Kwenzekeni
I-NVIDIA ithi ihlanganise I-BioNeMo Agent Toolkit ne-Anthropic's Claude Science ukuze ama-agent akwazi ukuthola futhi ashayele ama-microservices asendaweni noma akude e-BioNeMo NIM. Okuthunyelwe kwayo kobuchwepheshe kukhombisa ukuhamba komsebenzi okubuyisa ukulandelana kwamaprotheni, okukhiqiza ukuqondanisa kokuziphendukela kwemvelo, kusebenzisa izibikezelo ze-OpenFold3 ne-Boltz-2, futhi igcina izinto zobuciko eziwumphumela ukuze zibuyekezwe.
Iposi lobuchwepheshe lika-NVIDIA lika-Aug. 31 lichaza I-BioNeMo Agent Toolkit njengephakheji lamamodeli esayensi yempilo, imitapo yolwazi, nokugeleza komsebenzi okungavezwa njengamakhono abizelwa yi-ejenti. Le nkampani ithi ikhithi yamathuluzi ihlanganisa i-biology, chemistry, genomics, kanye nokutholakala kwezidakamizwa, futhi yakhelwe ukusebenza ngezinhlaka zama-ejenti ezehlukene.
Ekusetheni okubonisiwe, i-Claude Isayensi ihlela ama-microservices amathathu e-NVIDIA NIM: I-MSA Sesha ukuqondanisa kokuvela kwemvelo, i-OpenFold3 yokubikezela isakhiwo, kanye ne-Boltz-2 ngesethi yesibili yezibikezelo. I-NVIDIA ithi ama-benchmarks angaphakathi akhuphule ukunemba komsebenzi ukusuka ku-60% kuya ku-100% kanye nokusebenza kahle kwamathokheni cishe okuphindwe kabili; lezo zibalo zibikwe yinkampani futhi azihlolwa ngokuzimela kokuthunyelwe. Okokufundisa kudinga i-Claude Science, ukhiye we-NVIDIA API, kanye nokufinyelela endaweni yokusebenza noma umshini wamafu one-NVIDIA L40S noma i-H100 GPU. I-NVIDIA ilinganisela cishe u-700 GB wesitoreji sokuhamba komsebenzi, okuhlanganisa cishe u-490 GB wesizindalwazi se-UniRef30 kuphela kanye no-30–40 GB weziqukathi ze-Boltz-2 ne-OpenFold3. Okuthunyelwe futhi kuchaza ezinye izindlela lapho i-Claude Isayensi isebenza kukho ikhompuyutha ephathekayo ngenkathi ixhumeka ku-GPU ekude nge-SSH, ingqalasizinda ye-HPC, noma i-cloud computing.
Okokufundisa kusebenzisa iziqukathi zasendaweni ze-Docker ezixhunywe kumsingathi we-GPU futhi kudinga ukuhlolwa kwezempilo ngaphambi kokuthi amaphoyinti okugcina agunyazwe. Ngesibonelo salo sebhayoloji, ukuhamba komsebenzi kuqhathanisa iphrotheni ye-Seh1 C1GY11 evela ku-Paracoccidioides lutzii iyodwa kanye nozakwethu ohlongozwayo, i-C1HCX1. I-NVIDIA ibika ukuthi umenzeli ubuyise ukulandelana kwezinsalela ezingu-384 nezingu-976, ngokulandelanayo, futhi wathola ukulandelana okungu-202 kwephrotheni ngayinye phakathi nosesho lwe-MSA. Idale ukuqondana okungabhanqiwe kwamaketango angawodwana kanye nokuqondanisa okubhangqiwe kwezinhlobo zekesi elinamaketanga amabili. Ukuhamba komsebenzi kwabe sekusebenzisa izibikezelo ze-monomer ne-heteromer ngaphandle kwezifanekiso, ama-ligand, amaphakethe, noma ezinye izithiyo zesakhiwo, kusetshenziswa okukhiphayo kwe-mmCIF nokugcina izicelo, izimpendulo, izakhiwo, amamethrikhi, namaphutha.
The post reports that OpenFold3 produced an interface pTM, or iPTM, of 0.86 for the heteromer with MSA input, while Boltz-2 produced 0.82. In additional five-sample comparisons, the reported MSA-versus-no-MSA values were 0.85 versus 0.14 for OpenFold3 and 0.82 versus 0.19 for Boltz-2. NVIDIA says the samples clustered tightly, with standard deviations no greater than 0.006, and that more generous sampling budgets did not materially change the pattern. The two model families use different architectures and handle MSA pairing differently, but their MSA-supported interface scores were within 0.03 in the comparison described.
