cing

This has been a previous area of research for Google (https://ai.googleblog.com/2017/04/predicting-properties-of-m...). It remains routine to benchmark GNNs and other molecular machine learning models on predicting quantum mechanical properties including energies (which speed up geometry optimization)

Comment · 4 years ago

I agree with the sentiment of this paper (AF can enable drug discovery), but in this specific instance, the authors had a real opportunity contribute a general finding to the scientific community but instead they put in the lowest amount of effort (to a point where they're almost saying nothing at all).

The target had dozens of related structures in the protein databank, including relatives with ~40% sequence identity. This target family has a very similar structure, and conserved active site residues. It's relevant that this target has approved cross-CDK family inhibitors (and thousands of data points of CDK family binders on ChEMBL). The conventional way to enable structure-based design is to build a homology model using a similar structure (see here: https://swissmodel.expasy.org/repository/uniprot/Q8IZL9?temp...), and in this case, there is very low deviation from the AF2 model and this "old fashioned" approach.

To recap, this target had a decent model that would have likely sufficed for drug discovery. The community already knows that "homology models" can be used for structure-based drug design, so any methodological hypotheses of this paper are not supported by evidence.

Comment · 5 years ago

Not saying it's easy but ribosomal synthesis of consecutive non-canonical amino acids has been achieved by some groups (https://www.cell.com/cell-chemical-biology/fulltext/S2451-94..., https://pubs.acs.org/doi/10.1021/jacs.8b07247), and many of these peptides are extremely short. Figure 5 of this manuscript describes successful applications of this for hit identification often in the context of massive peptide library screens, https://pubs.acs.org/doi/10.1021/acs.accounts.1c00391

Comment · 5 years ago

Our startup routinely orders the synthesis of hundreds of peptides for technology validation and drug discovery research (not suitable for human consumption). Costs for a small quantity through a contract research organizion can be $200-$2000 USD per peptide depending on desired purity, length, and chemical complexity. For some applications peptide arrays are suitable, and can drive the costs down to $10 USD per peptide or lower. In both cases, the turnaround time is 4-6 weeks, even though a peptide chemist could do the job in about half the time for a rush order.

Comment · 5 years ago

There is innovation in this space. From green chemistry initiatives to replace hazardous solvents by CROs/industry invested in large-scale production of peptides, https://www.bachem.com/news/bachem-novo-nordisk-redesign-spp..., to routine solid-phase synthesis of peptides greater than 100 amino acids in hours (https://www.science.org/doi/10.1126/science.abb2491, being commercialized here https://www.amidetech.com/)

Comment · 5 years ago

One of the reasons we don't have them all is that individual genes can encode for multiple protein isoforms through alternative splicing. AlphaFold was only run on one. Otherwise, there's lots of important biochemical/biophysical processes that impact structure, as cells are only about 50% protein by weight.

Comment · 5 years ago

Just in case you're not joking, it's worth noting that the majority of distributed molecular simulation (past and present) is spent studying "folded proteins" to discover structures of proteins that are often hidden from methods like AlphaFold (currently). For example, https://www.nature.com/articles/s41557-021-00707-0

Comment · 5 years ago

Everything between the BRCT and RING domains of BRCA1 is an intrinsically unstructured region which DeepMind correctly predicts, https://pubmed.ncbi.nlm.nih.gov/15571721/

Another famous one would be R-domain of CFTR, which was not resolved in experimental structure determination, and AlphaFold models correctly show disorder there. Nothing to be done in those cases except perform molecular simulation or other experiments to assess dynamic ensembles, https://alphafold.ebi.ac.uk/entry/P13569

Comment · 5 years ago

Yet, there were still 136 human teams who competed in CASP14 (https://predictioncenter.org/casp14/docs.cgi?view=groupsbyna...), including DeepMind. Even if a significant fraction of these projects were done piggy-backing another grant, this work does receive research funding.

Comment · 5 years ago

The process is described in Supplementary, but where do you see the code to train the model? The repository is the inference pipeline.

Comment · 6 years ago

There's quite a nice plot from a review paper of D.E. Shaw Research that lists the timescale of several biological processes (and compares it to other experimental methods), https://www.annualreviews.org/doi/full/10.1146/annurev-bioph... (Figure 2). Anton has been extremely helpful for studying the basic science of protein dynamics in academia and has been applied in industry (namely at Relay Therapeutics), but drug discovery is a long process so we still haven't seen the fruits of those long simulations yet.