaches to further understanding of the microbiome–the trillions of microbes living on and within us. This fascinating, complex and dynamic ecosystem is crucial for human health, and when disrupted may contribute to a variety of diseases including infections, arthritis, allergies, cancer, heart and bowel disorders. Over the past decade, sequencing and other high-throughput methods have provided data about the microbiome at unprecedented scale.

We are looking for talented and highly motivated post-docs with strong mathematical backgrounds (computer science, computational biology, statistics, mathematics, ecology, physics, etc.) who want to develop and apply novel deep learning methods that will further understanding of the microbiome.  Applications include forecasting microbial population dynamics in the gut for rational design of therapies, predicting the impact of the microbiome on the onset or progression of human diseases, predicting interactions with the host immune system, elucidating host-microbial metabolic interactions, and discovering functions of uncharacterized microbial metabolites and proteins. From the machine learning perspective, areas of interest include:

  • Fully-differentiable interpretable probabilistic models based on relaxations and variational inference
  • Deep Bayesian, dynamical systems and other structured models
  • Neural topic models
  • Deep learning models using sequence information

The position could be a good fit for either someone with a strong machine learning background who wants to get domain-specific research experience, OR someone with a strong mathematical background who wants to get more machine learning experience.

Applicants should have a high level of interest in:

  • Applying new deep learning technologies to biomedical problems.
  • Advancing knowledge of the microbiome and its role in human health and disease.
  • Having your work make an impact on healthcare outcomes.
  • Working on an interdisciplinary team and collaborating with computational, wet lab and clinical scientists.

The candidate is expected to engage with the broader machine learning and computational biology communities by presenting work at top conferences, as well as publishing applications of new methods in high impact journals. Although some experience modeling biological or other complex systems is required, microbiome specific knowledge is not required.

About the lab: the Gerber Lab develops novel statistical machine learning models and high-throughput experimental systems to understand the role of the microbiota in human diseases, and applies these findings to develop new diagnostic tests and therapies. A particular focus of the Gerber Lab is understanding dynamic behaviors of host-microbial ecosystems. Our work in this area includes Bayesian statistical machine learning methods for discovering temporal patterns in microbiome data, inferring dynamical systems models from microbiome time-series data, or predicting host status from microbiome time-series data with human interpretable rules. We have applied these methods to a number of clinically relevant questions including understanding dynamic effects of antibiotics, infections and dietary changes on the microbiome, and designing bacteriotherapies for C. difficile infection and food allergy. We also apply our methods to synthetic biology problems, to engineer consortia of bacteria for diagnostic and therapeutic purposes.

Environment:  the Gerber Lab is located in the Division of Computational Pathology, which Dr. Gerber heads, at Brigham and Women’s Hospital (BWH) at Harvard Medical School (HMS), and the Massachusetts Host-Microbiome Center, which Dr. Gerber co-directs. BWH, an HMS affiliated teaching hospital is adjacent to the HMS main quad and is the second largest non-university recipient of NIH research funding. The broad mandate of the BWH Division of Computational Pathology is to develop and apply advanced computational methods for furthering the understanding, diagnosis and treatment of human diseases. The Division is situated within the BWH Department of Pathology, which houses over 40+ established investigators, 50+ postdoctoral research fellows, and 100+ research support staff. In addition, BWH is part of the greater Longwood Medical Area in Boston, a rich, stimulating environment conducive to intellectual development and research collaborations, which includes HMS, Harvard School of Public Health, Boston Children’s Hospital and the Dana Farber Cancer Institute.

Qualifications:

  • PhD in computer science, computational biology, ecology, mathematics, physics, statistics, or other quantitative discipline.
  • Excellent publication track record.
  • Strong mathematical background with track record developing novel models and methods.
  • Solid programming skills in Python, with PyTorch experience desirable.
  • Experience modeling biological or other complex systems required; microbiome experience desirable, but not required.
  • Superior communication skills and ability to work on multidisciplinary teams.

Email single PDF including cover letter, CV, unofficial transcripts, brief research statement and list of at least three references to Dr. Georg Gerber (ggerber@bwh.harvard.edu). In your CV, indicate whether you are a U.S. citizen/permanent resident or visa holder (and list visa type).

We are an equal opportunity employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, gender identity, sexual orientation, pregnancy and pregnancy-related conditions or any other characteristic protected by law.

Research Scientist, Machine Learning for Microbiome

The Microbiome AI/Deep Learning Lab in the Massachusetts Host-Microbiome Center and Division of Computational Pathology at Brigham and Women’s Hospital/Harvard Medical School is seeking a scientist with experience in machine learning.

