About¶
Website for browsing reviews of GO-CAMs.
This contains an initial pass of reviews of GO-CAMs with >2 causal edges, performed by the aurelian agentic framework using claude 3.7.
THIS IS A DEMO FIRST PASS AND NEEDS FURTHER TUNING
- Open the "Reviews" tab on the left to see all reviews
- The guidelines are provided for reference
- simple search in top right
Known Bugs¶
False positive warning about 'has input'¶
When I fed the GO-CAMs to the agent, the JSON was missing 'has input' to uniprot IDs (only CHEBI IDs includes). This means that the agent will sometimes mention that there is a missing input - this is not a hallucination, it's an upstream data bug.
Examples¶
-
61e0e55600000624-Cyclin_D_ubiquitination_and_degradation_by_AMBRA1__Human_
-
example of evaluating against guidelines (E3 ubiquitin ligase)
-
See also #970
-
VPE -- missing edge?
-
60ad85f700000110-receptor_signaling_pathway_via_JAK_STAT_via_upd2_dome__D_mel_
-
627d95ee00000955-Chondroitin_sulfate_catabolic_process__Mouse_
Accidental inclusion of non-causal models¶
For simplicity, we include all GO-CAMs with >2 causal edges. This is generally sufficient to exclude gene-centric models, however, a few may slip through due to spurious causal annotations. The reviews for these are typically very negative, which is a nice confirmation things are working.
For example,
- 60ad85f700000058-Atf2_mouse is clearly gene-entric
The review for this -- as expected complains that there needs to be a lot more causal connections, and overall this scores very low (2).
In addition there are some models that may be in-between, e.g.
Figures¶
A drawing agent was instructed to create an SVG of the GO-CAM (input is JSON). A review agent checks this to make sure the image is clear. It is meant to tell the draw agent to draw again if things are misaligned or text crosses boxes etc but this part does not work so well, and some images have floating chunks or incorrect legends, but overall the drawing agent seems to understand both the visual grammar of pathway figures and the intent of the model.
I deliberately left this quite unconstrained to see what kinds of styles the model would come up with, but we can easily constrain this to a house style, or give it a predefined set of components.
See:
Selected:
- FIG-646ff70100005137-IL33_signaling_pathway__Human_
- Illustrates intuitive drawing of co-receptors and different compartments
- the AI comes up with a set of glyphs for each MF type
- Intuitive labeling of GO terms to the side
- Correct visual mapping of CCs to compartments
- FIG-60ad85f700001873-epidermal_growth_factor_receptor_signaling_pathway_via_spi_Egfr__D_mel_
- compare the end points and regulation directions with standard drawing
- FIG-60ad85f700000189-BMP_signaling_pathway_via_dpp_tkv_put__D_mel
- FIG-5f46c3b700001407-TBK1_activation_via_TRAF3_autoubiquitination__Human_/
- understands the correct way to indicate protein modification
- the lines are a bit off for autoubiquitination
- FIG-5ee8120100002841-Inflammatory_signaling_involved_in_regulation_of_hematopoietic_stem_cell_differentiation_via_notch1a__tnfa__tnfrsf1b__jag1a__D_rerio_/
- good depiction of different cell types
- FIG-62b4ffe300004489-Regulation_of_the_JAK_STAT_pathway_by_calmodulin_in_response_to_interferon_gamma__Human_
- The AI marks the IFNG receptor with an asterisk to show it is implicit in the model
- FIG-62b4ffe300004795-Insulin_receptor_signaling_pathway_1__Mouse_
- FIG-641ce4dc00000914-Activation_of_Nf_kappa_B_via_ubiquitination_and_degradation_of_the_NF_kappa_B_inhibitor__Human_
- good way to indicate translocation