Imininingwane yomthombo: developer.nvidia.com ↗
Kungani kubalulekile
Isibonelo sibonisa ukuthi i-ejenti yocwaningo ye-AI ingaxhuma kanjani amamodeli akhethekile ebhayoloji ekuhambeni komsebenzi okuphindaphindekayo kunokumane nje ifinyeze izincwadi zesayensi. Iphinde ibike ukuthi ukuqondanisa kokuziphendukela kwemvelo kwaba yisinqumo esibonakalayo esibikezelwe sephrotheni kulokhu kuhlolwa, kuyilapho ikwenza kucace ukuthi isivumelwano semodeli akubona ubufakazi bokusebenzelana kwezinto eziphilayo.
The practical significance is the orchestration layer. Protein folding and complex prediction require specialized inputs, model-specific formats, and parameters that a general-purpose agent may not know how to select or apply. In NVIDIA’s account, Claude Science identifies the needed services, prepares the sequences and alignments, starts the endpoints, submits the predictions, and records the artifacts. That makes the AI agent an operator of a scientific pipeline, not simply a conversational interface to a single model.
The results also illustrate why input quality can matter as much as model selection. In NVIDIA’s test, removing the MSA caused the predicted heteromer interface confidence to fall sharply in both OpenFold3 and Boltz-2. OpenFold3’s reported monomer pLDDT fell from 82.3 with MSA to 36 without it, while Boltz-2’s corresponding value moved from 0.79 to 0.73 on its 0–1 scale. The comparison suggests that evolutionary information was especially important for placing the contact between the two chains, although these are confidence outputs from prediction services rather than measurements of a real biological complex.
The structural comparison adds a more specific hypothesis. NVIDIA says both models placed a group of C1HCX1 beta strands near the open edge of Seh1’s WD40 beta propeller, at a position associated with closing the final blade. Superposing the Seh1 cores reportedly produced C-alpha RMSDs of 0.68 angstrom for OpenFold3 and 0.65 angstrom for Boltz-2 over most of the chain. The company interprets this as the partner completing an existing fold rather than substantially remodeling it. Agreement between independent computational models makes the proposed geometry more useful as a target for investigation, but it does not establish that the proteins bind in living cells or perform the proposed function together.
I-Interactive Mechanism: Indlela Esebenza Ngayo Ngempela
Hlola ubuchwepheshe obuyisisekelo ngemuva kwalokhu kuthuthukiswa ngokuhlanganyela.
crm_get_transaction(id='4092').An agent must create a draft calendar event for Tuesday at 2 p.m. Which evidence would establish the requested result?
Ongakubuka ngokulandelayo
Imibuzo eyinhloko evulekile ukuthi ingabe ukugeleza komsebenzi kudlula ipheya yeprotheni eyodwa, kubiza malini nokuthi kuthatha isikhathi esingakanani ukusebenza, kanye nokuthi ingabe ukuhlolwa kwaselabhorethri kuyakuqinisekisa yini ukuhlobana okubikezelwe. I-NVIDIA ibika amabhentshimakhi ekhithi yamathuluzi yangaphakathi nemodeli yezikolo ukuzethemba, kodwa okuthunyelwe akuhlinzeki ngokuphindaphinda okuzimele, izilinganiso zesikhathi sokusebenza, noma ukuqinisekiswa kokuhlola.
The clearest limitation is biological validation. NVIDIA explicitly says the workflow predicts a C1GY11–C1HCX1 interaction and that the result has not been experimentally verified. The example is motivated by a prior structural observation involving Seh1 and a Mio-family partner, but this post itself reports a computational analysis.
Follow-up work would need laboratory evidence, such as biochemical or cellular tests, to determine whether the predicted association exists and whether it has a biological role. is also unresolved. The demonstration centers on one protein pair from one fungal species, one UniRef30 database profile, and specified search and sampling settings. The reported confidence changes show that MSAs were load-bearing in this case, but they do not establish that every protein complex benefits to the same degree or that a high interface score reliably predicts binding across different proteins.
NVIDIA’s internal task-correctness and token-efficiency figures likewise lack the definition, test set, comparison baseline, and independent evaluation needed to assess their broader meaning. Operational details will determine whether this is usable outside a demonstration. The post requires substantial local storage, compatible NVIDIA GPUs, container downloads, an API key, and manual approval of endpoints.
It says runtime metrics were present but empty for the reported runs, so readers cannot infer latency, energy use, cloud cost, or throughput. Boltz-2 and OpenFold3 also report confidence values on different scales and expose different fields, which limits direct numerical comparison. The next meaningful evidence would be reproducible runs by outside researchers, published resource measurements, broader protein-complex tests, and experimental confirmation of the structural hypothesis.