Editing Protein Engineering (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Zero-shot protein variant prediction with ESM-2:'''
<syntaxhighlight lang="python">
import torch
from transformers import EsmTokenizer, EsmForMaskedLM
import numpy as np
from itertools import product

tokenizer = EsmTokenizer.from_pretrained("facebook/esm2_t33_650M_UR50D")
model = EsmForMaskedLM.from_pretrained("facebook/esm2_t33_650M_UR50D")
model.eval()

AMINO_ACIDS = "ACDEFGHIKLMNPQRSTVWY"

def compute_variant_scores(wild_type_seq: str) -> dict:
    """
    Compute zero-shot fitness scores for all single-site mutants.
    Uses ESM-2 masked marginal log-likelihood.
    """
    encoded = tokenizer(wild_type_seq, return_tensors='pt')
    N = len(wild_type_seq)
    scores = {}

    with torch.no_grad():
        # Get wild-type log-likelihoods at each position
        for pos in range(N):
            masked_input = encoded['input_ids'].clone()
            masked_input[0, pos + 1] = tokenizer.mask_token_id  # +1 for [CLS]
            output = model(input_ids=masked_input,
                          attention_mask=encoded['attention_mask'])
            log_probs = torch.log_softmax(output.logits[0, pos + 1], dim=-1)
            wt_aa = wild_type_seq[pos]
            wt_score = log_probs[tokenizer.convert_tokens_to_ids(wt_aa)].item()
            for mut_aa in AMINO_ACIDS:
                if mut_aa == wt_aa: continue
                mut_score = log_probs[tokenizer.convert_tokens_to_ids(mut_aa)].item()
                delta_llr = mut_score - wt_score  # Positive = preferred over WT
                scores[f"{wt_aa}{pos+1}{mut_aa}"] = delta_llr

    return scores

# Rank mutations by predicted fitness improvement
scores = compute_variant_scores("MKTAYIAKQRQISFVK...")
top_mutations = sorted(scores.items(), key=lambda x: x[1], reverse=True)[:20]
print("Top predicted beneficial mutations:")
for variant, score in top_mutations:
    print(f"  {variant}: {score:.3f}")

# Combinatorial design: combine top singles via in silico directed evolution
# 1. Select top 5 single mutants
# 2. Generate all pairwise combinations
# 3. Score each combination
# 4. Prioritize top combinations for experimental validation
</syntaxhighlight>

; Protein engineering AI tools
: '''Variant prediction (zero-shot)''' → ESM-2 (Meta), EVE, ProteinGym benchmark
: '''Inverse folding (sequence design)''' → ProteinMPNN, LigandMPNN, ESM-IF
: '''De novo backbone design''' → RFDiffusion, Chroma (Generate Biomedicines), FrameDiff
: '''Antibody engineering''' → AntiFold, AbMap, IgLM, Absolut
: '''Structure-based design''' → PyRosetta, Boltz-1, AlphaFold3 + design
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">