docs: rewrite ESMFold2 guide around HIV-1 protease homodimer (#182)

* docs: remove em-dashes from ESMFold2 guide prose

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: rewrite ESMFold2 guide around HIV-1 protease homodimer

Restructure the ESMFold2 tutorial: fold the protease as a complex,
retrieve/visualize early, assess multi-chain confidence (pTM/ipTM/
pairwise ipTM grid + PAE/pLDDT plots), condition on an MSA, co-fold
with ritonavir, and cover ESMFold2-Fast and first-gen ESMFold. Cells
ship un-run with cleared outputs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: run ESMFold2 guide against dev, commit executed outputs

Execute the rewritten notebook end-to-end on the dev backend: protease
dimer fold (pTM 0.957 / ipTM 0.950), confidence breakdown, PAE/pLDDT
plots, MSA-conditioned fold, ritonavir co-fold, ESMFold2-Fast, and
first-gen ESMFold all succeed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs: update esmfold2 num_steps default to 100

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Mark Gee <jw.ziggee@gmail.com>

Author: 3 people