You will develop, deploy, and apply machine learning approaches, with a special emphasis on deep learning, to a variety of microbiology data sources. Applications will include forecasting microbial population dynamics in the gut, predicting impact of the microbiome on host phenotype, tracking infections in human populations, elucidating microbial metabolism, and discovering functions of uncharacterized microbial metabolites and proteins. An important component of the position will also include engagement with the broader research community to identify new application areas.

Applicants should have a high level of interest in:

  • Applying new deep learning technologies to biomedical problems.
  • Advancing knowledge of the microbiome and its role in human health and disease.
  • Having your work make a direct impact on healthcare outcomes.
  • Working on an interdisciplinary team and collaborating with computational, wet lab and clinical scientists.
  • Engaging with the broader research community to advance applications of AI/deep learning for the microbiome.

About the environment: The Microbiome AI/Deep Learning Lab is a newly established initiative within the Massachusetts Host-Microbiome Center (MHMC) and the Division of Computational Pathology (DCP) at Brigham and Women’s Hospital (BWH)/Harvard Medical School (HMS). With recent funding from the Massachusetts Life Sciences Center, the Lab is building a state-of-the-art compute cluster with extensive GPU and CPU nodes, with the objective of making advanced deep learning technologies broadly available to microbiome researchers. The MHMC is a research and core facility that has worked with 100+ groups in the US and internationally to promote understanding of host-microbiome interactions in health and disease, emphasizing a focus on function to define causative effects of the microbiota and to harness this knowledge in developing new therapies, diagnostics and further commercial applications. The DCP is a research division with a broad mandate to develop and apply advanced computational methods for furthering the understanding, diagnosis and treatment of human diseases. BWH is an HMS affiliated teaching hospital, adjacent to the HMS main quad, and the second largest non-university recipient of NIH research funding.

Required Qualifications:

  • PhD in Computational Biology, Computer Science, Physics, Statistics, Quantitative Microbial Genetics, Quantitative Ecology, or related quantitative discipline, with demonstrated experience in machine learning.
  • Strong publication track record.
  • Programming experience in Python.
  • Experience with Unix, shell scripting, and high-performance computing environments (e.g., SLURM/LSF).
  • Experience with bioinformatics methods and pipelines for next generation sequencing data analysis.
  • Experience with organizing and managing large multi-omics datasets.
  • Strong written and oral communication skills.

Desired Qualifications:

  • Experience with PyTorch.
  • Experience with microbiology/microbiome applications and metabolic modeling tools.

Email single PDF including cover letter, CV, and list of at least three references to Dr. Georg Gerber (ggerber#bwh.harvard.edu). In your CV, indicate whether you are a U.S. citizen/permanent resident or visa holder (and list visa type).

We are an equal opportunity employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, gender identity, sexual orientation, pregnancy and pregnancy-related conditions or any other characteristic protected by law.

Computational Biology (ML4Bio) Postdoctoral Fellow – Gibson Lab

Opening for a Postdoctoral Research Fellow to join the Gibson Lab https://gibsonlab.io at Harvard Medical School and Brigham and Women’s Hospital. We leverage tools from machine learning and control theory to understand biological systems. Control theoretic concepts are integrated both in the design of our optimization schemes and statistical machine learning models, as well as in the design of our in vitro and in vivo experiments. Our main area of focus is the microbiome and microbial dynamics more specifically. Applications include the design of bacteriotherapies (bugs-as-drugs), developing methods to learn microbial dynamics at ecosystem-scale, studying the impact of phages on microbial communities, methods for tracking low abundance pathogens, and methods for integrating multiple data modalities and prior knowledge (from other studies or databases) in time-series models. We focus on Bayesian methods that propagate measurement uncertainty throughout the model so that we can access confidence in model parameters and to help prioritize follow-up experiments. ML techniques applied include variational inference, Bayesian non-parametric models, and relaxation techniques (for making discrete models differentiable).

The specific project(s) you will be working on will fall under one of the following grants. Follow the links below for more details:

The candidate will also be encouraged to design their own experiments as well, which would then be carried out by staff in the germ-free mouse facility or in a collaborating wet lab. In addition to addressing our biological questions we also include key experimental components that can aid in validating our methods that would otherwise not be included in a purely hypothesis driven experiment. For a candidate wanting some wet lab experience we are looking to develop new single-molecule enzyme-linked immunosorbent assays (digital ELISA) to measure low abundance host inflammatory markers in feces (please mention this explicitly in your cover letter if interested).

