Krista Opsahl-Ong, Michael J Ryan, Josh Purtell, David Broman, Christopher Potts, Matei Zaharia, Omar Khattab. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Automating enterprise workflows could unlock $4 trillion/year in productivity gains. Despite being of interest to the data management community for decades, the ultimate vision of end-to-end workflow automation has remained elusive. Current solutions rely on process mining and robotic process automation (RPA), in which a bot is hard-coded to follow a set of predefined rules for completing a workflow. Through case studies of a hospital and large B2B enterprise, we find that the adoption of RPA has been inhibited by high set-up costs (12--18 months), unreliable execution (60% initial accuracy), and burdensome maintenance (requiring multiple FTEs). Multimodal foundation models (FMs) such as GPT-4 offer a promising new approach for end-to-end workflow automation given their generalized reasoning and planning abilities. To study these capabilities we propose ECLAIR, a system to automate enterprise workflows with minimal human supervision. We conduct initial experiments showing that multimodal FMs can address the limitations of traditional RPA with (1) near-human-level understanding of workflows (93% accuracy on a workflow understanding task) and (2) instant set-up with minimal technical barrier (based solely on a natural language description of a workflow, ECLAIR achieves end-to-end completion rates of 40%). We identify human-AI collaboration, validation, and self-improvement as open challenges, and suggest ways they can be solved with data management techniques.

Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. Importantly, the success of any mitigation strategy strongly depends on the \textit{structure} of the shift. Despite this, there has been little discussion of how to empirically assess the structure of a distribution shift that one is encountering in practice. In this work, we adopt a causal framing to motivate conditional independence tests as a key tool for characterizing distribution shifts. Using our approach in two medical applications, we show that this knowledge can help diagnose failures of fairness transfer, including cases where real-world shifts are more complex than is often assumed in the literature. Based on these results, we discuss potential remedies at each step of the machine learning pipeline.

Abstract Mitochondrial DNA (mtDNA) copy number is tightly regulated in tissues, and is both a critical determinant of mitochondrial function and a potential biomarker for disease. We and other groups have shown that the mtDNA copy number per cell can be directly estimated from whole-genome sequencing. The computation is based on the rationale that sequencing coverage should be proportional to the underlying DNA copy number for autosomal and mitochondrial DNA, and most computing time is spent calculating the average autosomal DNA coverage across ∼3 billion bases. That makes analyzing tens of thousands of available samples very slow. Here we present fastMitoCalc, which takes advantage of the indexing of sequencing alignment files and uses a randomly selected small subset (0.1%) of the nuclear genome to estimate autosomal DNA coverage accurately. It is more than 100 times faster than current programs. fastMitoCalc also provides an option to estimate copy number using a single autosomal chromosome, which could also achieve high accuracy but is slower. Using fastMitoCalc, it becomes much more feasible now to conduct analyses on large-scale consortium data to test for association of mtDNA copy number with quantitative traits or nuclear variants. Availability and Implementation fastMitoCalc is available at https://lgsun.irp.nia.nih.gov/hsgu/software/mitoAnalyzer/index.html Supplementary information Supplementary data are available at Bioinformatics online.