Abstract 6361: Identification of mitochondrial RNA polymerase inhibitors via deep convolutional neural networks: A therapeutic strategy for cancer metabolism
Bibliographic record
Abstract
Abstract Dysregulated metabolism is a hallmark of cancer and a substantial subset of many cancers rely on oxidative phosphorylation (OXPHOS) for growth and viability, including AML, breast cancer, lung cancer, glioblastoma, ovarian and pancreatic cancer. The electron transport chain (ETC) in mitochondria contains both nuclear DNA- and mitochondrial DNA-encoded subunits. Mitochondrial DNA-encoded subunits are essential for ETC function and are transcribed by the mitochondrial RNA polymerase POLRMT. We have previously validated POLRMT as an anticancer target in acute myeloid leukemia models. The challenge of inhibiting POLRMT with small molecules will arise from both a) selectivity to off targets and b) transport of the drug to the mitochondria. There exist several small nucleoside / nucleotide analogues that are known to inhibit RNA polymerase. However, this target space is rife with the opportunity for off-target activities and toxicity. Therefore, we targeted a novel pocket with the aim of finding novel chemical matter. Using AtomNet, an artificial intelligence platform that utilizes deep convolutional neural networks to predict small molecule recognition, a virtual library of 8 million compounds was screened against POLRMT. The top 72 hit compounds were tested in OCI-AML2 human acute myeloid leukemia cells for a potential decrease of mitochondrial RNA levels (MT-ND1) using reverse transcriptase polymerase chain reaction (RT-PCR). OCI-AML2 cells were treated with compounds at 0.1, 1 or 10 micromolar for 72 hours, 3 days or 6 days or with the positive control POLRMT ribonucleoside analogue inhibitor, 4'-azidocytidine. Gene expression was normalized to 18S. Twelve compounds demonstrated a time-dependent decrease in mitochondrial gene expression. In summary, these data indicate that functional inhibitors of human POLRMT can be identified rapidly via deep convolutional neural networks and machine learning techniques. Financial relationships: RL received an Artificial Intelligence Molecular Screening Award from Atomwise, and funding from the Centre for Collaborative Drug Research, Toronto, Canada. JW is an employee of Atomwise. Citation Format: Noor-Ul-Ain Khalid, Jeffrey M. Warrington, Rebecca Rachelle Laposa. Identification of mitochondrial RNA polymerase inhibitors via deep convolutional neural networks: A therapeutic strategy for cancer metabolism [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 6361.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".