Qualifications

  • PhD in computer science, applied mathematics, ecology, computational biology, systems biology, statistics, or other quantitative discipline
  • Excellent publication track record
  • Strong mathematical background with track record developing novel models and methods
  • Solid programming skills in Python; this isn’t a software engineering job, but you will need to be able to develop efficient implementations and apply your work to real biomedical data
  • Ability to reside in the U.S. and legally work in the country.

About the lab environment

The Gibson Lab is located in the Division of Computational Pathology at Brigham and Women’s Hospital (BWH), a Harvard Medical School teaching hospital, which is the second largest non-university recipient of NIH research funding. The broad mandate of the Division of Computational Pathology is to develop and apply advanced computational methods for furthering the understanding, diagnosis, and treatment of human diseases. The Division is situated within the BWH Department of Pathology, which houses over 40+ established investigators, 50+ postdoctoral research fellows, and 100+ research support staff. In addition, BWH is part of the greater Longwood Medical Area in Boston, a rich, stimulating environment conducive to intellectual development and research collaborations, which includes the Harvard Medical School quad, Harvard School of Public Health, Boston Children’s Hospital, and the Dana Farber Cancer Institute. Many of our lab members also have appointments at the Massachusetts Institute of Technology and the Broad Institute.

Applications Process

Submit: (1) brief research statement (not to exceed 2 pages); (2) curriculum vitae; (3) two most relevant publications; (4) names and contact information of three individuals who can serve as references to: Travis Gibson, tegibson@bwh.harvard.edu. If you wish to chat briefly over Zoom before submitting materials to learn more details about our ongoing work, please inquire about this possibility.

We are an equal opportunity employer and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, gender identity, sexual orientation, pregnancy and pregnancy-related conditions or any other characteristic protected by law.

The Massachusetts Lab for Artificial Intelligence/Deep Learning for the Microbiome

The Massachusetts Lab for Artificial Intelligence/Deep Learning for the Microbiome

Through a $3.3M grant from the Massachusetts Life Science Center and in-kind support from Brigham and Women’s Hospital and Mass General Brigham, the BWH Massachusetts Host-Microbiome Center (MHMC) and Division of Computational Pathology will establish a new lab to develop and apply advanced AI/deep learning technologies to microbiome research. Dr. Georg Gerber, Chief of BWH Computational Pathology and co-director of the MHMC will head the new lab.

The microbiome is inherently complex and dynamic. Multi-omic data characterizing microbes in culture systems, animal models, and human populations can provide unique and complementary insights into these rich host-microbial ecosystems. However, to fully realize the potential of these data, sophisticated computational approaches are needed.

Artificial Intelligence (AI), and in particular Deep Learning (DL), are revolutionizing many fields, such as speech and image recognition. These technologies are also increasingly impacting the biomedical sciences.

The Lab aims to unleash the power of AI and DL technologies for the microbiome field.

Anchored by a dedicated large GPU with Tesla A100 nodes and CPU compute clusters, the Lab will develop custom AI/DL applications for the microbiome, deploy existing software in a managed and easy-to-use environment, and provide outreach and education to the microbiome community. The Lab will be staffed by principal investigators in the Division of Computational Pathology, as well as an application scientist and network engineers.

A joint initiative between the Brigham and Women’s Hospital (BWH) Division of Computational Pathology and the Massachusetts Host-Microbiome Center (MHMC), the Lab is funded by the Massachusetts Life Sciences Center and Brigham and Women’s Hospital/Mass General Brigham. Industry and academic users will be able to access the Lab through the MHMC’s existing core services model and through collaborations.

Gerber lab study showing gut metabolites predict C. diff recurrence

Gerber lab study showing gut metabolites predict C. diff recurrence

Clostridioides difficile infection (CDI) is the most common hospital acquired infection in the USA, with recurrence rates > 15%. Although primary CDI has been extensively linked to gut microbial dysbiosis, less is known about the factors that promote or mitigate recurrence. Using broad metabolomics data and statistics and machine learning models, Jen Dawkins, a HST PhD student and member of the Gerber lab, showed the metabolites in the gut can accurately predict C. difficile recurrence. These findings have implications for development of diagnostic tests and treatments that could ultimately short-circuit the cycle of CDI recurrence, by providing candidate metabolic biomarkers for diagnostics development, as well as offering insights into the complex microbial and metabolic alterations that are protective or permissive for recurrence.

