Feature
b
, (x
i
)
|
Coefficient, (b
i
)
|
Genes within features
|
---|
Age | 0.0623 | Ā | Ā | Ā | Ā |
GG | 0.5450 | RPS4Y1 | Ā | Ā | Ā |
GS | 0.1661 | SLC7A11 | CLND10 | TKT | Ā |
GPY | 3.0205 | RUNX1T1 | AKR1C2 | Ā | Ā |
CA (1) | ā0.4406 | BST1 | CD177.1 | CD177.2 | Ā |
CA (2) | ā0.3402 | ATP12A | TSPAN2 | Ā | Ā |
CA (4) | 0.1725 | GABBR1 | MCAM | NOVA1 | SDC2 |
CA (7) | 0.5670 | CDR1 | CGREF1 | CLND22 | NKX3-1 |
CA (9) | ā0.3160 | EPHX3 | LYPD2 | Ā | Ā |
CA (10) | ā0.3791 | MIA | RNF150 | Ā | Ā |
Intercept (b0) | 3.3173 | Ā | Ā | Ā | Ā |
- a)Genomic gender was defined as GGā=ā1 (female) if RPS4Y1ā<ā7.5, 0 (male) otherwise. The predicted genomic smoking (GS) value was derived, where xā=ā40.8579-0.4462*SLC7A11-2.1298*CLND10-1.8256*TKT, and genomic smoking GSā=āex/(1+ ex). The predicted genomic pack years (GPY) value was derived, where xā=āā5.1429ā+ā2.1891*RUNX1T1 -0.9506*AKR1C2, and genomic pack years GPYā=āexp(x)/(1ā+āexp(x)). The generalized equation for the prediction classifier was: Scoreā=āey/(1+ ey), where, yā=āb
0
ā+āĘ©(b
i
*x
i
), where b
0
is the intercept, b
i
is the coefficient, and x
i
is the feature (as shown).
- b)Features include patient age (as reported), GG, GS, GPY as described in the methods, and CA (i), the lung cancer gene clusters (shown in FigureĀ 1).