Dawkins JJ, Allegretti JR, Gibson TE, McClure E, Delaney M, Bry L, Gerber GK. Gut metabolites predict Clostridioides difficile recurrence. Microbiome. 2022 Jun 9;10(1):87. doi: 10.1186/s40168-022-01284-1. PMID: 35681218; PMCID: PMC9178838.

Mahmood Lab’s deep learning-enabled assessment of cardiac transplant rejection study is published in Nature Medicine

Mahmood Lab’s deep learning-enabled assessment of cardiac transplant rejection study is published in Nature Medicine

Endomyocardial biopsy (EMB) screening represents the standard of care for detecting allograft rejections after heart transplant. Manual interpretation of EMBs is affected by substantial interobserver and intraobserver variability, which often leads to inappropriate treatment with immunosuppressive drugs, unnecessary follow-up biopsies and poor transplant outcomes. Here we present a deep learning-based artificial intelligence (AI) system for automated assessment of gigapixel whole-slide images obtained from EMBs, which simultaneously addresses detection, subtyping and grading of allograft rejection. To assess model performance, we curated a large dataset from the United States, as well as independent test cohorts from Turkey and Switzerland, which includes large-scale variability across populations, sample preparations and slide scanning instrumentation. The model detects allograft rejection with an area under the receiver operating characteristic curve (AUC) of 0.962; assesses the cellular and antibody-mediated rejection type with AUCs of 0.958 and 0.874, respectively; detects Quilty B lesions, benign mimics of rejection, with an AUC of 0.939; and differentiates between low-grade and high-grade rejections with an AUC of 0.833. In a human reader study, the AI system showed non-inferior performance to conventional assessment and reduced interobserver variability and assessment time. This robust evaluation of cardiac allograft rejection paves the way for clinical trials to establish the efficacy of AI-assisted EMB assessment and its potential for improving heart transplant outcomes.

Lipkova, J., Chen, T.Y., Lu, M.Y. et al. Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies. Nat Med 28, 575–582 (2022). https://doi.org/10.1038/s41591-022-01709-2

Gibson Lab receives $2.2 Million NIH R35 grant “Machine Learning and Control Principles for Computational Biology “

Gibson Lab receives $2.2 Million NIH R35 grant “Machine Learning and Control Principles for Computational Biology “

Grant Abstract: With our increasing ability to measure biological data at scale and the digitalization of health records, computational thinking is becoming ever more important in the biological science and healthcare. The research directions proposed in this grant look to build robust machine learning models and tools for computational biology by including principles and analysis from other engineering fields, like control, that have a proven record of incorporating robustness into the systems they have automated. This increased robustness will save resources during the development of these machine learning models. It will also lead to more reliable diagnostics, clinical tools, and machine learning based biological discoveries. We have proposed three future research directions at the intersection of machine learning, control, and computational biology (a) modeling dynamical systems, (b) robust optimization schemes (c) control principles for in vivo modeling of microbial communities. The first proposed research area involves the development of flexible models for performing inference on dynamical systems models with time-series data. Dynamical systems models are able to learn mathematically causal relationships between variables, compared to other models whose parameters may only have correlative relationships. Our flexible models will be differentiable allowing them to be trained using the same efficient algorithms and hardware that have propelled deep learning models into the spotlight. These differentiable methods will allow for us to more easily integrate the uncertainty associated with biological measurements into our models. The second research area looks to develop more robust gradient optimization algorithms, the work horse for training deep neural networks. Many of the popular algorithms used to train deep neural networks were not explicitly designed to be robust. By developing more robust optimization techniques machine learning models trained on disparate data sets at different hospitals or labs will be more reproducible and will require less time for tuning parameters, ultimately saving resources as well. These robust optimization techniques will also aid in the certification of machine learning based tools that will ultimately be deployed in the clinic. The third research area we propose is an approach for the discovery and design of robust microbial communities. Communities of commensal, or engineered, bacteria have long been proposed as alternative therapies for the treatment of gut related illness (“bugs as drugs”). We propose a top down approach to identifying putative microbial consortia members from time-series experiments with germ free mice colonized by complex flora. By beginning the consortia design process in vivo we hope to overcome the challenge that many other attempts at consortia construction have encountered where in vitro designed communities do not reproduce their intended properties once transferred into living host organisms. The tools from this work will be built using open access software and all data will be made easily accessible and explorable to the public.

Link to NIH AwardGibson Lab Website